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.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">></ETX>
Discussion(0)
No comments yet. Be the first to comment.