CASIA OpenIR  > 模式识别国家重点实验室  > 先进数据分析与学习
Fine-structured object segmentation via neighborhood propagation
Gong, Yongchao; Xiang, Shiming; Pan, Chunhong
Source PublicationPATTERN RECOGNITION
2016-12-01
Volume60Issue:nullPages:130-144
SubtypeArticle
AbstractThis paper presents a novel method for the challenging task of fine-structured (FS) object segmentation. The task is formulated as a label propagation problem on an affinity graph. The proposed method has mainly three advantages. First, to enhance the completeness and connectivity of FS objects, we introduce a novel neighborhood system combining both local and nonlocal connections, with a robust scheme for edge weight calculation. Second, appearance models are explicitly incorporated into the energy function as a term of region cost. This helps to further preserve the connectivity of the fine parts for which the label information is hard to propagate correctly via neighboring pixels alone. Third, the resulting energy minimization problem has a closed-form solution with global optimum guaranteed, showing an advantage over the FS object segmentation methods that suffer from NP-hardness. To enrich the evaluation of FS object segmentation methods, we created a new challenging data set. It consists of 100 natural images involving diverse FS objects, with accurately hand-labeled ground truth. Extensive experimental results demonstrate that our method is effective in handling FS objects and achieves the state-of-the-art performance. (C) 2016 Elsevier Ltd. All rights reserved.
KeywordFine-structured Object Segmentation Label Propagation Affinity Graph Local And nonLocal Neighborhood Region Cost
DOI10.1016/j.patcog.2016.05.025
Indexed BySCI
Language英语
Funding OrganizationNational Natural Science Foundation of China (61331018) ; National Natural Science Foundation of China (61370039) ; National Natural Science Foundation of China (61272331)
WOS IDWOS:000383525600012
Citation statistics
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/12635
Collection模式识别国家重点实验室_先进数据分析与学习
Corresponding AuthorXiang, Shiming
AffiliationNational Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences
First Author AffilicationChinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
Corresponding Author AffilicationChinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
Recommended Citation
GB/T 7714
Gong, Yongchao,Xiang, Shiming,Pan, Chunhong. Fine-structured object segmentation via neighborhood propagation[J]. PATTERN RECOGNITION,2016,60(null):130-144.
APA Gong, Yongchao,Xiang, Shiming,&Pan, Chunhong.(2016).Fine-structured object segmentation via neighborhood propagation.PATTERN RECOGNITION,60(null),130-144.
MLA Gong, Yongchao,et al."Fine-structured object segmentation via neighborhood propagation".PATTERN RECOGNITION 60.null(2016):130-144.
Files in This Item: Download All
File Name/Size DocType Version Access License
Fine-Structured Obje(3612KB)期刊论文作者接受稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Gong, Yongchao]'s Articles
[Xiang, Shiming]'s Articles
[Pan, Chunhong]'s Articles
Baidu academic
Similar articles in Baidu academic
[Gong, Yongchao]'s Articles
[Xiang, Shiming]'s Articles
[Pan, Chunhong]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Gong, Yongchao]'s Articles
[Xiang, Shiming]'s Articles
[Pan, Chunhong]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Fine-Structured Object Segmentation via Neighborhood Propagation.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.