摘要
该文提出了一种主元分析和BP神经网络相结合的人脸识别方法。其中主元分析方法用于提取人脸图像的特征,而BP神经网络用于对提取的人脸特征进行识别。实验结果表明,在进行人脸识别时,该文提出的主元分析和BP神经网络相结合的方法同传统的主元分析方法相比取得了良好的效果。此方法具有较高的识别率、较强的自适应性以及对噪声的鲁棒性。
An approach that combines principal component analysis (PCA) with BP neural network is proposed and applied to human face recognition in this paper. PCA is employed to extract face features, and BP neural network is used to classify the extracted features. Experimental results show that the proposed approach performs better than conventional PCA. The proposed approach has higher recognition rate, stronger adaptability and better robustness to noise.
出处
《杭州电子科技大学学报(自然科学版)》
2005年第6期67-70,共4页
Journal of Hangzhou Dianzi University:Natural Sciences
关键词
人脸识别
神经网络
主元分析
模式识别
face recognition
neural networks
principal component analysis
pattern recognition