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

1772 Scopus citations


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 publicationCVPR 2011
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Number of pages8
ISBN (Print)9781457703942
StatePublished - Aug 25 2011
Externally publishedYes

Bibliographical note

KAUST Repository Item: Exported on 2020-10-01
Acknowledgements: This research was supported by the 973 Program (2011CB302205), the 863 Program (2009AA01Z327), the Key Project of S&T (2011ZX01042-001-002), and NSFC (U0735001). Ming-Ming Cheng was funded by Google PhD fellowship, IBM PhD fellowship, and New PhD Researcher Award (Ministry of Edu., CN).


Dive into the research topics of 'Global contrast based salient region detection'. Together they form a unique fingerprint.

Cite this