PulseAugur
EN
LIVE 15:10:30

New topology-aware backbone enhances palm-vein biometric recognition

Researchers have developed a novel topology-aware global-local backbone for palm-vein recognition, a fine-grained biometric task. This approach integrates multi-scale local features with a structure-guided directional stream and a global pathway using six Topology-Aware Blocks. The system achieves high accuracy on public datasets, outperforming existing methods like ResNet50 and ViT-S in terms of parameter count and EER. AI

IMPACT Introduces a new method for biometric recognition by integrating local, structural, and global features, potentially improving accuracy in identification systems.

RANK_REASON The item describes a new research paper detailing a novel method for biometric recognition. [lever_c_demoted from research: ic=1 ai=1.0]

Read on Hugging Face Daily Papers →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

New topology-aware backbone enhances palm-vein biometric recognition

COVERAGE [1]

  1. Hugging Face Daily Papers TIER_1 English(EN) ·

    Topology-Aware Global-Local Mamba Networks for Palm Vein Biometrics

    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…