Pattern recognition by graph matching using the Potts MFT neural networks

-This paper is concerned with programming of the Potts mean field theory neural networks for pattern recognition by homomorphic mapping of the attributed relational graphs (ARG). In order to generate the homomorphic mapping from the scene relational graph to the model graph, we make use of the recently introduced [Suganthan, Technical Report, Nanyang Technical University (1994)] compatibility functions in relation to the Hopfield network. An efficient pose clustering algorithm is used to separate and localize different occurrences of any particular object model in the scene. The pose clustering algorithm also eliminates spurious hypotheses generated by the network and resolves ambiguities in the final interpretation. The performance of the proposed approach to pattern recognition by homomorphism is demonstrated using a number of line patterns, silhouette images and circle patterns. Pattern recognition Mean field theory neural networks Constrained optimization Inexact homomorphism Attributed relational graph matching Pose clustering