Person Identification Based on Different Colour Models Iris Biometric and Contourlet Transform

Abstract

Iris identification plays an important role in many applications like security, banking, access to buildings, and surveillance …. etc. Since the iris part of the eye image can be significantly affected by some factors, such as lighting conditions source, eyelids, eyelashes, pupil, sclera, and shadowing, therefore iris identification research is still wide and rich. The work proposed in this paper operates the iris identification system on the distorted colored images captured under visible light. The proposed idea minimizes the number of iris regions affected by distortion, by dividing the iris region into separable regions. Only the region without distortion part or region with distortion is less probable is used. The paper studies the effect of different color model such as HSV, YIQ, YCbCr, and RGB color models on iris identification. High quality feature extraction is introduced in this paper by using Contourlet Transform (CT). Euclidian Distance (ED) or Neural Network (NN) is used as classifiers. Simulation results show that the proposed method operating on non-distortion iris region outperforms the conventional method operating on the whole iris region for any selected color model and for standard databases (UPOL andUTIRIS) and a suggested one.