Accession Number : ADA282418

Title :   Object Recognition Using Multi-Layer Hopfield Neural Network.

Corporate Author : STATE UNIV OF NEW YORK AT BUFFALO DEPT OF ELECTRICAL AND COMPUTER ENGINEERING

Personal Author(s) : Young, Susan S. ; Scott, Peter D. ; Nasrabadi, Nasser M.

Report Date : 1992

Pagination or Media Count : 31

Abstract : An object recognition approach based on concurrent coarse-and-fine matching using a multi-layer Hopfield neural network is presented. The proposed network consists of several cascaded single layer Hopfield networks, each encoding object features at a distinct resolution, with bidirectional interconnections linking adjacent layers. The interconnection weights between nodes associating adjacent layers are structured to favor node pairs for which model translation and rotation, when viewed at the two corresponding resolutions, are consistent. This inter-layer feedback feature of the algorithm reinforces the usual intra-layer matching process in the conventional single layer Hopfield network in order to compute the most consistent model-object match across several resolution levels. The performance of the algorithm is demonstrated for test images containing single objects, and multiple occluded objects. These results are compared with recognition results obtained using a single layer Hopfield network.

Descriptors :   *PATTERN RECOGNITION, *NEURAL NETS, IMAGE PROCESSING, RESOLUTION, NODES, ALGORITHMS.

Subject Categories : Cybernetics
      Statistics and Probability

Distribution Statement : APPROVED FOR PUBLIC RELEASE