Multimodal recognition method based on fingerprint and finger vein

Finger vein recognition and fingerprint recognition are representative technologies for biometric identification. Due to the influence of environment and equipment, unimodal recognition has limitations in both performance and security. To this problem, this paper proposes a multimodal recognition algorithm based on fingerprint and finger vein. The method uses a two-channel convolutional neural network. The first channel uses the resNet50 network to process the preprocessed fingerprint image, and the second channel uses the resNet18 network to process the preprocessed finger vein image. Finally, the results of the two channels are fused to obtain the recognition results. Simulation results show that the proposed algorithm can effectively improve the accuracy of recognition.