An embedded system for iris recognition

Several systems require authenticating a person's identity before giving access to resources. With new advances in technology, biometrics is one of the most promising techniques in human recognition. Biometrics intends to identify a person by his physical and/or behavioural characteristics. This paper presents an approach for human authentication based on iris texture analysis. In this paper, we present a HW/SW implementation algorithm for detection and localisation of iris based on shape properties. The designed system has been implemented in a CYCLONE II DE2 Board using the NIOS II processor which is characterized by its flexibility and programmability. The data base CASIA version 1.0 is used for the test. The experimental results of the approach show the performance of our algorithms.