Fast Salient Object Detection Based on Segments

摘要：

In this paper we propose a novel salient object de tection algorithm based on segments, named SODS (Salient Object Detection based on Segments). We first segment an input image, and then extract a sat of features including multi-scale contrast,center-surround histogram, and color spatial distribution based on segments to describe a salient object locally, regionally, and globally. These three features are then combined linearly to get a saliency map to rep resent the salient object. We validate our approach on two public datasets. Experimental results prove that our method is much faster, more robust and accurate than ex isting salient object detection methods.

关键词： Salient object detection Visual attention Segment

作者: Liansheng ZHUANG Ketan TANG Nenghai YU Yangchun QIAN

作者单位: MOE-MS Key Laboratory of Multimedia Computing and Communication,University of Science and Technology of China,Hefei,230027,P.R.China

会议类型: 国际会议

会议名称: 2009 International Conference on Measuring Technology and Mechatronics Automation(ICMTMA 2009)(2009年检测技术与机械自动化国际会议)

会议地点: 长沙

会议语种:英文

页码: 469-472

在线出版日期: 2009-04-11（万方平台首次上网日期，不代表论文的发表时间）