Person Identification Based Colored Iris Biometric and Contour let Transform

Iris identification requires high quality iris image for high identification rate. 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, and then regions without distortion part are chosen. High quality feature extraction is introduced in this paper by using contourlet transform (CT) since the actual construction of the iris picture can be captured by CT. The normalized iris image is decomposed into a set of directional sub bands with features captured in various scales and different directions. Euclidian distance (ED) and neural network (NN) are used as classifiers, based on three channels (Red, Green, and Blue) of the color image. Simulation results show that the proposed method outperforms the classical methods operating on the whole iris for standard databases (UPOL and UBIRISv1) and a suggested one.