基于加权Fisher准则的线性鉴别分析及人脸识别

提出了一种基于加权Fisher准则线性鉴别分析的人脸识别方法。该方法引入了一种新的权函数对Fisher准则加权，以提高样本在低维线性空间中的可分性，然后探讨了高维、奇异情况下如何降低运算量的问题，并给出了一个简单高效的算法。在ORL标准人脸库上进行测试，由该算法抽取的特征在最近邻分类器和最小距离分类器下均达到96%的正确识别率，这一结果优于经典的特征脸和Fisher脸方法在该库上的识别结果。

Linear discriminant analysis based on weighted Fisher criteria and face recognition

A novel method based on weighted discriminant analysis for face recognition was proposed in this paper. First, the Fisher criterion was redefined by introducing a weighting of the contributions of individual class pairs to the overall criterion. Then, to deal with the high dimensional and singular case in face recognition problems, a simple and efficient algorithm was developed. Finally, the proposed algorithm was tested on ORL face database, and a recognition rate of 96% was achieved by using either a common nearest neighbor classifier or a minimum distance classifier. The experimental results show our method is superior to the classical Eigeafaces and Fisherfaces.