Robustness Designs of a Kind of Uncoupled CNNs with Applications

Abstract

The cellular neural/nonlinear network (CNN) is a powerful tool for image and video signal processing, robotic and biological visions, and higher brain functions. This paper discusses a general method for robustness designs of a kind of uncoupled CNNs. Two theorems provide parameter inequalities for determining parameter intervals for implementing prescribed image processing functions, respectively. Examples for detecting edges and corners in gray scale images are given.