Entropy of Primitive: From Sparse Representation to Visual Information   Evaluation

doi:10.1109/TCSVT.2015.2511838

CORC > 北京大学 > 信息科学技术学院

	Entropy of Primitive: From Sparse Representation to Visual Information Evaluation
	Ma, Siwei ; Zhang, Xiang ; Wang, Shiqi ; Zhang, Jian ; Sun, Huifang ; Gao, Wen
刊名	IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
	2017
关键词	Entropy of primitive (EoP) just-noticeable difference (JND) orthogonal matching pursuit sparse representation visual information NOTICEABLE-DISTORTION PROFILE IMAGE QUALITY ASSESSMENT VIDEO DICTIONARIES RESTORATION DIFFERENCE RECOVERY DOMAIN MODEL
DOI	10.1109/TCSVT.2015.2511838
英文摘要	In this paper, we propose a novel concept in evaluating the visual information when perceiving natural imagesthe entropy of primitive (EoP). Sparse representation has been successfully applied in a wide variety of signal processing and analysis applications due to its high efficiency in dealing with rich varied and directional information contained in natural scenes. Inspired by this observation, in this paper, the visual signal can be decomposed into structural and nonstructural layers according to the visual importance of sparse primitives. Accordingly, the EoP is developed in measuring the visual information. It has been found that the EoP changing tendency in image sparse representation is highly relevant with the hierarchical perceptual cognitive process of human eyes. Extensive mathematical explanations as well as experimental verifications have been presented in order to support the hypothesis. The robustness of the EoP is evaluated in terms of varied block sizes. The dictionary universality is also studied by employing both universal and adaptive dictionaries. With the convergence characteristics of the EoP, a novel top-down just-noticeable difference (JND) profile is proposed. The simulation results have shown that the EoP-based JND outperforms the state-of-the-art JND models according to the subjective evaluation.; National Basic Research Program of China (973 Program) [2015CB351800]; National Natural Science Foundation of China [61322106, 61572047, 61571017]; Post-Doctoral Science Foundation of China [2015M580018]; Shenzhen Peacock Plan; SCI(E); EI; ARTICLE; 2; 249-260; 27
语种	英语
内容类型	期刊论文
源URL	[http://ir.pku.edu.cn/handle/20.500.11897/457074]
专题	信息科学技术学院
推荐引用方式 GB/T 7714	Ma, Siwei,Zhang, Xiang,Wang, Shiqi,et al. Entropy of Primitive: From Sparse Representation to Visual Information Evaluation[J]. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,2017.
APA	Ma, Siwei,Zhang, Xiang,Wang, Shiqi,Zhang, Jian,Sun, Huifang,&Gao, Wen.(2017).Entropy of Primitive: From Sparse Representation to Visual Information Evaluation.IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY.
MLA	Ma, Siwei,et al."Entropy of Primitive: From Sparse Representation to Visual Information Evaluation".IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY (2017).