Gender-Specific Characteristics for Hand-Vein Biometric Recognition: Analysis and Exploitation

In recent years, vein-based biometric recognition has received ever-increasing attention from both academia and industry, due to the advantages it offers over traditional traits such as fingerprint, iris, face. Nonetheless, some issues related use of vein biometrics still need be investigated understood. Specifically, in this study, we speculate about gender-related variations patterns, their effects on verification performance. An analysis feasibility recognizing male female subjects depending hand-vein level similarity characterizing templates extracted populations, are here carried out considering three different databases. public VERA dataset, containing samples palm-vein two datasets images finger-vein i.e., UTFVP database, an in-house dataset collected with on-the-move contactless modality, considered. The obtained experimental results show that approach proposed perform gender allows reach accuracy up 95.83% outperform current state-of-the-art at 93.55%. It is also shown systems can benefit exploitation information regarding considered subjects, achievable rates significantly improved by designing a system relying gender-specific models for extracting employed discriminative templates.