SELF-ORGANIZING HOPFIELD NETWORK FOR ATTRIBUTED RELATIONAL GRAPH MATCHING

Although the analogue Hopfield model has been shown to be a plausible approach for solving combinatorial optimization problems such as the t ravelling salesman problem (TSP), it has not been effective in solving the object recognition problem by attributed relational graph matchin g, for many reasons. However, we1 recently enhanced the performance of the Hopfield network in attributed relational graph (ARG) matching by employing suitable energy and compatibility functions, a biased netwo rk initialization scheme and a hypothesis interpretation scheme using an efficient pose clustering algorithm. However, to generate the desir ed mapping, there is a need to fine tune many parameters that are high ly dependent upon the model and scene under consideration. In this pap er, a self-organizing Hopfield network is introduced that learns most of the network parameters and eliminates the need for specifying them a priori. To adaptively estimate the energy function parameter, a Liap unov indirect method based learning approach is employed. Other variab les, such as the temperature parameter and the convergence criterion, are heuristically determined. The proposed self-organizing network is applied to solve problems such as line patterns, silhouette images and circle pattern recognition. Its superior performance over the fixed w eight model is also demonstrated.