An Improved Iris Recognition System using Artificial Neural Network

Abstract

The aim of the research work is to propose an improved iris recognition system using Artificial Neural Network. Personal Authentication and Identity become a challenging task for us. The most recent development in the field of Information Technology with regard to individual authentication and their security moves towards biometric based programmed individual authentication framework. Iris recognition system is being effectively used in places where security is paramount. Iris identification has been found to be very effective in authentication due to its unique features. Iris recognition will perceive a man by breaking down his iris image. Each individual has unique iris and it remains stable throughout the life time of an individual. Iris is an internal organ that is highly secured by the eyelid and cornea. A neural network was created and the partitioned iris image data were given as the inputs. Here the Artificial Neural Network had to compare the iris image with the stored image and identify the person from the image. This error was then fed back (back propagated) to the neural network and used to adjust the weights such that the error decreased with each iteration and the neural model got closer and closer to producing the desired output.