Abstract

A discrete time version of Cellular–Neural Network (DCNN) is a paradigm of neural networks that has the realistic perspective to be implemented in VLSI. An investigation of DCNN capabilities for image processing is attempted. It is done through detailed study of two typical concrete problems: 1) associative storing, retrieving and restoring written literals, 2) image differentiation and integration (constructing contours, isolines, shadows). A general theoretical background is given in brief, and computer simulations results are presented.

File
Issue
Pages
15-21