Image Deblurring with Coupled Dictionary Learning

doi:10.1007/s11263-014-0755-z

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 先进时空数据分析与学习

	Image Deblurring with Coupled Dictionary Learning
	Xiang, Shiming1 ; Meng, Gaofeng1 ; Wang, Ying1 ; Pan, Chunhong1 ; Zhang, Changshui 2
发表期刊	INTERNATIONAL JOURNAL OF COMPUTER VISION
	2015-09-01
卷号	114 期号:2-3 页码:248-271
文章类型	Article
摘要	Image deblurring is a challenging problem in vision computing. Traditionally, this task is addressed as an inverse problem that is enclosed into the image itself. This paper presents a learning-based framework where the knowledge hidden in huge amounts of available data is explored and exploited for image deblurring. To this end, our algorithm is developed under the conceptual framework of coupled dictionary learning. Specifically, given pairs of blurred image patches and their corresponding clear ones, a learning model is constructed to learn a pair of dictionaries. Among them, one dictionary is responsible for the representation of clear images, while the other is responsible for that of the blurred images. Theoretically, the learning model is analyzed with coupled sparse representations for training samples. As the atoms of these dictionaries are coupled together one-by-one, the reconstruction information can be transmitted between the clear and blurry images. In application phase, the blurry dictionary is employed to reconstruct linearly the blurry image to be restored. Then, the reconstruction coefficients are kept unchanged along with the clear dictionary to restore the final results. The main advantage of our approach lies in that it works in the case of unknown blur kernels. Comparative experiments indicate the validity of our approach.
关键词	Image Deblurring Coupled Dictionary Learning Sparse Representation Multiple Kernel Deblurring
WOS标题词	Science & Technology ; Technology
DOI	10.1007/s11263-014-0755-z
关键词[WOS]	SPARSE REPRESENTATION ; SINGLE IMAGE ; K-SVD ; SUPERRESOLUTION ; RESTORATION ; ALGORITHM ; APPROXIMATION ; DECONVOLUTION ; OPTIMIZATION ; REGRESSION
收录类别	SCI
语种	英语
WOS研究方向	Computer Science
WOS类目	Computer Science, Artificial Intelligence
WOS记录号	WOS:000360071900009
引用统计	被引频次：27[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/8962
专题	多模态人工智能系统全国重点实验室_先进时空数据分析与学习
作者单位	1.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China 2.Tsinghua Univ, Dept Automat, TNList, Beijing 100084, Peoples R China
第一作者单位	模式识别国家重点实验室
推荐引用方式 GB/T 7714	Xiang, Shiming,Meng, Gaofeng,Wang, Ying,et al. Image Deblurring with Coupled Dictionary Learning[J]. INTERNATIONAL JOURNAL OF COMPUTER VISION,2015,114(2-3):248-271.
APA	Xiang, Shiming,Meng, Gaofeng,Wang, Ying,Pan, Chunhong,&Zhang, Changshui.(2015).Image Deblurring with Coupled Dictionary Learning.INTERNATIONAL JOURNAL OF COMPUTER VISION,114(2-3),248-271.
MLA	Xiang, Shiming,et al."Image Deblurring with Coupled Dictionary Learning".INTERNATIONAL JOURNAL OF COMPUTER VISION 114.2-3(2015):248-271.

条目包含的文件		下载所有文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
18_IJCV.pdf（7526KB）	期刊论文	作者接受稿	开放获取	CC BY-NC-SA	浏览下载