This PDF file contains the front matter associated with SPIE Proceedings Volume 10033 including the Title Page, Copyright information, Table of Contents, Introduction, and Conference Committee listing.

Based on Delaunay triangular mesh method, a LiDAR point cloud building edge extraction algorithm is put forward in this paper. First of all, filter LiDAR point cloud and extract the building points. Then establish a triangular mesh according to Delaunay method, and calculate the length of each triangular mesh, to get an average side length. Taking the average side length as threshold, when a triangle’s side length exceeds the threshold, its three points are considered as edge points. In this triangle, the short side is usually the building edge outline, whose length is less than the threshold. After linking the short side, the building edge circuit is obtained. Since building usually occupies larger space than the other surface features, the circuit with more points is kept, and then the building outline of building can be formed by using pipe algorithm for normalization. The processing result on the experimental airborne LiDAR point cloud data shows that the algorithm can extract the building edge quickly and efficiently from LiDAR point cloud data.

The notion of edge computing has gained much attraction in recent years as an enabling technology for smart city and internet of things applications. In this paper we report the system challenges and solutions encountered when designing and deploying the Macao Polytechnic Institute Smart City sensing system. A small fleet that serves as proof-of-concept for a country wide urban sensing system in Macao, S.A.R. We focus our attention on how a careful system design can ensure smooth operations and mitigate the natural tension between fleet owners and smart city operators. The first are keen to maximize the fleet operations and reduce the downtime, the later are interested in using the fleets to harvest high-quality and fine granularity sensor data. In designing the Macao Polytechnic Institute vehicular cloud we approached the design constraints and proposed system solutions to minimize the impact of the sensing platform on the fleet operations.

In this paper, a FEM-based model for elastic image registration is proposed for the medical images that containing abnormal region due to pathological changes. Such model is based on uniform triangulation and Bayesian theorem. Firstly, the continuous domain corresponding to the size of the registered images is discreted by applying uniform triangulation. According to the characteristics of the elastic match, the basis function are constructed on the vertices of the every triangles. Next, the pixels of the image that containing pathological changes is classified by using the region growth algorithm. Based on the Bayes theorem, the FEM-based model is then received, and the model is naturally an energy function that respect to the basis function. Therefore, the problem of the image registration can be translated into the problem of finding the minimum value of the energy function. The gradient descent method is used to calculate the value in this article. Finally, the result of the simulated experiment show the effectiveness and accuracy of the addressed model.

We introduce an algorithm for real-time sub-pixel accurate hard shadows rendering. The method focuses on addressing the shadow aliasing due to the limited resolution of shadow maps. We store a partial, approximate geometric representation of the scene’s surfaces which are visible to the light source. Inspired by the fact that aliasing occurs in the shadow silhouette regions, we present an edge detection algorithm using second-order Newton’s Divide Difference to divide shadow maps into two regions: depth-discontinuous region and depth-continuous region. A tangent estimation method based on the geometry shadow map is presented to recover the artifact aliasing of those silhouette regions. Experiments show that our algorithm eliminates the resolution issues and generates hard shadows with high quality.

Fast and reliable facial interest point detection is critical basis in intelligent human machine interaction to understand human behavior. Considering the depth data’s outstanding advantage on robustness of complex background and illumination variation, we address the problem of facial interest point's detection based on depth images rather than normal intensity images to locate points with salient depth discriminable characteristic. In this paper, we propose to extract Haar-like features from facial depth data for further classification of interested point detection. To alleviate the influence of head rotation, a novel local space rotation invariant (LSRI) feature extraction method is presented in the paper by adjusting the depth image with estimated rotation angles. In our experiments, we select 6 kinds of templates to extract the features and use algorithms including Adaboost, Random Forests, J48(a decision tree algorithm)as classifiers respectively to realize the interest point location. The experiment results show that our algorithm has high point location accuracy rate at 96.1%. The proposed LSRI feature outperforms the Haar-like feature in depth data without doing local posture adjustment.

Template matching algorithm is one of the important image-based Automatic Target Recognition methods. Traditional normalized cross correlation (NCC) algorithm used in infrared image matching has a strong antinoise performance but low computing speed. Meanwhile, although sequential similarity detection algorithm (SSDA) performs a shorter time than NCC, it has lower accuracy. In order to solve the low target recognition rate and slow speed of infrared image recognition problems, a new matching algorithm based on infrared image is presented, which integrates the advantages of two methods. The fusion algorithm improves the matching speed and reduces the probability of matching error. The experimental results confirm that the proposed approach has higher efficiency and accuracy in infrared image matching than original algorithms. Comparing with NCC and SSDA, it shortens large recognition time and enhances the right matching ratio respectively. In addition, the improved algorithm is real-time and robust against noise. It is significant to the research and development of automatic target recognition technology for different kinds of real-time detection system.

The human visual systems tend to integrate oriented line segments into groups if they follow the Gestalt principles. It is commonly acknowledged that early human visual processing operates bye first performing edge detection followed by perceptual organization to group edges into object-like structures. Edge groups can be used to improve a variety of tasks such as multi-threshold selection, object proposal generation sketch segmentation. In this paper, a perceptual grouping framework that organizes image edges into meaningful structures is proposed. The grouper formulates edge grouping as a spectral clustering problem, where a computation model based on Gestalt principles is developed to encode probabilities of candidate edge pairs. First, a probability model is proposed as grouping constraint inspired by the Gestalt principles, i.e. proximity, continuity and similarity. Then we take the grouping constraint as the input and perform spectral clustering to integrate edge fragments into groups. Experiments have shown that our algorithm can effectively organizes image edges into meaningful structures.

Laplacian of Gaussian (LoG) filter is a very conventional and effective edge detector which is used in edge detection. In the image denoising phase, we implemented the parallel method of Gaussian blur to the image so that we can get rid of the impact brought by the original image, and prevent the noise being amplified by Laplace operator. Then, in the phase of edge detection, the Laplace operator was applied to the result which has been processed and exported by the first phase. Through the optimization of these steps, the running performance will make a big difference compared to the pure Laplacian. Combining with the highly evolved Graphics Processing Unit (GPU), the way of parallel image processing will be more effective than the serial one. In this study, the parallel LoG Algorithm was implemented in different size images on NVIDIA GPU using Compute Unified Device Architecture (CUDA). By applying the parallel LoG algorithm suggested here, the time required to the process of edge detection would be narrowed down immensely and achieve speed up by factor 3.7x compared to the serial application running on CPU.

The efficiency of the detector point features to a stationary uncorrelated noise digital television image analysis is produced. Two methods to improve the reliability of the isolation characteristics of the scene on digital images in a stationary uncorrelated noise are presented. The requirements to ensure the necessary level of signal/noise ratio for effective computer analysis of the scene on the image detector television spot features are given. The research results will improve the effectiveness of computer analysis of the scene on the TV picture in the autonomous local navigation and positioning complexes based on vision systems in stationary uncorrelated noise.

Combined with the characteristics of the forward-looking template matching algorithm, this paper proposed an evaluation method for ATR algorithm based on decision tree. The image features of the simulated real-time images and the template images are extracted as the input attribute, and the recognition results of the real-time images are used as the label. The input attribute and the label make up the training samples, and a series of decision trees are generated through the CART algorithm. As the real-time image of the target area is difficult to obtain, the image features of the simulated real-time images of the target area are extracted, and then the recognition results and their confidence level are predicted by using different decision trees corresponding to different ATR algorithms. The ATR algorithms are evaluated by comparing the prediction results and their confidence level.

Feature description and matching are at the base of many computer vision applications. However, traditional local descriptors cannot fully describe all information of features, and there are so many feature points and so long local descriptors that the matching steps are time-consuming. In order to solve these problems. This paper proposed a new efficient method for description and matching, called TSMwGLD (the two-step matching with global and local Descriptors). In TSMwGLD, first, it designed a simple global descriptor and then found N best-matching points by using global descriptors, and at the same time it could eliminate lots of points which didn’t match in global information. Next, the method continued the matching step to find the best-matching point by using the local descriptors of N candidate points. So the whole matching process could become faster because the distances between global descriptors with the size of 8 were computed more easily than local descriptors with the size of 64 in SURF. The experimental results show that TSMwGLD results in increased accuracy and faster matching than original method. Especially for blurred images with textures, the matching time is less than tenth of original and the whole description and matching process is about two times faster than SURF.

Inverse Synthetic Aperture Radar (ISAR) has been widely used in civil and military fields. Due to ISAR imaging mechanism, the obtained image data contain lots of unwanted area with respect to desired target, which not only wastes the storage space, but also reduces the efficiency of further processing like target recognition. So different methods of ISAR target extraction from the imaging area are elaborated, which can extract the desired target from the background, particularly of noise and clutter. Then the methods are compared and assessed in terms of processing speed and extraction effect, merits and demerits of each method are also summarized.

Convolutional Neural Network is a hot research topic in image recognition. The latest research shows that Deep CNN model is good at extracting features and representing images. This capacity is applied to image retrieval in this paper. We study on the significance of each layer and do image retrieval experiments on the fusion features. Caffe framework and AlexNet model were used to extract the feature information about images. Two public image datasets, Inria Holidays and Oxford Buildings, were used in our experiment to search for the influence of different datasets. The results showed the fusion feature of Deep CNN model can improve the result of image retrieval and should apply different weights for different datasets.

This paper consider the problem of detecting range-distributed targets using high resolution radar(HRR) in compound-Gaussian clutter without secondary data. To overcome the lack of training data, we first assume that clutter returns can be clustered into groups of cells sharing the same value of the noise power. Then an adaptive modified generalized likelihood ratio test (A-GLRT) detector is proposed by replacing the unknown parameters with their maximum likelihood estimations (MLEs). The proposed A-GLRT detector do not need secondary data and ensures constant false alarm rate (CFAR) property with respect to the unknown statistics of the clutter. Performances of this proposed detectors are assessed through Monte Carlo simulations and are shown to have better detection performance compared with existing similar modified generalized likelihood ratio test (MGLRT) detector.

In the approaching tracking process, we get infrared images from far to near, and the target in the images varies from small to big. The main problems in the tracking process are the large variety of scale, the change of target’s posture and intensity, the collusion of interferences. This paper focuses on the whole tracking and detection process when the target and inferences exist at the same time and block each other. We propose an approach which includes several cues. Firstly, according to the amount of target pixels, the target is divided into small target and shaped target. Then we use the information of the target displacement rate to track and detect the small target which only has several pixels and is unstable. For the shaped target, we can make use of the target’s contrast information. Lastly, we validate our method by designing an experiment which simulates the entire tracking and detection process. The test shows that our method improve the performance.

Although TLD (Tracking-Learning-Detection) algorithm can enable the long-term tracking, there are still many problems in it. In this paper, an improvement is made on the detection module of TLD to satisfy the need of time and accuracy. First, we use the Kalman Filter to narrow the detection range of the detector effectively. Then, we replace the traditional detector with Cascaded Random Forest detector, combining the global and local search strategy, which can reduce the computation burden of the algorithm, and achieve the real-time object tracking. The experimental results on various benchmark video sequences show that the proposed approaches compared with the traditional tracking algorithms not only presents robustness and tracking accuracy in stable background or complex conditions, but also obtains the best computing speed with the use of the Cascaded Random Forest.

Robustly and automatically detecting multi-object is an important and challenging task in complex and dynamic scenarios where the object features, illumination and background etc., are often time-variable. In this paper, a novel frame work of multi-object detection is presented based on multi-orientation saliency features fusion. Firstly, four orientations Gabor filtering is used to extract the saliency features from image sequence. Then, grayscale morphological processing, area filtering and binarization are employed to highlight the possible object regions. Furthermore, the duty ratio and scale ratio of every possible region are utilized to select the candidate object regions. Finally, the intersection states among four orientations candidate regions are judged, and the optimal object region is obtained by weighted fusing in terms of intersection area and candidate region duty ratios. Results from experiments show the excellent performance of the proposed algorithm in unrestrained and complex scenarios.

Moving target detection is a significant research content of image processing and computer vision. Precise detection of moving target is the basic of target positioning, target tracking and target classification. There are many applications of it in intelligent monitoring, traffic statistics and many other fields. How to detect the moving object in a bad weather, for example, a heavy foggy day, is a problem that needs be solved in the engineering, we all know that the haze has been a quite serious environment problem in our life! The paper is based on this. First, getting rid of fog in the video, and then, extracting the features of pixels, establishing features dictionaries, building models for background by features matching in order to extract foreground. The result shows that the proposed algorithm can detect the moving target accurately in a foggy day.

In this paper, we propose a novel salient object detection approach, which aims in suppressing distractions caused by the small scale pattern in the background and foreground. First, we employ a structure extraction algorithm as a preprocessing step to smooth the textures, eliminate high frequency components and retain the image’s main structure information. Second, we segment the texture maps are computed and fused according to the color contrast and center prior cues. To better exploit each pixel’s color and position information, we refine the fused saliency map. Experiments on two popular benchmark datasets demonstrate that our proposed approach achieves state-of-the-art performance compared with sixteen other state-of-the-art methods in terms of three popular evaluation measures, i.e., Precision and Recall curve, Area Under ROC Curve and F-measure value.

In order to accurately detect the fabric defects in production process, an effective fabric detection algorithm based on Gabor filter and low-rank decomposition is proposed. Firstly, the Gabor filter features with multi-scale and multiple directions are extracted from the fabric image, then the extracted Gabor feature maps are divided into the blocks with size 16×16 by uniform sampling; secondly, we calculate the average feature vector for each block, and stack the feature vectors of all blocks into a feature matrix; thirdly, an efficient low rank decomposition model is built for feature matrix, and is divided into a low-rank matrix and a sparse matrix by the accelerated proximal gradient approach (APG). Finally, the saliency map generated by sparse matrix is segmented by the improved optimal threshold algorithm, to locate the defect regions. Experiment results show that low-rank decomposition can effectively detect fabric defect, and outperforms the state-of-the-art methods.

Conventionally, SAR Automatic Target Detection(ATD)are often performed in SAR image domain. A novel scheme of SAR target detection in the state of non-imaging is presented. More precisely, this paper addresses adaptive detection of SAR possibly extended targets when implemented on range-compressed but azimuth-uncompressed SAR raw data. The SAR target detection is established in the context of space-time adaptive processing (STAP) and the spatial-temporal steering vector of an airborne stripmap SAR is derived by exploiting signature diversity, namely of the fact that SAR can change the transmitted signal as the azimuth varies. The generalized adaptive subspace detector (GASD) is employed to detect range-spread target from SAR raw data. Performance analysis of the proposed detector via Monte Carlo simulation shows the validity of this new detection scheme.

An algorithm of detection and tracking of multiple small moving space junks under the complex star sequential images is proposed in this paper. Firstly we take image smoothing and adaptive threshold segment to improve the weight of junks. Furthermore, back neighborhood frame correlation (BNFC) is proposed to detect and locate the junk which is sheltered by bigger interfaced stars. Through cross projection method, we could extract the centroid of the moving junks. At last, the Kalman Filter is used to track and estimate the trajectory of moving junks. Experiments show that through this algorithm the multiple small space junks could be detected and tracked effectively and accurately under complex star background with good performance in low error rate and good real-time processing.

Infrared small-target detection plays an important role in image processing for infrared remote sensing. In this paper, we formulate this problem as salient region detection, which is inspired by the fact that a small target can often attract attention of human eyes in infrared images. We show that the convolution of the image amplitude spectrum with a low pass Gaussian kernel of an appropriate scale is equivalent to an image saliency detector. In this paper, we present a quaternion representation of an image which is composed of its intensity after denoising, the horizontal gradient and the vertical gradient. Therefore, a new method for infrared small target based on hyper complex Fourier transform (HFT) is proposed. The saliency map is obtained by reconstructing the 2D signal using the original phase and the amplitude spectrum, filtered at an appropriate scale. Experimental results demonstrate that the proposed algorithm is able to predict salient regions on which people focus their attention.

Sea-surface weak target detection based on fractal characteristics has drawn intensive attentions in radar community recent years. However, the fractal differences between target and sea clutter are not probably significant due to the fact that target echo has been corrupted by clutter. The time-frequency distribution generated by Hilbert-Huang transform (HHT) indicates that the spectrum of target echo is mainly distributed near zero frequency, which is different from the spectrum of sea clutter. In order to enhance the difference of fractal characteristics between target and clutter, this paper applies Empirical Mode Decomposition (EMD), the first procedure of HHT, to extract the lower frequency components of radar raw echo. Then, Hurst exponent is used to construct the fractal detector. Simulation results using real data show that the performance of this new algorithm is better than the raw data-based Hurst-exponent method and the EMD-based box-dimension method.

To improve the tracking accuracy of maneuvering target, a tracking algorithm based on parameter adaptive current statistical (CS) model is proposed. According to the relationship between the acceleration increment and displacement, the acceleration variance is adjusted adaptively. According to the statistical distance of the measurement residuals, the target maneuver characteristics are determined, and then the maneuvering frequency and the filter gain coefficient of the model are adjusted to improve the matching degree between the algorithm model and the target maneuver model. The simulation results show that the tracking algorithm based on the parameter adaptive CS model can improve the tracking performance of the strong maneuvering target.

In order to realize the effective detection of surface structure targets in hyperspectral images, an improved target detection algorithm was proposed in this paper presents to solve the CEM algorithm problems which the large object extraction efficiency is low .First, the image was preprocessed, including end-member extraction, SAM classification. Second, after the ship pixels were subtracted from all pixels, the correlation matrix of pure background pixels was constructed to detect ship target. Third, the biggest write region was found as sea region by mathematical morphology. Finally, the false target pixels were removed from all target pixels using the characteristics which ship targets were surrounded in seawater, so the final ship targets were selected in the end. Experimental results show that the final max ratio between the energy of detection target and the energy of background increased greatly, the target signal is enhanced and the background signal is suppressed by the improved algorithm.

Nowadays, object recognition in 3D scenes has become an emerging challenge with various applications. However, an object can’t be represented well by artificial features derived only from 2D images or depth images separately, and supervised learning method usually requires lots of manually labeled data. To address those limitations, we propose a cross-modality deep learning framework based on contractive autoencoders for 3D scenes object recognition. In particular, we use contractive autoencoding to learn feature representations from 2D and depth images at the same time in an unsupervised way, it is possible to capture their joint information to reinforce detector training. Experiments on 3D image dataset demonstrate the effectiveness of the proposed method for 3D scene object recognition.

