Phase-based salient object detection

Jia Wan; Kin Man Lam

doi:10.1109/ICSPCS.2012.6508015

Phase-based salient object detection

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

Abstract

In this paper, we propose an efficient approach to computing saliency maps and determining salient areas in images. Biologically inspired feature maps are first constructed for a given image, and the phase information is then extracted from each feature map in the frequency domain. Finally, a saliency map is formed by using the phase information, followed by a smoothing operation. Experiment results show that our proposed algorithm is computationally efficient and can detect salient objects accurately.

Original language	English
Title of host publication	6th International Conference on Signal Processing and Communication Systems, ICSPCS 2012 - Proceedings
DOIs	https://doi.org/10.1109/ICSPCS.2012.6508015
Publication status	Published - 1 Dec 2012
Event	6th International Conference on Signal Processing and Communication Systems, ICSPCS 2012 - Gold Coast, QLD, Australia Duration: 12 Dec 2012 → 14 Dec 2012

Conference

Conference	6th International Conference on Signal Processing and Communication Systems, ICSPCS 2012
Country/Territory	Australia
City	Gold Coast, QLD
Period	12/12/12 → 14/12/12

Keywords

saliency map
salient object detection
spectral-domain analysis
visual attention

ASJC Scopus subject areas

Computer Networks and Communications
Signal Processing

More information

10.1109/ICSPCS.2012.6508015

Cite this

@inproceedings{856bc24e232c448ba46a5fafb10fd69b,

title = "Phase-based salient object detection",

abstract = "In this paper, we propose an efficient approach to computing saliency maps and determining salient areas in images. Biologically inspired feature maps are first constructed for a given image, and the phase information is then extracted from each feature map in the frequency domain. Finally, a saliency map is formed by using the phase information, followed by a smoothing operation. Experiment results show that our proposed algorithm is computationally efficient and can detect salient objects accurately.",

keywords = "saliency map, salient object detection, spectral-domain analysis, visual attention",

author = "Jia Wan and Lam, {Kin Man}",

year = "2012",

month = dec,

day = "1",

doi = "10.1109/ICSPCS.2012.6508015",

language = "English",

isbn = "9781467323932",

booktitle = "6th International Conference on Signal Processing and Communication Systems, ICSPCS 2012 - Proceedings",

note = "6th International Conference on Signal Processing and Communication Systems, ICSPCS 2012 ; Conference date: 12-12-2012 Through 14-12-2012",

}

TY - GEN

T1 - Phase-based salient object detection

AU - Wan, Jia

AU - Lam, Kin Man

PY - 2012/12/1

Y1 - 2012/12/1

N2 - In this paper, we propose an efficient approach to computing saliency maps and determining salient areas in images. Biologically inspired feature maps are first constructed for a given image, and the phase information is then extracted from each feature map in the frequency domain. Finally, a saliency map is formed by using the phase information, followed by a smoothing operation. Experiment results show that our proposed algorithm is computationally efficient and can detect salient objects accurately.

AB - In this paper, we propose an efficient approach to computing saliency maps and determining salient areas in images. Biologically inspired feature maps are first constructed for a given image, and the phase information is then extracted from each feature map in the frequency domain. Finally, a saliency map is formed by using the phase information, followed by a smoothing operation. Experiment results show that our proposed algorithm is computationally efficient and can detect salient objects accurately.

KW - saliency map

KW - salient object detection

KW - spectral-domain analysis

KW - visual attention

UR - http://www.scopus.com/inward/record.url?scp=84880275449&partnerID=8YFLogxK

U2 - 10.1109/ICSPCS.2012.6508015

DO - 10.1109/ICSPCS.2012.6508015

M3 - Conference article published in proceeding or book

SN - 9781467323932

BT - 6th International Conference on Signal Processing and Communication Systems, ICSPCS 2012 - Proceedings

T2 - 6th International Conference on Signal Processing and Communication Systems, ICSPCS 2012

Y2 - 12 December 2012 through 14 December 2012

ER -

Phase-based salient object detection

Abstract

Conference

Keywords

ASJC Scopus subject areas

More information

Other files and links

Fingerprint

Cite this