A two-stage approach to saliency detection in images

Zheshen Wang, Baoxin Li

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

63 Citations (Scopus)

Abstract

Researches in psychology, perception and related fields show that there may be a two-stage process involved in human vision. In this paper, we propose an approach by following a two-stage framework for saliency detection. In the first stage, we extend an existing spectrum residual model for better locating visual pop-outs, while in the second stage we make use of coherence based propagation for further refinement of the results from the first step. For evaluation of the proposed approach, 300 images with diverse contents were manually and accurately labeled. Experiments show that our approach achieves much better performance than that from the existing state-of-art.

Original languageEnglish (US)
Title of host publicationICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Pages965-968
Number of pages4
DOIs
StatePublished - 2008
Event2008 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP - Las Vegas, NV, United States
Duration: Mar 31 2008Apr 4 2008

Other

Other2008 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP
CountryUnited States
CityLas Vegas, NV
Period3/31/084/4/08

Fingerprint

psychology
propagation
evaluation
Experiments

Keywords

  • Image analysis
  • Image processing
  • Object detection
  • Pattern recognition

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Signal Processing
  • Acoustics and Ultrasonics

Cite this

Wang, Z., & Li, B. (2008). A two-stage approach to saliency detection in images. In ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings (pp. 965-968). [4517772] https://doi.org/10.1109/ICASSP.2008.4517772

A two-stage approach to saliency detection in images. / Wang, Zheshen; Li, Baoxin.

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. 2008. p. 965-968 4517772.

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

Wang, Z & Li, B 2008, A two-stage approach to saliency detection in images. in ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings., 4517772, pp. 965-968, 2008 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP, Las Vegas, NV, United States, 3/31/08. https://doi.org/10.1109/ICASSP.2008.4517772
Wang Z, Li B. A two-stage approach to saliency detection in images. In ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. 2008. p. 965-968. 4517772 https://doi.org/10.1109/ICASSP.2008.4517772
Wang, Zheshen ; Li, Baoxin. / A two-stage approach to saliency detection in images. ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. 2008. pp. 965-968
@inproceedings{7ca29358d0a142a4900520e8daa3b281,
title = "A two-stage approach to saliency detection in images",
abstract = "Researches in psychology, perception and related fields show that there may be a two-stage process involved in human vision. In this paper, we propose an approach by following a two-stage framework for saliency detection. In the first stage, we extend an existing spectrum residual model for better locating visual pop-outs, while in the second stage we make use of coherence based propagation for further refinement of the results from the first step. For evaluation of the proposed approach, 300 images with diverse contents were manually and accurately labeled. Experiments show that our approach achieves much better performance than that from the existing state-of-art.",
keywords = "Image analysis, Image processing, Object detection, Pattern recognition",
author = "Zheshen Wang and Baoxin Li",
year = "2008",
doi = "10.1109/ICASSP.2008.4517772",
language = "English (US)",
isbn = "1424414849",
pages = "965--968",
booktitle = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",

}

TY - GEN

T1 - A two-stage approach to saliency detection in images

AU - Wang, Zheshen

AU - Li, Baoxin

PY - 2008

Y1 - 2008

N2 - Researches in psychology, perception and related fields show that there may be a two-stage process involved in human vision. In this paper, we propose an approach by following a two-stage framework for saliency detection. In the first stage, we extend an existing spectrum residual model for better locating visual pop-outs, while in the second stage we make use of coherence based propagation for further refinement of the results from the first step. For evaluation of the proposed approach, 300 images with diverse contents were manually and accurately labeled. Experiments show that our approach achieves much better performance than that from the existing state-of-art.

AB - Researches in psychology, perception and related fields show that there may be a two-stage process involved in human vision. In this paper, we propose an approach by following a two-stage framework for saliency detection. In the first stage, we extend an existing spectrum residual model for better locating visual pop-outs, while in the second stage we make use of coherence based propagation for further refinement of the results from the first step. For evaluation of the proposed approach, 300 images with diverse contents were manually and accurately labeled. Experiments show that our approach achieves much better performance than that from the existing state-of-art.

KW - Image analysis

KW - Image processing

KW - Object detection

KW - Pattern recognition

UR - http://www.scopus.com/inward/record.url?scp=51449118807&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=51449118807&partnerID=8YFLogxK

U2 - 10.1109/ICASSP.2008.4517772

DO - 10.1109/ICASSP.2008.4517772

M3 - Conference contribution

AN - SCOPUS:51449118807

SN - 1424414849

SN - 9781424414840

SP - 965

EP - 968

BT - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

ER -