A Continuation Method for Graph Matching Based Feature Correspondence

被引:16
作者
Yang, Xu [1 ]
Liu, Zhi-Yong [1 ,2 ,3 ]
Qiao, Hong [1 ,2 ,3 ]
机构
[1] Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China
[2] Chinese Acad Sci, Ctr Excellence Brain Sci & Intelligence Technol, Shanghai 200031, Peoples R China
[3] Univ Chinese Acad Sci, Beijing 100049, Peoples R China
关键词
Feature correspondence; graph matching; continuous method; continuation method; combinatorial optimization; OPTIMIZATION;
D O I
10.1109/TPAMI.2019.2903483
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Feature correspondence lays the foundation for many computer vision and image processing tasks, which can be well formulated and solved by graph matching. Because of the high complexity, approximate methods are necessary for graph matching, and the continuous relaxation provides an efficient approximate scheme. But there are still many problems to be settled, such as the highly nonconvex objective function, the ignorance of the combinatorial nature of graph matching in the optimization process, and few attention to the outlier problem. Focusing on these problems, this paper introduces a continuation method directly targeting at the combinatorial optimization problem associated with graph matching. Specifically, first a regularization function incorporating the original objective function and the discrete constraints is proposed. Then a continuation method based on Gaussian smoothing is applied to it, in which the closed forms of relevant functions with respect to the outlier distribution are deduced. Experiments on both synthetic data and real world images validate the effectiveness of the proposed method.
引用
收藏
页码:1809 / 1822
页数:14
相关论文
共 50 条
[41]   A New Graph-based Flooding Matching Method for Ontology Integration [J].
Hai Bang Truong ;
Ngoc Thanh Nguyen ;
Quoc Uy Nguyen ;
Trong Hai Duong .
2013 IEEE INTERNATIONAL CONFERENCE ON CYBERNETICS (CYBCONF), 2013,
[42]   ROML: A Robust Feature Correspondence Approach for Matching Objects in A Set of Images [J].
Jia, Kui ;
Chan, Tsung-Han ;
Zeng, Zinan ;
Gao, Shenghua ;
Wang, Gang ;
Zhang, Tianzhu ;
Ma, Yi .
INTERNATIONAL JOURNAL OF COMPUTER VISION, 2016, 117 (02) :173-197
[43]   ROML: A Robust Feature Correspondence Approach for Matching Objects in A Set of Images [J].
Kui Jia ;
Tsung-Han Chan ;
Zinan Zeng ;
Shenghua Gao ;
Gang Wang ;
Tianzhu Zhang ;
Yi Ma .
International Journal of Computer Vision, 2016, 117 :173-197
[44]   Feature matching method with multigeometric constraints [J].
Xu, Dong ;
Huang, Qian ;
Liu, Wenyong ;
Bessaih, Hadjar ;
Li, Chidong .
JOURNAL OF ELECTRONIC IMAGING, 2016, 25 (06)
[45]   A RKHS interpolator-based graph matching algorithm [J].
van Wyk, MA ;
Durrani, TS ;
van Wyk, BJ .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2002, 24 (07) :988-995
[46]   Robust Underwater Image Stitching Based on Graph Matching [J].
Yang, Xu ;
Liu, Zhi-Yong ;
Li, Chuan ;
Wang, Jing-Jing ;
Qiao, Hong .
INTELLIGENCE SCIENCE AND BIG DATA ENGINEERING, ISCIDE 2017, 2017, 10559 :521-529
[47]   A graph matching algorithm with brightness order local feature description [J].
Bao, Wenxia ;
Hu, Gensheng ;
Liang, Dong ;
Zhang, Yan .
Harbin Gongcheng Daxue Xuebao/Journal of Harbin Engineering University, 2015, 36 (03) :399-403
[48]   Two-stage graph matching point cloud registration method based on graph attention network [J].
Guo, Jiacheng ;
Liu, Xuejun ;
Zhang, Shuo ;
Yan, Yong ;
Sha, Yun ;
Jiang, Yinan .
JOURNAL OF APPLIED REMOTE SENSING, 2024, 18 (03)
[49]   An Accurate Matching Query Method of Natural Language Knowledge Graph Based on Hierarchical Graph Topological Sequence [J].
Zou, Qifeng ;
Lu, Chaoze .
IEEE ACCESS, 2022, 10 :24080-24094
[50]   Learning Graph Matching [J].
Caetano, Tiberio S. ;
McAuley, Julian J. ;
Cheng, Li ;
Le, Quoc V. ;
Smola, Alex J. .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2009, 31 (06) :1048-1058