Sciweavers

Share
CVPR
2011
IEEE

Global Contrast based Salient Region Detection

8 years 27 days ago
Global Contrast based Salient Region Detection
Reliable estimation of visual saliency allows appropriate processing of images without prior knowledge of their content, 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.
Ming-Ming Cheng, Guo-Xin Zhang, Niloy J. Mitra, Xi
AttachmentsSize
ImgSaliency.zip21.19 KB
Added 24 May 2011
Updated 24 May 2011
Type Conference
Year 2011
Where CVPR
Authors Ming-Ming Cheng, Guo-Xin Zhang, Niloy J. Mitra, Xiaolei Huang, Shi-Min Hu
Attachments 1 file(s)
Comments (0)
books