Global contrast based salient region detection

Ming Ming Cheng, Guo Xin Zhang, Niloy J. Mitra, Xiaolei Huang, Shi Min Hu

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

1471 Citations (Scopus)

Abstract

Reliable estimation of visual saliency allows appropriate processing of images without prior knowledge of their contents, and thus remains an important step in many computer vision tasks including image segmentation, object recognition, and adaptive compression. We propose a regional contrast based saliency extraction algorithm, which simultaneously evaluates global contrast differences and spatial coherence. The proposed algorithm is simple, efficient, and yields full resolution saliency maps. Our algorithm consistently outperformed existing saliency detection methods, yielding higher precision and better recall rates, when evaluated using one of the largest publicly available data sets. We also demonstrate how the extracted saliency map can be used to create high quality segmentation masks for subsequent image processing.

Original languageEnglish (US)
Title of host publication2011 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2011
PublisherIEEE Computer Society
Pages409-416
Number of pages8
ISBN (Print)9781457703942
DOIs
StatePublished - Jan 1 2011

Publication series

NameProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
ISSN (Print)1063-6919

Fingerprint

Object recognition
Image segmentation
Computer vision
Masks
Image processing
Processing

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Vision and Pattern Recognition

Cite this

Cheng, M. M., Zhang, G. X., Mitra, N. J., Huang, X., & Hu, S. M. (2011). Global contrast based salient region detection. In 2011 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2011 (pp. 409-416). [5995344] (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition). IEEE Computer Society. https://doi.org/10.1109/CVPR.2011.5995344
Cheng, Ming Ming ; Zhang, Guo Xin ; Mitra, Niloy J. ; Huang, Xiaolei ; Hu, Shi Min. / Global contrast based salient region detection. 2011 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2011. IEEE Computer Society, 2011. pp. 409-416 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition).
@inproceedings{878f4ef5fd274e93b8b3f9f46b1c3872,
title = "Global contrast based salient region detection",
abstract = "Reliable estimation of visual saliency allows appropriate processing of images without prior knowledge of their contents, and thus remains an important step in many computer vision tasks including image segmentation, object recognition, and adaptive compression. We propose a regional contrast based saliency extraction algorithm, which simultaneously evaluates global contrast differences and spatial coherence. The proposed algorithm is simple, efficient, and yields full resolution saliency maps. Our algorithm consistently outperformed existing saliency detection methods, yielding higher precision and better recall rates, when evaluated using one of the largest publicly available data sets. We also demonstrate how the extracted saliency map can be used to create high quality segmentation masks for subsequent image processing.",
author = "Cheng, {Ming Ming} and Zhang, {Guo Xin} and Mitra, {Niloy J.} and Xiaolei Huang and Hu, {Shi Min}",
year = "2011",
month = "1",
day = "1",
doi = "10.1109/CVPR.2011.5995344",
language = "English (US)",
isbn = "9781457703942",
series = "Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition",
publisher = "IEEE Computer Society",
pages = "409--416",
booktitle = "2011 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2011",
address = "United States",

}

Cheng, MM, Zhang, GX, Mitra, NJ, Huang, X & Hu, SM 2011, Global contrast based salient region detection. in 2011 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2011., 5995344, Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, IEEE Computer Society, pp. 409-416. https://doi.org/10.1109/CVPR.2011.5995344

Global contrast based salient region detection. / Cheng, Ming Ming; Zhang, Guo Xin; Mitra, Niloy J.; Huang, Xiaolei; Hu, Shi Min.

2011 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2011. IEEE Computer Society, 2011. p. 409-416 5995344 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition).

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

TY - GEN

T1 - Global contrast based salient region detection

AU - Cheng, Ming Ming

AU - Zhang, Guo Xin

AU - Mitra, Niloy J.

AU - Huang, Xiaolei

AU - Hu, Shi Min

PY - 2011/1/1

Y1 - 2011/1/1

N2 - Reliable estimation of visual saliency allows appropriate processing of images without prior knowledge of their contents, and thus remains an important step in many computer vision tasks including image segmentation, object recognition, and adaptive compression. We propose a regional contrast based saliency extraction algorithm, which simultaneously evaluates global contrast differences and spatial coherence. The proposed algorithm is simple, efficient, and yields full resolution saliency maps. Our algorithm consistently outperformed existing saliency detection methods, yielding higher precision and better recall rates, when evaluated using one of the largest publicly available data sets. We also demonstrate how the extracted saliency map can be used to create high quality segmentation masks for subsequent image processing.

AB - Reliable estimation of visual saliency allows appropriate processing of images without prior knowledge of their contents, and thus remains an important step in many computer vision tasks including image segmentation, object recognition, and adaptive compression. We propose a regional contrast based saliency extraction algorithm, which simultaneously evaluates global contrast differences and spatial coherence. The proposed algorithm is simple, efficient, and yields full resolution saliency maps. Our algorithm consistently outperformed existing saliency detection methods, yielding higher precision and better recall rates, when evaluated using one of the largest publicly available data sets. We also demonstrate how the extracted saliency map can be used to create high quality segmentation masks for subsequent image processing.

UR - http://www.scopus.com/inward/record.url?scp=80052948224&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80052948224&partnerID=8YFLogxK

U2 - 10.1109/CVPR.2011.5995344

DO - 10.1109/CVPR.2011.5995344

M3 - Conference contribution

AN - SCOPUS:80052948224

SN - 9781457703942

T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

SP - 409

EP - 416

BT - 2011 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2011

PB - IEEE Computer Society

ER -

Cheng MM, Zhang GX, Mitra NJ, Huang X, Hu SM. Global contrast based salient region detection. In 2011 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2011. IEEE Computer Society. 2011. p. 409-416. 5995344. (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition). https://doi.org/10.1109/CVPR.2011.5995344