Global contrast based salient region detection

Cheng, Ming-Ming, Zhang, Guo-Xin, Mitra, Niloy J., Huang, Xiaolei and Hu, Shi-Min ORCID: https://orcid.org/0000-0001-7507-6542 2011. Global contrast based salient region detection. Presented at: IEEE Conference on Computer Vision and Pattern Recognition, Providence, RI, USA, 20-25 June 2011. 2011 IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2011). Los Alamitos, CA: IEEE, pp. 409-416. 10.1109/CVPR.2011.5995344

Full text not available from this repository.

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.

Item Type:	Conference or Workshop Item (Paper)
Date Type:	Publication
Status:	Published
Schools:	Computer Science & Informatics
Subjects:	Q Science > QA Mathematics > QA76 Computer software
Publisher:	IEEE
ISBN:	9781457703942
ISSN:	1063-6919
Last Modified:	25 Oct 2022 08:16
URI:	https://orca.cardiff.ac.uk/id/eprint/52110

Citation Data

Cited 1719 times in Scopus. View in Scopus. Powered By Scopus® Data

Actions (repository staff only)

Edit Item