An Embedded Fingerprint Authentication System

Fingerprint authentication is one of the most reliable and widely used personal identification method. However, manual fingerprint authentication is tedious, inaccurate, time-consuming and costly that it is not capable of meeting today´s increasing performance necessities. An automatic fingerprint authentication system (AFAS) is widely needed. It plays a very essential role in forensic and civilian applications such as criminal identification, access control, and ATM card verification. This paper describes the design and implementation of an Embedded Fingerprint Authentication system which operates in two stages: minutia extraction and minutia matching. The present technological era is demanding reliable and cost-effective personal authentication systems for large number of daily use applications where security and privacy performance of the information is required. Biometrics authentication techniques in combination with embedded systems technologies give a demanding solution to this need. This paper explains the hardware-software co-design responsible for matching two fingerprint minutiae sets and suggests the use of reconfigurable architectures for Automatic Fingerprint Authentication System. Moreover, this paper explains the implementation of a fingerprint algorithm using a Spartan-6FPGA, as an appropriate portable and low cost device. The experimental results show that system meets the response time requirements of Automatic Fingerprint Authentication System with high speed using hardware-software co-design.