20-04-2017, 01:59 PM
A biometric system provides automatic identification of an individual based on a unique characteristic or characteristic possessed by the individual. Iris recognition is considered the most reliable and accurate biometric identification system available. Most commercial iris recognition systems use proprietary algorithms developed by Daugman, and these algorithms are capable of producing perfect recognition rates. However, published results have generally been produced under favourable conditions, and there have been no independent trials of the technology. The work presented in this thesis involved the development of an "open source" iris recognition system to verify both the uniqueness of the human iris and its biometric performance. In order to determine the recognition performance of the system, two databases of digitized images of grayscale eyes were used. The iris recognition system consists of an automatic segmentation system that is based on the Hough transform and is able to locate the circular iris and the pupil region, occluding eyelids and eyelashes and reflections.