제어로봇시스템학회:학술대회논문집
- 제어로봇시스템학회 1992년도 한국자동제어학술회의논문집(국내학술편); KOEX, Seoul; 19-21 Oct. 1992
- /
- Pages.619-623
- /
- 1992
회전량에 불변인 제한 신경회로망을 이용한 패턴인식
Rotation-invariant pattern recognition system with constrained neural network
초록
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 networks 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 calssify 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.
키워드