Median LDA: A Robust Feature Extraction Method for Face Recognition

In the existing LDA models, class mean vector is always estimated by the class sample average. In small sample size problems such as face recognition, however, the class sample average does not suffice to provide an accurate estimate of the class mean based on a few of given samples, particularly when there are outliers in the sample set. To overcome this weakness, we use the class median vector to estimate the class mean vector in LDA modeling. The class median vector has two advantages over the class sample average: (1) the class median (image) vector preserves useful details in the sample images and (2) the class median vector is robust to outliers that exist in training sample set. The proposed median LDA model is evaluated using three popular face image databases. All experiment results indicate that median LDA is more effective than the common LDA and PCA.