Homomorphic graph matching of articulated objects by an integrated recognition scheme

In the last few years, several attempts have been made to the study of object recognition under affine transformation, but all these studies have concentrated on graph isomorphism. There has not been any discussion of solving the graph homomorphism problem under affine transformation to date. Therefore, in this paper, an integrated approach, which combines the advantages of both the genetic algorithm and Hopfield neural network, is proposed for solving object recognition under this condition. The genetic algorithm is first used, to find the near-optimal solution including all the poses of the model in the scene. Then the Hopfield network is implemented and repeated to find each pose of the model. This method can solve occluded object recognition problems, and it can also obtain the homomorphic mapping indicating multiple occurrences of a model in the scene. The system is used to recognize articulated objects, and we do not need to know in advance that there is one in the scene. Kinematic properties like the position of the joint, relative displacement can be found for the articulated object. Through experiments, we can demonstrate that the proposed method is robust.