PATTERN-RECOGNITION BY GRAPH MATCHING USING THE POTTS MFT NEURAL NETWORKS

This paper is concerned with programming of the Potts mean field theor y neural networks for pattern recognition by homomorphic mapping of th e attributed relational graphs (ARG). In order to generate the homomor phic mapping from the scene relational graph to the model graph, we ma ke use of the recently introduced [Suganthan, Technical Report, Nanyan g Technical University (1994)] compatibility functions in relation to the Hopfield network. An efficient pose clustering algorithm is used t o separate and localize different occurrences of any particular object model in the scene. The pose clustering algorithm also eliminates spu rious 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.