Template design of cellular neural networks using code theory for object counting
Megumi Fukumoto, Min-Ai Oh, Mamoru Tanaka · 1992
Cellular neural networks can perform parallel signal processing in real time. They are imbued with some global properties because of the propagation effects of the local interactions during the transient regime. Using cellular neural networks for some pattern matching, it is very useful to give a simple target, such as feature-point extraction. In this paper pattern learning is done by using graph and code theories. Some simulation results are given.>