Abstract—Iris identification has received extremely attention as a reliable approach to human identification in the world today. It is very effective for person identification due to the iris’ unique features and the protection of the iris from the environment and aging. In this paper, we present a simple and effective method to create an iris recognition system by considering biological characteristics of iris where we used artificial neural networks for iris pattern recognition. The proposed approach is verified and it showed good results in terms of false acceptance ratio, false rejection ratio and noise immunity. In addition, the developed algorithm can uses for the another biometrics like fingerprint and retina.
Index Terms—Iris recognition, feature extraction, iris code, neural networks, multi layer perceptron, back propagation error.
H. Mohammadi is with the Department of Electrical Engineering, Islamic Azad University, Sarvestan branch, Sravestan, Iran (e-mail: amir200@engineer.com).
M. Mohammadi is with the Department of Computer Engineering, Islamic Azad University, Dezful branch, Dezful, Iran (e-mail: mofard@gmail.com).
M. Nadisenjani is with the Computer Engineering Department, Islamic Azad University, Ashtian branch, Ashtian, Iran (e-mail: nadi.mahdieh@gmail.com).
[PDF]
Cite:Hossein Mohammadi, Mohammad Mohammadi, and Mahdieh Nadisenjani, "An Effective Identification Systems Based on Iris Texture Analysis," International Journal of Computer Theory and Engineering vol. 5, no. 3, pp. 396-400, 2013.