Multimodal biometric recognition has been widely used in identity authentication. However, how to fuse the multimodal images together reliably and effectively is still a challenging problem in practice. In this paper, combining multimodal traits, fingerprint (FP), finger-vein (FV) and finger-knuckle-print (FKP), as a global representation of a finger, a new pixel-based granular fusion method is proposed. In the proposed method, each unimodal image is first viewed as an atomic hypersphere granule with a center denoted by a real N-dimensional pixel-value vector. Thus, for a finger trait, a triangle can be constituted by the centers corresponding to three atomic granules such that an inscribed circle of it can be formed subsequently. A fused hypersphere granule of a finger is therefore generated coordinately by combing centers of the FV granule and the inscribed circle. Finally, the fuzzy inclusion measure is used to compute the similarity between two fusion hypersphere granules for image matching. Experiment results show that the proposed granular fusion method at pixel level is reliable and effective.

In the classroom, students can get the most benefit for themselves when attend and participate in the classroom. Roll-call is a classical method that mostly uses for the class participation enrollment. The time that used for this method is depended on the number of students; the more number of students, the more time to spend. This work presents the method that improves the class participation enrollment process Thus, we developed the face detection and face recognition system by applying the WebRTC. Since it is a platform independent, we could capture the participant faces from anywhere without an installation. In addition, the three standard face detection and recognition algorithms were applied in two main processes properly. The result showed that system can improve the class participation enrollment accuracy to be more precise and persuaded the student to attend the class as well. Moreover, the system can install to the classroom easily because it is developed in form of the web application and needs an only web camera for the additional device.

In order to fully describe the texture informations of the image, and to distinguish the sub-regions which contain different texture informations, this paper proposes a method of facial expression recognition based on adaptively weighted improved Local Binary Pattern (LBP). Firstly, the whole face region and expression sub-regions of eyebrows, eyes, nose and mouth are isolated by preprocessing. Secondly, the features of the sub-regions are extracted by improved LBP, the Fisher Linear Discriminant (FLD) is applied to calculated the weights of sub-regions, and then the weighted histograms of expression sub-regions are fused as the histogram of facial expression feature. Finally, the fused features are classified by Support Vector Machine (SVM). The experiments are performed on JAFFE and Extended Cohn-Kanada database(CK+), and the experimental results demonstrate that the proposed method has better recognition performance.

The proliferation of portable and even wearable visual sensing devices e.g. SenseCam, Google Glass, etc. is creating opportunities for automatic indexing and management of digitally-recorded everyday behaviour. Although the detection of semantic concepts within narrow domains has now reached a satisfactory performance level based on automatic mapping from low-level features to higher level semantics, in wearable sensing and life-logging, a diversity of everyday concepts are captured by the images and this challenges the performance of automatic concept detection and activity indexing based on this. In this paper, we investigated and compared factorization methods in utilising the semantics of concept re-occurrence and co-occurrence patterns. The factorized results are then input to activity recognition to show the efficacies in enhancing recognition performances.

Cascade shape regression has been proven to be an accurate, robust and fast framework for face alignment. Recently, a lot of methods based on this framework have emerged which focus on boosting learning method or extracting geometric invariant features. Despite the great success of these methods, none of them are initialization independent, which limits their prediction performance to some complex face shapes. In this paper, we propose a novel initialization scheme called high-quality initial shape estimation to generate high-quality initial face shapes. First, we extract Gabor features to represent facial appearance. Then we minimize the square error between the target shapes and the estimated initial shapes using a random regression forest and binary comparison features. Finally, we use a standard cascade shape regressor to regress the estimated initial shape for robust face alignment. Experimental results show that our method achieves state-of-the-art performance on the 300-W dataset, which is the most challenging dataset today.

Aircraft detachable hatch covers are usually fixed via quick-release screws. Given the number of screws on one hatch cover, it is possible that some of them are forgotten to be tightened (i.e., faulty screws) after the inspection because of careless and overtiredness of ground crews, which may lead to security risks. In this paper, a method based on image recognition is proposed to identify faulty screws. By analyzing the characteristics of the hatch cover images, image threshold segmentation, dilation and erosion operations are firstly used to pre-process the image. Then, every screw section can be approximately located. A series of sub-images each containing only one complete screw are divided from the original image. After that, Hough transformation is adopted to calculate the longest line in each sub-image. Based on the comparative result of the longest line and the predetermined threshold, whether the screw is faulty can be determined. Then, the proposed method is applied to a hatch cover, which shows that it is effective to faulty screws recognition.

In order to carry on the gait recognition fast and effectively, a novel gait recognition based on (2D)² PCA and HMM is proposed in this paper . Firstly, establish a stable background model by using the adaptive background modeling and get the goal of human motion by using background subtraction. As for the existence of the shadow of the human body and inanity, this article makes shadow detection and elimination by using color space conversion respectively and handles human target image soothingly by using regional filling and morphological filtering on smoothing. the number of high-dimensional video images is high, uses the (2D)²PCA features extracted to reduce the dimensions so as to solve the curse of dimensionality, makes use of HMM to classification training of Gait features extracted, then the classification results are analyzed. This gait recognition system is achieved loading OpenCV under VC++6.0 visual library. Our experimental results demonstrate that the method is effective and has achieved a good recognition effect on CASIA gait database including three different multi-views.

For problem of influence of different size of receptive fields to DCNN modeling on offline handwritten Chinese character recognition (HCCR), the relationships of the receptive field, the number of parameter, the number of layer, the number of feature map and the size of the area occupied by the basic strokes of Chinese characters have been deeply researched and verified with experiment. With a Softmax classifier of output layer, GPU techniques are applied to accelerate model training and Drop-out method is adopted to prevent over-fitting. The research results of the theory and the experiment are important reference in the light of reasonable or effective selection of receptive field size for DCNN model in HCCR applications. It also provides a method for selecting the size of the receptive field for DCNN in HCCR.

Due to the target-aspect sensitivity of high-resolution range profile (HRRP), the average range profile template of equiangular division is used in the method of Max Correlation Coefficient-Template Matching Method (MCC-TMM) according to the scattering center model. In fact, the target electromagnetic scattering can’t be described perfectly by scattering center model. The sensitivity of target HRRP is not the same at different attitude angles. The impacts of the equiangular division under different target-aspect on the target recognition are studied in this paper. A new frame segmentation method based on cross correlation coefficient is proposed. Simulation results based on five aircraft models show that the presented method can improve recognition performance efficiently in comparison with MCC TMM.

Estimating focus of attention of individuals highly depends on head pose. This paper proposes an entropy weighted Gabor-phase feature description (EWGP) for head pose estimation. Gabor features represent robustness and invariability in different orientation and illuminance. However, this is not enough to express the amplitude character in images. Instead, phase congruency functions well in amplitude expression. Both illuminance and amplitude vary in terms of different regions. We regard entropy information as vote to evaluate the two aforementioned features. More specifically, entropy is represented for the randomness and content of information. We aim to utilize entropy as weight information, to fuse Gabor and phase matrix in every region. The proposed EWGP represents dramatically different when comparing to other feature matrix in datasets Pointing04. Experimental results demonstrates our case is superior to state of the art feature matrix.

In order to solve the identification of projectile surface defect category of which body defect detection system, the classifier of the body defect detection system was designed. The mathematical model of BP neural network and support vector machine (SVM) network classifier were established respectively and realized by using VC + + program and MATLAB, the number of nodes in the middle layer were determined, and the detection performance of the two kinds of classifiers were tested. Test samples were collected from magnetic particle detection images of 3 models which included 20 samples containing cracks and 600 without defects. The results show that the SVM defect classification network classifier has higher recognition rate than the BP neural network, but BP network has stronger stability classification than the SVM.

The aim of the paper is to present the neural image analysis as a method useful for identifying the position of the corpus luteum of domestic bovine on digital USG (UltraSonoGraphy) images. Corpus luteum is a transient endocrine gland that develops after ovulation from the follicle secretory cells. The main function of the corpus luteum is the production of progesterone, which regulates many reproductive functions. In the presented studies, identification of the corpus luteum was carried out on the basis of information contained in ultrasound digital images. Position of the corpus luteum was considered in two locations: on the surface of the ovary and within its parenchymal. Prior to the classification, the ultrasound images have been processed using a sharpening filter - unsharp mask. To generate a classification model, a Neural Networks module implemented in the STATISTICA was used. Five representative parameters describing the ultrasound image were used as learner variables. On the output of the artificial neural network was generated information about the location of the corpus luteum. Results of this study indicate that neural image analysis may be a useful instrument for identifying the bovine corpus luteum in the context of its location on the surface or in the ovarian parenchyma. Best-generated artificial neural network model was the structure of MLP (Multi Layer Perceptron) 5:5-364- 285-1:1.

Image segmentation is one of the most important parts of image processing. Several segmentation models have been proposed during study for recent decades. However noise, low contrast, and intensity inhomogeneity on images are still big challenges for image segmentation. Thus this paper presents an improved segmentation method based on well-known local Gaussian distribution fitting (LGDF) model. We first apply automatic initialization based on simple threshold segmentation to dealing with the drawback that LGDF model is sensitive to initialization position. Then we utilize result of effective and efficient Canny edge detector to get noteworthy edge information and after further processing we gain an edge field. The edge field is used to reduce the probability of local minima on regions far from true boundaries and to force evolving curve to snap to target boundaries. The experimental results demonstrate the advantages of our method on not only medical and synthetic images but also some natural images.

Peach fruit has inhomogeneous colors including green, white and red. The work aimed at studying peach fruit recognition method under natural environment. Firstly, peach was conducted with image segmentation pretreatment using OTSU dynamic threshold segmentation method based on R-G color description. Fruit region was demarcated in original image. Secondly, peach fruit was distinguished using improved NNPROD algorithm after accelerated optimization. At last, the effectiveness of the method was evaluated by experiments.

We propose a novel external force for active contours by normalizing normal and tangent components of the gradient vector flow (GVF) along a generalized edge within the iteration process. The normal and tangent components normalization based GVF (NTCN-GVF) is inspired by the CN-GGVF which normalizes the x- and y-components of the generalized GVF (GGVF) to strengthen the smaller downward component of the external force within the long and thin indentations (LTIs). However, the strengthening effect is sensitive to the orientation of LTIs and excessive in homogeneous areas. NTCN-GVF behaves like CN-GGVF along the edge and conventional vector-based normalized GVF in homogeneous areas. Consequently, the NTCN-GVF snake can capture differently orientated LTIs and preserve weak edges while maintaining other desirable properties of enlarged capture range and noise robustness. Finally, experimental results are presented to verify the effectiveness of the method.

In this paper, an interactive image segmentation method with high accuracy and low time consumption is developed. The method regards the "shrinking bias" issue of traditional graph cuts as a benefit and makes full use of it by using the deformed multiresolution technique, which can also provide a partial solution to it incidentally. The input image is first coarsened deformedly to some low resolutions with the different width-length ratios simultaneously, and then GrabCut method is applied on them to obtain the different segmentations. To sum up the differences of these coarse labeling results, a "weighted map" is constructed to present possibilities of each area for foreground or background, which can describe the object in details with high accuracy. Finally, the "weighed map" is used to refine the trimap for building the more accurate Gaussian mixture models and graph cuts model to assign the final segmentation labeling. Our method is evaluated on two famous benchmarks extensively. The experimental results indicate that our proposed method has the higher segmentation accuracy as well as the lower time consumption when compared with the GrabCut and even the recently proposed OneCut.

This paper proposes an interactive texture segmentation method based on GrabCut. In order to extract the texture features effectively, a new texture descriptor is designed by integrating the nonlinear compact multi-scale structure tensor (NCMSST) and total variation flow (TV-flow). NCMSST is constructed by means of dimension reduction and nonlinear filtering for the traditional multi-scale structure tensor (MSST), and TV-flow is used to compensate the loss of large-scale texture descriptive ability by extracting local scale information. Then, the GrabCut framework is applied to deal with the texture image segmentation, and the corresponding experiment results demonstrate the superiority of our proposed texture descriptor in terms of high efficiency and accuracy.

Hierarchical grouping and window scoring are two important branches of region proposal. Each branch has its advantages and disadvantages. We propose a novel region proposal framework based on saliency detection to integrate their advantages. We first use salient region detection method to divide an image into salient regions and non-salient regions. In salient regions, we use hierarchical grouping method to generate proposals. On the contrary, in the nonsalient regions, we use window scoring method. At last, linear combination is employed to fuse the different scores of these two methods. Experiments show that our method achieves the superior quality to the state-of-the-arts.

Optical coherence tomography (OCT) is a new imaging technology which is widely used in the field of ophthalmology, and retinal tissue layers segmentation plays an important role in the diagnosis of retinal diseases. This paper proposed an OCT macular retinal segmentation method based on the prior information of retinal structure and the optimized boundary tracking algorithm and realized the automatic segmentation of nine retinal layers. After image preprocessing, according to the multi-scale morphological operations and retinal structure characteristics, the optimal initial points were acquired in the parafovea domain. According to the new definition of boundary description feature, this paper optimized the traditional boundary tracking algorithm, and segmented the retinal boundaries. This paper analyzed 100 retinal OCT images, which come from 50 healthy participants from 18 to 29 years old, then compared our segmentation results with graph-based segmentation results and manual segmentations labeled by two experts. Experimental results showed that our method can accurately and effectively segment nine retinal layers (mean square error of boundary position is 1.18 ± 0.40 pixels), and is close to the results of manual segmentation (1.06±0.22 pixels), better than the literature segmentation results (3.02±1.03 pixels).

We present a novel method to segment an object from multiview images using level set method. Our approach takes advantage of the unique property of level set method in the flexibility of objective energy function design and the adaptability to cut boundary with arbitrary topology. We introduce an iterating optimized 3D level set framework for view coherent segmentation and propose three forces in this framework to drive the convergence of level set to the ideal boundary. In between, the point cloud term and the edge term are designed to give an as-good-as-possible boundary indicator for the level set function, while the local color discriminative classifier is iteratively updated with the multiview silhouette and the 3D point cloud to drive the deformation of the zero level set. Extensive experimental results demonstrate that our approach can produce much more accurate edge localization and more coherent segmentation result across views, compared with the state-of-the-art methods, even for the case of very challenging foreground topologies and ambiguous foreground-background color distribution.

Focus on the multi-component image segmentation issue, a hierarchical model is proposed in this paper. The idea is to do segmentation iteratively. The (k+1)-th implementation is carried out not on the whole image domain but on the subimage which is detected as the objects region at the k-th segmentation. In order to achieve this purpose of selective segmentation, a region characteristic function which takes 1 for pixel in the given region and 0 otherwise is introduced, and a novel energy function is proposed based on it. The proposed energy function is convex, thus it can easily apply the fast minimization algorithm and obtain the global minima. In this paper, the well-known split Bregman method is used to minimize the proposed energy function. Experiments demonstrate that the proposed model is able to deal with multicomponent images. And comparisons show that the model is more accurate and efficient.

The performance of the classic split-and-merge segmentation algorithm is hampered by its rigid split-and-merge processes, which is insensitive to the image semantics. This paper proposes efficient algorithm and computing structure to optimize the split-and-merge processes by using the optimal dichotomy based on parallel computing. Compared to the common quadtree method, the optimal dichotomy split algorithm is shown to be more adaptive to the image semantics, which means it can avoid excessive split to some degree. We also overcome the problem that the merge iteration process requires too much by diving the image into some fixed width and height sub-images, these sub-images have one pixel wide boarder overlapped to confirm the edge information not lost. Based on the parallel computing model and platform, these sub-images’ edge can be detected within the map procedure rapidly, then we reduce the sub-images’ edges to get the whole final image segment result.

Changes in the structure of the retina can reflect a variety of pathological physiological changes. To analyze the structural characteristics of the retina layers, an automated segmentation algorithm of retinal layers was developed. This algorithm, based on the Dijkstra's algorithm, limiting the search region with statistics information of layer thickness information, constructs a graph from every 2D OCT image and use a shortest path algorithm to iteratively segment multiple layers. The experiments showed that this segmentation algorithm has great repeatability, accuracy, and high efficiency.

According to the evaluation criteria of edge detection, for the design needs of the best edge filter, selection rule of wavelet basis for edge detection is determined. And in this paper multi-scale local modulus maximum of wavelet is used for edge detection; while for threshold selection, block adaptive method is used. In contrast to conventional modulus maximum edge detection method, the improved algorithm can achieve better edge detection effect while suppressing noise.

Intelligent transportation system is one of the hot topics of current research, including a very critical technology is automatic identification system of traffic signs. In identification system, since image acquisition is affected by the environment, the resulting image quality is uneven, which requires an algorithm suitable for a variety of quality digital images to identify the type of traffic signs. This paper makes some improvement of the originally perfect Canny edge detection operator, to make it suitable for different images, so we can quickly and accurately detect the image edge, further facilitate matching work, automatically identify traffic signs. Experimental results show that the improved Canny edge detection algorithm is fast, and the detected edge is clear and accurate.

In order to select the optimal threshold for pedestrian segmentation in infrared images, a novel algorithm based on local autocorrelation is proposed. The algorithm calculates the local autocorrelation feature of a given image. Next, it constructs a new feature matrix based on this spatial correlation and the original grayscale. Then, it obtains an automatic threshold related with local combined features using the geometrical method based on histogram analysis. Finally, it extracts the image region of pedestrian and yields the binary result. It is indicated by the experiments that, the proposed method performs good result of pedestrian region extraction and thresholding, and it is reasonable and effective.

With the wide application of machine vision technology in agricultural fields, the image-based pests diagnosis of rice planthoppers becomes a fast and effective approach. Although the effective automatic segmentation is a very important pretreatment technology for the analysis of rice planthopper images, the traditional graph cuts based active contour method has the shrinking bias problem during segmentation. This paper proposes an innovative approach to overcome that problem. By changing bidirection dilation of the contours to inside direction dilation to improve the overlap of adjacent contour neighborhoods and reduce the computation scale, the shrinking bias problem is improved effectively. The result shows that the approach adopted in this paper can clearly segment the contour of rice planthoppers.

