For Full-Text PDF, please login, if you are a member of IEICE,|
or go to Pay Per View on menu list, if you are a nonmember of IEICE.
Co-saliency Detection Linearly Combining Single-View Saliency and Foreground Correspondence
Huiyun JING Xin HE Qi HAN Xiamu NIU
IEICE TRANSACTIONS on Information and Systems
Publication Date: 2015/04/01
Online ISSN: 1745-1361
Type of Manuscript: LETTER
Category: Image Recognition, Computer Vision
saliency detection, co-saliency, foreground-correspondence,
Full Text: PDF(4.1MB)>>
The research of detecting co-saliency over multiple images is just beginning. The existing methods multiply the saliency on single image by the correspondence over multiple images to estimate co-saliency. They have difficulty in highlighting the co-salient object that is not salient on single image. It is caused by two problems. (1) The correspondence computation lacks precision. (2) The co-saliency multiplication formulation does not fully consider the effect of correspondence for co-saliency. In this paper, we propose a novel co-saliency detection scheme linearly combining foreground correspondence and single-view saliency. The progressive graph matching based foreground correspondence method is proposed to improve the precision of correspondence computation. Then the foreground correspondence is linearly combined with single-view saliency to compute co-saliency. According to the linear combination formulation, high correspondence could bring about high co-saliency, even when single-view saliency is low. Experiments show that our method outperforms previous state-of-the-art co-saliency methods.