Associative network applications to low-level machine vision

Abstract

This paper explores the application of a parallel computational model, the associative network, to problems in low-level machine vision. A formal description of the associative network model is presented. Then associative networks are designed for performing Boolean functions, edge detection, and the Hough transform. Associative networks feature very flexible processor interconnections. The flexible processor interconnections allow for parallelism in the algorithm design beyond what is feasible in other parallel computational models. This work demonstrates that image processing transformations, often too slow to be practical on a sequential machine, can be executed rapidly with associative networks.