회전량에 불변인 제한 신경회로망을 이용한 패턴 인식

Abstract

In pattern recognition, the conventional neural networks contain a large number of weights and require considerable training times and preprocessor to classify a transformed patterns. In this paper, we propose a constrained pattern recognition method which is insensitive to rotation of input pattern by various degrees and does not need any preprocessing. Because these neural network can not be trained by the conventional training algorithm such as error back propagation, a novel training algorithm is suggested. As such a system is useful in problem related to classify overse side and reverse side of 500 won coin. As an illustrative example, identification problem of overse and reverse side of 500 won coin is shown.