Approximate least-squares attributed graph matching via bayesian inference
Michaël Antonie van Wyk, Barend Jacobus van Wyk, T. JANSE VAN RENSBURG · SAIEE Africa Research Journal · 2005
In this paper we present a novel derivation of the polynomial time approximate Least-Squares Graph Matching (LSGM) algorithm for solving the attributed graph matching (AGM) problem. Here the algorithm is shown to follow from a Bayesian inference framework. This algorithm is robust against random differences existing between the two graphs to be matched. However, mathematical analysis of the algorithm shows that it is only suitable for solving full-graph matching problems.