用拓扑感知网络提升掌纹静脉识别精度，参数少、效果优。
Topology-Aware Global-Local Mamba Networks for Palm Vein Biometrics
- 设计拓扑感知模块，融合局部纹理、结构方向与全局路径信息。
- 在两个数据集上分别达到99.13%和92.42%准确率，错误率最低。
- 适合追求高精度且轻量级的生物特征识别应用。
掌纹静脉识别是一项细粒度生物特征任务，局部血管纹理与整体血管树布局均携带判别性信息，但公开数据集仍有限。我们提出一种拓扑感知的全局-局部骨干网络，包含多尺度局部特征、基于固定Sobel幅值边缘先验的结构引导方向流，以及六个拓扑感知块内的四方向状态空间扫描全局路径。分阶段门控融合按顺序整合局部、结构与全局表征。在HKPUNIR数据集上，本方法实现99.13%的top-1准确率和0.08%的EER，参数量仅7.2M；在VERA Palm Vein数据集上，准确率达92.42%，EER为0.61%。在相同模型中，其EER最低，参数最少，优于ResNet50、Vim-S、ViT-S和GLVM。尽管GLVM在top-1准确率和FLOPs方面仍最优，本方法在平衡性能与效率上表现突出。代码可申请获取。
原文摘要 · Abstract (English)
Palm-vein recognition is a fine-grained biometric task in which both local vascular texture and the global layout of the vessel tree carry discriminative information, while public datasets remain limited. We propose a topology-aware global-local backbone that combines multi-scale local features, a structureguided directional stream built on a fixed Sobel-magnitude edge prior, and a four-direction state-space scan global pathway within six Topology-Aware Blocks. A staged gated fusion integrates local, structural, and global representations in that order. On HKPUNIR, our method achieves 99.13% top-1 accuracy and 0.08% EER with 7.2 M parameters; on VERA Palm Vein, it achieves 92.42% accuracy and 0.61% EER. Across both datasets it attains the lowest EER among ResNet50, Vim-S, ViT-S, and GLVM at the smallest parameter count, while GLVM remains the strongest in top-1 accuracy and the cheapest in FLOPs. Code is available upon request.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。