Laplacian bidirectional PCA for face recognition

Two-dimensional principal components analysis (2DPCA) needs more coefficients than principal components analysis (PCA) for image representation and hence needs more time for classification. The bidirectional PCA (BDPCA) is proposed to overcome these drawbacks of 2DPCA. Both 2DPCA and BDPCA, however, can work only in Euclidean space. In this paper, we propose Laplacian BDPCA (LBDPCA) to enhance the robustness of BDPCA by extending it to non-Euclidean space. Experimental results on representative face databases show that LBDPCA works well and it surpasses BDPCA.