Issue No. 02 - February (2011 vol. 33)
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/TPAMI.2010.70
Nanning Zheng , Xi'an Jiaotong Uinversity, Xi'an
Xiaoou Tang , Chinese University of Hong Kong, Hong Kong
Heung-Yeung Shum , Microsoft, Redmond
Jingdong Wang , Microsoft Research Aisa, Beijing
Tie Liu , Xi'an Jiaotong University, Xi'an and IBM Research-China, Beijing
Jian Sun , Microsoft Research Asia, Beijing
Zejian Yuan , Xi'an Jiaotong Uinversity, Xi'an
In this paper, we study the salient object detection problem for images. We formulate this problem as a binary labeling task where we separate the salient object from the background. We propose a set of novel features, including multiscale contrast, center-surround histogram, and color spatial distribution, to describe a salient object locally, regionally, and globally. A conditional random field is learned to effectively combine these features for salient object detection. Further, we extend the proposed approach to detect a salient object from sequential images by introducing the dynamic salient features. We collected a large image database containing tens of thousands of carefully labeled images by multiple users and a video segment database, and conducted a set of experiments over them to demonstrate the effectiveness of the proposed approach.
Salient object detection, conditional random field, visual attention, saliency map.
Nanning Zheng, Xiaoou Tang, Heung-Yeung Shum, Jingdong Wang, Tie Liu, Jian Sun, Zejian Yuan, "Learning to Detect a Salient Object", IEEE Transactions on Pattern Analysis & Machine Intelligence, vol. 33, no. , pp. 353-367, February 2011, doi:10.1109/TPAMI.2010.70