In order to conquer the problems of time consumption, over segmentation and over merger existing in watershed segmentation and merger algorithm, a watershed algorithm in wavelet filed has been proposed in this paper. In the algorithm, the original image is decomposed into lower resolution ratio by wavelet transformation so as to reduce the processing data and enhance the speed of algorithm. Because over segmentation problem originates from small fluctuation or noise, a simple and effective technique for selecting optimal threshold is designed. Moreover, on purpose of avoiding the loss of edge information, a merging strategy based on edge information is introduced in the region merging. The experimental results show that the processed images obtained by our algorithm succeed in avoiding the over segmentation and over merger of watershed algorithm, and its calculating efficiency is also enhanced to some extent.

A study was carried out to analyse the quality and usefulness of methods of edge identification in the case of images of winter rape leaves. For this purpose a five available methods that are implemented in Matlab were used. The methods such as: Sobel, Robert, Prewitt, Canny's algorithms and on the other hand Laplacian of Gaussian were compared. The study focused on the image characteristics extraction and based on the results select those methods that will best respond on the research problem, which was to found the relationship between the detected edges, and incidence spots of fungal diseases in the oilseed rape cultivation. The aim of the article was to present the possibilities of using Matlab function to compare two approaches to edge detection. The first approach was the transformation of the images into gray-scale and create a histogram. The second one focused on dividing the image into three RGB components palette and then proceed with thresholding. On such prepared samples was conducted edge detection by used the above-mentioned methods.

A new segmentation algorithm based on partial adaptive thresholds is proposed to divide the cell images efficiently. First, it divides the whole image into several parts, then computes the grads histogram each parts and performs OTSU segmentation, at last, it considers the effect of the noise in the image and removes the noise with morphologic noise filter. The experimental results show that the algorithm has a good effect to differentiate and divide the detail of the cell image, and it is applied to the image that is not obvious between background and objects and being some noise.

Intensity inhomogeneity and noise are two major obstacles for segmenting medical images. The global kernel mapping based piecewise constant model (PCM) has superior performance on resisting noise, though it fails to cope with intensity inhomogeneity. In order to overcome the difficulty caused by intensity inhomogeneity, we first establish an energy based on kernel mapping in a neighborhood of a pixel. Then such energies for all pixels in an image are integrated to formulate the energy of the local kernel mapping based PCM. Energy minimization has been implemented in level set framework. Comparative experimental results show that our proposed model has higher segmentation accuracy in the presence of intensity inhomogeneity and noise.

This article proposed an image segmentation algorithm based on Voronoi Diagram (VD). VD is a well-known technique in computational geometry, which generates clusters of intensity values using information from the vertices of the external boundary of Delaunay triangulation (DT). The image domain is partitioned into a group of sub-regions by Voronoi tessellation, each of which is a component of homogeneous regions. In this way, it is possible to produce segmented image regions. Voronoi-based image segmentation can be extended to RGB images without converting them into grayscale. Its mathematical formulation and practical implementations are also discussed and given. We test the method on and also compare it with K-means algorithms using segmentation examples; the results demonstrate excellent performance and competence of the proposed method.

Denoising is the primary preprocessing step before subsequent clinical diagnostic analysis of MRI data. Common patch-based denoising methods rely heavily on the degree of patch matching, which limits their performance by the necessity of finding sufficiently similar patches. In this paper, we propose a global filtering framework, in which each voxel is restored with information from the whole 3D image. This global filter is not restricted to any specific patchbased filter, as it is a low-rank approximation using the Nyström method combined with a low sampling rate and a kmeans clustering adaptive sampling scheme. Experiments demonstrate that this method utilizes information effectively from the whole image for denoising, and the framework can be applied on top of most patch-based methods to further improve the performance.

The de-noising effect of many methods depends on the accuracy of the noise variance estimation. In this paper, we propose an effective algorithm for the noise variance estimation in shearlet domain. Firstly, the noisy image is decomposed into the low-frequency sub-band coefficients and multi-directional high-frequency sub-band coefficients based on the shearlet transform. Secondly, based on the high-frequency sub-band coefficients, the value of the noise variance is estimated using the Median Absolute Deviation (MAD) method. Thirdly, we choose some variance candidates in the neighborhood of the estimated value, and calculate the Residual Autocorrelation Power (RAP) of every variance candidate based on the Bayesian maximum a posteriori estimation (MAP) method. Finally, the accuracy of the noise variance estimation is improved using the residual autocorrelation power. A range of experiments demonstrate that the proposed method outperforms the traditional MAD method. The accuracy of the noise variance estimation has increased by 91.2% compared with the MAD method.

Nonlocal Means is an effective denoising method, which takes advantage of the fact that natural image has selfsimilarity. However, the original nonlocal means may not find enough similar candidates for some non-repetitive image blocks. In order to mitigate these drawbacks, we propose an improved nonlocal means method using adaptive preclassification in this paper. The proposed method employs the threshold-based clustering algorithm to classify noisy image blocks adaptively. Then, a rotational block matching method is adopted to find the appropriate distance measurement between two blocks in an image. Experimental results on a set of well-known standard images show that the proposed method is effective, especially when the image contains large amount of noise.

Remote sensing satellite image de-noising is an important step in image preprocessing. Four de-noising algorithms for remote sensing images are investigated in this paper: BM3D, DCT, K-SVD, and wavelet threshold method. A modified method based on K-SVD is also proposed. The basic principles of the four kinds of de-noising methods are introduced, and the modified method is analyzed thoroughly. In the improved method, high-frequency information is extracted through High-pass filtering, and then sparse representation and reconstruction are carried out to maintain the detail information. Comparative experiments are conducted to reveal the advantages and disadvantages of each method in satellite images de-noising, and the results demonstrate that the proposed method can get better de-noising result as well as keeping the details at the same time.

Image denoising is a very important step in image processing. In recent years, a lot of image denoising algorithms have been proposed, several of them are transform domain based methods, such as wavelet, contourlet, and shearlet. Shearlet is a new type of multiscale geometric analysis tool, which can obtain a sparse representation of the image and produce the optimal approximation. The transform generates shearlet functions with different features by scaling, shearing, and translation of the basic functions. In this paper, we introduced shearlet transformation into optical coherence tomography images to reduce noise, and proposed a multiscale, directional adapted speckle reduction method. Experiment results showed the effectiveness of the proposed method.

This paper proposes a simple and accurate estimation of the additive white Gaussian noise for the noise-contaminated digital images. One can easily estimate the noise level through singular value decomposition (SVD) to the noise-polluted image if an image is deteriorated by the additive white Gaussian noise. As described in the paper, the sum of some specific singular values has the linear relationship with the standard deviation of noise. Based on no correlation between noises, we add known noises upon a noise image. Then noise level is estimated by solving a nonlinear over-determined matrix equation. The proposed algorithm was experimentally tested by the benchmark images and outperforms estimation method of selecting weak textured patches using principal component analysis (PCA). The proposed method is more independent on the original image information and presents a higher accuracy and a stronger robustness for a range of noise level in various images.

The regularization method has recently been an efficient approach to make the process of image denoising wellposed, while preserving image textures and details become more intractable. However, when it's applied to image denoising industry in 5G environment, iterative computation time for TV variation regularization algorithm must be reduced, considering the requirements for practicability. In this paper, a fast algorithm based on Chambolle dual factors is presented and denoising duration of TV denoising model is improved by reducing stopping criteria for iteration on the premise of unchanged denoising effect based on the utility concept. In addition, evaluation methods for the edge protection effect are improved and personal subjective factors brought by traditional evaluation methods are reduced. Furthermore, numerical experiments show that the proposed method can achieve better results in removing the noise, restraining staircase effect, preserving directional texture as well as significantly reduce denoising duration.

In order to reduce the shadow in traditional linear SAR image, a multi-angle SAR non-coherent image fusion algorithm based on HIS statistic characteristics is proposed. By converting SAR image to HIS space, a threshold based on the statistic characteristics of SAR image’s HIS parameter is calculated and SAR images of different observation angles, which have been filtered according to the threshold previously calculated, are fused by non-coherent accumulation method. The fused image not only effectively reduces the image shadow, but also improves the detection probability of targets. The simulation results verify the effectiveness of the proposed algorithm.

Aiming at solving the problems of part edges loss and blurred texture information in the image fusion process of infrared light image and visible light image, an improved algorithm based on regional texture smoothness and gradation mutation degree for the infrared light and visible light image fusion is proposed. Firstly, Non-subsampled Contourlet transform(NSCT) is adopted. The multi-scale and multi-direction sparse decomposition is performed for the infrared light source image and visible light source image. Then the low-frequency component reflecting the image approximate contents and the every bandpass directional subband components reflecting the image detail characteristics are obtained respectively. The fusion method based on the gradation mutation weighted average for the low-frequency subband component is adopted, and the fusion method based on the composition of regional texture smoothness and Laplace energy sum for the high-frequency subband is adopted. Finally, the fusion image is reconstructed through the NSCT reversed transform. The experimental results show that in the condition of reserving the source image information, the fusion image clarity is raised, the detail information and brightness contrast are enhanced by this fusion method.

Sparse representation based image fusion has been widely studied recently. However, it’s not popular in some fields for the high time complexity. In this paper, a new image fusion method based on group sparse representation is proposed to overcome this problem. The K-SVD method is utilized to get the sparse representation of the source images. Therefore, it is necessary to find the best size of the group according to its property about time consuming. And there is no need to sparse all the patches once but to sparse some groups simultaneously. Because every group image vectors sparse representation is unique from the others, using the parallel-processing strategy can reduce the time badly. Besides, all dictionaries are learned from local source image vectors, so the quality of the results fused by the group sparse representation method will be better than those fused by the normal sparse representation methods. Compared with four types of state-of-the-art algorithms, the proposed method has the excellent fusion performance in experiments.

The modified image fusion methods are developed for merging ZY-3 remote sensing images. The main objective of this research is to study the effects of image fusion, based on the information capacity of panchromatic and multispectral ZY-3 images. The image fusion techniques include PCA transform, BT transform, G-S transform, and HSV transform. The experimental results show that the spatial resolution of images merged by PCA, BT G-S and HSV transforms is higher than the original ZY-3 image, and these four transforms techniques merge the features of the panchromatic and multispectral images very well. However, the hue of the HSV merged image is different from the original image, which indicates HSV led to obvious color distortion. The hue of the PCA merged image is also approximately the same as for the original image, without image distortion. Furthermore, the discussion of the information capacity considers quantity in terms of the spectral authenticity and the entrop, which indicates images merged by PCA showing higher spatial resolution and better spectral features, compared with images merged by the other three transforms. Although losing some spectral information, images merged by HSV also showed higher spatial resolution. Therefore, PCA is very efficient and highly accurate for merging ZY-3 images.

Using the simplified pulse coupled neural network (S-PCNN) model and hue, saturation and value (HSV) color space, an effective color image fusion algorithm was proposed in this paper. In the HSV color space, using S-PCNN, the feature region clustering of each component (H, S, V) was done; the fusion of the various components of the different source images based on the oscillation frequency graph (OFG) was achieved; then through the inverse HSV transform to get RGB color image, the fusion of the color image were realized. Experimental results show that the algorithm both in the subjective visual effect and objective evaluation criteria is superior to other common color image fusion algorithms.

In this paper, two novel non-reference objective image fusion quality evaluation metrics are presented. The novel metrics are based on the correlation between human visual perception and quantized discrete cosine transform coefficients. Hamming distance is adopted to calculate similarity, and then the novel metrics are deduced. The influence of quantization table selection is analyzed. Experiments verify the effectiveness and efficiency of the novel metrics.

In order to enhance texture and contrast information, a fractional differential algorithm using a family of controlling functions was proposed in this paper. Firstly, a fractional differential texture enhancement mask was put forward. In order to enhance the contrast of the image while enhancing texture, a family of control functions was designed, and then, an improved mask was get. To determine the optimal fractional differential order, an adaptive differential function is designed. Experiments and results showed that the proposed method has good effectiveness for image texture and contrast enhancement.

Motion blur due to camera shaking during exposure is one common phenomena of image degradation. Image motion deblurring is an ill-posed problem, so regularization with image prior and (or) PSF prior is used to estimate PSF and (or) recover original image. In this paper, we exploit image edge prior to estimate PSF based on useful edge selection rule. And we still adopt L₁ norm of PSF to ensure its sparsity and Tikhonov regularization to ensure its smoothing during the PSF estimation procedure. And the Laplacian image prior is adopted to restore latent image. The experiment shows that the proposed algorithm outperforms other algorithms.

In the present paper the target restoration of range-gated imaging in scattering environments is investigated. The degradation matrix of the laser beam and the scattering mediums is estimated by a specified backscattering image from the atmospheric scattering mediums. A variational model is proposed to eliminate the influence of the degradation matrix. Experiments of range-gated imaging are carried out to capture the images of the targets and scattering mediums. The proposed method is performed to restore the target images based on the backscatter images from the scattering mediums. The experimental results show the proposed variational method is effective to eliminate the effects of nonuniformity of the laser beam and smoke and to obtain the correct reflectivity distribution of the target, as well as smoothing the noise.

This letter presents a novel enhancement method for fog-degraded images based on dominant brightness level analysis in analyzing the characteristics of the images captured by daylight sensor on photoelectric radar surveillance system. We first perform discrete wavelet transform(DWT) on the input images and perform contrast limited adaptive histogram equalization(CLAHE) operation on LL sub-band, and then decompose the LL sub-band into low-,middle-,and high-intensity layers using Gaussian filter. After the intensity transformation and inverse DWT, the resulting enhanced image is obtained by using the guided filter.

The popularity of vision-based surveillance systems arouses much research attention in improving the accuracy and efficiency of people localization. Using probabilistic occupancy map (POM) becomes one of the mainstream approaches to people localization due to its great localization accuracy under severe occlusions and lighting changes. However, to enable the usage of rectangular human models and the subsequent 2-D integral image computation, it is assumed that videos are taken at head or eye level. Even so, the computation complexity is still high. Moreover, surveillance videos are often taken from security cameras located at a higher-up location with an oblique viewing angle, so that human models may be quadrilateral and the pixel-based 2-D integral image cannot be utilized. Accordingly, we propose the use of 1-D integral images which are produced for foreground object(s) in an image along equally-spaced line samples originated from the vanishing point of vertical lines (VPVL). Experimental results show that the proposed approach does improve the efficiency and effectiveness of the POM approach in more general camera configurations.

Recovering a latent image from its blurry version is a severely ill-posed problem. In this paper a post process method is proposed for accurately estimating motion blur kernel based on its prior knowledge. And considering the small details destroy blur kernel estimation, an image decomposition process is executed before the estimation, which can decompose the image into cartoon and texture components. In the iterative framework, the cartoon that contains the main structures will be used to blur kernel estimation for avoiding the artifacts introduced by small texture. In addition, the algorithm adopted in the paper dynamically adjusts the size of patch which contains blur kernel instead of using the fix one as other works. Experimental results show that our method can get the more precise blur kernel and obtain the inspiring deblurring version from single blurry image.

In the haze and other weather conditions, the scattering of atmospheric particles leads to a serious degradation of the captured images. In this paper, we present a new fast defogging method based on physical model. The algorithm is based on the atmospheric scattering model to simplify the atmospheric scattering model by using the white balance. A fast bilateral filtering method is used to estimate the atmospheric veil, and then recover the visibility. The time complexity of the algorithm is linear function of the number of image pixels, which has a very fast execution speed. Experimental results show that the proposed algorithm can effectively restore the contrast and color of the scene, so that the image can be improved significantly.

A new method is proposed on unsharp masking sharpening technique for image enhancement, and it suppresses the noise sensitivity widely existing in traditional unsharp masking sharpening algorithm. This algorithm can efficiently suppress the noise in relatively flat regions, it sharpens and enhances the regions which require sharpening and enhancement. In this paper, we use the different gradient weighting coefficients according to the weight distribution to process the different detailed regions. By taking advantage the characteristics of human vision, it efficiently enhances the particular region that is sensitive to the human eyes. Compared with several unsharp masking sharpening algorithms, this algorithm can efficiently suppress the noise in the image, smooth the relatively flat region, and enhance the details.

Hyperspectral imagery has high spectral resolution, and spectrum of it has always been non-linear. The traditional classification methods cannot get better result when the number of samples is small. Combined with the theory of deep learning, a new semi-supervised method based on stacked autoencoders (SAE) is proposed for hyperspectral imagery classification. Firstly, with stacked autoencoders, a deep network model is constructed. Then, unsupervised pre-training is carried combined SOFTMAX classifier with unlabeled samples. Finally, fine-tuning the network model with small labeled samples, the SAE-based classifier can be got to learn implicit feature of spectrum of hyperspectral imagery and achieve classification of hyperspectral imagery. According to comparative experiments, the results indicate that the proposed method is effective to improve the hyperspectral imagery classification accuracy in case of small samples.

Though the support vector machine and relevance vector machine have been successfully applied in hyperspectral imagery classification, they also have several limitations. In this paper, a hyperspectral imagery classification method based on the probabilistic classification vector machines is proposed. In the Bayesian framework, a signed and truncated Gaussian prior is adopted over every weight in the probabilistic classification vector machines, where the sign of prior is determined by the class label, and the EM algorithm has been adopted for the parametric inference to generate a sparse model. This algorithm can solve the problem that the relevance vector machine is based on some untrustful vectors, which influences the accuracy and stability of the model. The experiments on the OMIS and PHI images were performed, and the results show the advantages of the hyperspectral imagery classification method based on probabilistic classification vector machines.

The analysis and interpretation of satellite images generally require the realization of a classification step. For this purpose, many methods over the year have been developed with good performances. But with the explosion of VHR images availability, these methods became more difficult to use. Recently, deep neural networks emerged as a method to address the VHR images classification which is a key point in remote sensing field. This work aims to evaluate the performance of fine-tuning pretrained convolutional neural networks (CNNs) on the classification of VHR imagery. The results are promising since they show better accuracy comparing to that of CNNs as features extractor.

Visual features used in state-of-the-art image clustering methods lack of learning, which leads to low representational power. Furthermore, the efficiency of traditional clustering methods is low for large image dataset. So, a fast image clustering method based on convolutional neural network and binary K-means is proposed in this paper. Firstly, a large-scale convolutional neural network is employed to learn the intrinsic implications of training images so as to improve the discrimination and representational power of visual features. Secondly, ITQ hash algorithm is applied to map the high dimensional deep features into low-dimensional hamming space, and multi-index hash table is used to index the initial clustering centers so that the nearest center lookup becomes extremely efficient. Finally, image clustering is accomplished efficiently by binary K-means algorithm. Experimental results of ImageNet-1000 datasets indicate that the expression ability of visual features is effectively improved and the image clustering performance is substantially boosted compared with state-of-the-art methods.

