文献类型：期刊文献

英文题名：Salient Object Detection via Structure Extraction and Region Contrast

作者：Zhang, Qing[1];Lin, Jiajun[2];Li, Xiaodan[1]

机构：[1]Shanghai Inst Technol, Coll Comp Sci & Informat Engn, Shanghai 201418, Peoples R China;[2]East China Univ Sci & Technol, Inst Automat, Shanghai 200237, Peoples R China

年份：2016

卷号：32

期号：6

起止页码：1435

外文期刊名：JOURNAL OF INFORMATION SCIENCE AND ENGINEERING

收录：;EI(收录号：20164402964419);WOS:【SCI-EXPANDED(收录号:WOS:000388542900002)】；

基金：This work was supported by National Science Foundation of China under Grant No. 61401281 and Science Foundation of Shanghai under Grant No. 14ZR1440700.

语种：英文

外文关键词：saliency object detection; visual attention; saliency; region of interest; structure extraction

摘要：In this paper, we propose a novel salient object detection approach, which aims in suppressing distractions caused by the small scale pattern in the background and foreground. First, we employ a structure extraction algorithm as a pre-processing step to smooth the textures, eliminate high frequency components and retain the image's main structure information. Second, we segment the texture-suppressed image into perceptually homogenous regions. Third, two saliency feature maps are computed and fused according to the color contrast and center prior cues. To better exploit each pixel's color and position information, we refine the fused saliency map. Experiments on two popular benchmark datasets demonstrate that our proposed approach achieves state-of-the-art performance compared with sixteen other state-of-the-art methods in terms of three popular evaluation measures, i.e., Precision and Recall curve, Area Under ROC Curve and F-measure value.