Robust designs of a kind of uncoupled CNNs with nonlinear templates

The robust designs for cellular neural/nonlinear network (CNN) templates are one of the important issues for the practical applications of CNNs. This paper establishes two new theorems for robust designs of a kind of uncoupled CNNs. The theorems provide parameter inequalities to determine parameter intervals for implementing prescribed image processing functions, respectively. Three examples for detecting edges, corners or contours in images are presented to illustrate the effectiveness of the methodology.