Palmprint recognition based on 2-dimension PCA

PCA (principal component analysis) is a successful feature detection method for pattern recognition. It is the optimal dimension compression technique based on second-order information, in the sense of mean-square error. It deals with image vector whose dimension is usually high. 2DPCA is a novel PCA method for image matrix, and it can calculate the covariance matrix more precise. In this paper we combined the new 2DPCA method and PCA to palmprint recognition, and first we apply 2DPCA to the image matrix and we make an improvement in the selection of principal components. We select the principal component that is better for classification. Then we apply 1DPCA to the projected vectors for dimension reduction. At last we apply the method to PoIyU Palmprint Database. The experiment result shows that our method got more recognition rate with lower dimensions.