Study on Multi-Biometric Feature Fusion and Recognition Model

摘要

The single biometric identification technology has the inherent and difficult overcoming shortcomings, so multi-modal biometric fusion and identification techniques were proposed to improve the performance and accurate rate of identification system. This paper proposed a model combined with 2-Dimensional Fisher Linear Discriminant Analysis for face and iris feature fusion and recognition. First face and iris images are compressed respectively to preprocess the images, and the two corresponding original feature matrixes are obtained. Then the two original feature matrixes are integrated into one matrix, and formed a combined feature matrix. Third 2DFLD is applied to feature extraction to the combined feature matrix, so a fused feature matrix is constructed. At last, Nearest Neighbor Decision rule is applied in the process of recognition. Experiment results show the recognition rate is greatly improved.