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
[21]   NCC Based Correspondence Problem for First- and Second-Order Graph Matching [J].
Cui, Beibei ;
Creput, Jean-Charles .
SENSORS, 2020, 20 (18) :1-26
[22]   The Palm Vein Graph Feature Extraction and Matching [J].
Arakala, Arathi ;
Hao, Hao ;
Davis, Stephen ;
Horadam, K. J. .
2015 INTERNATIONAL CONFERENCE ON INFORMATION SYSTEMS SECURITY AND PRIVACY (ICISSP), 2015, :295-303
[23]   A new graph matching method for point-set correspondence using the EM algorithm and Softassign [J].
Sanroma, Gerard ;
Alquezar, Rene ;
Serratosa, Francesc .
COMPUTER VISION AND IMAGE UNDERSTANDING, 2012, 116 (02) :292-304
[24]   Towards affine-invariant graph matching: A directed graph based method [J].
Zhu, Ming ;
Cheng, Shuo ;
Yao, Qiang ;
Tang, Jun ;
Wang, Nian .
DIGITAL SIGNAL PROCESSING, 2020, 106
[25]   GLMNet: Graph learning-matching convolutional networks for feature matching * [J].
Jiang, Bo ;
Sun, Pengfei ;
Luo, Bin .
PATTERN RECOGNITION, 2022, 121
[26]   Point correspondence by a new third order graph matching algorithm [J].
Yang, Xu ;
Qiao, Hong ;
Liu, Zhi-Yong .
PATTERN RECOGNITION, 2017, 65 :108-118
[27]   Robust Anatomical Correspondence Detection by Hierarchical Sparse Graph Matching [J].
Guo, Yanrong ;
Wu, Guorong ;
Jiang, Jianguo ;
Shen, Dinggang .
IEEE TRANSACTIONS ON MEDICAL IMAGING, 2013, 32 (02) :268-277
[28]   Contextual Correspondence Matters: Bidirectional Graph Matching for Video Summarization [J].
Zhang, Yunzuo ;
Liu, Yameng .
COMPUTER VISION - ECCV 2024, PT LXXXVII, 2025, 15145 :300-317
[29]   Random Deep Graph Matching [J].
Xie, Yu ;
Qin, Zhiguo ;
Gong, Maoguo ;
Yu, Bin ;
Liang, Jiye .
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, 2023, 35 (10) :10411-10422
[30]   Stroke correspondence based on graph matching for detecting stroke production errors in Chinese character handwriting [J].
Hu, Zhihui ;
Leung, Howard ;
Xu, Yun .
ADVANCES IN MULTIMEDIA INFORMATION PROCESSING - PCM 2007, 2007, 4810 :734-+