Feature Fusion of Palmprint and Face Based on KFDA

Feature fusion of palmprint and face based on Kernel Fisher discriminant analysis (KFDA) was proposed in the paper. The essence of KFDA is Kernel Principal Component Analysis (KPCA) plus Linear Discriminant Analysis (LDA). Thus we first obtained the KPCA fusion features, and then calculated the final fusion features by LDA. The discriminant vectors existing in null space and range space of within-class scatter matrix were calculated respectively by dual space analysis. The experiment results showed that multimodality outperformed than the unimodality in both identification and authentication aspect.