(2D)2UDP: A New Two-Directional Two-Dimensional Unsupervised Discriminant Projection for Face Recognition

Abstract

Based on manifold learning, a new feature extraction method is proposed for face recognition in the paper. The new method is called two-directional two-dimensional unsupervised discriminant projection ((2D)2UDP), which simultaneously works image matrix in the row direction and in the column direction for feature extraction. The experimental results on ORL face databases and AR face databases indicate that the proposed method has higher recognition rate and more stable.