基于差别特征的神经网络人脸识别  

Neural Network Based on Difference Features in Recognition of Human Faces

作　　者：陈刚[1] 戚飞虎[1] 

机构地区：[1]上海交通大学计算机科学与工程系,上海200030

出　　处：《计算机工程》2000年第8期9-10,111,共3页Computer Engineering

基　　金：国家自然科学基金!(69772002)

摘　　要：根据视觉识别的差别特征分辨特性，该文对自联想神经网络进行了改进，提出了基于差别特征的识别方法．文中采用ＯＲＬ人脸图象库进行的对比识别实验表明，改进后的差别特征神经网络对原人脸图象和加高斯噪声的人脸图象，都较自联想神经网络识别率高，证实了差别特征的有效性．We applied the principle and difference features. based on which we presented an improved auto-association neural network. Using ORL face database. the face recognition experiment compared auto-association network and the difference features based network with Original face images and the ones added Gauss noises. It showed that foe difference features based neural network performed better than the old one and proved the efficiency of the difference features.

关 键 词：神经网络 差别特征 人脸识别 模式识别 人脸图象 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]