基于偏最小二乘法与支持向量机的人脸识别

该文认为在人脸识别中，偏最小二乘回归方法作为一种新的降维方法，在处理小样本问题时具有明显优势，而主元分析方法作为一种传统的降维方法在选择分量时没有考虑类信息，因而有可能忽略掉重要的分类信息。支持向量机（SVM）模式识别方法具备良好的分类性能和鲁棒性。该文提出了一种基于偏最小二乘与支持向量机的人脸识别方法。利用偏最小二乘回归分析对人脸图像进行降维和特征提取，再利用支持向量机对特征向量进行分类识别。ORL人脸库的仿真结果证明偏最小二乘回归方法比主元分析方法更有效。

Face Recognition Based on Partial Least Squares and Support Vector Machine

The paper considers partial least squares (PLS) as a new dimension reduction technique for the feature vector to overcome the small sample size problem in face recognition. Principal component analysis (PCA), a conventional dimension reduction method selects the components with maximum variability, irrespective of the class information. So PCA does not necessarily extract features that are important for the discrimination of classes. Support Vector Machine (SVM) is a popular discriminant method for the very purpose of achieving high separability between the different patterns in whose classification one is interested with good classification and robust performance. This paper proposes a face recognition method based on PLS and SVM. The PLS is used to reduce the dimension and extract the feature, then the SVM is used for classification. The experimental results on ORL databases show that PLS is to be preferred over PCA when classification is the goal and dimension reduction is needed.