A novel approach to iris recognition for personal authentication

This paper examines automated iris recognition as a biometrically based technology for personal identification and verification. Although numerous iris recognition algorithms have been proposed, this paper define the texture of irises have not been extensively studied. In this paper, to localize the iris we used canny edge detection algorithm and circular Hough transform. After Localization, we counter clockwise un-wrapped the circular iris to get a rectangular texture block with a fixed size called Normalization. The normalized iris image thus obtained has low contrast and may have non-uniform brightness caused by the position of light sources. So in this paper we enhanced the lighting corrected image by means of Histogram Equalization. Then a set of one-dimensional intensity signals that reflect their various spatial modes is constructed. Gaussian Hermite moments are used for distinguishing features. A resulting high dimensional feature vector is mapped into a low dimensional subspace using Fisher linear discriminant.