Abstract: Linear Discriminant Analysis（LDA） is a linear feature extracting method using Fisher’s criterion in face recognition.
The main challenge of LDA is that its transformation matrix can not be computed directly；consequently，the discriminant
vectors become very complicated，for the cases when the number of training samples is less than the dimensionality of the
feature space.In this paper，a new LDA method is proposed using a modified Fisher’s criterion.Experiments are conducted using ORL face database to present the superior performance of the proposed method，particularly for the cases when the number
of training samples is small.

摘要： 线性特征提取在人脸识别中的应用非常广泛，LDA是其主要方法之一，它基于Fisher 判别准则，然而，当人脸训练样本数小于人脸样本向量的维数时，变换矩阵将无法直接得到，因此线性判别分析过程失效。采用了一种改进的基于Fisher 准则的LDA方法，针对小样本问题提出了一种有效地解决类内散布矩阵奇异的方法，而且用ORL人脸数据进行了实验验证。实验证明该方法在正确识别率方面表现突出。