摘要
文中提出了一种基于复空间中从类平均向量中提取判别信息的K L变换的人脸识别新方法。在ORL人脸库上实验结果表明所提出的方法不仅识别性能优于经典的Eigenfaces和Fisherfaces,而且最佳识别率达到97%。
This paper presented a new face recognition method based on the KL transformation, which enables to extract discriminatory information contained in classmean vectors in the complex space. Experimental results on ORL face database show that the proposed method not only is more effective than the classical Eigenfaces and Fisherfaces, but also achieves a recognition accuracy of 97%.
出处
《计算机应用》
CSCD
北大核心
2003年第7期15-17,共3页
journal of Computer Applications
基金
国家自然科学基金资助项目 (6 0 0 72 0 3 4)
关键词
特征融合
复K-L变换
特征抽取
人脸识别
feature fusion
complex K-L transformation
feature extraction
face recognition