Iris Recognition based on Local sharp Variation Points

A wide variety of systems require reliable personal recognition schemes. With the development of biometric recognition technology it is found that iris is one of the most reliable biometric recognition schemes because of its randomly distributed features and unique characteristics. The method discussed in this paper recognized the key local variation points to represent the characteristics of the iris. Thus to characterize the most important features from two dimensional original iris images, a set of 1-D intensity signals which consist of most sharp variations is constructed. In later stage a dyadic wavelet transform is used to precisely locate the position of local sharp variations points which is recorded as features. Exclusive OR operation is used as matching metric. The system performance is analyzed on 756 iris images of standard CASIA-Iris-Version1 database. Keywords—Local Sharp Variation Points, Dyadic Wavelet, Equal Error rate, Genuine Accept rate. I. In tr odu c ti on Security of computer and financial systems plays a crucial role, nowadays. These systems require remembering many passwords that may be forgotten or even stolen, which is disastrous for the user. To avoid these problems, b iometrical systems based on physiological characteristics of a person are taken into consideration in different applications. Among various approaches, iris-based personal recognition is referred to as the most promising one because of its high accuracy, good stability, and high recognition speed [i]. The iris texture is different between persons and between the left and right eye of the same person. The color of the iris can change as the amount of pigment in the iris increases during childhood. Nevertheless, for most of a human’s lifespan, the appearance of the iris is relat ively constant [ii].The iris is a thin circu lar d iaphragm, which lies between the cornea and the lens of the human eye. A front view of human eye is shown in Figure 1. The iris is perforated close to its centre by a circular aperture known as the pupil. The function of the iris is to control the amount of light entering through the pupil, and this is done by the sphincter and the dilator muscles, which adjust the size of the pupil. Figure 1: Front View of Human Eye. [ii] Image processing techniques can be employed to extract the unique iris pattern from a digit ised image of the eye, and encode it into a biometric template, which can be stored in a database. This biometric template contains an objective mathematical representation of the unique informat ion stored in the iris, and allows comparisons to be made between templates. When a subject wishes to be identified by iris recognition system, their eye is first photographed, and then a template created for their iris region. This template is then compared with the other templates stored in a database until either a matching template is found and the subject is identified, or no match is found and the subject remains unidentified. In 1994, John Daugman obtained the patent for “Biometric personal identification system based on iris analysis” [iii]. Some other iris recognition systems were also developed by other people, such as Wildes et al. [iv], Lim et al. [v], Boles and Boashash [vi] and Li-ma et al. [vii]. Iris feature is convenience for a person to prove his/her identity based on him/her biometrics at any place and at any time. Iris recognition system includes iris capturing, image pre-processing, iris region localization, iris region normalizat ion, iris feature extract ion and template matching. Every part is very important for correct recognition person identity. II. Approach of Iris Recognition Iris images consists of many randomly distributed irregular small blocks, such as freckles, Coronas, stripes, furrows, crypts etc. Such randomly d istributed and irregular blocks constitute the most distinguishing characteristics of the human iris. These irregular b locks are considered as kind of transient signals which consist of key local sharp variation points [vii], [ix]. The method disused in this paper locates the position of important local sharp variation points in order to form a feature set. As shown in algorithm figure 2, first iris and pupil boundaries are International Journal of Scientific Engineering and Technology (ISSN : 2277-1581) Volume No.3 Issue No.4, pp : 403-407 1April 2014 IJSET@2014 Page 404 marked in the original eye image from which iris region is localized. In order to achieve invariance to translation and scale, the annular iris region is normalized into the rectangular block of fixed size. The irregularity in the block leads to local sharp variation points which are used to form a set of 1-D intensity signal. The position of these variation points is recorded as the feature template by using wavelet analysis. Finally to find the similarity or dissimilarity between the two templates exclusive OR operator is used. The detailed explanation is discussed in the following sections. Figure 2: A lgorithm of Implemented Method Iris localization: The first step in an iris recognition is to locate iris and pupil in an image of eye as shown in figure 3(b). In general, the pupil and the iris are not concentric also pupil rad ius is not in a fixed ratio to the iris radius [ii]. Hence, parameters such as x-y co-ordinates and radius corresponding to both the iris and the pupil are needed to know. This stage is termed as “Iris localization or iris segmentation”. The implemented system uses an automatic segmentation algorithm based on the circular Hough transform [viii] in which an edge map is generated by calculating the first derivatives of intensity values in an eye image and then thresholding the result. From the edge map, votes are cast in Hough space for the parameters of circles passing through each edge point. These parameters are the centre coordinates and the radius r, which are able to define any circle according to the following equation, Iris Normalization: The dimensional inconsistencies between eye images occur due to the stretching of the iris caused by pupil dilation from varying levels of illumination, varying imaging distance, rotation of the camera, head tilt, and rotation of the eye within the eye socket .Such elastic deformation in iris texture will affect the matching results. Thus to achieve more accurate recognition result the normalization process is used which produce iris regions, which have the same constant dimensions. The normalized iris image is shown in figure 3(c). For this purpose Daugman’s Rubber Sheet model is used [iii], [v iii]. This homogenous rubber sheet model remaps each point within the iris region to a pair of polar coordinates (r, θ) where r is on the interval [0, 1] and θ is angle [0,2π]. The remapping of the iris region from (x, y) Cartesian coordinates to the normalised non-concentric polar representation is modelled by the following equations,