FINE-STRUCTURED OBJECT SEGMENTATION VIA LOCAL AND NONLOCAL NEIGHBORHOOD PROPAGATION
Gong, Yongchao; Xiang, Shiming; Wang, Lingfeng; Pan, Chunhong
2015-09
会议名称IEEE International Conference on Image Processing
页码4619-4623
会议日期2015-9-27 ~ 2015-9-30
会议地点Québec City, Canada
摘要In this paper, we present a novel method for the challenging task of fine-structured (FS) object segmentation. This task is formulated as a label propagation problem on an affinity graph. To enhance the completeness and connectivity of the FS objects, we introduce a novel neighborhood system combining both local and nonlocal connections, together with a robust scheme for edge weight calculation. Additionally, region cost is incorporated into the energy function to further maintain the connectivity of fine parts where the propagation is hard to reach. An appealing advantage of the proposed method is that the energy minimization has a closed-form solution and global optimum is guaranteed. Comparative experimental results on three datasets demonstrate the effectiveness of the proposed method.
关键词Fine-structured (Fs) Object Segmentation Affinity Graph Local And nonLocal Neighborhood System Region Cost Closed-form Solution
收录类别EI
语种英语
文献类型会议论文
条目标识符http://ir.ia.ac.cn/handle/173211/14489
专题模式识别国家重点实验室_先进数据分析与学习
作者单位National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences
推荐引用方式
GB/T 7714
Gong, Yongchao,Xiang, Shiming,Wang, Lingfeng,et al. FINE-STRUCTURED OBJECT SEGMENTATION VIA LOCAL AND NONLOCAL NEIGHBORHOOD PROPAGATION[C],2015:4619-4623.
条目包含的文件 下载所有文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
Fine-structured obje(2348KB)会议论文 开放获取CC BY-NC-SA浏览 下载
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Gong, Yongchao]的文章
[Xiang, Shiming]的文章
[Wang, Lingfeng]的文章
百度学术
百度学术中相似的文章
[Gong, Yongchao]的文章
[Xiang, Shiming]的文章
[Wang, Lingfeng]的文章
必应学术
必应学术中相似的文章
[Gong, Yongchao]的文章
[Xiang, Shiming]的文章
[Wang, Lingfeng]的文章
相关权益政策
暂无数据
收藏/分享
文件名: Fine-structured object segmentation via local and nonlocal neighborhood propagation.pdf
格式: Adobe PDF
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。