Image Signature: Highlighting Sparse Salient Regions

被引：667

作者：

Hou, Xiaodi ^{[1
]}

Harel, Jonathan ^{[2
]}

Koch, Christof ^{[3
,4
]}

机构：

[1] CALTECH, Dept Computat & Neural Syst, Pasadena, CA 91125 USA

[2] CALTECH, Dept Elect Engn, Pasadena, CA 91125 USA

[3] CALTECH, Dept Biol & Computat & Neural Syst, Pasadena, CA 91125 USA

[4] Korea Univ, Dept Brain & Cognit Engn, Seoul 136713, South Korea

来源：

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE | 2012年 / 34卷 / 01期

基金：

新加坡国家研究基金会;

关键词：

Saliency; visual attention; change blindness; sign function; sparse signal analysis; ATTENTION; SCENE; RECONSTRUCTION; PHASE;

D O I：

10.1109/TPAMI.2011.146

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

We introduce a simple image descriptor referred to as the image signature. We show, within the theoretical framework of sparse signal mixing, that this quantity spatially approximates the foreground of an image. We experimentally investigate whether this approximate foreground overlaps with visually conspicuous image locations by developing a saliency algorithm based on the image signature. This saliency algorithm predicts human fixation points best among competitors on the Bruce and Tsotsos [1] benchmark data set and does so in much shorter running time. In a related experiment, we demonstrate with a change blindness data set that the distance between images induced by the image signature is closer to human perceptual distance than can be achieved using other saliency algorithms, pixel-wise, or GIST [2] descriptor methods.

引用

页码：194 / 201

页数：8