Learning Graph Matching with a Graph-Based Perceptron in a Classification Context

Romain Raveaux (1) , Maxime Martineau (1) , Donatello Conte (1) , Gilles Venturini (1)

1 LIFAT - Laboratoire d'Informatique Fondamentale et Appliquée de Tours

Many tasks in computer vision and pattern recognition are formulated as graph matching problems. Despite the NP-hard nature of the problem, fast and accurate approximations have led to significant progress in a wide range of applications. Learning graph matching functions from observed data, however, still remains a challenging issue. This paper presents an effective scheme to parametrize a graph model for object matching in a classification context. For this, we propose a representation based on a parametrized model graph, and optimize it to increase a classification rate. Experimental evaluations on real datasets demonstrate the effectiveness (in terms of accuracy and speed) of our approach against graph classification with hand-crafted cost functions.

Mots clés: Learning graph matching; graph classification; graph edit distance

Domaines: Vision par ordinateur et reconnaissance de formes [cs.CV]; Traitement des images [eess.IV]; Traitement du signal et de l'image [eess.SP]

Romain Raveaux, Maxime Martineau, Donatello Conte, Gilles Venturini. Learning Graph Matching with a Graph-Based Perceptron in a Classification Context. International Workshop on Graph-Based Representations in Pattern Recognition GbRPR 2017, May 2017, Anacapri, Italy. ⟨hal-01576056⟩