Accurate Iris Boundary Detection in Iris-Based Biometric Authentication Process Somnath Dey and Debasis Samanta School of Information Technology, Indian Institute of Technology, Kharagpur, India-721302 somnath dey2003@yahoo.co.in, dsamanta@iitkgp.ac.in Abstract. This paper presents an efficient technique for accurate de- tection of iris boundary, which is an important issue for any iris-based biometric identification system. Our proposed technique follows scaling, histogram equalization, edge detection and finally removal of unnecessary edges present in the eye image. Scaling and removing unnecessary edges enables us to reduce the search space for iris boundary. Experimental results show that with our approach it is possible to detect iris boundary as much as 98% of the eye images in CASIA database accurately and it needs only 25% time compared to the existing approaches. Keywords: Iris recognition; biometric authentication; image segmenta- tion; image processing. 1 Introduction Now a days, biometric system is widely used for automatic recognition of an individual based on some unique characteristic owned by the individual. Iris recognition is a method of biometric identification based on high-resolution im- ages of the irises of an individual’s eyes. Iris is a thin contractile diaphragm, which lies between pupil and the white sclera of a human eye. Different parts of an eye image is shown in Fig. 1. In iris biometric system, an important task is iris localization. It is observed that the iris localization task is the most computationally intensive task. In iris localization task, we try to locate iris part from an eye image. Iris part Fig. 1. The typical components in an eye image A. Ghosh, R.K. De, and S.K. Pal (Eds.): PReMI 2007, LNCS 4815, pp. 600–607, 2007. c  Springer-Verlag Berlin Heidelberg 2007