摘要
提出利用主元分析 (PCA)和学习矢量量化神经网络 (LVQ)相结合的方法进行人脸识别。在ORL人脸库上的实验证明 ,这种方法的识别效率高 ,对表情和姿态的变化具有一定的鲁棒性 。
This paper proposes a face recognition method based on PCA and LVQ neural networks. PCA is applied to get the eigen vector of the images, then these eigen values are used as the input of the Learning Vector Quantization Networks, and the output of LVQ networks are the result of classification. The experiments on Cambridge ORL database show that this method is more powerful and efficient than the classical Fisherfaces and eigenfaces methods.
出处
《舰船电子工程》
2004年第6期99-102,共4页
Ship Electronic Engineering
基金
湖北省自然科学基金资助项目 (编号 :2 0 0 4ABA0 6 8)
