Artificial Neural Network Based Iris Recognition System

Abstract

This paper deals with biometric personal identification based on iris recognition using artificial neural network. The Iris recognition system includes pupil detection, and the enhancement, region of interest of iris detected from an eye image then, the iris recognition using neural network approach. For the localization of the inner and outer boundaries of the iris region is being proposed a fast algorithm by us. Located pupil is detected from an eye image, and, after enhancement, located iris part is detected from an eye image, it is represented by a dataset. In this paper, we proposed a neural network based iris recognition approach by analyzing iris patterns. Hough transforms are used for localizing the part of iris region; then, histogram equalization was applied to the iris an image for making the shapes an image more distinctive. The gray-level iris images, experimented in this work, were obtained from the Institute Automation Chinese Academy of Science (CASIA) iris images database version 1.0.