The classification properties of artificial neural networks, i.e. Self-Organizing Feature Map (SOFM), has been used for the qualitative identification of five varieties of potatoes popular in Poland. The research was based on empirical data obtained in the form of digital images of potatoes, generated at various production phases. They serve to generate a “non-model” SOFM typology map that present the centers of classification example clusters. The radial neurons constituting the structure of the generated typological map were given suitable labels representing the individual varieties. This created the opportunity to build a neural separator to effectively classify the chosen varieties of potatoes produced in Poland.

The aim of the research was to investigate the possibility of using the methods of neural image analysis and neural modeling to determine the content of dry weight of compost based on photographs taken under mixed visible and UV-A light conditions. The research lead to the conclusion that the neural image analysis may be a useful tool in determining the quantity of dry matter in the compost. Generated neural model RBF 30:30-8-1:1 characterized by RMS error 0,076378 and this networks is more effective than RBF 19:19-2:1:1 which works in visible light conditions.

Composting is one of the most appropriate methods to manage sewage sludge. In the composting process it is essential to ensure possibly rapid detection of the early maturity stage in the composted material. The aim of the study was to generate neural classification models for the identification of this stage in the composted mixture of sewage sludge and rapeseed straw. These models were constructed using the MLP network topology. The datasets used in the construction of neural models were based on information contained in images of composted material photographed under visible light. The input variables were values of 25 parameters concerning colour of images in the RGB, HSV models and the greyscale and converted to binary images, as well as values of 21 texture parameters. The neural models were constructed iteratively. A neural network developed in a given iteration did not contain inputs, which the sensitivity analysis from the preceding iteration showed to be potentially non-significant. The classification error for the generated models ranged from 2.44 to 3.05%. The optimal model in terms of the lowest value of the classification error and thus the lowest number of required input variables contained 23 neurons in the input layer, 50 neurons in the hidden layer and 2 neurons in the output layer.

This paper describes the research, whose goal was to develop an effective method based on the image analysis techniques for the evaluation of the slugs behaviour in the laboratory studies. The main task of the developed computer method is to assist in evaluating the degree of slugs’ acceptance of different plant species and varieties as food and to evaluate the effectiveness of active substances used against slugs. The laboratory tests are conducted in a climate chamber, into which are placed containers with grazing slugs, leaf circles and a hiding place. A video camera is installed in each container to monitor the slugs’ activity. The data from the cameras are stored on hard disks connected to a digital recording device. The task of the proposed computer algorithms is to perform automatic analysis of the stored video material. Video image analysis can be used to determine parameters relating to the slugs’ daily activity, the speed and trajectory of their movement, and the rate and extent of the damage done to the leaves. This task is performed in several stages including: movement detection, object recognition, object tracking and determination of the quantity of leaf damage.

The soil classification aspect is a very modern item within the scope of property management, and is closely related to managing the land register according to geodetic and cartographic law. The identification and systematics related to the soils in Poland is based on criteria that considers soil development under the influence of the geological features of the soil formation process as well as permanent human operation and use. Soil quality assessment with regard to its use value is increasingly based on IT methods in combination with algorithms and artificial intelligence (AI) tools. The aim of this study is to develop suitable models and implement an IT system to identify and classify the soil valuation classes with use of AI methods.

Image perceptual hashing is a notable concept in the field of image processing. Its application ranges from image retrieval, image authentication, image recognition, to content-based image management. In this paper a novel image hashing algorithm based on SURF and KPCA, which extracts speed-up robust feature as the perceptual feature, is proposed. SURF retains the robust properties of SIFT, and it is 3 to 10 times faster than SIFT. Then, the Kernel PCA is used to decompose key points’ descriptors and get compact expressions with well-preserved feature information. To improve the precision of digest matching, a binary image template of input image is generated which contains information of salient region to ensure the key points in it have greater weight during matching. After that, the hashing digest for image retrieval and image recognition is constructed. Experiments indicated that compared to SIFT and PCA based perceptual hashing, the proposed method could increase the precision of recognition, enhance robustness, and effectively reduce process time.

The aim of this paper was to design and implement an information technology (IT) system supporting the analysis and interpretation of image descriptors. The software is characterized by its versatility and speed in operating while processing series of digital images. The computer system can be expanded by new methods and is dedicated as a kernel of an expert system. The application seeks to extract the parameters of quality characteristics of agricultural crops - in this case, potatoes – in order to generate a set of data as a .csv file. The system helps to prepare the assessment of quality parameters of potatoes and generate mathematical models using Artificial Neural Network (ANN) simulators such as MATLAB ANN Toolbox or STATISTICA ANN toolbox in order to create a training dataset and information in that dataset.

The aim of the study was create a new, non-invasive method of assessing the quality of sugar beet topping using computer image analysis and artificial neural networks. In paper was carried out the analysis the methods used so far to topping assessment of roots and analysis of the possibilities of using the new proposed method. Classical methods allow an assessment only after harvest of roots (after pull out roots), and the proposed method enables the assessment before harvesting sugar beets. The study used 50 images of topped sugar beet roots, which have been subjected to computer analysis in order to improve the image contrast and brightness. The image was converted from color to images in grayscale, and was carried out segmentation and morphological transformations. Binary image was used to determine the surface area and root circuit and topping circiut. This information was used as input to the neural network, which was expanded to two features, ie. the ratio of the areas and circuits. On the output of the network was information about the topping in the form 0 and 1. Created neural network MLP 6:6-26-1:1 allowed for a sensitivity analysis, which returned information about two important features independent, ie. the surface area of the root and root surface area to topping. The analysis found that it is possible to use methods of computer image analysis for non-invasive assessment of the quality topping sugar beets.

In this paper the authors present a research tool in the form of an IT system used to analyse the status of agricultural crops with the simultaneous use of spatial data and raster images sourced from drones. The authors have designed and delivered their original IT system using the latest technologies, including SQL Server 2012, ADO.NET Entity Framework API, Google Maps API, HTML5 and the Visual Studio 2013 integrated development environment. The system comprises a set of applications that support the process of collecting and processing of interrelated geographic data and raster images.

A new feature extraction scheme for evaluating the complexity of Electromagnetic Environment (EME) is presented based on the generalized S transform and morphological pattern spectrum (MPS) in this study. Firstly, the EME signals were transformed to time-frequency image (TFI) by the generalized S transform, which combines the separate strengths of the short-time Fourier transform and wavelet transforms. Secondly, the MPS, which has been widely used in image processing area, is employed to characterize the TFI of EME signals. We also investigated the influence of structure element (SE) to the MPS. Four types of SE, mean the line SE, square SE, diamond SE and circle SE, are utilized and compared for computing the MPS. EME signals with four complexity degree are simulated to evaluate the effectiveness of the presented method. Experimental results have revealed that the presented feature extraction scheme is an effective tool for discriminating the complexity of EME.

A new plantar surface reference system was developed for the investigation of walking characteristic based on plantar pressure. The research involved the recording, image-processing and analysis of signalised plantar pressure video clip of trial of 15 adults who performed a short gait on a custom-built walking access-ramp of comfortable inclination. A plantar TekScan pressure sensing system was placed on the ramp to capture the pressure video clip. Custom-designed soft-rubber targets were affixed to the medial foot axis before the trial. The video clips were processed to obtain the position of the new plantar surface reference system by locating the imprint or signature of the targets in the video frames. Pressure data were extracted from the video frames. The pressure data consisted of plantar-time-integral and peak pressure of four plantar regions. The results showed that the difference in the pressure data was statistically significant at the forefoot region between ascending and descending ramp-walking. Based on the limited number of older adults recruited in the trail, findings shows that they are more predisposed to accidental fall while executing a descending walk.

A high capacity lossless information hiding algorithm that based on histogram shift of prediction residual image is proposed in this paper. Prediction residual image is established by calculating the difference between each pixel and the reference pixel according to the proposed scan orders. Then secret information is embedded by using the method of histogram to shift multiple histogram peaks of prediction residual image, when information hiding is proceed for multiple times, the problem that embedding capability will decrease along with the increase of the embedding levels is improved by alternately changing the scan orders. Experiment results are provided to demonstrate that the proposed algorithm is superior to the other state of art schemes in the terms of embedding capability versus PSNR while image distortion can be still acceptable when the capability reaches 1 bit per pixel.

researchers. By using chaotic maps based random S-box selection, multiple substitution boxes can be used to reduce the correlation among the adjacent pixels of an image but this key dependent nature of substitution methodology makes it vulnerable to chosen plain text attack (CPA). To address these issues, a substitution methodology based on propagating cipher block chaining (PCBC) with a new diffusion technique has been proposed. PCBC is known to be CPA resistant. The effect of first round diffusion is being transferred to next round of diffusion, when first pixel is replaced by last pixel XORed with first the pixel of image. Extensive analyses indicate that proposed solution is secure and achieves best results.

This paper proposes a kind of fast image encryption algorithm based on permutation and diffusion architecture. An improved 1D chaotic map with three control parameters is adopted to enlarge the key space. Generalized Fibonacci- Lucas transform (GFLT) is utilized to change the positions of pixels of plain image in permutation. In order to enhance the security, the round number of permutation relates to image itself and the transform kernel of GFLT is varied and depends on both the chaotic map and plain image. In diffusion stage, the bidirectional diffusion operation is adopted, which reduces the time cost comparing with general diffusion process. Meanwhile, secure hash algorithm (SHA) is used to produce external key streams, which constitute the initial values of chaotic map and the round number of permutation. Hence, our encryption has large key space to resist the brute attack and the ability of resistance of the chosen/known attack due to the improved 1D chaotic map and SHA. Experimental simulations and security analysis both demonstrate that the proposed image encryption method can enhance the security level and at the same time reduce the computation load.

This weakness is a critical threat for privacy with the widely used in the security applications. To protect the privacy and reduce the storage space during the biometric recognition, based on Compressed Sensing and Dual-tree Complex Wavelet Transform, we proposed a novel biometric image encryption algorithm. Firstly, the coefficients matrix are attained by performing DT-CWT on biometric image for its higher near shift-invariance property and greater directional selectivity. Then, the measurement matrix is generated by pseudo-random gauss measurement matrix which combined with one-dimensional (1-D) Logistic chaotic system. To improve the security of the encryption algorithm, the measurement matrix is scrambled and diffused by combining with 1-D Logistic mapping and Fibonacci scrambling algorithm. At last, the orthogonal matching pursuit (OMP) algorithm is employed to reconstruct the original image approximately. The experimental results demonstrate that the proposed encryption algorithm not only achieves the state of the art performance but also outperforms the existing image encryption methods with respect to the compressibility and the security.

Digital watermarking is an efficient technique for copyright protection in the current digital and network era. In this paper, a novel robust watermarking scheme is proposed based on singular value decomposition (SVD), Arnold scrambling (AS), scale invariant feature transform (SIFT) and majority voting mechanism (MVM). The watermark is embedded into each image block for three times in a novel way to enhance the robustness of the proposed watermarking scheme, while Arnold scrambling is utilized to improve the security of the proposed method. During the extraction procedure, SIFT feature points are used to detect and correct possibly geometrical attacks, and majority voting mechanism is performed to enhance the accuracy of the extracted watermark. Our analyses and experimental results demonstrate that the proposed watermarking scheme is not only robust to a wide range of common signal processing attacks (such as noise, compression and filtering attacks), but also has favorable resistance to geometrical attacks.

This paper proposes a digital watermarking algorithm of combining the chaos with the wavelet transform. Firstly, three-color separation is performed over dual carrier images; secondly, chaotic scrambling is carried out over RGB components of the watermark using different secret keys, followed by wavelet transform; then, corresponding components are embedded, allowing for improved watermark security, as different secret keys are used for different components; furthermore, according to the property of human vision system being variably sensitive to different regions of the wavelet transformed image, the watermark is embedded into medium and low frequency domain of wavelet transform, so as to balance transparency and robustness of the watermark. Experimental results show that this watermarking algorithm has kept image quality relatively well with high security, and exhibited good robustness to such attacks as Gaussian and compression etc.

Through the research of the existing image compression algorithms based on wavelet transformation, and from the construction of wavelet filter, by calculating the image local measures with directional characteristics, this paper selects appropriate measure predictor to separately deal with the lowest frequency sub-band coefficients, at the same time, while more efficiently scanning and positioning, quantitatively coding for the other high frequency sub-band coefficients through means of the maximum table. Experimental results show that the improved algorithm greatly reduces the coding time in the premise of no reconstructed image quality changes.

Credit card account number detection and extraction from camera-based images is of vital importance in automatically inputting system of mobile devices. In this paper, we propose a novel framework to detect and extract credit card account number from camera-based images. Firstly radon transformation is used to detect and correct the degree of skew of the credit card, Secondly a morphological binary map is generated by calculating difference between the closing image and the opening image. Then horizontal projection and k-means are applied to get the card-number lines. Candidate regions are connected by using a morphological dilation operation. Last text lines are refined using a sliding window and an SVM classifier trained on two local texture distribution features: HOG and an improved local region binary pattern (LRBP). Experiences show the proposed method is robust to different contrast and complex environment.

In this paper, a new robust multiple description image coding method with a modified interleaving sampling and a modified interpolation method using block compressed sensing is proposed. In the encoding process, the original image is decomposed into several sub-images by using the modified interleaving sampling and the redundant bits are added to enhance the reconstruction accuracy. For each sub-image the description is obtained in the block compressed sensing (BCS). In the decoding process, the signal is reconstructed from the sparse measurements by using the optimization algorithm. Our analysis and simulation results showed that the proposed method is a balanced multiple description coding scheme with higher accuracy of reconstruction and higher efficiency of coding.

Aim to authenticate the integrity of 2D CAD engineering graphics, two reversible watermarking schemes based on asymmetric histogram shifting and complementary embedding are proposed. On the basis of coordinates and phases data correlation, multiple prediction errors are obtained to construct asymmetric histograms. Watermark is embedded by modifying the asymmetric histograms in opposite directions with dual complementary embedding strategy. Experimental results indicate that the proposed method outperforms prior works not only in capacity, but also in imperceptibility.

In this paper, we propose a discrete wavelet transform (DWT)-singular value decomposition (SVD) gray-scale image watermark method based on the irregular Low-density Parity-check (LDPC) codes with unequal error protection (UEP). As one of the best effective ways of protecting copyright of multimedia data, digital watermark technology is widely researched by experts and learners. The difficulty of researching gray-level watermark lies in large embedding capacity. As there exists most important parts, less important portions and non-important materials in the gray-level watermark image, it is not reasonable to treat equally different parts of gray-level watermark image. According to this idea, we put forward the method by using irregular LDPC codes with UEP to protect different importance-level parts. The high degree bits protect important parts, the low-degree bits protect non-important portions. The experimental results indicate that the proposed scheme can apparently achieve high imperceptibility of embedded image and high robustness defined by the peak signal to noise ratio (PSNR) against image processing attacks.

It is a challenging task to build efficient and robust model for aircraft detection. In our object recognition system, aircraft detection is a main task, which faces various problems, such as blur, occlusion, and shape variation and so on. Existing approaches always require a set of complex classification model and a large number of training samples, which is inefficient and costly. In order to deal with these problems, we employ location based informative features to reduce the complexity of training data. With the employment of location based informative features, simple classifiers will manifest high performance instead of complex classifier which requires more complicated strategy for training. Further, our system needs to update the model frequently which is similar to online learning method, in order to reducing computational complexity, a very sparse measurement matrix is applied to extract features from feature space. The construction of this sparse matrix is based on the theory of sparse representation and compressed sensing. From the experimental results, the detection rate and cost of our proposed method is better than other traditional method.

An image encryption method based on fractional Fourier transform (FRFT) and odd-even quantification is proposed in this paper. First of all, Arnold transform is used to scramble a binary watermark image P to obtain W. The carrier image I is divided into 8×8 overlapping blocks, and then a FRFT with an order of (a,b) is performed on each block. After that, odd-even quantification is carried out on the transform coefficients of each block. Then one-bit watermark information is embedded into each block. Finally, the FRFT with an order of (-a,-b) is performed on each block embedded with the watermark information, obtaining the watermarked image. Simulation and various attack tests are carried out. The results show that the algorithm has very good robustness against image cut, salt and pepper noise, brightness adjustment, contrast adjustment, etc. The keys also have more degrees of freedom and better sensitivity, improving the image encryption performance.

Through in-depth study of the existing discrete cosine transform (DCT) watermarking technology, this paper presents a double encryption watermarking algorithm to enhance the security of watermark information. In the watermark embedding stage presents a new adaptive blind watermarking algorithm based on DCT domain, to achieve binary watermark embedding after double encryption. This algorithm effectively reduces the complexity of the watermark extraction algorithm, and ensures the security of watermark while improving the invisibility, so it has a strong confidentiality, robustness and resistance to attack.

Image secret sharing is an important branch in secret sharing; and it is a hot topic in the information security of images. For the correlation between adjacent pixels of an image is highly close, the shadow images will reveal the shapes of the original secret image after performing sharing process directly. Currently, the common method is using a permutation function, which is based on a cryptographic key, to permute the pixels of the secret image before sharing process. Then to safeguard the key brings a new problem. It is attractive to find a way to disrupt the correlation between neighboring pixels of an image. In this paper, pixel field is established to break up the correlation between adjacent pixels and it can reconstruct the secret image precisely based on pixel field in this paper. A perfect and ideal (k, n) threshold scheme based on Cauchy RS codes is proposed in this paper.

A total number of 270 ultrasound images of m. longissimus behind the 13th thoracic vertebrae were obtained on 90 lamb carcasses. Three different scanning frequencies were used (5.0, 7.5 and 10.0 MHz) in order to analyse how the frequency of the ultrasound wave affects the changes of pixel brightness in the ultrasound image. In the images obtained with 10 MHz probe the brightness of the 1st region was higher by 27% and 25% (P≤0.01) compared to the same region of images obtained with 5 MHz and 7.5 MHz frequency probe. The 3rd region of muscle cross-sections obtained with 10 MHz frequency was very dark, with the brightness lower by 22,5% and 28,3% compared to the same region of images obtained with 5 MHz and 7.5 MHz frequency. In the images obtained with 10 MHz scanning frequency, the decrease of brightness from the 1st to the 3rd region of the image was very sharp. While in the images obtained by means of 5 and 7.5 MHz ultrasound frequency, the brightness changes between the regions were very fluent. To conclude, the results of the presented research reveal that high ultrasound frequency has a negative impact on ultrasound image brightness and may reduce the information value of the image.

