AGVBench: A Reliability-Oriented Benchmark of Data Augmentation for Vein Recognition

2026-07-02

AI Summary

Existing data augmentation methods in vein recognition often disrupt critical fine-grained structures and lack comprehensive evaluation of reliability, robustness, and security. This work proposes the first reliability-oriented augmentation evaluation framework tailored for vein recognition, introducing AGVBench—a benchmark that systematically assesses 30 augmentation strategies across five public datasets and seven backbone architectures, including CNNs, Vision Transformers (ViTs), and vein-specific models. The study reveals that multi-image mixing augmentations (e.g., MixUp, PuzzleMix), while improving accuracy, suffer from poor calibration and weak adversarial robustness; geometric transformations frequently degrade performance; and augmentation efficacy varies significantly between palmprint and finger vein modalities. To foster reproducible research, the project provides standardized evaluation protocols and open-source code.

Abstract

Vein recognition is a secure biometric technology often constrained by limited annotated data and imaging variations. While data augmentation mitigates this, strategies designed for natural images may disrupt the fine-grained topology and textures essential for identity discrimination. We present AGVBench, which evaluates 30 representative augmentation strategies on five public palm- and finger-vein datasets with seven backbone architectures, covering classic CNNs, vision transformers, and vein-specific recognition models. Our results show that multi-image mixing methods (e.g., MixUp, PuzzleMix, StarMixup) generally provide the strongest recognition performance. However, they are often poorly calibrated and vulnerable to adversarial perturbations, revealing a clear inconsistency between clean accuracy and adversarial security. We also find that severe geometric transformations frequently degrade recognition, which is potentially due to feature misalignment or spatial cropping, and that augmentation effectiveness varies across palm and finger vein datasets. These findings prove that accuracy-centric evaluation is insufficient for biometric augmentation. AGVBench provides standardized protocols to support reproducible research and guide the design of reliable, secure, and robust vein recognition systems. Our codebase is available at https://github.com/Advance-VeinTech-Innovators/AGVBench.

Problem

• vein recognition
• data augmentation
• reliability
• adversarial robustness
• biometric security

Innovation

• vein recognition
• data augmentation
• reliability benchmark
• adversarial robustness
• multi-image mixing