Abstract
Biometric identification is an important security application that requires non-intrusive capture and real-time processing. Recently, identification by vein patterns has been suggested as a promising alternative. In this paper we study the potential of Cellular Neural Networks implemented on a Field-Programmable Gate Array to handle the person identification based on hand veins in real time. With a minimal distance measure of 2 pixels for False Feature Elimination, it has a True Acceptance Rate of 65% and a False Rejection Rate of 5%. The performance rises drastically with increasing pixel distance and will therefore be camera sensitive.
Original language | English |
---|---|
Title of host publication | Proceedings SSoCC |
Publication status | Published - 2006 |
Event | SSoCC (Swedish System-on-Chip Conference), 2006 - Kolmården, Kålmården, Sweden Duration: 2006 May 4 → 2006 May 5 |
Conference
Conference | SSoCC (Swedish System-on-Chip Conference), 2006 |
---|---|
Country/Territory | Sweden |
City | Kålmården |
Period | 2006/05/04 → 2006/05/05 |
Subject classification (UKÄ)
- Electrical Engineering, Electronic Engineering, Information Engineering