Product graph-based higher order contextual similarities for inexact subgraph matching

作者：

Highlights：

• Contextual Similarities are proposed using Tensor Product Graph for graph matching.

• CS are obtained by diffusing the pairwise ones in the context of entire graph.

• Graph matching is formulated as a function of CS & solved with a linear programming.

• Well defined constraints are used to guide the node and edge selection procedure.

摘要

•Contextual Similarities are proposed using Tensor Product Graph for graph matching.•CS are obtained by diffusing the pairwise ones in the context of entire graph.•Graph matching is formulated as a function of CS & solved with a linear programming.•Well defined constraints are used to guide the node and edge selection procedure.

论文关键词：Subgraph matching,Product graph,Random walks,Backtrackless walks,Contextual similarities,Graphic recognition

论文评审过程：Received 31 March 2017, Revised 28 August 2017, Accepted 5 December 2017, Available online 7 December 2017, Version of Record 21 December 2017.

论文官网地址：https://doi.org/10.1016/j.patcog.2017.12.003