Comparison of Iris Segmentation Methods for Performance Enhancement of Recognition
Minal K. Pawar, S. S. Lokhande · CiiT international journal of digital image processing · 2012
Authentication is very critical in security applications. Recently biometrics is gaining more attention for authentication of person. Biometrics is the science which deals in identification of person based on his physiological and/or behavioral characteristics. The most popular biometric authentication scheme employed for the last few years has been Iris Recognition. Iris recognition is one of the most trustworthy method due to rich and unique textures of the iris, non-invasiveness, stability of iris pattern throughout the human life time, public acceptance, and availability of user friendly capturing devices. The paper addresses on accurate iris segmentation by comparing performance of three segmentation methods for an improved texture extraction, as it is reported that most failures to match in iris recognition system result from inaccurate iris segmentation. The novel scheme of Geodesic Active Contours (GACs) is used to extract the iris and its performance is compared over the traditional Integro-differential operator and Hough transform.