中文摘要：

线性判别分析（LDA）用于人脸识别时，存在因训练样本不足引起类内散布矩阵奇异的小样本问题．基于LDA的传统零空间方法首先去掉总体散布矩阵的零空间进行降维，可以避免小样本问题．提出了一种加权零空间特征提取方法，并对加权系数进行了讨论．在人脸数据库上的实验结果验证了其有效性．

英文摘要：

Linear discriminant analysis（LDA） often encounters a small-sample-size（SSS） problem when used in face recognition because there are not enough training samples and the within scatter matrix is singular. The traditional LDA-based null space algorithm can effectively avoid the SSS problem by first removing the null space of total scatter matrix. A new feature extraction method called weighted null space was proposed, and the selection of weight parameters was discussed. Experimental results on face databases demonstrated its validity.