With the increase of the ratio between signal bandwidth and carrier frequency in the synthetic aperture sonar system, most of conventional imaging algorithms cannot be used for their narrow band approximation inherently. This paper analyzes the determining factors in designing an effective chirp scaling (CS)-based algorithms for focusing the wideband and wide swath synthetic aperture data. Based on the analysis, it is a great potential in designing an effective CS-based wideband and wide swath algorithm for taking into account the higher-order terms with respect to the range baseband frequency in the approximation of the 2-D spectrum and taking into account the higher-order range-variant terms in the approximation of the equivalent chirp rate. The results of simulation show the effectiveness of the theory analysis.

In this paper, an evaluation criterion based on image complexity is proposed in ghost imaging. According to the iterative performance of ghost imaging, characteristic factors of describing image complexity are introduced for seeking a new evaluation criterion to improve evaluation method. The proposed image complexity can be utilized to assess the iterative performance of different ghost imaging algorithms. The assessment results indicate that the proposed image complexity has a similar function with SNR, which is used to evaluate the iterative performance of ghost imaging. Compared with other existing evaluation methods, the obvious advantage is availability when the original image is unknown, and experiment results demonstrate that the new evaluation criterion is valid in ghost imaging.

This paper presents a novel approach to creating panoramic image from a single lens. Unlike current panoramic image methods, which usually require two cameras or more to stitch images beside, our system does not require any controlled motions or constraints on how the image is taken. For example, a captured image taken from a hand-held digital camera device can be reformed into cylindrical image. Because we represent our panoramic image is carried out through polar transform. Our method to create panoramic image is fast and effective because it directly constructed by pixels accumulation. Methods to build the panoramic image by single lens are presented. By the obtained panoramic image, we can explore the virtual environment using standard 3D viewers and hardware without requiring special purpose players. The complete designed image capture system will be presented in the conference for eliciting more application development.

Narrow-band radar which emits the signal restricted by bandwidth limitation has a low resolution in range profile so that it usually applies to target detection and tracking. However, the rotating target’s micro-doppler is used to image by Narrow-band radar that provides a new idea for target recognition. Due to the characteristics of narrow-band radar echoes from spinning targets, an imaging method based on Bayesian Compressive Sensing (BCS) is proposed according to the sparsity nature of narrow-band radar echoes from spinning targets. Simulation results show that the proposed approach is able to provide a sharp and sparse image absence of side-lobes which is the common problem in conventional complex-valued back-projection method and has fewer artifacts compared to the previous version of Compressive Sensing (CS) based methods.

In view of the problem that there are some defects such as poor noise immunity, poor stability, large amount of computation and high redundancy of target feature extraction method in three-dimensional(3D) reconstruction, an accurate and rapid method of extracting laser stripe was put forward according to the continuity of laser stripe pixels in this paper, which references the theoretical characteristics of structure laser and binocular vision, and uses the laser stripe projected onto the surface of the measured object as feature. Through repeated experiments and theoretical analysis comparison, the results show that the method has a great improvement in the accuracy, precision and computational efficiency of extracting laser stripe.

The free-form surface does not has stable texture and feature points. The existing 3D reconstruction algorithms for the free-form surface extract uncertain quantity of feature points which appear in random location because of image noise and different brightness. A novel 3D reconstruction method through projecting a grid on free-form surface is presented. Gridlines are treated as texture on the free-form surface. On the basis, the feature texture is extracted and feature points are precisely matched, the 3D reconstruction is completed according to recognizing and extracting the grid feature. The method is verified its feasibility and validity after applying it on several models.

Aiming at reducing the number of iterations in variational method used to reconstruct image gradient field and overlarge data memory space caused by Kronecker’s direct product operation, the paper discusses a matrix transform method to complete the reconstructing of image gradient field. The algorithm maintains the size of matrix constant and requires no iterations and the algorithm’s time complexity and space complexity are O(N), which meets the basic requirements in engineering calculations.

In order to improve the sampling rate and the quality of reconstructed images of electrical capacitance tomography (ECT) system, a new ECT image reconstruction algorithm based on compressed sensing (CS) theory is proposed. Firstly, using discrete Fourier orthogonal basis, the original image gray signal can be transformed into a sparse signal. Then, the electrodes are excited randomly and the capacitance values of different electrode pairs are also measured in a random order. Thus, the capacitance signals and the corresponding observation matrix are obtained. After that, using L1 regularization model and primal dual interior point method, the reconstruction of original gray image can be obtained. Finally, the simulation experiments are performed. Simulation results have shown that the relative error of the reconstructed images obtained by the proposed method is smaller than the corresponding images obtained by the LBP algorithm and the Landweber algorithm.

Quickly and accurately processing and saving high resolution thermal image sequences is a key technique in the field of thermal wave nondestructive testing. Based on the theory of thermal wave attenuation, this paper proposed a simple, fast and anti-noise global compression and reconstruction algorithm and showed the ability to improve the reliability and speed. Firstly the new algorithm divides the thermal image spatially and classifies thermal sequence. Then each curve in different temperature drop periods was fitted and lastly the compression and reconstruction of thermal sequence is fulfilled simultaneously in space and time by using the typical classified curve parameters as the compression and reconstruction parameters of thermal sequence. To verify the effect of the new algorithm, the experiment and comparison were carried out. The results show that the algorithm is a rapid, accurate and reliable. Compared with the current fitting compression method, it not only has a strong compression and anti-noise ability but also improve the operation speed up to hundreds of thousands of times.

The influence factors of underwater acoustic propagation are the basis of underwater acoustics. Considering the characteristic of shallow sea environment, two kinds of typical sound profiles in the WOA05 dataset are chosen for investigation in this paper. Under different restrictions, the characteristics of the two typical sound profiles are analysed contrastively by changing the bottom sediment, the depth of sound source and the frequency of sound source with the application of KRAKEN normal mode model. The influence of different kinds of ocean environment on the imaging of acoustics imaging device underwater is analysed. The simulation results show that the influence degree of sound speed profile by bottom sediment is related to the profile shape and the sound attenuation is reduced with the increase of source depth. Furthermore, the sensitivities of different sound speed profiles to sound frequency were different.

FDK algorithm widely used in cone beam CT image reconstruction has strict requirements on the geometric alignment of cone beam CT system. In terms of the cone beam CT system, especially the micro-CT system, the actual installation accuracy is difficult to meet the requirements of micro level positioning, it inevitably leads to image distortion. To solve this kind of problem, this paper proposes a geometric calibration method based on the square-line phantom. Firstly, we acquire square-line phantom projection in a fixed direction under different voltages, frame frequency and exposure time , and analytically determine the calibration geometry of the cone beam system. Finally reconstruct image using modified FDK algorithm， which has well calibrated the geometric errors of cone beam CT system. The experiments demonstrate that the proposed method has good noise immunity, and the positioning accuracy can meet the needs of practical application.

Lossy compression is preferred for many of applications; however, it is not preferred in the remote sensing community, because the use of lossy compression may change the features of remote sensing data. In this paper, we study the effect of lossy compression on two of the most common indices for vegetation feature extraction; Normalized Difference Vegetation Index (NDVI), and Normalized Difference Water Index (NDWI). The study is performed over several Landsat ETM+ images, and our experimental results show that the different transformations used in lossy compression techniques exhibit different impacts on the reconstructed NDVI and/or NDWI. We have also observed that, for certain compression techniques, a low PSNR may represent more vegetation features. This work shows the recommended compression techniques related to Landsat image vegetation quantity. Results and discussion provide helpful guidelines for joint classification and compression of remote sensing images.

Radiometric calibration is an important part for space remote sensing camera to obtain an accurate radiation value of ground target. The main significance of radiometric calibration is to reduce the influence by external scene and internal parameters of camera and to recover the real radiation property of objects. In order to break the limitation of line array imaging sensor, we propose a radiometric calibration method based on camera state matrix for area array camera. According to camera response characteristics, calculate and fit a functional relationship between the input radiance energy and the output digital number. Meanwhile, analyse and describe the procedure of radiometric calibration in detail. Experimental results indicates that the calibration method can provide high accuracy linear fitting parameters and can be widely applied to a large variety digital imaging systems.

Compressive sensing (CS) theory has achieved significant success in the field of synthetic aperture radar (SAR) imaging. Recent studies have shown that SAR imaging for sparse scene can also be successfully performed with 1-bit quantized data. Existing reconstruction algorithms always involve large matrix-vector multiplications which make them much more time and memory consuming than traditional matched filtering (MF) -based focusing methods because the latter can be effectively implemented by FFT. In this paper, a novel CS approach named BCS-AO for SAR imaging with 1-bit quantized data is proposed. It adopts the approximated SAR observation model deduced from the inverse of MFbased methods and is solved by an iterative thresholding algorithm. The BCS-AO can handle large-scaled data because it uses MF-based fast solver and its inverse to approximate the large matrix-vector multiplications. Both the simulated and real data are processed to test the performance of the novel algorithm. The results demonstrate that BCS-AO can perform sparse SAR imaging effectively with 1-bit quantized data for large scale applications.

This paper reports the experimental results of radar imaging using radio waves carrying orbital angular momentum (OAM) for the first time. The phased uniform circular array is employed to generate radio waves carrying various OAM modes. The echoes of all modes are measured sequentially in time by a single antenna. The phase distributions of several modes are measured through near-field measurement system. The azimuthal profiles of single and double corner reflectors are reconstructed by Fourier technique and the azimuth resolution is analyzed. Imaging results verify the ability of azimuth resolution without relative motion using OAM modulation.

Electromagnetic (EM) vortex carrying Orbital Angular Momentum (OAM) has received more attention recently due to infinite degree of information modulation and unique methods of information acquisition. This paper clarified multi- OAM generation method and introduced a novel radar imaging theory to improve azimuthal resolution by utilizing abundant OAM modes. Subsequently radiated characteristics were analyzed with EM software simulation and numerical simulation to evaluate the potential of EM vortex imaging. The results show that phase distribution and OAM purity in main lobe can satisfy imaging performance. Incoherent pattern direction problem and side lobe energy depressing can be solved by adjusting the radius of concentric uniform circular array.

Based on a few ground control points, the affine transform model, a polynomial model and rational function model are adopted to correct the ZY-3 remote sensing imagery. Because of the traffic and economic issues only 7 ground control points (GCPs) are collected with high location accuracy, and they all only employed to solve the coefficient of the geometrical transformation model. So there are no residual GCP for the evaluation of the correction accuracy and an intuitive and effective accuracy evaluation method is presented for correction result superimposed with topographic maps to verify the geometric correction accuracy. The experimental result shows that having difficulty in obtaining sufficient quantity of the control points, rational function model could be recommended to correct the ZY-3 imagery and obtain the corrective result with relatively high accuracy, which has certain application value, and it is a good method in absence of GCP to use topographic map to evaluate the correction accuracy.

The resolution of a conventional optical imaging radar system is constrained by the diffraction limit of the telescope’s aperture. The combination of the lidar and synthetic aperture processing techniques can overcome the diffraction limit and provide a higher resolution air borne remote sensor. Atmospheric turbulence is an important factor affecting the lidar imaging, and phase screen simulation method is an effective method to simulate the degradation of laser signal propagating in turbulent atmosphere. This paper proposes a kind of phase screen generation method based on Monte-Carlo random factor. The expansion of phase data units can be selected by Monte-Carlo random factor which can increase the randomness of phase screens. The radar imaging with different turbulence intensity is also calculated in this paper, then the improved rank one phase estimation autofocus method is used to compensate the imaging phase errors. The results show that the method of generating phase screen is consistent with the statistics of atmospheric turbulence, which can well simulate the effect of atmospheric turbulence on synthetic aperture lidar, and the influence on synthetic aperture lidar azimuth resolution is greater when atmospheric turbulence is stronger. Improved rank one phase estimation algorithm has good autofocus effect, which can effectively compensate the phase errors and enhance the image quality degraded by turbulence.

Normalized difference vegetation index, also known as the normalized difference vegetation index, is widely used in the study of vegetation and the research of plant phenology by means of remote sensing image. It is the best indicator of plant growth condition and the spatial distribution of vegetation density, bearing a linear relation with density of the vegetation distribution. NDVI can reflect the background image of plant canopy, such as soil, damp ground, withered leaves, roughness, etc. and it is also related to the vegetation. It has a variety of advantages, such as a higher detection sensitivity of vegetation, a higher detection range of vegetation coverage, the ability of eliminating the terrain and the community structure of shadows and radiated interference, the weakening of the noise brought by the angle of the sun and the atmosphere, etc. However, NDVI is also susceptible to canopy background variations, which lead to NDVI values of the soil pixels in plants shadows and vegetation pixels close in high spatial resolution data, thus, the separability of the foregoing two kinds of pixels of NDVI data is not satisfactory enough. In order to improve the separability of NDVI extracted from soil pixels and vegetation pixels, this paper, on the basis of NDVI, Red-band Enhanced Normalized Difference Vegetation Index (RNDVI) is constructed by introducing a red band strengthening coefficient , realize the nonlinear tensile of the NDVI value, as to increase the separability of vegetation pixels and the shadow of the soil pixels .On this basis, RNDVI threshold method and RNDVI-SVM method are employed to extract vegetation pixels from the high spatial resolution data obtained by Field Imaging Spectrometer System (FISS). The experimental results show that the accuracy of vegetation pixels extraction using RNDVI can be higher than using NDVI.

SAR can be used in topographic mapping at any time with all weather situations. In order to realize accurate surveying and mapping with SAR, a positioning scheme of airborne stereo SAR images with POS and one GCP (Ground Control Point) is proposed. In this scheme, the instantaneous position and velocity of antenna are obtained from the POS data, the close range and the Doppler center frequency are calibrated with only one GCP so as to realize accurate positioning of airborne stereo SAR images. The stereo SAR images obtained by Chinese airborne SAR system were utilized in positioning experiments. The errors of positioning were calculated and analyzed. The results demonstrated that the proposed scheme is valid.

With the rapid development of optical measurement techniques, monitoring heavy metal content in soil with hyperspectral image is a very important. Spectroscopic techniques are capable of higher speed, lower cost and less damage, which providing a better method for monitoring heavy metals in soil for environmental protecting purposes. This paper proposes a new insight of multiple regression in applying the hyperspectral image data to the estimation of heavy metals concentration, e.g. mercury content in soil. The sample points were scanned by a spectroradiometer within a wavelength region from 325 to 1075 nm. The data of hyperspectral images measured from the soil is preprocessed in the experiment, and the methods include resampling, first-order differential, and continuum removal, etc.. The algorithms of stepwise multiple regression are established accordingly, and the accuracy of each equation is tested. The analysis results showed that the accuracy of reciprocal logarithm works better than other methods, which has shown that it is feasible to predict the content of mercury by using stepwise multiple regression.

Unmanned Aerial Vehicle Remote Sensing (UAVRS) have developed rapidly driven mainly for military reconnaissance, earth observation and scientific data collection between military and civilian users over the past decade. However, automatic registration of UAVRS images has become a problem of blocks for the wide applications. In this paper, an algorithm based on both Random Sample Consensus (RANSAC) and least-squares method is proposed to improve the image registration performance of SIFT algorithm. On the one hand, RANSAC can remove inaccurate feature point pairs that SIFT detected. On the other hand, given all rough feature matches based on SIFT features, least-squares match is used to carry out precise matching. The experiment results show that our proposal can effectively estimate matching error with an average correct matching rate of 92.8%. And also the new algorithm had faster matching rate for the same number of images under the same experimental platform. As a result, the algorithm can improve greatly the accuracy of matching, but also to reduce the computation load based on the experiment results. Automatic registration of UAVRS images can be obtained in real time. After pre-matching by SIFT feature matching algorithm, the least squares matching is used to match accurately, which can be satisfied for the relative orientation of low-altitude remote sensing images automatically.

Aiming at the quality evaluation of synthetic aperture radar (SAR) image, a normalized evaluation index system combining the characteristics of grayscale image and electromagnetic scatter is established referencing analytic hierarchy process (AHP) at first. Then, the relationships between indexes and image quality are analyzed, as the distribution ranges and variation principles of indexes are determined by statistics. Eventually, the quality evaluation method is proposed, and some simulation results are presented. The method raised in this paper is simple, effective and robust, applied well to image quality assessment that has reference particularly.

Unbalanced economic growth of cities in developing countries in recent past has affected urban environment adversely. Rapid urbanization has led to increase in the impervious surface within urban landscape. Further, this increase is associated with partial or complete loss of natural drainage in urban catchment area. This paper presents anticipated increase in runoff within a urban catchment area of Pune-Pimpri-Chinchwad Municipal Corporation (PPCMC), India due to increase in the impervious surface over a decade. We used Landsat 7 images from 2001-2014 for detecting impervious surfaces within the region. Supervised classification of the area was done using Support Vector Machine (SVM). Digital Elevation Image (DEM) is acquired from CARTOSAT-1 for analysis of various catchment basins present in region. Finally we calculated runoff for 2001 and 2014 using rational flow equation. The comparison of 2001 and 2014 for PPCMC indicates increase in urban runoff by 87.8 percent just because of increase in impervious surface.

Because of the variety and complexity of defects in the fabric texture image, fabric defect detection is a challenging issue in the fields of machine vision. In this paper, a novel fabric defect detection method is proposed based on wavelet transform and background estimating. Firstly, the feature map of the fabric image is generated according to wavelet transform. Secondly, the multi-backgrounds are estimated by averaging the divided blocks of the feature map, and the saliency maps are generated by comparing the map blocks with the estimating backgrounds. Thirdly, an integrated saliency map is generated by a fusing method. Finally, the contrast between foreground and background is enhanced by estimating the probability density function of the saliency map, and the threshold segmentation algorithm is adopted to locate the defect area. Experiment results show that the proposed algorithm is superior to the state of the art detection methods.

Ship detection is a key topic for surveillance of coastal areas. In this paper, a new method based on salience map and kernel density is proposed to detect inshore ships with high-resolution Synthetic Aperture Radar (SAR) images. Firstly, two-dimensional wavelet transform is employed to extract the salience map of SAR image, and the difference between targets and background is effectively enhanced. Secondly with the Constant False Alarm Rate (CFAR) detector, we achieve the suspected ship targets. Finally, combining geometric features and kernel density, the false alarm targets are removed. The proposed method can effectively detect the inshore ship targets with the high correct detection rate and quality factor. Experiments on real high-resolution SAR images demonstrate the performance of the proposed method.

