22 March 2012 Hypergraph-based saliency map generation with potential region-of-interest approximation and validation
Author Affiliations +
Abstract
A novel saliency model is proposed in this paper to automatically process images in the similar way as the human visual system which focuses on conspicuous regions that catch human beings' attention. The model combines a hypergraph representation and a partitioning process with potential region-of-interest (p-ROI) approximation and validation. Experimental results demonstrate that the proposed method shows considerable improvement in the performance of saliency map generation.
© 2012 SPIE and IS&T
Zhen Liang, Zhen Liang, Hong Fu, Hong Fu, Zheru Chi, Zheru Chi, Dagan Feng, Dagan Feng, } "Hypergraph-based saliency map generation with potential region-of-interest approximation and validation," Journal of Electronic Imaging 21(1), 013012 (22 March 2012). https://doi.org/10.1117/1.JEI.21.1.013012 . Submission:
JOURNAL ARTICLE
5 PAGES


SHARE
RELATED CONTENT


Back to Top