Robust Finger Vein Recognition Based on Deep CNN with Spatial Attention and Bias Field Correction

As one of the biometric information based authentication technologies, finger vein recognition has received increasing attention due to its safety and convenience. However, it is still a challenging task to design an efficient and robust finger vein recognition system because of the low quality of the finger vein images and lack of sufficient number of training samples with annotated information. In this paper, we propose a novel CNN-based finger vein recognition approach with bias field correction and spatial attention mechanism. The bias field correction is to remove the unbalanced bias field of the original images by using a two-dimensional polynomial fitting algorithm, and the spatial attention module is to extract robust vein patterns from the input finger vein image through paying more attention to the informative contents of the input with a U-Net. Moreover, several measures, including the data augmentation, a multistage transfer learning strategy, and a label smoothing scheme, are exploited to improve the performance of the proposed method. Extensive experiments have been conducted in the work on two public databases, and the results show that the proposed approach outperforms the existing state-of-the-art methods.