# An Efficient Finger Vein Recognition Method Based on Improved Lightweight MobileNet

## TL;DR

A new lightweight neural network method improves finger vein recognition accuracy and efficiency, making it suitable for real-time and embedded systems.

## Contribution

The novel LCNN framework enhances finger vein recognition with minimal computational cost and high accuracy.

## Key findings

- The proposed LCNN achieves 97.1% and 98.3% recognition accuracy on SDUMLA-HMT and Lab-Vein datasets.
- The method reduces parameter complexity and computational cost with an average inference time of 12.6 ms.
- The approach maintains high accuracy under illumination variation and resource constraints.

## Abstract

What are the main findings?
The proposed LCNN framework significantly enriches finger vein feature representation while minimizing structural complexity and computational burden without impairing recognition precision.A robust multi-stage preprocessing strategy combined with a compact network design achieves stable identification under illumination variation and resource-limited conditions.

The proposed LCNN framework significantly enriches finger vein feature representation while minimizing structural complexity and computational burden without impairing recognition precision.

A robust multi-stage preprocessing strategy combined with a compact network design achieves stable identification under illumination variation and resource-limited conditions.

What are the implications of the main findings?
The results affirm that lightweight deep architecture preserves superior accuracy while enabling efficient real-time integration within embedded biometric recognition systems.The proposed method provides useful design insights for developing efficient, scalable, and secure biometric recognition systems in future edge-intelligent applications.

The results affirm that lightweight deep architecture preserves superior accuracy while enabling efficient real-time integration within embedded biometric recognition systems.

The proposed method provides useful design insights for developing efficient, scalable, and secure biometric recognition systems in future edge-intelligent applications.

Finger vein recognition has emerged as a highly robust and intrinsically stable biometric technology, demonstrating great potential in identity authentication and intelligent security applications. However, conventional methods still suffer from constraints in feature representation and computational efficiency, particularly under challenging conditions such as illumination variation, pose deviation, and noise interference. To address these challenges, this study presents an efficient finger vein recognition approach based on a lightweight convolutional neural network (LCNN) architecture. The proposed framework integrates a multi-stage image preprocessing pipeline for automatic vein region detection, advanced denoising, and refined texture enhancement, which is subsequently followed by compact feature modeling within a lightweight deep network. Extensive experiments on the public Shandong University Machine Learning and Applications-Homologous Multi-Modal Traits (SDUMLA-HMT) dataset and a self-acquired Laboratory Finger-Vein (Lab-Vein) dataset validate the superiority of the proposed method, achieving recognition accuracies of 97.1% and 98.3%, respectively, surpassing existing benchmark models. Moreover, the model demonstrates notable reductions in parameter complexity and computational cost, achieving an average inference time of only 12.6 ms, which confirms its strong real-time capability and suitability for embedded deployment. Overall, the proposed approach attains a desirable trade-off between accuracy and efficiency, offering meaningful implications for the advancement of lightweight biometric recognition systems.