Palmprint recognition based on modified DCT features and RBF neural network
Pengfei Yu, Dan Xu · 2008
In this paper, a novel palmprint recognition approach is presented. A modified Discrete Cosine Transform based feature extraction method is used to obtain palmprint features. Furthermore, a Radial Basis Function Neural Network is employed for palmprint classification. In order to facilitate the training of Radial Basis Function Neural Network, Principal Components Analysis is applied to reduce these features to a reasonable dimension. The experiment results show that the method is effective.