Residential Collegefalse
Kernel embedding transformation learning for graph matching
Yu, Yu Feng1; Chen, Long2; Huang, Ke Kun3; Zhu, Hu4; Xu, Guoxia5
Source PublicationPattern Recognition Letters

Graph matching, which aims to establish correspondences between two geometrical graphs, is a general and powerful tool for pattern recognition and computer vision. However, many factors degrade the matching accuracy. The graph structure suffering from deformation and rotation variations is a key issue in the process of matching. In this work, we propose a joint framework in the reproducing kernel Hilbert space (RKHS) for graph matching with deformation and rotation variations, which incorporates the kernelized unary alignment and local structure alignment into a joint framework. Specifically, the proposed method is able to enhance the node to node correspondence and the edge to edge correspondence and avoids the effect of deformation and rotation by maximizing the similarities between the source graph and the transformed target graph in the reproducing kernel Hilbert space. Meanwhile, an effective algorithm is presented to solve the joint framework. Comprehensive discussion, involving convergence analysis and parameter sensitive analysis, are as well proposed. Promising experimental results in the variety of graph matching tasks such as deformation and rotation are provided to evidence the superiority of the proposed method.

KeywordCorrespondence Deformation Variation Graph Matching Transformation Learning
URLView the original
Indexed BySCIE
WOS Research AreaComputer Science
WOS SubjectComputer Science, Artificial Intelligence
WOS IDWOS:000877215000009
Scopus ID2-s2.0-85139825864
Fulltext Access
Citation statistics
Cited Times [WOS]:0   [WOS Record]     [Related Records in WOS]
Document TypeJournal article
Affiliation1.Department of Statistics, Guangzhou University, Guangzhou, 510006, China
2.Department of Computer and Information Science, University of Macau, Macau, 999078, China
3.School of Mathematics, Jiaying University, Meizhou, 514015, China
4.College of Telecommunication and Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing, 210003, China
5.Department of Computer Science, Norwegian University of Science and Technology, Gjovik, 2815, Norway
Recommended Citation
GB/T 7714
Yu, Yu Feng,Chen, Long,Huang, Ke Kun,et al. Kernel embedding transformation learning for graph matching[J]. Pattern Recognition Letters,2022,163:136-144.
APA Yu, Yu Feng,Chen, Long,Huang, Ke Kun,Zhu, Hu,&Xu, Guoxia.(2022).Kernel embedding transformation learning for graph matching.Pattern Recognition Letters,163,136-144.
MLA Yu, Yu Feng,et al."Kernel embedding transformation learning for graph matching".Pattern Recognition Letters 163(2022):136-144.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Yu, Yu Feng]'s Articles
[Chen, Long]'s Articles
[Huang, Ke Kun]'s Articles
Baidu academic
Similar articles in Baidu academic
[Yu, Yu Feng]'s Articles
[Chen, Long]'s Articles
[Huang, Ke Kun]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Yu, Yu Feng]'s Articles
[Chen, Long]'s Articles
[Huang, Ke Kun]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.

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