Share Email Print

Journal of Electronic Imaging

Spatial encoding of visual words for image classification
Author(s): Dong Liu; Shengsheng Wang; Fatih Porikli
Format Member Price Non-Member Price
PDF $20.00 $25.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

Appearance-based bag-of-visual words (BoVW) models are employed to represent the frequency of a vocabulary of local features in an image. Due to their versatility, they are widely popular, although they ignore the underlying spatial context and relationships among the features. Here, we present a unified representation that enhances BoVWs with explicit local and global structure models. Three aspects of our method should be noted in comparison to the previous approaches. First, we use a local structure feature that encodes the spatial attributes between a pair of points in a discriminative fashion using class-label information. We introduce a bag-of-structural words (BoSW) model for the given image set and describe each image with this model on its coarsely sampled relevant keypoints. We then combine the codebook histograms of BoVW and BoSW to train a classifier. Rigorous experimental evaluations on four benchmark data sets demonstrate that the unified representation outperforms the conventional models and compares favorably to more sophisticated scene classification techniques.

Paper Details

Date Published: 31 May 2016
PDF: 5 pages
J. Electron. Imag. 25(3) 033008 doi: 10.1117/1.JEI.25.3.033008
Published in: Journal of Electronic Imaging Volume 25, Issue 3
Show Author Affiliations
Dong Liu, Jilin Univ. (China)
Shengsheng Wang, Jilin Univ. (China)
Fatih Porikli, The Australian National Univ. (Australia)
Commonwealth Scientific and Industrial Research Organisation (Australia)

© SPIE. Terms of Use
Back to Top