OPT OpenIR  > 光学影像学习与分析中心
Object Discovery via Cohesion Measurement
Guo, Guanjun1,2; Wang, Hanzi1,2; Zhao, Wan-Lei1,2; Yan, Yan1,2; Li, Xuelong3
Department光学影像学习与分析中心
2018-03-01
Source PublicationIEEE TRANSACTIONS ON CYBERNETICS
ISSN2168-2267
Volume48Issue:3Pages:862-875
Contribution Rank3
Abstract

Color and intensity are two important components in an image. Usually, groups of image pixels, which are similar in color or intensity, are an informative representation for an object. They are therefore particularly suitable for computer vision tasks, such as saliency detection and object proposal generation. However, image pixels, which share a similar real-world color, may be quite different since colors are often distorted by intensity. In this paper, we reinvestigate the affinity matrices originally used in image segmentation methods based on spectral clustering. A new affinity matrix, which is robust to color distortions, is formulated for object discovery. Moreover, a cohesion measurement (CM) for object regions is also derived based on the formulated affinity matrix. Based on the new CM, a novel object discovery method is proposed to discover objects latent in an image by utilizing the eigenvectors of the affinity matrix. Then we apply the proposed method to both saliency detection and object proposal generation. Experimental results on several evaluation benchmarks demonstrate that the proposed CM-based method has achieved promising performance for these two tasks.

KeywordCohesion Measurement (Cm) Object Proposal Generation Salient Object Detection Spectral Clustering
DOI10.1109/TCYB.2017.2661995
Indexed BySCI ; EI
Language英语
WOS IDWOS:000424826800004
EI Accession Number20170803378976
Citation statistics
Document Type期刊论文
Identifierhttp://ir.opt.ac.cn/handle/181661/30770
Collection光学影像学习与分析中心
Affiliation1.Xiamen Univ, Fujian Key Lab Sensing & Comp Smart City, Xiamen 361005, Peoples R China;
2.Xiamen Univ, Sch Informat Sci & Engn, Xiamen 361005, Peoples R China;
3.Chinese Acad Sci, Xian Inst Opt & Precis Mech, Ctr Opt Imagery Anal & Learning, State Key Lab Transient Opt & Photon, Xian 710119, Shaanxi, Peoples R China
Recommended Citation
GB/T 7714
Guo, Guanjun,Wang, Hanzi,Zhao, Wan-Lei,et al. Object Discovery via Cohesion Measurement[J]. IEEE TRANSACTIONS ON CYBERNETICS,2018,48(3):862-875.
APA Guo, Guanjun,Wang, Hanzi,Zhao, Wan-Lei,Yan, Yan,&Li, Xuelong.(2018).Object Discovery via Cohesion Measurement.IEEE TRANSACTIONS ON CYBERNETICS,48(3),862-875.
MLA Guo, Guanjun,et al."Object Discovery via Cohesion Measurement".IEEE TRANSACTIONS ON CYBERNETICS 48.3(2018):862-875.
Files in This Item:
File Name/Size DocType Version Access License
Object Discovery via(2009KB)期刊论文出版稿开放获取CC BY-NC-SAView Application Full Text
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Guo, Guanjun]'s Articles
[Wang, Hanzi]'s Articles
[Zhao, Wan-Lei]'s Articles
Baidu academic
Similar articles in Baidu academic
[Guo, Guanjun]'s Articles
[Wang, Hanzi]'s Articles
[Zhao, Wan-Lei]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Guo, Guanjun]'s Articles
[Wang, Hanzi]'s Articles
[Zhao, Wan-Lei]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Object Discovery via Cohesion Measurement.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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