Object Recognition Using Multi-Layer Hopfield Neural Network

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 conventional single layer Hopfield nets in order to compute the model-object match which is most consistent across several resolution levels. The performance of the algorithm is demonstrated in cases of images containing single and multiple occluded objects. These results are compared with recognition results obtained using a single layer Hopfield network.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jan 01, 1994
Accession Number
ADA282417

Entities

People

  • Nasser M. Nasrabadi
  • Peter D. Scott
  • Susan S. Young

Organizations

  • University at Buffalo

Tags

DTIC Thesaurus Topics

  • Algorithms
  • Artificial Intelligence
  • Artificial Intelligence Computing
  • Artificial Intelligence Software
  • Computer Vision
  • Computers
  • Engineering
  • Models
  • Neural Networks
  • New York
  • Object Recognition
  • Pattern Recognition
  • Recognition
  • Rotation
  • Translations
  • Two Dimensional

Fields of Study

  • Computer science

Readers

  • Computer Networking
  • Computer Vision.
  • Neural Network Machine Learning.

Technology Areas

  • AI & ML
  • AI & ML - Neural Networks