Two-Dimension PCA for Facial Expression Recognition

In this paper, the two-dimension principal component analysis (2DPCA) arithmetic is introduced and applied to the facial expression recognition system, which is based on seven basic facial expressions. We compared and analyzed two single-direction 2DPCA, two-direction 2DPCA (2D-2DPCA) and the PCA arithmetic under theoretical analysis. The experimental results on two facial expression databases show that two single-direction 2DPCA and 2D-2DPCA are better than PCA under both the person-dependent and person-independent conditions and the 2D-2DPCA arithmetic is the best