Principal Components Analysis Based Iris Recognition and Identification System
E. Mattar
E. Mattar, Department of Electrical and Electronics Engineering, College of Engineering, University of Bahrain, P. O. Box 13184, Kingdom of Bahrain.
Manuscript received on April 05, 2013. | Revised Manuscript received on April 28, 2013. | Manuscript published on May 05, 2013. | PP: 430-436 | Volume-3, Issue-2, May 2013. | Retrieval Number: B1585053213/2013©BEIESP
Open Access | Ethics and Policies | Cite
© The Authors. Published By: Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: This article focuses on the employment of iris recognition technique and their application in security systems. The implementation of such a system is based on the processing of an iris (scene) using Principle Component Analysis known in the literature as (PCA). This is done by an iris segmentation algorithm of (Libor Masek). Libor Masek algorithm is utilized here to segment an iris from some undesired noises and ingredients in an eye image. This rather helps to acquire the most accurate iris scene. Eigen irises are hence obtained using the PCA method. Eigen of irises are then utilized to train an Artificial Neural Network (ANN) recognition system. This is followed by transforming a set of irises into a new space. Transformed irises are accumulated in a database, where they are compared with a set of test irises transformed in the same state of the recognition cycle. The proposed system has resulted in accurate results up to 91% for identifying a pre-stored individuals.
Keywords: Iris recognition, Principal Component Analysis, Pattern recognition, Eigen vectors.