Share Email Print
cover

Proceedings Paper

SAR Image despeckling via sparse representation
Author(s): Zhongmei Wang; Xiaomei Yang; Liang Zheng
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

SAR image despeckling is an active research area in image processing due to its importance in improving the quality of image for object detection and classification.In this paper, a new approach is proposed for multiplicative noise in SAR image removal based on nonlocal sparse representation by dictionary learning and collaborative filtering. First, a image is divided into many patches, and then a cluster is formed by clustering log-similar image patches using Fuzzy C-means (FCM). For each cluster, an over-complete dictionary is computed using the K-SVD method that iteratively updates the dictionary and the sparse coefficients. The patches belonging to the same cluster are then reconstructed by a sparse combination of the corresponding dictionary atoms. The reconstructed patches are finally collaboratively aggregated to build the denoised image. The experimental results show that the proposed method achieves much better results than many state-of-the-art algorithms in terms of both objective evaluation index (PSNR and ENL) and subjective visual perception.

Paper Details

Date Published: 19 November 2014
PDF: 7 pages
Proc. SPIE 9264, Earth Observing Missions and Sensors: Development, Implementation, and Characterization III, 92641O (19 November 2014); doi: 10.1117/12.2069168
Show Author Affiliations
Zhongmei Wang, Univ. of Electronic Science and Technology of China (China)
Sichuan College of Architectural Technical College (China)
Xiaomei Yang, Institute of Geographic Sciences and Natural Resources Research (China)
Liang Zheng, 15th Institute of China Electronics Technology Group Corp. (China)


Published in SPIE Proceedings Vol. 9264:
Earth Observing Missions and Sensors: Development, Implementation, and Characterization III
Xiaoxiong Xiong; Haruhisa Shimoda, Editor(s)

© SPIE. Terms of Use
Back to Top