Improved Saliency Optimization Based on Superpixel-Wised Objectness and Boundary Connectivity

摘要：

　　Salient object detection is one of the most challenging problems in computer vision and has extensive applications in many fields.Most existing algorithms detect salient object by employing various features.In this work,a bottom-up salient region measurement that integrates superpixel-wised objectness and boundary connectivity is proposed.Furthermore,to improve the result of the salient region measurement,an improved saliency optimization is put forward.Experimental results on three benchmark datasets demonstrate the effectiveness of the proposed method,which can further improve the accuracy of saliency detection than other six state-of-the-art approaches on MSRA10k,DUTOMRON and SED1.

关键词： Visual attention Salient object detection Objectness Boundary connectivity

作者: Yanzhao Wang Guohua Peng

作者单位: School of Natural and Applied Sciences,Northwestern Polytechnical University,Xian 710072,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: 218-228

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）