Title :
CNN cloning template: connected component detector
Author :
Matsumoto, T. ; Chua, L.O. ; Suzuki, H.
Author_Institution :
Dept. of Electr. Eng., Waseda Univ., Tokyo, Japan
fDate :
5/1/1990 12:00:00 AM
Abstract :
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}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
Keywords :
character recognition; neural nets; CNN; cellular neural network; cloning template; connected component detector; handwritten character recognition system; handwritten numbers; recognition rates; vector; Cellular neural networks; Character recognition; Circuits and systems; Cloning; Detectors; Handwriting recognition; Testing;
Journal_Title :
Circuits and Systems, IEEE Transactions on
