融合典型相关与最大散度差的特征抽取方法

提出了一种融合典型相关分析与最大散度差鉴别分析的特征抽取新方法。该方法首先利用典型相关分析方法实现了特征信息的融合，有效地消除了特征之间的信息冗余。然后，通过采用最大散度差鉴别分析方法将训练样本中的类别信息加以充分的利用，从而有效的提高了人脸识别的正确率。最后，在ORL标准人脸库上和Yale人脸库上的实验结果验证了本文算法的有效性。

Combination of canonical correlation analysis and maximum scatter dfference discriminate analysis for feature extraction

A new method of combination of Canonical Correlation Analysis(CCA) and Maximum Scatter Difference Discriminate Analysis(MSDDA) is developed in this paper.According to the idea of CCA,it suits for information fusion;What is more,it eliminates the redundant information within the features.According to the idea of Maximum Scatter Difference Discriminate Analysis (MSDDA),the information of classes is fully utilized so the correct rate of face recognition is increased much more.Finally,extensive experiments performed on both ORL face database and YALE face database verify the effectiveness of the proposed method.