고유얼굴과 퍼지 신경망을 이용한 얼굴인식 기법

Abstract

In this paper, we propose a face recognition method using eigenfaces and fuzzy neural networks. In the proposed method, fuzzy membership degrees are assigned to 50 eigenface weights. These membership degrees are then inputed to a neural network to be trained. After training, the output value of the neural network is interpreted as the degree of face's closeness to other faces in the training database. Experimental results show that the proposed method can recognize faces more accurately than using other pattern classification methods.