A spectral-multiplicity-tolerant approach to robust graph matching
作者：
Highlights：
• We propose a spectral-multiplicity-tolerant graph matching approach.
• The spectral multiplicity is modeled in the matching error measurement.
• The exact graph matching is solved by alternative optimization.
• The inexact graph matching is solved by warping two graphs into the same size.
• Our approach achieves higher accuracy and robustness.
摘要
•We propose a spectral-multiplicity-tolerant graph matching approach.•The spectral multiplicity is modeled in the matching error measurement.•The exact graph matching is solved by alternative optimization.•The inexact graph matching is solved by warping two graphs into the same size.•Our approach achieves higher accuracy and robustness.
论文关键词：Attributed graph matching,Spectral multiplicity,Spectrum normalization,Graph warping,Shape retrieval
论文评审过程：Received 10 March 2012, Revised 25 February 2013, Accepted 5 March 2013, Available online 14 March 2013.
论文官网地址：https://doi.org/10.1016/j.patcog.2013.03.003
