OBJECT RECOGNITION BY A HOPFIELD NEURAL NETWORK

A two-dimensional (2-D) model-based object recognition technique is introduced in this paper to identify and locate isolated or overlapping 2-D objects in any position and orientation. A cooperative feature matching technique is proposed that is implemented by a Hopfield neural network. The proposed matching technique uses the parallelism of the neural network to globally match all the objects (they may be overlapping or touching) in the input scene against all the object models in the model-database at the same time. A global model graph representing all the object models is constructed where each node in the graph represents a feature that has a numerical feature value and is connected to other nodes by an arc representing the relationship or compatibility between them. Object recognition is formulated as matching this global model graph with an input scene graph representing a single object or several overlapping objects. A 2-D Hopfield binary neural network is implemented to perform a subgraph isomorphism in order to obtain the matching features between the two graphs. The synaptic interconnection weights between the neurons are designed such that matched features belonging to the same model receive excitatory supports, and matched features belonging to different models receive an inhibitory support or a mutual support depending on whether the input scene consists of an isolated object or several overlapping objects. The coordinate transformation for mapping each pair of matched nodes from the model onto the input scene is calculated, followed by a simple clustering technique to eliminate any false matches. The orientation and the position of objects in the scene are then calculated by averaging the transformation of correct matched nodes. Simulation results are shown to illustrate the performance of the system for scenes containing an isolated object or several overlapping objects. Finally the performance of the proposed technique is compared with that of a relaxation technique.