Face Recognition via Optimal Mean Robust Linear Discriminant Analysis

In this paper, we propose a novel linear discriminant analysis (RLDA) method to realize the face recognition problem. The optimal mean removing operator is used to remove the optimal mean of the loss function automatically. In addition, the joint l2,1 -norm minimization on regularization and error measurement is introduced in the loss function. The experimental results on the stand face datasets with different ratio corruption validate the superiority of our method.