Image Super-Resolution Based on Structure-Modulated Sparse   Representation

doi:10.1109/TIP.2015.2431435

CORC > 北京大学 > 信息科学技术学院

	Image Super-Resolution Based on Structure-Modulated Sparse Representation
	Zhang, Yongqin ; Liu, Jiaying ; Yang, Wenhan ; Guo, Zongming
刊名	IEEE TRANSACTIONS ON IMAGE PROCESSING
	2015
关键词	Super-resolution ridge regression sparse representation dictionary learning gradient histogram HIGH-RESOLUTION IMAGE EDGE-DIRECTED INTERPOLATION LINEAR INVERSE PROBLEMS SUPER RESOLUTION RECONSTRUCTION ALGORITHMS VIDEO REGULARIZATION REGISTRATION DICTIONARIES
DOI	10.1109/TIP.2015.2431435
英文摘要	Sparse representation has recently attracted enormous interests in the field of image restoration. The conventional sparsity-based methods enforce sparse coding on small image patches with certain constraints. However, they neglected the characteristics of image structures both within the same scale and across the different scales for the image sparse representation. This drawback limits the modeling capability of sparsity-based super-resolution methods, especially for the recovery of the observed low-resolution images. In this paper, we propose a joint super-resolution framework of structure-modulated sparse representations to improve the performance of sparsity-based image super-resolution. The proposed algorithm formulates the constrained optimization problem for high-resolution image recovery. The multistep magnification scheme with the ridge regression is first used to exploit the multiscale redundancy for the initial estimation of the high-resolution image. Then, the gradient histogram preservation is incorporated as a regularization term in sparse modeling of the image super-resolution problem. Finally, the numerical solution is provided to solve the super-resolution problem of model parameter estimation and sparse representation. Extensive experiments on image super-resolution are carried out to validate the generality, effectiveness, and robustness of the proposed algorithm. Experimental results demonstrate that our proposed algorithm, which can recover more fine structures and details from an input low-resolution image, outperforms the state-of-the-art methods both subjectively and objectively in most cases.; Beijing Natural Science Foundation [4142021]; China Post-Doctoral Science Foundation [2013M530481]; National Natural Science Foundation of China [61201442]; National High-Tech Technology Research and Development Program (863 Program) of China [2014AA015205]; SCI(E); EI; ARTICLE; zhangyongqin@pku.edu.cn; liujiaying@pku.edu.cn; yangwenhan@pku.edu.cn; guozongming@pku.edu.cn; 9; 2797-2810; 24
语种	英语
内容类型	期刊论文
源URL	[http://ir.pku.edu.cn/handle/20.500.11897/417002]
专题	信息科学技术学院
推荐引用方式 GB/T 7714	Zhang, Yongqin,Liu, Jiaying,Yang, Wenhan,et al. Image Super-Resolution Based on Structure-Modulated Sparse Representation[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2015.
APA	Zhang, Yongqin,Liu, Jiaying,Yang, Wenhan,&Guo, Zongming.(2015).Image Super-Resolution Based on Structure-Modulated Sparse Representation.IEEE TRANSACTIONS ON IMAGE PROCESSING.
MLA	Zhang, Yongqin,et al."Image Super-Resolution Based on Structure-Modulated Sparse Representation".IEEE TRANSACTIONS ON IMAGE PROCESSING (2015).