Robust Designs for Shadow Projection CNN
Weidong Li, Lequan Min · 2008
The cellular neural/nonlinear network (CNN) has become a useful tool for image and signal processing, biological visions, and higher brain functions. Based on our previous research, this paper gives local rules, and set up a series theorems of robust designs for shadow projection CNN in processing binary images, which provide parameter inequalities to determine parameter intervals for implementing the prescribed image processing function. Some numerical simulation examples are given.