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

1584 Scopus citations

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 publicationCVPR 2011
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Pages409-416
Number of pages8
ISBN (Print)9781457703942
DOIs
StatePublished - Aug 25 2011
Externally publishedYes

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

Cite this