Image compressed sensing recovery via adaptive dictionary learning

Tao Zhu; Junwei Xu; Lei Cai; Weihong He; Youjun Xiang; Yuli Fu

doi:10.1117/12.2573113

Translator Disclaimer

12 June 2020 Image compressed sensing recovery via adaptive dictionary learning

Tao Zhu, Junwei Xu, Lei Cai, Weihong He, Youjun Xiang, Yuli Fu

Proceedings Volume 11519, Twelfth International Conference on Digital Image Processing (ICDIP 2020); 115191J (2020) https://doi.org/10.1117/12.2573113
Event: Twelfth International Conference on Digital Image Processing, 2020, Osaka, Japan

Abstract

This paper addresses the image compressed sensing recovery problem. To improve the recovery quality, instead of using a fixed dictionary that is generally a universal one trained in an off-line manner for sparse representations of image patches, we adopt an adaptive dictionary learning strategy. Inspired by the monotone fast iterative shrinkagethresholding algorithm, a dictionary learning algorithm is introduced in this work. Also, we abandon the classic method that breaks an image into fully overlapping patches, and propose a new overlapping patches extraction method, which decreases the number of patches and saves much run-time, while achieves similar recovery qualities.

Citation Download Citation

Tao Zhu, Junwei Xu, Lei Cai, Weihong He, Youjun Xiang, and Yuli Fu "Image compressed sensing recovery via adaptive dictionary learning", Proc. SPIE 11519, Twelfth International Conference on Digital Image Processing (ICDIP 2020), 115191J (12 June 2020); https://doi.org/10.1117/12.2573113

ACCESS THE FULL ARTICLE