CNN cloning template: connected component detector
Takashi Matsumoto, Leon Ong Chua, Hirotaka Suzuki · IEEE Transactions on Circuits and Systems · 1990
An extremely simple cloning template for a cellular neural network (CNN) is presented that is capable of detecting the number of connected components of a vector in (+1, -1)/sup N/. By exploiting this capability, an architecture for a handwritten character recognition system was obtained. A preliminary test result (100 handwritten numbers, 0-9) shows 94-100% correct recognition rates.>