A class of sparsely connected autoassociative morphological memories for large color images

  • Authors:
  • Marcos Eduardo Valle

  • Affiliations:
  • Department of Mathematics, State University of Londrina, Londrina, Brazil

  • Venue:
  • IEEE Transactions on Neural Networks
  • Year:
  • 2009

Quantified Score

Hi-index 0.00

Visualization

Abstract

This brief introduces a new class of sparsely connected autoassociative morphological memories (AMMs) that can be effectively used to process large multivalued patterns, which include color images as a particular case. Such as the single-valued AMMs, the multivalued models exhibit optimal absolute storage capacity and one-step convergence. The remarkable feature of the proposed models is their sparse structure. In fact, the number of synaptic junctions--and consequently the required computational resources--usually decreases considerably as more and more patterns are stored in the novel multivalued AMMs.