1 Abstract—Iris pattern is an important biological feature of human body; it becomes very hot topic in both research and practical applications. In this paper, an algorithm is proposed for iris recognition and a simple, efficient and fast method is introduced to extract a set of discriminatory features using first order gradient operator applied on grayscale images. The gradient based features are robust, up to certain extents, against the variations may occur in contrast or brightness of iris image samples; the variations are mostly occur due lightening differences and camera changes. At first, the iris region is located, after that it is remapped to a rectangular area of size 360x60 pixels. Also, a new method is proposed for detecting eyelash and eyelid points; it depends on making image statistical analysis, to mark the eyelash and eyelid as a noise points. In order to cover the features localization (variation), the rectangular iris image is partitioned into N overlapped sub-images (blocks); then from each block a set of different average directional gradient densities values is calculated to be used as texture features vector. The applied gradient operators are taken along the horizontal, vertical and diagonal directions. The low order norms of gradient components were used to establish the feature vector. Euclidean distance based classifier was used as a matching metric for determining the degree of similarity between the features vector extracted from the tested iris image and template features vectors stored in the database. Experimental tests were performed using 2639 iris images from CASIA V4-Interival database, the attained recognition accuracy has reached up to 99.92%. Keywords—Iris recognition, contrast stretching, gradient features, texture features, Euclidean metric. I. INTRODUCTION IOMETRICS is the study of behavioral or physical characteristics of human including items such as finger prints, face, hand geometry, voice and iris. Among the biometrics, iris has highly accurate and reliable characteristics. An iris has unique structure and it remains stable over a person life time, which is observed through the clinical evidence [1]. The created iris patterns of human are largely completed at the eighth month after his porn. Pigment accretion can continue into the first postnatal year. Formation of unique iris patterns is random and not related to any genetic factor. Due to the epigenetic nature of iris, two eyes of an individual contain completely independent iris patterns. Iris has unique features and highly complex patterns to be used as a biometric [2], [3], therefore, the iris recognition systems are very reliable and could be used in most secure places [4], [5]. Many feature extraction algorithms have been developed in the literature; Iman A. Saad is with the Electronic Computer Center, University of Mustansiriyah, Baghdad, Iraq (e-mail: eman_abduljabbar@yahoo.com). Dr. Loay E. George works with the Department of Computer Science, College of Science, University of Baghdad, Baghdad, Iraq (e-mail: loayedwar57@yahoo.com). they differ either in the iris feature representations or in the pattern matching algorithms. Most of the studies concentrated on extracting texture feature information from iris region, such that they contain inherent characteristics of the iris that are essential to iris recognition. Daugman [6] made use of two-dimensional Gabor filters to demodulate texture phase structure information of the iris, use the result to get the iris texture characteristics of the local phase, and then to the match, the difference between a pair of iris codes was measured by their Hamming distance. After Daugman work, many scholars proposed a variety of iris recognition methods. Boles and Boashah introduced an algorithm for iris recognition based on the wavelet transform zero crossing detection; they calculated zero-crossing representation of 1D wavelet transform at various resolution levels of a virtual concentric circle on an iris image to characterize the texture of the iris image. Monro [7] developed an iris coding method based on DCT for feature extraction. He used Iris images obtained from CASIA database, version 1 and the Bath database. Azizi and Pourreza [8] proposed a set of local and global properties of an iris image for establishing iris feature vector. Also, some sets of local binary features based on Haar wavelet [9]. Sarhan [10] used discrete cosine transform for feature extraction and artificial neural networks for classification. ridgelet and curvelet transform [11] have been introduced. Sheeba et al. [12] proposed a method uses both Local Binary Pattern (LBP) to extract texture features and Learning Vector Quantization (LVQ) method for classification. The performance of iris recognition system depends on the good image quality and extremely clear iris texture details. Some attributes (contrast, brightness and existing noise) are highly sensitive to the specific characteristics of each image. Different lightening or camera properties can lead to images, for the same scene, have pixels' values very different with each other; these big differences would cause significant matching failure rates. Most of the existing iris recognition methods extract either the multi resolutional or the directional features of iris image. They may use Gabor filter or wavelet transforms (with two or four quantization levels) to establish the feature vector. This kind of features has robustness to contrast and illumination changes. These methods do not utilize a significant component of the rich discriminatory information available in the iris signatures. Aim of this paper is to introduce a novel iris recognition method based on the gradient components distribution to extract iris features; the kind of these features is robust against the local illumination changes may appear in the iris image. Iman A. Saad, Loay E. George Iris Recognition Based On the Low Order Norms of Gradient Components B World Academy of Science, Engineering and Technology International Journal of Computer and Information Engineering Vol:8, No:8, 2014 1356 International Scholarly and Scientific Research & Innovation 8(8) 2014 scholar.waset.org/1307-6892/9999069 International Science Index, Computer and Information Engineering Vol:8, No:8, 2014 waset.org/Publication/9999069