摘要
提出了用ＢＰ神经网络对人脸图像进行特征提取和识别的方法，讨论了ＢＰ网络结构的设计， 输入、输出层的设计，隐层结点数的选取等问题．对由１０人，每人３幅图像组成的人脸图像数据库做 识别实验，结果表明， ＢＰ具有很强的自适应性，对有噪声、残缺和戴眼镜的图像识别效果较好．
In this paper, BP neural network is used to extract and recognize the features of human face images. The design of BP network structure and input and output layer, as Well as the problem of determining the number of hidden layer's neural nodes are discussed. Experiments have been conducted for a human face image database of 10 persons with 3 images per person. The recognition results show that BP has robust adaptability and can correctly identify face images with noise, deformity and wearing glasses.
出处
《沈阳工业大学学报》
CAS
2000年第4期346-348,共3页
Journal of Shenyang University of Technology
