14 December 2015 A novel algorithm of super-resolution image reconstruction based on multi-class dictionaries for natural scene
Author Affiliations +
Proceedings Volume 9815, MIPPR 2015: Remote Sensing Image Processing, Geographic Information Systems, and Other Applications; 981515 (2015) https://doi.org/10.1117/12.2204775
Event: Ninth International Symposium on Multispectral Image Processing and Pattern Recognition (MIPPR2015), 2015, Enshi, China
Abstract
Super-resolution image reconstruction is an effective method to improve the image quality. It has important research significance in the field of image processing. However, the choice of the dictionary directly affects the efficiency of image reconstruction. A sparse representation theory is introduced into the problem of the nearest neighbor selection. Based on the sparse representation of super-resolution image reconstruction method, a super-resolution image reconstruction algorithm based on multi-class dictionary is analyzed. This method avoids the redundancy problem of only training a hyper complete dictionary, and makes the sub-dictionary more representatives, and then replaces the traditional Euclidean distance computing method to improve the quality of the whole image reconstruction. In addition, the ill-posed problem is introduced into non-local self-similarity regularization. Experimental results show that the algorithm is much better results than state-of-the-art algorithm in terms of both PSNR and visual perception.
© (2015) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Wei Wu, Wei Wu, Dewei Zhao, Dewei Zhao, Huan Zhang, Huan Zhang, } "A novel algorithm of super-resolution image reconstruction based on multi-class dictionaries for natural scene", Proc. SPIE 9815, MIPPR 2015: Remote Sensing Image Processing, Geographic Information Systems, and Other Applications, 981515 (14 December 2015); doi: 10.1117/12.2204775; https://doi.org/10.1117/12.2204775
PROCEEDINGS
7 PAGES


SHARE
Back to Top