14 December 2015 Image super-resolution reconstruction via RBM-based joint dictionary learning and sparse representation
Author Affiliations +
Proceedings Volume 9815, MIPPR 2015: Remote Sensing Image Processing, Geographic Information Systems, and Other Applications; 981528 (2015) https://doi.org/10.1117/12.2214097
Event: Ninth International Symposium on Multispectral Image Processing and Pattern Recognition (MIPPR2015), 2015, Enshi, China
Abstract
In this paper, we propose a method for single image super-resolution(SR). Given the training set produced from large amount of high-low resolution image patches, an over-complete joint dictionary is firstly learned from a pair of high-low resolution image feature space based on Restricted Boltzmann Machines (RBM). Then for each low resolution image patch densely extracted from an up-scaled low resolution input image , its high resolution image patch can be reconstructed based on sparse representation. Finally, the reconstructed image patches are overlapped to form a large image, and a high resolution image can be achieved by means of iterated residual image compensation. Experimental results verify the effectiveness of the proposed method.
© (2015) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Zhaohui Zhang, Zhaohui Zhang, Anran Liu, Anran Liu, Qian Lei, Qian Lei, } "Image super-resolution reconstruction via RBM-based joint dictionary learning and sparse representation", Proc. SPIE 9815, MIPPR 2015: Remote Sensing Image Processing, Geographic Information Systems, and Other Applications, 981528 (14 December 2015); doi: 10.1117/12.2214097; https://doi.org/10.1117/12.2214097
PROCEEDINGS
7 PAGES


SHARE
Back to Top