KAUST DepartmentVisual Computing Center (VCC)
Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
Permanent link to this recordhttp://hdl.handle.net/10754/622089
MetadataShow full item record
AbstractReliable 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.
CitationCheng M-M, Zhang G-X, Mitra NJ, Huang X, Hu S-M (2011) Global contrast based salient region detection. CVPR 2011. Available: http://dx.doi.org/10.1109/CVPR.2011.5995344.
SponsorsThis 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).