发表机构
School of Cyber Science and Engineering, Southeast University; Engineering Research Center of Blockchain Application, Supervision and Management (Southeast University), Ministry of Education; Purple Mountain Laboratories; School of Computer Science and Engineering, Nanyang Technological University; Lee Kong Chian School of Medicine, Nanyang Technological University; Faculty of Engineering, Shenzhen MSU-BIT University; VinUniversity; Institute of Automation, Chinese Academy of Sciences（东南大学网络空间科学与工程学院; 教育部区块链应用与监管管理工程研究中心（东南大学）; 紫金山实验室; 南洋理工大学计算机科学与工程学院; 南洋理工大学李光前医学院; 深圳北理莫斯科大学工程学院; VinUniversity; 中国科学院自动化研究所）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对指静脉识别缺乏大规模公开数据集的问题，提出FVeinSyn框架，通过解耦血管拓扑与成像外观合成生成50万张指静脉图像，训练的模型在8个公开数据集上平均准确率提升27.43%。
AI 中文摘要
指静脉识别的一大挑战是缺乏大规模公开数据集。现有数据集包含的身份数量少，且每根手指的样本有限，限制了基于深度学习的方法的发展。为解决该问题，我们提出FVeinSyn，这是一个用于指静脉的大规模可控合成数据生成框架，它明确将血管拓扑结构的合成与成像外观的合成解耦，以缓解训练样本不足带来的身份多样性不足、真实度受限等问题。具体而言：首先，指静脉身份生成器采用随机L系统，在生理和几何约束下对血管拓扑结构进行建模，生成符合解剖学要求且具有身份辨识度的血管图案。随后，级联区域感知GAN将拓扑图渲染为逼真的近红外图像。最后，类内多样性生成器引入几何和光学扰动，以模拟真实的类内变化。利用FVeinSyn，我们生成了50万张图像（1万个静脉身份，每个身份50个样本）并开展了广泛评估。结果显示，FVeinSyn在真实度、身份多样性、血管图案一致性和类内多样性方面具有显著优势。在八个公开数据集上，使用FVeinSyn训练的模型仅在真实数据基准上表现更优，平均准确率提升了27.43%。代码可在以下网址获取：this https URL。
英文摘要
A major challenge in finger vein recognition is the lack of large-scale public datasets. Existing datasets contain few identities and limited samples per finger, restricting the advancement of deep learning-based methods. To address this, we propose FVeinSyn, a large-scale controllable synthetic data generation framework for finger vein. It explicitly decouples synthesis of vascular topology and imaging appearance to mitigate the limitations caused by insufficient training samples, such as inadequate identity diversity and restricted realism. Specifically: first, a finger vein identity generator models vascular topology under physiological and geometric constraints using stochastic L-systems, producing anatomically valid and identity-distinctive vascular patterns. Then, a cascaded region-aware GAN renders the topological maps into realistic near-infrared images. Finally, an intra-class diversity generator introduces geometric and optical perturbations to simulate realistic intra-class variations. Using FVeinSyn, we generated 500,000 images (10,000 vein identities, 50 samples per identity) and conducted extensive evaluations. Results show that FVeinSyn holds significant advantages in realism, identity diversity, vascular pattern consistency, and intra-class diversity. Models trained with FVeinSyn outperform real-data-only baselines a cross eight public datasets, achieving an average accuracy improvement of 27.43\%. The code is available at: https://github.com/EvanWang98/Synthetic-Finger-Vein-Generator.
