Global Contrast based Salient Region Detection

13 years 7 months ago

Download cg.cs.tsinghua.edu.cn

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.

Real-time Traffic

Computer Vision. | Saliency Detection |

posted by KylinCheng

Post Info
More Details (+)

Added	24 May 2011
Updated	24 May 2011
Authors	Ming-Ming Cheng
OS	Windows
Language	C

Ming-Ming Cheng, Guo-Xin Zhang, Niloy J. Mitra, Xiaolei Huang, Shi-Min Hu. Global Contrast based Salient Region Detection. IEEE CVPR, p. 409-416, Colorado Springs, Colorado, USA, June 21-23, 2011.

Comments (0)

	RepFinder: Finding Approximately Repeated Scene Elements for Image Editing 513 views
	Global Contrast based Salient Region Detection 721 views
	Global Contrast based Salient Region Detection 1079 views
	Connectedness of Random Walk Segmentation 1793 views
	Connectedness of Random Walk Segmentation 528 views

Sciweavers

Global Contrast based Salient Region Detection

Computer Vision. | Saliency Detection |

Explore & Download

Productivity Tools

Document Tools

Image Tools

Sciweavers