A method for improving the reliability of an iris recognition system

This paper proposes a technique for improving the performance of an iris recognition system. The proposed method is a variation of the Daugman's method used 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. The idea introduced here is that the most distinctive iris features are more concentrated in some specific regions. Hence, only points from these regions are selected for generating the rectangular representation of the iris. The goal of this paper is to show that it is possible to improve the reliability of the system by choosing points from different regions of the iris. Some simulations of the process have been described and the experimental results show that the proposed method has an encouraging performance.