Visual Conspicuity Index: Spatial Dissimilarity, Distance, and Central Bias

doi:10.1109/LSP.2011.2167752

CORC > 计算技术研究所 > 中国科学院计算技术研究所 > 中国科学院计算技术研究所期刊论文 > 英文

	Visual Conspicuity Index: Spatial Dissimilarity, Distance, and Central Bias
	Duan, Lijuan 1; Wu, Chunpeng 1; Miao, Jun 2; Bovik, Alan C.3
刊名	IEEE SIGNAL PROCESSING LETTERS
	2011-11-01
卷号	18 期号:11 页码:690-693
关键词	central bias conspicuity dissimilarity spatial distance visual saliency
ISSN号	1070-9908
DOI	10.1109/LSP.2011.2167752
英文摘要	We propose an image conspicuity index that combines three factors: spatial dissimilarity, spatial distance and central bias. The dissimilarity between image patches is evaluated in a reduced dimensional principal component space and is inversely weighted by the spatial separations between patches. An additional weighting mechanism is deployed that reflects the bias of human fixations towards the image center. The method is tested on three public image datasets and a video clip to evaluate its performance. The experimental results indicate highly competitive performance despite the simple definition of the proposed index. The conspicuity maps generated are more consistent with human fixations than prior state-of-the-art models when tested on color image datasets. This is demonstrated using both receiver operator characteristics (ROC) analysis and the Kullback-Leibler distance metric. The method should prove useful for such diverse image processing tasks as quality assessment, segmentation, search, or compression. The high performance and relative simplicity of the conspicuity index relative to other much more complex models suggests that it may find wide usage.
资助项目	National Basic Research Program of China[2009CB320902] ; Beijing Natural Science Foundation[4102013] ; Beijing Natural Science Foundation[4072023] ; Natural Science Foundation of China[61175115] ; Natural Science Foundation of China[60702031] ; Natural Science Foundation of China[60970087] ; Natural Science Foundation of China[61070116] ; Natural Science Foundation of China[61070149] ; Natural Science Foundation of China[60802067]
WOS研究方向	Engineering
语种	英语
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号	WOS:000296012600003
内容类型	期刊论文
源URL	[http://119.78.100.204/handle/2XEOYT63/13082]
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Duan, Lijuan
作者单位	1.Beijing Univ Technol, Coll Comp Sci & Technol, Beijing 100124, Peoples R China 2.Chinese Acad Sci, Key Lab Intelligent Informat Proc, Inst Comp Technol, Beijing 100190, Peoples R China 3.Univ Texas Austin, Lab Image & Video Engn, Dept Elect & Comp Engn, Austin, TX 78712 USA
推荐引用方式 GB/T 7714	Duan, Lijuan,Wu, Chunpeng,Miao, Jun,et al. Visual Conspicuity Index: Spatial Dissimilarity, Distance, and Central Bias[J]. IEEE SIGNAL PROCESSING LETTERS,2011,18(11):690-693.
APA	Duan, Lijuan,Wu, Chunpeng,Miao, Jun,&Bovik, Alan C..(2011).Visual Conspicuity Index: Spatial Dissimilarity, Distance, and Central Bias.IEEE SIGNAL PROCESSING LETTERS,18(11),690-693.
MLA	Duan, Lijuan,et al."Visual Conspicuity Index: Spatial Dissimilarity, Distance, and Central Bias".IEEE SIGNAL PROCESSING LETTERS 18.11(2011):690-693.