Application of Genetic Algorithms to Improve the Reliability of an Iris Recognition System

In this paper, it is applied the basis of genetic algorithms to develop a technique to improve the performance of an iris recognition system. The proposed technique uses the principle of the method proposed by Daugman [ 1,2] to normalize the iris region. Daugman used a rectangular representation of the iris generated from a uniform selection of points along the whole extension of the iris. This paper introduces the idea that if the points were selected non-uniformly over the iris region it is possible to find a distribution of points which makes the sistem more reliable. The genetic algorithms are used to find a distribution of points which leads the system to a better result. Some simulations of the process are described and the experimental results are shown in the end.