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.