Error-tolerant graph matching using homeomorphism

Abstract

Graph matching is the task of computing the resemblance of graphs. While in exact matching, a strict one-to-one correspondence should exist between two graphs or among their subgraphs, on the other hand in error-tolerant matching a strict correspondence is not necessary, and some similarity measure should be exhibited between two graphs or their subgraph depending on some tolerance value or noise. In this paper, we present a new approach to error-tolerant matching using graph homeomorphism to measure the structural resemblance of two graphs. © 2017 IEEE.