Forest disturbances in South China caused by pine wood nematode may result in widespread tree mortality. In order to decrease damage to forest ecosystem and huge loss to national economy, early detection, early diagnosis to individual infected tree is essential to forest management agencies. However field survey is hard to achieve the fine management requirements. Satellite remote sensing technology has the characteristics of landscape of coverage, convenient, and fast in formation acquisition, so it is one of the most important and most effective means of red attack monitoring. The support vector machine(SVM) classification algorithm have been proposed as an alternative for classification of remote sensing data. The study is based on a multispectral Worldview-2(WV-2) scene and uses support vector machine(SVM) methods. We compared the eight bands with three bands of the image based on SVM and came to the conclusion that WorldView-2 are suitable for individual tree identification. Three visible bands spectral data can also discriminate discolored individual tree successfully. In other words, three visible bands of remote sensing can meet the requirements of red attack pine estimation and extraction.

In order to increase the accuracy of locating the object by UAV, a robust algorithm based on image-reconnaissance is proposed. First, to record real-time objects reconnoitered by the photovoltaic system on the image. Then, to combines the target’s coordinates on the image with UAV flight parameters. Finally, through coordinate transformation, geometric calculation and other processes, it is able to locate the target’s geodetic coordinates. Monte Carlo simulation is introduced to the simulation experiments, to prove that this targeting method can meet the requirements of practical application. Experimental results show that the proposed algorithm has a good real-time performance, accuracy and reliability.

Aiming at automatic visual inspection of texture surface, a texture surface defect detection method is proposed based on statistical feature of subimage. The proposed method only uses a simple image feature, gray level difference of subimage without image enhancing to detect defects on texture surface directly, avoid the feature computation of high dimension space and the learning process of large numbers of defective and defect-free similar images, which is nonsupervised detection and improving algorithm efficiency. A variety of texture surfaces from industrial manufacture materials are chosen to conduct experiments. Detection time is about few seconds and accuracy is 93.6%. Experiment results prove the proposed method can online detect various texture surface defects effectively.

The detection of cracking on the road surface is an important issue in many countries to insure the maintenance and the monitoring of the roadways. This paper proposes a method which adapts the single pair shortest path A* algorithm to the detection of cracks within pavement images. The proposed A* algorithm computes the crack skeleton by calculating the minimal path between a pair of pixels which belong to the crack structure. Compared with the widespread and ubiquitous Dijkstra’s algorithm and to its bidirectional version, the proposed A* reduces the amount of the visited pixels; it is thus about 4 times faster than Dijkstra while keeping a large similarity coefficient with the ground truth.

The detection accuracy of facial landmarks or eye feature points is influenced by geometric constraint between the points. However, this constraint is far from being research in existing convolutional neural network (CNN) based points detection. Whether strict geometric constraint can improve the performance is not studied yet. In this paper, we propose a new approach to estimate the eye feature points by using single CNN. A deep network containing three convolutional layers is built for points detection. To analyze the influence of geometric constraint on CNN based points detection, three definitions of the eye feature points are proposed and used for calibration. The experiments show that excellent performance is achieved by our method, which prove the importance of the strict geometric constraint in points detection based on CNN. In addition, the proposed method achieves high accuracy of 96.0% at 5% detection error, but need less computing time than the cascade structure.

Architecture distortion is one of the most common signs of breast cancer in mammograms, and it is difficult to detect due to its subtlety. Computer-Aided Diagnosis (CAD) technology has been widely used for the detection and diagnosis of breast cancer. In this paper, Gabor filters and phase portrait analysis are used to locate suspicious regions based on the image characteristic of architectural distortion. Twin bounded Support Vector Machine (TWSVM), a kind of binary classifier, is employed reduce the large amounts of false positives. In this paper, we proposed a novel feature selection which is based on Multiple Twin Bound Support Vector Machines Recursive Feature Elimination (MTWSVM-RFE). The results showed that our proposed method detect the region of architecture distortion with high accuracy.

With the rapid development of smart city and intelligent transportation systems(ITS), traffic surveillance plays an important role on traffic and city safety. However, due to the variation of the illumination conditions and complex urban scenarios, camera-based vehicle detection becomes an emerging and challenging problem. In this paper, an effective and robust framework of rear-view vehicle detection for complex urban surveillance is proposed. Firstly, original image is decomposed into red-green-blue(RGB) color space with multi-channel enhancement technique. The region of interested (ROI) are then located by the unique color and texture utilizing maximally stable extremal region(MSER) algorithm. Furthermore, with special and relatively fixed spatial relationship of rear-lamp and license plate, a novel spatial combination feature (SCF) description is proposed. By utilizing the state-of-art support vector machine(SVM) on the proposed SCFs, the vehicle detection problem is recast into a supervised learning classification problem. The proposed method is fully evaluated and tested under different illumination conditions and real complex urban scenarios. Experimental results demonstrate the effectiveness and the robustness for the proposed detection framework.

While pedestrian detection is a hot topic in recent years, a lot of scholars have proposed many models whose performance are improved gradually. Meanwhile, there are two issues coming. On the one hand, the algorithm complexity increases rapidly with improving the detection accuracy. On the other hand, in the particular images each model have its advantages. So, a single model is very difficult to adapt to the all condition of all images. If a variety of models are merged simply, there is no doubt that causes the high complexity and dimension disaster. Furthermore, it can’t bring the performance of each model into full play. By introducing the recommender system into pedestrian detection, we propose a adaptive-scenario model-selection method for pedestrian detection. On the training set, we structure the rating matrix by combining the model-task rating and the scenes features, and use the collaborative filtering method to chose the appropriate models. In our experiments, we construct model set with significantly different models which are especially discriminating on the aspect of algorithm complexity. The test results in PASCAL VOC datasets show that the accuracy of our method is a little better than the best performance model in the model set. Meanwhile, the average efficiency is obviously improved by our method due to our recommender system selecting a percentage of the low complexity models. The experiments shows that our proposed recommender system can effectively recommend the suitable detection model from model set. The approach has the same significance for other detection task.

This paper proposes a border connectivity-based spatiotemporal saliency model for videos with complicated motion and complex scenes. Based on the superpixel segmentation results of video frames, feature extraction is performed to obtain the three features, including motion orientation histogram, motion amplitude histogram and color histogram. Then the border connectivity is exploited to evaluate the importance of three features for distance fusion. Finally the background weighted contrast and saliency optimization are utilized to generate superpixel-level spatiotemporal saliency maps. Experimental results on a public benchmark dataset demonstrate that the proposed model outperforms the state-of-the- art saliency models on saliency detection performance.

Text detection in images is an important prerequisite for many image content analysis tasks. Actually, nearly all the widely-used methods focus on English and Chinese text detection while some minority language, such as Uyghur language, text detection is paid less attention by researchers. In this paper, we propose a system which detects Uyghur language text in images. First, component candidates are detected by channel-enhanced Maximally Stable Extremal Regions (MSERs) algorithm. Then, most non-text regions are removed by a two-layer filtering mechanism. Next, the rest component regions are connected into short chains, and the short chains are connected into complete chains. Finally, the non-text chains are pruned by a chain elimination filter. To evaluate our algorithm, we generate a new dataset by various Uyghur texts. As a result, experimental comparisons on the proposed dataset prove that our algorithm is effective for detecting Uyghur Language text in complex background images. The F-measure is 83.5%, much better than the state-of-the- art performance of 75.5%.

Without any special training, people have the talent of understanding the image content. So the trustworthiness of photographs plays an important role in many areas such as criminal investigation and journalism. But in this digital world, the high-quantity commodity hardware and the low-cost image editing software give a cheap way of tampering the digital images without and clue of changing. In this paper, we introduce some passive-blind methods for detecting multi-image fakery, which means that adding a new object from another image into the image or replaying the original object by another object from a different photo. According to the characteristic of multi-image fakery, we propose two optional kinds of solution: technical method and analyzing method. Both of the two kinds of solution are effective and useful. Further more; the combine of them can reach a better performance.

In the actual optical imaging system, in order to increase cell sensitivity or meet the needs of a large field of view, a large size CCD pixel is usually chosen as detection unit. This can not meet the Nyquist sampling theorem, and it belongs to ill-sampling. The geometric resolution of optical diffraction limited system image is directly restricted by the size of CCD pixel. In this paper, a reasonable optical mask is chosen, and this ensures the access to the CCD image information before sampling is lossless. Space spectral filtering technology is used, and appropriate resolution of the image is acquired. The method improves the resolution decline due to ill-sampling. By mathematical and simulation analysis, the effect of geometric super resolution image can be achieved.

As an effective super-resolution reconstruction technique, the original iterative back-projection (IBP) suffers from jaggy artifacts around the edge caused by the initial estimation of high-resolution image obtained with traditional interpolation methods like bilinear interpolation. In this paper, we present an edge-preserving iterative back-projection method for image super-resolution, which employs an effective edge-preserving interpolation method called iterative curvature based interpolation (ICBI) method for up-sampling to get the initial estimation of high-resolution image. The proposed method combines the IBP algorithm with the ICBI method which is a two-step grid filling and an iterative correction of the interpolated pixels obtained by minimizing an objective function depending on the second-order directional derivatives of the image intensity. Experiment results increases the PSNR compared to other existing algorithms and also improves edge quality of the image considerably.

Super-resolution has been extensively studied for decades, but its application to a real-world image still remains challenging. In this paper, a novel approach for image super-resolution algorithm based on local self-similarity (SRLS) is proposed. First, a limited window is used to bind several similar patches of the input image into a same group. Then the high-resolution image can be inferred by using the image capturing model. The experiment shows that the proposed algorithm achieves improvement in image quality and provides more details.

To reduce the reconstruction error in dictionary training and reconstruction, an image super-resolution algorithm via multistage sparse coding (SMSC) is proposed in this paper. The combined Lanczos3 and IBP algorithm is used as the first method to estimate the high resolution image. In dictionary training, the feature and reconstruction error of estimated images are used to train multistage feature dictionaries and error dictionaries. In reconstruction, using feature dictionaries and error dictionaries, the error term of the estimated image is reconstructed by sparse coding to improve the image quality stage by stage. The experiment shows that, the proposed algorithm outperforms other the-state-of-art SR algorithm SISR in image quality, while the reconstruction time remains in low level.

Super-resolution (SR) reconstruction produces one or a set of high-resolution (HR) images from a set of low-resolution (LR) images. Regularization is a classical method for SR reconstruction. It contains only one fixed regularization parameter in most cases. Considering the difference between the LR images, such as noise, resolution, and the registration error, each LR image should correspond to different parameters according to a certain rule. Hence, we used generalized regularization schemes which contain multiple parameters. In order to obtain the optimal parameters, a new adaptive regularization method based on constrained particle swarm optimization algorithm (ARCPSO) is proposed. The initial value of each parameter is adaptive given. Furthermore, the particle swarm optimization (PSO) algorithm is applied to automatically select the optimal parameters in the proper range of initial values. The experimental results verify the effectiveness of our algorithm and demonstrate the superiority of our approach compared with traditional regularization methods.

Clinical practice requires multiple scans with different modalities for diagnostic tasks, but each scan does not produce the image of the same resolution. Such phenomenon may influence the subsequent analysis such as registration or multimodal segmentation. Therefore, performing super-resolution (SR) on clinical images is needed. In this paper, we present a unified SR framework which takes advantages of two primary SR approaches – self-learning SR and learning-based SR. Through the self-learning SR process, we succeed in obtaining a second-order approximation of the mapping functions between low and high resolution image patches, by leveraging a local regression model and multi-scale self-similarity. Through the learning-based SR process, such patch relations are further refined by using the information from a reference HR image. Extensive experiments on open-access MRI images have validated the effectiveness of the proposed method. Compared to other advanced SR approaches, the proposed method provides more realistic HR images with sharp edges.

In order to improve the precision and speed of the three-dimensional point cloud registration, it is suggested the three-dimensional point cloud registration based on ICP algorithm employing k-d tree optimization in this paper. First of all, the centre superposition method is adopted to realize the point cloud coarse registration, and then improve the traditional ICP where the K-D tree is used to quickly search the closest pair of points to enhance the speed of the point cloud registration. Finally the Three dimensional point cloud coarse registration is completed precisely. The method overcomes the defects of the traditional ICP algorithm using Euclidean distance to determine the closest pair of points which is time-consuming and plains lots of work. On the basis of this method, the experiment can be verified through different density Bunny Stanford point cloud data. The result shows that using K-d tree optimization of ICP algorithm, the precision, speed and stability of the point cloud registration is improved when the centre superposition method is adopted to realize the three dimensional point cloud coarse registration.

Real-time full frame view of surveillance camera provides integral visual information of scene. High definition imaging and zooming are widely adopted when observers want to capture more detail information of targets. The optical zooming can provide high zoom ratio detail images of target as well as maintain imaging definition, however, it fails to obtain full view of scene when zoomed, and the field of observation decreases to region of target. Digital zooming is an effective approach to keep the balance between imaging field and visual detail information. This paper presents a method of stepless zooming for digital video camera which could be widely used in autonomous pan, tilt and zoom surveillance system. In view of hardware resources and algorithm realizability, an optimized zooming processing structure is proposed. According to input zoom ratio parameter, it can extract pixels of region of interest adaptively and display with original imaging size by mapping and interpolation algorithms. Experimental results indicate that the stepless zooming method can be capable of achieving 1080p high definition imaging and 30 frame/s video capture.

A new single image super-resolution method based on self-similarity across different scales and pyramid model is proposed. In order to enrich the diversity of the training patches but not increase the computational complexity, we rotate the low resolution input image by a certain angle from 0° to 90° and down-sample them into 2 layers pyramid model respectively. However, most self-similarity super-resolution algorithms was carried out by the fixed size of patch. So, in this paper we observe the effect of patch size using the various patch size then pick out the most appropriate patch size. During the mapping process, we use the Fast Library for Approximate Nearest Neighbors (FLANN) to search the corresponding nine closest patches in high-frequency pyramid then carry out Gaussian weighted (SSD), which can avoid the occasionality and mismatch by using the nearest neighbor strategy. Finally, the local constraint and the iterative back projection algorithm are adopted to optimize the reconstructed image. Experimental results validate that the algorithm is better than the traditional algorithm in visual effects and computational complexity.

To achieve auto-exposure in digital cameras, image brightness is widely used because of its direct relationship with exposure time. Although image entropy which represents information measure of image is widely used in various image processing applications, it has not been used on FPGA in AE system due to its complex calculation. Image with maximum entropy value contains more information. So this paper presents an algorithm based on image entropy. By searching maximum entropy value, the image can get an appreciate exposure. What’s more, by using formula manipulation of image entropy and piecewise linearization of the log function, the optimized algorithm grasps the overall change rule in stead of traditional calculation and has been realized on FPGA. The experiment results show that on basis of 10M work frequency of CMOS image sensor (electronic shutter, 1024 by 1024 pixels, on-chip 12-bit ADC) and 100M clock frequency of FPGA (ALTERA-EP2S60F48414N), this algorithm works well. And at the same time, the algorithm improves the amount of image information and increases the accuracy of auto exposure.

Finite element analysis employed for the adjuvant treatment of spinal diseases has yet to consider the effect of gravity on analytical results. This article simulates the gravity environment on the simulated spine of a standing human body to employ finite element analysis and calculate the changes in stress and node displacement of the lumbar spine. Analytical and calculation results demonstrate that in standing pose with the gravity, the stress distribution of each vertebral body surface is five to six times of that of the intervertebral disc, and for the small joint node, the stress and displacement is increased mostly by 16.57% or decreased mostly by 72.36%.

The sparse scanning imaging methods for x-ray CT is a promising approach to speed up scanning or reduce radiation dose to patients. The major problem for sparse parallel projections is hard to reconstruct high quality image. It suffers severe streak artifacts in reconstruction if the popular filtered back projection (FBP) method is employed. Although several total variation (TV) regularization based algorithms have been developed for sparse-view CT imaging, they still face challenges in both time consumption and computational complexity when the objective image is large. In this paper, a CT reconstruction algorithm, which is named INNG-TV (iterative next-neighbor regridding-total variation), based on extrapolation in frequency is proposed to improve the performance. We first convert data, which is sampled from parallel beam CT, into frequency domain by Fourier transform and linear interpolation. In the following process of iteration, the known data of projection in Fourier space keep constant, whereas the unknown data are estimated by INNG extrapolation. At the same time, prior knowledge and constrained optimization, such as non-negativity constraint and total variation regularization, are introduced to image reconstruction in image space. The numerical simulation results show that the proposed method has better performance in reconstruction quality than ART-TV (algebraic reconstruction technique-total variation). The proposed method not only demonstrates its superiority in time consumption, but also offers outstanding reconstruction quality for sparse-view scan, which makes it significant to sparse-view CT imaging.

Multiple instance learning algorithms have been increasingly utilized in many applications. In this paper, we propose a novel multiple instance learning method called GM-Citation-KNN for the microcalcification clusters (MCCs) detection and classification in breast images. After image preprocessing and candidates generation, features are extracted from the potential candidates based on a constructed graph. Then an improved version of Citation-KNN algorithm is used for classification. Regarding each bag as a graph, GM-Citation-KNN calculate the graph similarity to replace the Hausdoff distance in Citation-KNN. The graph similarity is computed by many-to-many graph matching which allows the comparison of parts between graphs. The proposed algorithms were validated on the public breast dataset. Experimental results show that our algorithm can achieve a superior performance compared with some state-of-art MIL algorithms.

Medical image fusion plays an important role in biomedical research and clinical diagnosis. In this paper, an efficient medical image fusion approach is presented based on pulse coupled neural network (PCNN) combining multi-objective particle swarm optimization (MOPSO), which solves the problem of PCNN parameters setting. Selecting mutual information (MI) and image quality factor (^QAB/F) as the fitness function of MOPSO, the parameters of PCNN are adaptively set by the popular MOPSO algorithm. Computed tomography (CT) and magnetic resonance imaging (MRI) are the source images as experimental images. Compared with other methods, the experimental results show the superior processing performances in both subjective and objective assessment criteria.

