Multi-Scale Semantic Model for Unsupervised Object Segmentation

摘要：

　　It is difficult to segment instances of object classes accurately unsupervised in images,because of the complexity of structures,inter-class differences,background interference and so on.A multi-scale semantic model method is proposed to overcome the disadvantages existing in most of the relative methods.This method uses generative model to deal with the objects obtained by multi-scale segmentations instead of whole image,and calculates kinds of visual features to mine the topic information of every object.In the segmentation process,a semantic correlative function of every segment block based on KL divergence is built up and minimized to select the object correct regions.Experimental results demonstrate the effectiveness of the proposed method.

关键词： Image process object segmentation semantic model multi-scale LDA

作者: Yu Li Xiangjuan Li Yasen Zhang Xian Sun Hongqi Wang

作者单位: Institute of Electronics, Chinese Academy of Sciences, Beijing 100190, China;Key Laboratory of Techn Institute of Electronics, Chinese Academy of Sciences, Beijing 100190, China;Key Laboratory of Techn

会议类型: 国际会议

会议名称: 2012 2nd international Conference on Materials Science and Information Technology(2012第二届材料科学与信息技术国际会议)(MSIT2012)

会议地点: 西安

会议语种:英文

页码: 859-864

在线出版日期: 2012-08-24（万方平台首次上网日期，不代表论文的发表时间）