CMOS IMPLEMENTATION OF AN ANALOGICALLY PROGRAMMABLE CELLULAR NEURAL-NETWORK

The criteria to design the basic building blocks of an analogically pr ogrammable cellular neural network (CNN) in a 1.5-mum CMOS technology are reported. The simulated electrical performances of a 10 x 10 CMOS CNN, constituted of about 8000 MOS transistors, are presented and disc ussed. Finally, it is shown that the designed CNN can be successfully used to perform such useful functions as noise removal, edge detection , hole filling, shadow detection, and connected component recognition.