Research of 2DPCA principal component uncertainty in face recognition

This paper studied 2DPCA ( two-dimensional principal component analysis ) principal component feature vectors for face recognition, it found that different principal component had the different role, and then it studied 2DPCA principal component uncertainty, it is good to distinguish 2DPCA principal component role. Using uncertainty knowledge to calculate the weights of 2DPCA principal components, and the last weights was found by optimization of weights, the principal components were processed by using weighted in the process of recognition. ORL face images were used to test the algorithm, the results indicate that the algorithm has good recognition performance.