Abstract: To overcome the drawbacks of the existing discriminant locality preserving projections algorithm for feature extraction,a discriminant local median preserving projections algorithm is proposed for face recognition.The algorithm obtains the optimal projection matrix by maximizing the between-class distances and minimizing the within-class distances simultaneously.It makes use of class medians to calculate the between-class distances to preserve the useful details in the images.Besides,it designs a different similarity weighting mechanism to be apt to preserve neighborhood structure of intra-class samples with little noise such that the robustness of recognition performance is further improved.Experiments on the ORL,Yale and AR face databases validate the effectiveness of the proposed algorithm.