Enhancing Finger Vein Authentication through Deep Learning: A Comparative Study of U-Net and Sequential Models

Abstract

The use of finger veins as biometric authentication is becoming increasingly popular. However, low-quality finger vein images pose challenges, necessitating innovative approaches for accurate authentication. This research investigates the potential of deep learning techniques in addressing this issue, focusing on two prominent architectures: U-Net and the proposed Sequential Model. The study conducts a comparative analysis of the performance of these models in low-quality finger vein image authentication scenarios. U-Net, known for its image segmentation capabilities, is explored for feature extraction, while the Sequential Model, incorporating a modified VGG16 architecture, brings temporal context through LSTM layers. The research presents an in-depth evaluation of both models based on accuracy, recall, precision, and other relevant metrics. The findings shed light on the suitability of each approach for enhancing the reliability of finger vein authentication in challenging data quality contexts.