Region enhanced scale-invariant saliency detection

被引：62

作者：

Liu, Feng ^{[1
]}

Gleicher, Michael ^{[1
]}

机构：

[1] Univ Wisconsin, Dept Comp Sci, 1210 W Dayton St, Madison, WI 53706 USA

来源：

2006 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO - ICME 2006, VOLS 1-5, PROCEEDINGS | 2006年

关键词：

D O I：

10.1109/ICME.2006.262821

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Saliency measures the low-level stimuli to human vision, and serves as an alternative to semantic image understanding. This paper presents a region enhanced scale-invariant saliency detection method. Our method constructs a scale-invariant saliency map from an image, segments the image into regions, and enhances the saliency map with the region information. Compared with previous methods, our method has advantages in providing robust scale-invariant saliency, giving meaningful region information for applications, and eliminating misleading high-contrast edges.

引用

页码：1477 / +

页数：2

共 16 条

[1]

[Anonymous], 2003, PROC 16 ANN ACM S US, DOI DOI 10.1145/964696.964707

[2] A visual attention model for adapting images on small displays [J].

Chen, LQ ;

Xie, X ;

Fan, X ;

Ma, WY ;

Zhang, HJ ;

Zhou, HQ .

MULTIMEDIA SYSTEMS, 2003, 9 (04) :353-364

[3]

Comaniciu D., 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision, P1197, DOI 10.1109/ICCV.1999.790416

[4]

Hu YM, 2004, I C CONT AUTOMAT ROB, P993

[5]

HU YQ, 2005, P ACM MULT 2005

[6] A model of saliency-based visual attention for rapid scene analysis [J].

Itti, L ;

Koch, C ;

Niebur, E .

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1998, 20 (11) :1254-1259

[7] Computational modelling of visual attention [J].

Itti, L ;

Koch, C .

NATURE REVIEWS NEUROSCIENCE, 2001, 2 (03) :194-203

[8]

LI Y, 2003, ICME 2003

[9]

Liu Feng, 2005, UIST '05, P153

[10]

Liu H., 2004, IMIR, P84

← 1 2 →