An Automatic Approach to Iris Extraction and Recognition

Biometric systems are used for the automatic recognition of a person based on the unique characteristics or features possessed by that person. Many biometric systems are available now–a-days. Iris Recognition System is one of the most consistent and reliable biometric identification system available. Iris Recognition is the recognition of an individual based on iris features. Several methods have been presented in the past few years to improve the performance of iris recognition systems. Iris recognition system consists of: Iris Acquisition, iris Localization, iris feature extraction and matching .In this paper ,we have introduced a new step known as feature selection which is used after feature extraction. This is done so as to use only useful features for matching. The emphasis in this paper is to obtain efficient and robust algorithm for iris recognition. Iris localization is done by using circular hough transform. Feature extraction is done by using SIFT algorithm. For feature selection, Genetic Algorithm is used. Performance evaluation is done on IIT Delhi Iris database using FAR and FRR metrics. The experimental results show that the proposed method is more robust and accurate.