Team Members
Summary
The current biometric-based authentication approaches for face recognition rely on facial characteristics on or over the skin surface. Some of these characteristics have low permanency, which can be altered, and their phenomenology varies significantly with environmental factors (e.g., lighting). In contrast, vascular biometric templates are gaining increasing popularity due to the simple and contact-free capture and resilience to presentation attacks. The motivation behind this study is to capitalize on the permanency of innate characteristics under the skin surface. Our research explores the state-of-the-art in Biometric Graph Comparison, a technique to register and compare vascular biometric templates by representing them as formal graphs. This research shows the benefits of graph representation for facial vascular biometrics and the advantages of graph topology in matching vascular biometric graphs.