Joint Transformation Learning via the L2,1-Norm Metric for Robust Graph Matching

Research output: Journal Publications and ReviewsRGC 21 - Publication in refereed journalpeer-review

16 Scopus Citations
View graph of relations

Author(s)

  • Yu-Feng Yu
  • Guoxia Xu
  • Min Jiang
  • Hu Zhu
  • Dao-Qing Dai

Related Research Unit(s)

Detail(s)

Original languageEnglish
Article number8704989
Pages (from-to)521-533
Journal / PublicationIEEE Transactions on Cybernetics
Volume51
Issue number2
Online published2 May 2019
Publication statusPublished - Feb 2021

Abstract

Establishing correspondence between two given geometrical graph structures is an important problem in computer vision and pattern recognition. In this paper, we propose a robust graph matching (RGM) model to improve the effectiveness and robustness on the matching graphs with deformations, rotations, outliers, and noise. First, we embed the joint geometric transformation into the graph matching model, which performs unary matching over graph nodes and local structure matching over graph edges simultaneously. Then, the L2,1 -norm is used as the similarity metric in the presented RGM to enhance the robustness. Finally, we derive an objective function which can be solved by an effective optimization algorithm, and theoretically prove the convergence of the proposed algorithm. Extensive experiments on various graph matching tasks, such as outliers, rotations, and deformations show that the proposed RGM model achieves competitive performance compared to the existing methods.

Research Area(s)

  • Graph matching, joint transformation, similarity metric

Citation Format(s)

Joint Transformation Learning via the L2,1-Norm Metric for Robust Graph Matching. / Yu, Yu-Feng; Xu, Guoxia; Jiang, Min et al.
In: IEEE Transactions on Cybernetics, Vol. 51, No. 2, 8704989, 02.2021, p. 521-533.

Research output: Journal Publications and ReviewsRGC 21 - Publication in refereed journalpeer-review