Whiplash-associated disorder (WAD) is a commonly occurring injury that often results from neck trauma suffered in car accidents. However the cause of the condition is still unknown and there is no definitive clinical test for the presence of the condition. Researchers have begun to analyze the size of neck muscles and the presence of fatty infiltrates to help understand WAD. However this analysis requires a high precision delineation of neck muscles which is very challenging due to a lack of distinctive features in neck magnetic resonance imaging (MRI). This paper presents a novel atlas-based neck muscle segmentation method which employs discrete cosine-based elastic registration with affine initialization. Our algorithm shows promising results based on clinical data with an average Dice similarity coefficient (DSC) of 0.84±0.0004.

Computer-aided diagnosis (CAD) system is helpful for lesion detection. In this study, we proposed a new mass detection method with analysis of bilateral mammograms. First of all, the mass candidates were detected in single view. To utilize the information in dual view, we match corresponding regions in mediolateral oblique (MLO) and craniocaudally (CC) views of the breast. In this paper, we introduced twin support vector machines (TWSVM) as classifier for mass detection, and proposed a new method for feature selection called multiple twin support vector machines (MTWSVM-RFE) to improve the accuracy of detection.

Shape drawing tests are widely used by practitioners to assess the neuropsychological conditions of patients. Most of these neuropsychological figure drawing tests comprise a set of figures drawn on a single sheet of paper which are inspected to analyze the presence or absence of certain properties and are scored accordingly. An automated scoring system for such a test requires the extraction and identification of a particular shape from the set of figures as a vital preprocessing step. This paper presents a system for effective segmentation and recognition of shapes for a well-known clinical test, the Bender Gestalt Test (BGT). The segmentation is based on connected component analysis, morphological processing and spatial clustering while the recognition is carried out using shape context matching. Experiments carried out on offline images of hand drawn samples contributed by different subjects realize promising segmentation and classification results validating the ideas put forward in this study.

The traditional iris localization algorithms have strict requirements on the image acquisition equipment and the light condition. When the iris images are taken in non-ideal imaging conditions, the localization precision decreases greatly or completely failed. Aiming at these problems, a fast iris localization algorithm under visible light condition is proposed in this paper. The algorithm preprocesses the eye images first. An improved starburst algorithm is then used to detect the feature points. Finally, use the least square algorithm and the RANSAC algorithm to locate the iris contour. The experimental results show that the algorithm is robust to the image quality and can locate the iris quickly and accurately in video image sequences.

Hyperspectral imaging is an emerging imaging modality for medical applications. It provides more information than traditional optical image for owning two spatial dimensions and one spectral dimension. Multi dimension information of hyperspectral images can be used to classify different tissues and cells, while it’s difficult to distinguish them by traditional methods. The processing method presented in this paper is composed of two main blocks: Support Vector Machine (SVM) algorithm is adopted to identify different components of blood cells through the spectral dimension. In order to make it easy for blood cell counting, some morphological processing methods are used to process images through the spatial dimensions. This strategy, applying SVM and morphological processing methods, has been successfully tested for classifying objects among erythrocytes, leukocytes and serums in raw samples. Experimental results show that the proposed method is effective for red blood cells identification.

The whole process of text detection in scene images always contain three steps: character candidate detection, false character candidate removal, words extraction. However some errors appear in each step and influence the performance of text detection. According to the disadvantages of each step, we propose the compensation methods to solve these problems. Firstly, a filter based on color of stroke named Stroke Color Transform is used to ensure the integrality of characters and remove some false character candidates. Secondly, a classifier is trained based on gradient features is adopted to remove false character candidates. Thirdly, an extractor based on color of consecutive character named Character Color Transform is employed to extract undetected characters. The proposed technique is test on the two public datasets i.e. ICDAR2011 dataset, ICDAR2013 dataset, the experimental results show that our approach outperforms the state-of-the-art methods.

Porous media have a wide range of applications in the field of material science and geology. The achievement of the shape parameters of a porous medium gives great significance to the reconstruction of the medium and the calculation of physical parameters such as porosity and permeability. A kind of particular porous media are focused on in the paper which are composed of randomly packed spheres made of glass. A modified Hough transform method using scanning electron microscope (SEM) images is proposed to detect the particles that compose the medium. The raw gray level image is preprocessed using a Gaussian filter. Then a modified vote mechanism is applied to transform the edge points obtained by gradient map into the accumulation array of the center locations. After a non-maximum suppression, final circle centers are picked up and their radii are estimated. The method is conducted on several SEM images, indicating the method can achieve a remarkable accuracy of ~75%.

There are various forgeries in digital images without leaving any obvious traces of tampering due to powerful image processing and editing software. Copy-move forgery is a common type of image forgery in which a part of digital image is copied and pasted to another part in the same image with the intent of disguising some details. Based on scale invariant feature transform, a new blind detection method using Haar wavelet and ring descriptor is proposed in this paper. The method proposed not only makes the feature more stable and distinctive but also reduces the detection time dramatically. Results of experiment show that the method proposed is not only effective on different forgeries but also robust to post image processing, such as noise, blur, JPEG compression, scaling, rotation, or even compound image processing.

Topology of vector fields based on Morse decompositions has been a more numerically stable representation than the conventional trajectory-based topology. The refinement for Morse decompositions means to get the optimal results with lower computations. To address the problems in the already existing refinement methods, which contain too many empirical parameters and vague refinement objectives, this paper proposes a novel refinement method for Morse decompositions of vector fields based on a new refinement criterion using robust critical simplexes. Firstly, the critical simplexes are defined and detected by a robust manner. Secondly, the Morse sets can be classified by their regions and the detected critical simplexes. And a new refinement criterion for identifying Morse sets to refine based on the classification of Morse sets is built. Finally, the refinement flow of the proposed method is presented. Experimental results demonstrate the availability and effectiveness of the proposed method.

Snow is a kind of complicated objects that has irregular shape. Therefore, the topic of snow three-dimensional visualization is always challenging. The real-time rendering accumulated snow is of great importance to improve reality in the scene simulation. In this paper, we put forward an algorithm based on predecessors which introduces Perlin Noise and smoothing algorithms, combining with incline coefficient and exposure coefficient. This algorithm makes snow accumulation more natural. Rendering by combining geometry and texture, complexity of large-scale scene is dropped off sharply. Using occlusion map which is processed by image processing, this algorithm could update occlusion relationship of objects in the scene and get better results. Experiment results show that the proposed algorithm accelerates the rendering and be suitable for large real-time snow accumulated rendering.

Image representation is the key part of image classification, and Fisher kernel has been considered as one of the most effective image feature coding methods. For the Fisher encoding method, there is a critical issue that the single GMM only models features within a rough granularity space. In this paper, we propose a method that is named Multi-scale and Multi-GMM Pooling (MMP), which could effectively represent the image from various granularities. We first conduct pooling using the multi-GMM instead of a single GMM. Then, we introduce multi-scale images to enrich the model’s inputs, which could improve the performance further. Finally, we validate out proposal on PASCAL VOC2007 dataset, and the experimental results show an obvious superiority over the basic Fisher model.

The convolution neural network (CNN) is becoming more and more powerful in many areas such as image classification and speech recognition. Some projects begin to apply it on mobile phones, but often need plenty of time due to the huge amount of computation. This paper uses a deep learning framework named MXNet to realize the forward process on the mobile phone. In order to lower the time it costs, we focus on how to use the other computing device on the chip—the mobile GPU. We choose the OpenCL to offload the most time consuming layer in the CNN—convolution layer to the GPU. Besides that, this paper makes several improvements to achieve better performance and finally the experimental results demonstrate that the forward process only takes half the time in our algorithm. To the best of the authors’ knowledge, this work is the first published implantation of CNN accelerating on mobile GPU.

In this paper, we develop a novel method for blind image quality assessment (BIQA) based on image complete pixel level information. First, traditional rotation invariant uniform local binary pattern (LBP) histogram is extracted from grayscale image as perceptual quality aware feature. Second, except for the signs of local pixel differences, the magnitudes of local pixel differences in grayscale image are also encoded by LBP, and the joint histogram between the signs and magnitudes of local pixel differences is also calculated as part of the perceptual feature. Finally, the support vector regression (SVR) is utilized to learn the mapping between the combined perceptual feature and human opinion scores. Experimental results show that the proposed method is highly correlated with human opinion scores and achieves competitive performance with state-of-the-art methods for quality evaluation and distortion classification.

The paper introduces a new approach to tone correction of color images through a spherical color model. Although color changes more smoothly under the spherical model, some colors of the model cannot be displayed in the RGB color cube. The paper demonstrates the disadvantage does not affect the applications of the general techniques of tone correction in the spherical model. The achromatic component defined by the spherical model is separated from a given image with tonal imbalance, and then a tone correction function is performed on the component. The resulting achromatic component is combined with the original chromaticity to produce a tone corrected image. In the spherical color model, tone correction functions can be designed such that the corrected colors are within the RGB color cube for display. Technical requirements of the tone correction functions are discussed, and comparisons are made between the spherical color model and other similar color models including the commonly used HSV and HSL. Empirically, the effects of the general tone correction techniques in the spherical color model are close to those in the HSV color model.

This paper shows the results of the automatic design of a generic heat sink, through a morphogenesis algorithm done in Matlab. This algorithm is based on two-dimensional fractal images, generated by Lindenmayer systems, which create the heat sink shape. Those shapes iteratively evolve through a genetic algorithm in order to maximize their heat dissipation capability, estimating it through measurements of their surface and volume. Evaluation process was supported by image processing algorithms. Finally finite elements simulations are carried out in order to determine the real heat dissipation capability of each design and thus obtaining some valid heat sink shapes.

The convergence speed of a single least mean square (LMS) filter contradicts its stable state error incompatibly. Such a situation significantly restrains the performance of the recognition system. The convex combination of least mean square (CLMS) algorithm is employed in this paper to ensure that had good output. However, the rule for modifying mixing parameter is based on the steepest descent method, when the algorithm converges, it will take a lot of detours and do a lot of hard. In order to settle this problem, a new rule based on the conjugate gradient method is proposed in this paper. Meanwhile, modified hyperbolic tangent function is used to reduce computational complexity. Theoretical analysis and simulation results demonstrate that under different simulation environment, the proposed algorithm performs good property of mean square and tracking.

Beam hardening artifact is common in X-ray computed tomography (X-CT). Using the metal sheet as a filter to preferentially attenuate low-energy photons is a simple and effective way for beam hardening artifact correction. However, generally it requires a large quantity of experiments to compare the filter material and thickness, which is lack of guidance of theory. In this paper, a novel filter design method for beam hardening correction, especially for middle energy X-CT, is presented. First, the spectrum of X-ray source under a certain tube voltage is estimated by Monte Carlo (MC) simulation or other simulation methods. Next, according to the X-ray mass attenuation coefficients of the object material, the energy range to be retained can be roughly determined in which the attenuation coefficients change slowly. Then, the spectra filtering performance with different filter materials and thicknesses can be calculated using the X-ray mass attenuation coefficients of each filter material and the simulated primitive spectrum. After that, the mean energy ratio (MER) of post-filter mean energy to pre-filter mean energy is obtained. Finally, based on the spectrum filtering performance and MER of the metal material, a suitable filter strategy is easily selected. Experimental results show that, the proposed method is simple and effective on beam hardening correction as well as increasing the image quality.

In this article, a new adaptive weighted mean filter is proposed to detect and remove high density impulse noise in digital images. The proposed method consists of detecting stage and filtering stage. In the detecting stage, all pixels are labeled based on the proposed classification principle. Besides, all pixels are set with different weights, which are used to confirm the size of the sliding window. In filtering stage, a new weighted mean filter synthesizes both the information of center pixel and the relationship of all the pixels in the sliding window. Hence, the center pixel, labeled “the noise-free pixel” remains unchanged. The “noise-like pixels” and “clear-like pixels” are replaced by the weighted mean of the current window. The simulation result shows that the performance of the proposed filter is better than some existing methods, both in vision and quantitative measurements.

This manuscript deals with the permutation and scaling ambiguities inherent to an Independent Component Analysis (ICA) framework when continuously mixed signals are split in time and processed in a block-by-block manner. For each adjacent block, we choose the demixing matrix of the previous block as the initialization matrix for separating the subsequent block. By using the demixing matrices of the previous blocks, the separation process of the subsequent blocks is largely simplified, and the corresponding computational cost is thereby significantly reduced. Therefore, compared with previous similar methods, our proposed method is much more efficient in terms of computational speed, which is particularly striking when a large number of blocks is applied. We conducted simulations to validate the effectiveness of our proposed method.

In order to analyze brain activity signals, it is important to remove any artifact of the obtained data so that we can further provide diagnosis of possible symptoms. There are many different ways to do denoising of the given signals. In this paper, we test several biosignals and obtain an optimal ways to denoise the data and perform time frequency analysis of an EEG signal.

Nowadays, with the development of space exploration technologies, satellites and other spacecraft have undertaken more important and complicated space science missions, which require powerful processing capabilities to conduct large amounts of probe data real-time processing and analysis. However, the raw data generation rate of space exploration is always far beyond space transmission ability, so orbit compression for original data is an essential technology. Digital Signal Processors (DSPs) with powerful signal processing capabilities have been widely used in various information processing spacecraft systems. However, the utilization of full DSPs’ performance potential depends on parallelism of programs. Based on the C6000, a series of commercial high performance DSP processors, the paper implement the entire discrete wavelet transform module in JPEG2000 image compression algorithm with linear assembly language. Combined with characteristics of DSP instruction sets and features of specific programs, we optimize programs and improve the execution performance by an order of magnitude than previous.

The main objective of Electronic Support Measure (ESM) is to detect and analyze the threating radar emitters in the surrounding environment. These objectives can be obtained by receiving, measuring, and sorting the intercepted signals, respectively. In the thick of these functions, sorting is absolutely essential. In complex environment, sorting radar pulses is highly problematic, since an enormous number of pulses are received from different emitters in an interleaving form with high noise levels. Conventional sorting techniques have illustrated inefficient results, especially in the presence of modern radar signal such as agility and frequency hopping. In order to ameliorate the sorting performances, we introduce a new sorting algorithm based on similarity and hierarchical clustering techniques, and we denoted it as “Similarity method”. The Similarity method performs magnificent performances without prior knowledge about radars’ emitters, and it is aimed at tackling unconventional circumstances, (i.e. noise pulses, agility signal and hopping frequency). The Similarity method is compared with some existed method, and the simulation results proved its efficiency.

In this paper, a new modulation recognition algorithm is proposed. Communication Signals are recognized and classified based on Clustering techniques. Proposed algorithm uses Clustering Validity Measures as a key features extracted from MQAM signals. Fuzzy C-mean Clustering (FCM) is applied on received MQAM signal to produce a membership matrix of different clusters. Clustering Validity Measures are applied on the membership function. Different MQAM signals have different values of Validity Measures. This feature recognizes most MQAM signals with high confidentiality. At low SNR cases, a neural network with a conjugate gradient Learning approach is utilized to enhance algorithm performance. Fletcher-Reeves learning approach can improve the speed and rate of convergence. Simulation results prove the validity of proposed algorithm. No prior information is needed using proposed algorithm. Misclassification rate is less for low order MQAM signals.

We proposed an efficient method of direction of arrival (DOA) estimation for coherent signal based on sparse signal reconstruction. For the inter-atom interference of redundant dictionary affecting the feasibility of sparse signal reconstruction, in this paper, our method for the DOA estimation of coherent signal is based on regularized orthogonal matching pursuit (ROMP) algorithm by designing adaptive sensing dictionary to mitigate the inter-atom interference (AMIAI). Simulated results demonstrate effectiveness of the method by plotting spatial spectrum, by comparing the rootmean-square error (RMSE) of some methods and Cramér-Rao Lower Bound (CRLB) and by comparing the running time of some methods. Our approach makes effort to improve the estimation performance of algorithm and has overload capability.

This paper focuses on the low complexity detection for the Faster-than-Nyquist (FTN) signaling, which is an important problem in the practical application. Considering intersymbol interference (ISI) and colored noise caused by FTN, a new whiten matched filter (WMF) is proposed to decorrelate the colored noise with matrix decomposition. Exploring the structure of upper-triangle matrix, the detection problem for FTN is transformed to a similar type problem of tree-searching. A novel receiver for FTN is proposed based on sphere detection algorithm. Furthermore, for reducing the random detection complexity, a new way is proposed to choose an initial sphere radius size. Numerical results suggest that the proposed method for choosing the initial sphere radius size performs well even in the low signal-to-noise ratio (SNR) region. Moreover, the bit error rate (BER) performance of the proposed method reaches the maximum-likelihood (ML) bound closely.

The main objective of Electronic Support Measure (ESM) system is to obtain threatening emitters by receiving, measuring, and sorting radar pulses. Through these steps, sorting radar pulses is absolutely essential to differentiate between the threatening emitters. A large number of sorting algorithms have been proposed to tackle this issue; however, most of them suffer from lack of success in such circumstances (agility signal, clutter or noise pulses, and missing pulses). In this paper, four partition clustering methods are considered for sorting radar pulses under the influence of clutter (noise) and missing pulses. Besides, the significant impact of initiation clustering upon the sorting performances is discussed. Finally, the simulation results demonstrated lucid analysis of the compared methods’ performances, and identified the most amenable algorithm for sorting radar signal.

Pose imitation is for two shapes to study pose from each other. It has been a hot area in shape deformation and we improve the original graphical pose imitation method by introducing signal thought. Laplace framework is often used in pose imitation and geometrical information involved Laplace operator performs better in preserving original shape’s mass smooth part by carrying much intrinsic information of graph. However, the two shapes’ bases in Laplace feature space need to be well mapped before utilizing classical pose imitation algorithm, which makes it an obstacle to introduce the geometry related Laplace operator. In our work, the problem is solved by proposing signal transfer algorithm and based on it, we put out an effective pose imitation framework using edge length related Laplace operator. Our method well suits to 2-dimension shape and good results of pose imitation have been achieved.

Traditional subspace detection for the second-order Gaussian (SOG) model signal is generally considered in the homogeneous or partially homogeneous environments. This paper addresses the problem of the subspace detection for the SOG signal in the presence of the nonhomogeneous noise whose covariance matrices in the primary and secondary data are assumed to be random, with some appropriate distributions. Within this nonhomogeneous framework, a novel adaptive subspace detector is proposed in terms of an approximate generalized likelihood ratio test (AGLRT) and the Gibbs sampling strategy. The numerical result evaluates the performance of the subspace detector with Monte Carlo method under nonhomogeneity.

