Finger Vein Recognition Algorithm Based on MobileNet and ConvNeXt

Finger vein recognition is an emerging biometric technology with broad application prospects in the field of security. It has the advantages of high anti-counterfeiting, high security and ease of use. However, current finger vein recognition algorithms still have limited accuracy due to incomplete feature extraction. To solve this problem, this paper proposes a finger vein recognition algorithm based on the MobileNet and ConvNeXt network (M-Cnet). M-Cnet uses ConvNeXt to extract the overall features of the finger vein image, and uses MobileNet to extract the local detail features of the image. Finally, the overall features and local features are weighted and fused, and the recognition classification is performed on this basis. The experimental results show that M-Cnet can effectively extract finger vein features with high recognition accuracy.