Geometry Constrained Sparse Coding for Single Image Super-resolution

OPT OpenIR > 光谱成像技术研究室

	Geometry Constrained Sparse Coding for Single Image Super-resolution
	Xiaoqiang Lu; Haoliang Yuan; Pingkun Yan; Yuan Yuan; Xuelong Li
	2012
会议名称	IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
会议录名称	2012 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)
页码	1648-1655
会议日期	JUN 16-21, 2012
会议地点	Providence, RI
出版地	NEW YORK
出版者	IEEE
产权排序	1
摘要	The choice of the over-complete dictionary that sparsely represents data is of prime importance for sparse coding based image super-resolution. Sparse coding is a typical unsupervised learning method to generate an over-complete dictionary. However, most of the sparse coding methods for image super-resolution fail to simultaneously consider the geometrical structure of the dictionary and corresponding coefficients, which may result in noticeable super-resolution reconstruction artifacts. In this paper, a novel sparse coding method is proposed to preserve the geometrical structure of the dictionary and the sparse coefficients of the data. Moreover, the proposed method can preserve the incoherence of dictionary entries, which is critical for sparse representation. Inspired by the development on non-local self-similarity and manifold learning, the proposed sparse coding method can provide the sparse coefficients and learned dictionary from a new perspective, which have both reconstruction and discrimination properties to enhance the learning performance. Extensive experimental results on image super-resolution have demonstrated the effectiveness of the proposed method.
作者部门	光学影像分析与学习中心
收录类别	CPCI（ISTP） ; EI
ISBN号	978-1-4673-1228-8
语种	英语
ISSN号	1063-6919
文献类型	会议论文
条目标识符	http://ir.opt.ac.cn/handle/181661/20501
专题	光谱成像技术研究室
推荐引用方式 GB/T 7714	Xiaoqiang Lu,Haoliang Yuan,Pingkun Yan,et al. Geometry Constrained Sparse Coding for Single Image Super-resolution[C]. NEW YORK:IEEE,2012:1648-1655.

条目包含的文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
Geometry Constrained（293KB）			限制开放	CC BY-NC-SA	请求全文