In this paper, we propose a no-reference video quality evaluation method based on HEVC bitstream. The method extracts feathers from HEVC bitstream to estimate quality of the video. We choose Quantization Parameter Average (QPavg) and Skip Coding Unit Percent (Skip%) as features, PSNR as objective video quality evaluation method, and use linear regression to get the evaluation model. Experiment result shows that the method can accurately predict the objective quality of HEVC encoded video.

This paper proposes a novel video stabilization method based on FREAK. That method combines the advantages of the fast speed of binary features and the high efficiency and robustness to parallax of 2D feature trajectories, which avoids inheriting the limitation to parallax from other 2D methods. In order to make the smoothed camera paths as flat as shot by a smoothly moving platform, we take full consideration of 2-degree gradients of the trajectories. This is done by adding a 2-degree regularization to the bundled paths optimization equations. Moreover, a spectral technique is employed to improve the accuracy of original feature matching results. Experiments demonstrate the competitive performance of our proposed method.

In this paper, a novel co-saliency model is proposed with the aim to detect co-salient objects in multiple videos. On the basis of superpixel segmentation results, we fuse the temporal saliency and spatial saliency with a superpixel-level object prior to generate the intra saliency map for each video frame. Then the video-level global object/background histogram is calculated for each video based on the adaptive thresholding results of intra saliency maps, and the seed saliency maps are generated by using similarity measures between superpixels and the global object/background histogram. Finally, the co-saliency maps are generated by the recovery process from the seed saliency measures to all regions in each video frame. Experimental results on a public video dataset show that the proposed video co-saliency model consistently outperforms the state-of-the-art video saliency model and image co-saliency models.

Real-time video de-noising is an active research topic in video surveillance application, aimed at improving the degraded video’s quality. In this paper, the key methods of frame rate conversion and wavelet de-noising during video processing are studied and a real-time wavelet HD-video (High Definition) de-noising system based on FPGA (Field Programmable Gate Array) platform is designed. With frame rate conversion module, 3-level wavelet transform, and BayesShrink adaptive threshold filtering, the proposed system achieves a real-time HD-video de-noising processing with better performance. Experiments show that this system can satisfy the requirements of varieties of input video source formats and real-time processing, and the peak signal to noise rate of the de-noising images is significantly improved.

Considering the requirement of measurement for video probe, a method that uses line-structured laser to measure points, lines and surfaces of the object is presented. The line-structured light imaging model is built, where the linear laser is used as an auxiliary light source irradiating on the surface of the object. Compared to the object image, the proportional coefficient is calibrated with multiplying factor in different distance and laser line position. The geometry parameters are calculated based on the measurement platform. The experimental results show that the measuring error is less than 10%, and the method is suitable for the requirements of the video probe.

The current interpolation based distributed video codecs get excellent rate distortion performance at the cost of high decoder complexity and delay, which make them almost impractical. An efficient way to solve the problem is to use extrapolation instead of interpolation in side information generation. The proposed codec combines the state-of-the-art optical flow based extrapolation algorithm with modulo operation based low complexity pixel domain distributed video codec and gets high R-D performance. The proposed codec enables the successful encoding and decoding of the frames, thus reducing the delay of the whole system. Simulation results show that the proposed codec outperforms other interpolation and extrapolation based codecs in a series of video sequences. Additionally, the decoding complexity is as low as 1/50 of the traditional distributed video codec without increasing the complexity of the encoder.

Event recognition is the process of determining the event type and state of crowd on video under analysis by a machine learning process. In order to improve the accuracy, this paper proposes a method that using optical flow of corner points and convolutional neural network to recognize crowd events on video. First, extract and filter the FAST (Features from Accelerated Segment Test) corner points. Then, track those points using Lucas-Kanade optical flow and get coordinate vectors. Finally, train an improved convolutional neural network based on LeNet model. Experiment on the PETS 2009 dataset using surveillance systems shows that, Average error rate for classifying the 6 crowd events is 0.11. So the method can recognize a variety of defined crowd events and improve the accuracy of recognition.

Segmentation of moving objects from video sequences is the fundamental step in intelligent surveillance applications. Numerous methods have been proposed to obtain object segmentation. In this paper, we present an effective approach based on the mixture of Gaussians. The approach makes use of a feedback strategy with multiple levels: the pixel level, the region level, and the frame level. Pixel-level feedback helps to provide each pixel with an adaptive learning rate. The maintenance strategy of the background model is adjusted by region-level feedback based on tracking. Frame-level feedback is used to detect the global change in scenes. These different levels of feedback strategies ensure our approach’s effectiveness and robustness. This is demonstrated through experimental results on the Change Detection 2014 benchmark dataset.

In the contemporary age, usage of the street view systems like Google Street View is becoming increasingly common. These systems, make the visualization of the real street ambience easier on the Geographic Information System and also aids the users to effortlessly plan and determine their intended place of travel. However, such street view systems are generally not updated on a regular basis because the street view service provider requires numerous cars mounted with panoramic cameras to capture the real roadside surroundings. The main aim of this paper is to propose a novel model that can create image sequences of random street view at any place by employing the images acquired from automotive video recorders. The notion of this model is identical to the theory of dynamic street view frames preserved by the common handlers. The proposed model is employed to design a framework that can map any frame recorded by a video event data recorder to the already available databank consisting of several panoramic street view images. A new image warping technique has been proposed to reduce the geometric distortion present in the recreated street view frames.

Traffic data collected at intersections are essential information for traffic signal operations, traffic control, and intersection design and planning. Compared with highway traffic detections, traffic surveillance at intersections has more challenges due to the variety of road users and weaving caused by traffic conflicts. One of these problems is the detection failure of stopping road users. The other challenge is to track objects during occlusion caused by traffic conflicts. In this study, a real time video surveillance system is developed to detect, track and classify road users at intersections. At first, an improved Gaussian Mixture Model (GMM) is utilized to detect road users, including temporary stopping objects due to traffic conflicts. Then, a motion estimation approach is used to get the trajectories of road users. Finally, the Back Propagation Neural Network (BPNN) is employed to classify pedestrians, bicycles, and vehicles. Experimental results show that the proposed traffic surveillance system is effective and successful for road user detection, tracking and identification at intersections.

Matrix factorization technique has wide applications in data analysis, in which Semi-nonnegative Matrix Factorization (Semi-NMF) can learn an effective low-dimensional feature representation by semi-nonnegative limit inspired from cognition, and has a unique physical meaning that the whole is composed of the parts. In addition, the fashionable Deep Semi-NMF can learn more hidden information by deep factorization. But they do not consider the intrinsic geometric structure of complex data. However more effective feature representations can obtain by using the geometric structure information of complex data and local invariance. In this paper we regularize Semi-NMF and Deep Semi-NMF by using the neighbor graph for keeping the intrinsic geometric structure of the original data. So we propose two novel feature extracting algorithms: Graph Regularized Semi-NMF and Graph Regularized Deep Semi-NMF. The clustering experimental results on several benchmark datasets show that our Graph Regularized Semi-NMF and Graph Regularized Deep Semi-NMF outperform obviously Semi-NMF and Deep Semi-NMF respectively.

This paper investigates the 3D object retrieval problem by adapting a Convolution Network and introduce triplet loss into the training process of network. The 3D objects are converted to vexolized volumetric grids and then fed into the network. The outputs from the first full connection layer are taken as the 3D object descriptors. Triplet loss is designed to make the learned descriptors more suitable for retrieval. Experiments demonstrate that our descriptors are distinctive for objects from different categories and similar among those from the same category. It is much better than traditional handcrafted features like SPH and LFD. The superiority over another deep network based method ShapeNets validates the effectiveness of the triplet loss in driving same-class descriptors to assemble and different-class ones to disperse.

In general, visual trackers employ hand-crafted feature descriptors to track the object, which limits their performance. In this paper, a novel Restricted Boltzmann Machine based Tracker (RBMT) is proposed to enhance the robustness. RBMs are introduced to learn multiple feature descriptors for the different image cues which are transformed from the given images. A data augment method is introduced to online train the RBMs so as to make the learnt feature descriptors specific for different tracked objects. To make the proposed tracker adapted to drastic varying scenes, a feature selection method is also developed to fuse the multiple cues in feature level for the design of appearance-based classifiers. Our experimental results have shown that the proposed tracker can obtain promising performances compared with the other state-of-the-art approaches.

Dimensional measurement for hot forgings is a key factor to improve the level of forging technology in industry field. However, the high temperature, large size and hostile environment increase difficulties to guarantee the robustness and speed of the measurement. In this paper, a robust real-time image processing method based on laser-aided binocular machine vision system is proposed. Firstly, images with clear laser stipes are acquired using spectral selection method, by which the influences of thermal radiation and ambient light can be reduced. Then, to improve the speed of extraction and the robustness of matching, an extraction method based on the information consistency of the images acquired by the system and a matching method based on sequential consistency and epipolar constraints are presented. Dimensional reconstruction models for square and axial forgings are built. Finally, the image processing results are used to reconstruct the feature dimensions of a ceramic plate in the laboratory as well as forgings in a forge. Experiments show that, the root-mean-square error of the reconstructed points is 0.002mm and the relative error for width reconstruction is 0.638% in a cold state. Lengths and diameters of hot large forgings are reconstructed robustly and in real time. It is verified that the method proposed in this paper can satisfy the requirements of precision, speed and robustness for measurement of large hot forgings in industrial field.

In this paper, the convolutional neural networks with the pre-trained kernels are applied to the video surveillance system, which has been built along the Shanghai-Hangzhou high-speed railway to monitor the railway clearance scene and will output the alarm images with the dangerous intruding objects in. The video surveillance system will firstly generate the images which are suspected of containing the dangerous objects intruding the clearance. The convolutional neural networks with the pre-trained kernels are applied to process these suspicious images to eliminating the false alarm images, only contain the trains and the empty clearance scene, from other suspicious images before the final output. Experimental result shows that, the process of each test image only takes 0.16 second and has a high accuracy.

Constructing visual vocabularies in the bag of visual word (BoVW) model is a critical step, most visual vocabularies is generated either by the k-means algorithm or its improved algorithm. Visual vocabularies generated by these methods have the problem of low discriminative and long running time. For these problems, a BoVW model is proposed based on binary hashing and space pyramid. Firstly, extract the local feature points from the images. Second, learn binary hashing functions, which map the local feature points into visual words, and filter the visual words and generate the visual vocabularies whose visual word is binary hash code. Third, Combined with spatial pyramid matching model, the new BoVW model represents the image by the histogram vector of space pyramid. Finally, the BoVW model is used in image classification and retrieval to verify the effectiveness of the model. Experimental results on the common datasets show that visual vocabularies in our model has higher discriminative and expression ability. Compared with other methods, our model has higher classification accuracy and better retrieval performance.

Large visual dictionaries are often used to achieve good image classification performance in bag-of-features (BoF) model, while they lead to high computational cost on dictionary learning and feature coding. In contrast, using small dictionaries can largely reduce the computational cost but result in poor classification performance. Some works have pointed out that pooling locally across feature space can boost the classification performance especially for small dictionaries. Following this idea, various pooling strategies have been proposed in recent years, but they are not good enough for small dictionaries. In this paper, we present a unified framework of pooling operation, and propose two novel pooling strategies to improve the performance of small dictionaries with low extra computational cost. Experimental results on two challenging image classification benchmarks show that our pooling strategies outperform others in most cases.

At present, g²o (general graph optimization) is the main method of reducing the accumulated errors of point cloud registration, an important step of 3D scene reconstruction. However, the huge amount of point cloud data produced in the application process leads to the failure of meeting real -time request. Since cuboid is the most common indoor geometric structure of buildings , this paper presents an optimization method using planar features of point cloud. We rapidly extract the planes from point cloud and modify the transfer matrix of pair point c louds based on planar rotation. Results show that, by regulating down sampling threshold, the treatment time of each frame of point cloud data can be approximately shortened to 1.8486s in comparison of 3.08683s by g²o. Besides, the algorism ensures the matching effect and thus has strong robustness.

There is an emerging interest on using background prior in saliency detection. However, these methods fail to locate the position of background accurately. In this paper, a novel saliency detection approach which chooses more precise background regions is proposed. First, in order to pick out the real background from the boundary of the image, the background probability is measured by boundary ratio. Next, according to the geodesic distance to background regions, the edge saliency map and color saliency map are calculated in the Edge and RGB-LAB-XY feature space, respectively. Furthermore, combining the saliency cues by using an energy function, the final saliency map is generated. The proposed model has the following two advantages: the erroneous background removal guarantees the accuracy of background and the detection of objects located at the boundary of image; the energy minimization enable the detected objects to be more complete and edges of targets to be clearer. Comprehensive experiments on two benchmark datasets demonstrate the superiority of the proposed algorithm over the 5 state-of-the-art methods.

Han Chang’an City is the first cosmopolitan city and was the largest metropolis at that time in the world. As well known for the center of Han nationality culture, Han Chang’an City has been considered as the famous culture heritage that plays an important role in exploring 5000 years history of China. With the purpose of reviving the glories of Han Chang’an City, model reconstruction, navigation system and user interaction of Han Chang’an city with the technique of virtual scene were performed in this paper. In this system, Unity3D is chosen as the 3D platform, 3D Max is used to model the scene, and JavaScript and C# are used as the programming languages. Furthermore, by combined with Gaode Map, the functions including navigation system, roaming, cultural relics display and multimedia have been implemented.

In low-power and high-density real time locating systems, time difference of arrival (TDOA) technique outperforms other ranging techniques. The realization of TDOA-based high resolution indoor localization directly depends on the performance of clock synchronization. In this paper, we introduce a clock synchronization method based on the Kalman filter. The updated clock skew from the Kalman filter is incorporated into the calibration of the difference of arrival time to achieve highly accurate localization of moving targets. Experiments show that our method provides a nanosecond level synchronization resolution and has good robustness to clock synchronization period and non-line-of-sight error, which is quite suitable for indoor localization scenario.

Transfer learning problem aims at matching the joint distributions of the source and the target datasets so that the model learned from the source dataset can be applied to the target dataset. Unfortunately, the joint distribution of the database may be very hard to estimate in many applications. Since the joint distribution can be written as the product of the marginal and the conditional distributions, we propose the TSM, which tries to match the latter two distributions respectively, instead of directly matching the joint distributions. The proposed TSM consists of two parts: a feature learning part which matches the marginal distributions by learning a shared feature space, and a classifier training part which matches the conditional distributions by training an adaptive classifier in the shared feature space. Comprehensive experiments prove that the superior performance of the TSM on several transfer learning datasets. And the improvements are 12.86% on the USPS/MNIST dataset and 9.01% on the PIE1/PIE2 dataset compared to the best baseline.

Dropout is proved to have a good ability of controlling overfitting and improving deep networks’ generalization. However, dropout adopts a constant rate to train the parameters of each layer, reducing the classification accuracy and efficiency. Aiming at this problem, the paper proposes a dropout rate distribution model by analyzing the relationship between the dropout rate and the layers of the deep network. First, we gave the formal description of the dropout rate to reveal the relationship between the dropout rate and the layers of the deep network. Second, we proposed a distribution model for determining the dropout rate in each layer training. Experiments are performed on MNIST and CIFAR-10 datasets to evaluate the performance of the proposed model by comparison with networks of constant dropout rates. Experimental results demonstrate that our proposed model performs better than the conventional dropout in classification accuracy and efficiency.

In order to resolve the phase ambiguity in parameter estimation of a high frequency source with uniform circular array (UCA), this paper presents an algorithm via clustering to obtain the source’s 3-D parameters (azimuth angle, elevation angle, and range) unambiguously. By computing the phase differences between centro-symmetric sensors and employing some mathematics, angle parameters of the source can be decoupled and be estimated. Then, a plural matrix is developed based on ambiguity search, where each column includes a plural constituted by real angle parameters. Further, the unambiguous angle parameters can be obtained by the means of clustering based on range. A one dimension MUSIC method is applied to estimate range parameter after the angle parameters have been obtained. Numerical examples are also presented to demonstrate the performance of the proposed algorithm.

Finding the optimal solution to the problem of selecting clustering centers and improving the performance of existing density-based clustering algorithms, a novel clustering method is proposed in this paper. Our algorithm discovers data clusters according to cluster centers that are identified by a higher density than their nearby points and by a comparatively large distance from points with higher density, and then it finds optimal cluster centers by iteration based on genetic algorithm. We present an exponential density analysis to reduce the impact of model parameters and introduce a penalty factor in order to overcome the excursion of search region for accelerating convergence. Experiments on both artificial and UCI data sets reveal that our algorithm achieves results on Rand Statistic competitive with a variety of classical algorithms.

Faster-than-Nyquist (FTN) signaling has been considered a promising technique for higher frequency bandwidth efficiency. However, symbol detection at the receiver suffers rather high computation complexity due to the intentionally introduced infinite inter-symbol interference (ISI) caused by the way of FTN signaling. For solving this problem, a new method is proposed based on precoding at the transmitter. In this schema, precoding technique is used to eliminate the ISI and lower complexity of the detection of the receiver and Turbo-code is used to reduce the system’s bit error rate (BER). Moreover, the precoding method can be extended to the MQAM. Numerical examination of the proposed method shows performance improvement of the proposed approach over FTN signaling.

In order to improve the efficiency of rendering terrain based on digital elevation model (DEM), a mesh simplification algorithm based on vertex importance and hierarchical clustering tree is presented. The vertexes of terrain blocks are firstly trained using K-means clustering analysis, and then we select representative vertexes of each cluster according to vertex importance. Secondly, coarse meshes are constructed on the basis of these representative vertexes. Thirdly, we seam all coarse meshes. Finally, repeat the above steps until we accomplish the whole simplification process. For the new insertion point, a hierarchical clustering tree is used to record intermediate results, which is applied to view dependent rendering for terrain. Experiment show that, the algorithm improves the efficiency and reduces memory consumption. At the same time, it maintains geometric characteristics of terrain.

In the view of solving the combinatorial optimization problems, there are some faults for Ant Colony Optimization(ACO), such as the long compution and easy to fall into local optimum. To solve these problems, the improved ACO based Differential Evolution(DETCACS) is presented. Different from other DEACO, the transforming between natural number coding and real number is applied in the path planning in the new algorithm ,so that the multiple populations differential evolution and guiding cross can be used to ensuring the diversity. Moreover ,The cross removing strategy are applied to accelerate the convergence process. At last, combined with classic Traveling Salesman Problem(TSP) instances in MATLAB, the DETCACS algorithm shows good performance.