Development of an Iris-Based Access Control System Using a Two-Level Segmentation Approach
Security of lives and assets has become a very interesting issue worldwide. Ability to restrict access to unauthorized users via an identification system that cannot be compromised at a very fast rate is highly desirable because it can be very costly if not achievable. In this work, a new segmentation technique that is suitable for segmenting black people's irises was developed. The system was simulated using irises of black people's faces captured in Nigeria and iris images from Chinese Academy of Sciences Institute of Automation (CASIA), a standard iris database. The False Acceptance Rate (FAR) and False Rejection Rate (FRR) of the two image databases were obtained with varying Hamming Distances of 0.26, 0.30, 0.35, 0.39 and 0.45 respectively.