Saliency Region Detection via Graph Model and Statistical Learning

摘要：

　　Saliency region detection plays an important role in computer vision aiming at discovering the salient objects in an image.This paper proposes a novel saliency detection algorithm(named as GMSL)via combining graph model and statistical learning.Firstly,the algorithm generates an initial saliency map by manifold ranking and optimizes it with absorbing Markov chain,both of which are based on graph model.Then,Bayes estimation with color statistical models is utilized as statistical learning to assign the saliency values to each pixel and further purify the map.Extensive experiments comparing with several state-ofthe-art saliency detection works tested on different datasets demonstrate the superiority of the proposed algorithm.

关键词： Saliency detection Graph model Statistical learning

作者: Ling Huang Songguang Tang Jiani Hu Weihong Deng

作者单位: Beijing University of Posts and Telecommunications,Beijing,China Wuhan Research Institute of Posts and Telecommunications,Wuhan,China

会议类型: 国际会议

会议名称: 第七届全国模式识别学术会议(The 7th Chinese Conference on Pattern Recognition,CCPR2016)

会议地点: 成都

会议语种:英文

页码: 3-13

在线出版日期: 2016-11-03（万方平台首次上网日期，不代表论文的发表时间）