Transferring Segmentation from Image to Image via Contextual Sparse Representation

摘要：

　　It is still a fundamental task to segment objects out from diverse background.To tackle this task,we propose a transferring segmentation framework,which aims to automatically segment new images when a single segmented example is given.Our segmentation approach is developed under the observation that some regions of foreground and background are often very similar but rarely share similar contextual information.To this end,we propose to construct a contextual dictionary by incorporating neighboring information as context.The segmentation task is finally accomplished in way of supervised classification via sparse representation with the constructed contextual dictionary.Experimental results on diverse natural images demonstrate that the proposed method achieves favorable results in both visual quality and accuracy.

关键词： Image Segmentation Contextual Dictionary Sparse Representation Superpixel

作者: Shuangshuang Li Yonghao He Shiming Xiang Lingfeng Wang Chunhong Pan

作者单位: NLPR,Institute of Automation,Chinese Academy of Sciences,100190,Beijing,China

会议类型: 国际会议

会议名称: Chinese Conference on Pattern Recognition, CCPR(2014年全国模式识别学术会议)

会议地点: 长沙

会议语种:英文

页码: 1-11

在线出版日期: 2014-11-01（万方平台首次上网日期，不代表论文的发表时间）