Deep Learning for Finger Vein Recognition: A Brief Survey of Recent Trend

TL;DR

This paper reviews recent advances in deep learning techniques applied to finger vein image recognition, highlighting key trends, challenges, and future directions in this biometric field.

Contribution

It provides a comprehensive summary of 46 recent studies on deep learning for finger vein recognition, categorizing them by neural network tasks and discussing future research directions.

Findings

Deep learning has significantly improved finger vein recognition accuracy.

Various neural network architectures have been explored for this task.

Challenges include data scarcity and variability in finger vein images.

Abstract

Finger vein image recognition technology plays an important role in biometric recognition and has been successfully applied in many fields. Because veins are buried beneath the skin tissue, finger vein image recognition has an unparalleled advantage, which is not easily disturbed by external factors. This review summarizes 46 papers about deep learning for finger vein image recognition from 2017 to 2021. These papers are summarized according to the tasks of deep neural networks. Besides, we present the challenges and potential development directions of finger vein image recognition.