Saliency detection via divergence analysis: A unified perspective

Jia Bin Huang, Narendra Ahuja

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

A number of bottom-up saliency detection algorithms have been proposed in the literature. Since these have been developed from intuition and principles inspired by psychophysical studies of human vision, the theoretical relations among them are unclear. In this paper, we present a unifying perspective. Saliency of an image area is defined in terms of divergence between certain feature distributions estimated from the central part and its surround. We show that various, seemingly different saliency estimation algorithms are in fact closely related. We also discuss some commonly used center-surround selection strategies. Experiments with two datasets are presented to quantify the relative advantages of these algorithms.

Original languageEnglish (US)
Title of host publicationICPR 2012 - 21st International Conference on Pattern Recognition
Pages2748-2751
Number of pages4
StatePublished - Dec 1 2012
Event21st International Conference on Pattern Recognition, ICPR 2012 - Tsukuba, Japan
Duration: Nov 11 2012Nov 15 2012

Publication series

NameProceedings - International Conference on Pattern Recognition
ISSN (Print)1051-4651

Other

Other21st International Conference on Pattern Recognition, ICPR 2012
CountryJapan
CityTsukuba
Period11/11/1211/15/12

Fingerprint

Experiments

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition

Cite this

Huang, J. B., & Ahuja, N. (2012). Saliency detection via divergence analysis: A unified perspective. In ICPR 2012 - 21st International Conference on Pattern Recognition (pp. 2748-2751). [6460734] (Proceedings - International Conference on Pattern Recognition).

Saliency detection via divergence analysis : A unified perspective. / Huang, Jia Bin; Ahuja, Narendra.

ICPR 2012 - 21st International Conference on Pattern Recognition. 2012. p. 2748-2751 6460734 (Proceedings - International Conference on Pattern Recognition).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Huang, JB & Ahuja, N 2012, Saliency detection via divergence analysis: A unified perspective. in ICPR 2012 - 21st International Conference on Pattern Recognition., 6460734, Proceedings - International Conference on Pattern Recognition, pp. 2748-2751, 21st International Conference on Pattern Recognition, ICPR 2012, Tsukuba, Japan, 11/11/12.
Huang JB, Ahuja N. Saliency detection via divergence analysis: A unified perspective. In ICPR 2012 - 21st International Conference on Pattern Recognition. 2012. p. 2748-2751. 6460734. (Proceedings - International Conference on Pattern Recognition).
Huang, Jia Bin ; Ahuja, Narendra. / Saliency detection via divergence analysis : A unified perspective. ICPR 2012 - 21st International Conference on Pattern Recognition. 2012. pp. 2748-2751 (Proceedings - International Conference on Pattern Recognition).
@inproceedings{afde280031294347ad718396a7920174,
title = "Saliency detection via divergence analysis: A unified perspective",
abstract = "A number of bottom-up saliency detection algorithms have been proposed in the literature. Since these have been developed from intuition and principles inspired by psychophysical studies of human vision, the theoretical relations among them are unclear. In this paper, we present a unifying perspective. Saliency of an image area is defined in terms of divergence between certain feature distributions estimated from the central part and its surround. We show that various, seemingly different saliency estimation algorithms are in fact closely related. We also discuss some commonly used center-surround selection strategies. Experiments with two datasets are presented to quantify the relative advantages of these algorithms.",
author = "Huang, {Jia Bin} and Narendra Ahuja",
year = "2012",
month = "12",
day = "1",
language = "English (US)",
isbn = "9784990644109",
series = "Proceedings - International Conference on Pattern Recognition",
pages = "2748--2751",
booktitle = "ICPR 2012 - 21st International Conference on Pattern Recognition",

}

TY - GEN

T1 - Saliency detection via divergence analysis

T2 - A unified perspective

AU - Huang, Jia Bin

AU - Ahuja, Narendra

PY - 2012/12/1

Y1 - 2012/12/1

N2 - A number of bottom-up saliency detection algorithms have been proposed in the literature. Since these have been developed from intuition and principles inspired by psychophysical studies of human vision, the theoretical relations among them are unclear. In this paper, we present a unifying perspective. Saliency of an image area is defined in terms of divergence between certain feature distributions estimated from the central part and its surround. We show that various, seemingly different saliency estimation algorithms are in fact closely related. We also discuss some commonly used center-surround selection strategies. Experiments with two datasets are presented to quantify the relative advantages of these algorithms.

AB - A number of bottom-up saliency detection algorithms have been proposed in the literature. Since these have been developed from intuition and principles inspired by psychophysical studies of human vision, the theoretical relations among them are unclear. In this paper, we present a unifying perspective. Saliency of an image area is defined in terms of divergence between certain feature distributions estimated from the central part and its surround. We show that various, seemingly different saliency estimation algorithms are in fact closely related. We also discuss some commonly used center-surround selection strategies. Experiments with two datasets are presented to quantify the relative advantages of these algorithms.

UR - http://www.scopus.com/inward/record.url?scp=84874560046&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84874560046&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84874560046

SN - 9784990644109

T3 - Proceedings - International Conference on Pattern Recognition

SP - 2748

EP - 2751

BT - ICPR 2012 - 21st International Conference on Pattern Recognition

ER -