Comparision of Iris Identification by Using modified SIFT and SURF keypoint Descriptor

Abstract

A wide variety of systems require reliable personal recognition schemes to either confirm or determine the identity of an individual requesting their services. The purpose of such schemes is to ensure that only a legitimate user, access the rendered service. A biometrics system is essentially a pattern recognition system, which makes a personal identification by determining the authenticity of a specific physiological or behavioral characteristic possessed by the user. Iris serves as one of the excellent biometric traits due to the stability and randomness of its unique features. After localization of the iris, Scale Invariant Feature Transform (SIFT) is used to extract the local features. But SIFT is found out to be computational complex.So in this paper another keypoint descriptor ,Speeded Up Robust Features (SURF), is tested and then modified which compare the performance of different descriptor and hence gives promising results with very less computations. We finally carry out a comparision of both the descriptors performance wise.