发表机构
University of Auckland（奥克兰大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对掌纹识别的数据集限制问题，提出拓扑感知全局-局部Mamba网络，在两个公开掌纹数据集上以较少参数实现低等错误率，且浮点运算量表现优异。
AI 中文摘要
掌纹识别是一项细粒度生物识别任务，局部血管纹理与血管树的全局布局均携带判别信息，但公开数据集有限。我们提出一种拓扑感知全局-局部主干网络，结合多尺度局部特征、基于固定Sobel幅度边缘先验构建的结构引导方向流，以及6个拓扑感知块内的四方向状态空间扫描全局通路，采用分阶段门控融合按序整合局部、结构与全局表征。在HKPUNIR数据集上，本方法以720万参数实现99.13%的Top-1准确率与0.08%的等错误率（EER）；在VERA掌纹数据集上，实现92.42%的准确率与0.61%的EER。在两个数据集上，本方法在ResNet50、Vim-S、ViT-S、GLVM中参数规模最小且EER最低，同时GLVM保持Top-1准确率最优且浮点运算量（FLOPs）最低。代码可应要求提供。
英文摘要
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.
