Format

Send to

Choose Destination
IEEE Trans Pattern Anal Mach Intell. 2011 Feb;33(2):353-67. doi: 10.1109/TPAMI.2010.70.

Learning to detect a salient object.

Author information

1
Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University, Beijing, China. liultie@cn.ibm.com

Abstract

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.

PMID:
21193811
DOI:
10.1109/TPAMI.2010.70

Supplemental Content

Full text links

Icon for IEEE Engineering in Medicine and Biology Society
Loading ...
Support Center