Iris recognition is one of the biometric methods commonly used for personal recognition. In this paper, single value decomposition (SVD), principal component analysis (PCA), automatic feature extraction (AFE) and independent component analysis (ICA) are used to extract the feature of the iris from a pattern called IrisPattern based on the iris image. IrisPatterns are classified using Feedforward Backpropagation Neural Network (BPNN) and Support Vector Machines (SVM) with Radial Basis Function (RBF) kernels of different sizes, and a comparative study is carried out. From the experimental result, it is observed that ICA is the most appropriate feature extraction method for both BPNN and SVM with Gaussian RBF, and SVM with Gaussian RBF can classify faster than BPNN. A biometric recognition system can be used with a range of physiological characteristics (e.g. fingerprint, palm print, hand geometry, face, iris, ear shape and retinal vein) and behavioral characteristics (e.g. gait, voice , signature and keystroke dynamics) to provide automatic identification of individuals based on their intrinsic physical and/or behavioral characteristics. Among these biometric data, iris recognition is one of the most accurate and reliable biometric methods for identification due to the following characteristics (i) The iris pattern has a complex and distinctive pattern such as arcuate ligaments, crypts, crown, freckles, furrows, ridges, rings and a zigzag collar [1]. (ii) they possess 266 degrees of freedom of variability and uniqueness on the order of one in 1072 [2]. However, iris recognition also has disadvantages. Some parts of the iris are usually occluded by the eyelid and eyelashes. The boundaries of the pupil and iris are not always circles and their centers are not in the center of the paper (black or almost black). To find the pupil, a linear threshold (of value 70 in the present work) is applied to the image as (1) where f is the original iris image and g is the thresholded image. By applying this, pixels with intensity greater than the empirical value of 70 are converted to 1 (black) and the others are assigned to 0 (white). Some parts of the eyelashes satisfy (1), but have an area much smaller than the pupil area. We can remove all small regions other than the pupil by applying code segment (2) for each region R if AREA(R) < 2500 (2) sets all pixels of R to 0Thus, we get the pupil region. Two imaginary orthogonal lines are drawn passing through the centroid of the pupil region and the first pixel with zero intensity, from the center to the ends are the boundaries of the binarized pupil. The output of this process is shown in Figure 2.