A unified formulation of a class of graph matching techniques
作者：
Highlights：
• We show that graph matching methods based on relaxation labeling, spectral graph theory and the tensor theory have the same mathematical form by employing power iteration technique.
• We demonstrate that differences among these methods have little impact on the final matching result according to our experiment results.
• We propose a fast framework to accelerate the matching procedure, which could greatly improve the matching performance.
摘要
•We show that graph matching methods based on relaxation labeling, spectral graph theory and the tensor theory have the same mathematical form by employing power iteration technique.•We demonstrate that differences among these methods have little impact on the final matching result according to our experiment results.•We propose a fast framework to accelerate the matching procedure, which could greatly improve the matching performance.
论文关键词：Graph matching,Relaxation labeling,Spectral graph theory,Tensor theory
论文评审过程：Received 22 September 2018, Revised 9 April 2019, Accepted 15 June 2019, Available online 20 June 2019, Version of Record 25 June 2019.
论文官网地址：https://doi.org/10.1016/j.patcog.2019.06.008
