IOSR Journal of Computer Engineering (IOSR-JCE) e-ISSN: 2278-0661, p- ISSN: 2278-8727Volume 12, Issue 3 (Jul. - Aug. 2013), PP 59-67 www.iosrjournals.org www.iosrjournals.org 59 | Page A Robust Approach in Iris Recognition for Person Authentication Chinni. Jayachandra 1 H. Venkateswara Reddy 2 B. Suresh Kumar 3 B. Sruthi 4 1 M.Tech (C.S.E), VCE, Hyderabad, India, 2 Associate Professor in CSE, VCE, Hyderabad, India, 3 M.Tech (C.S.E), VCE, Hyderabad, India, 4 M.Tech (C.S.E), VCE, Hyderabad, India, Abstract: In Iris recognition authentication process, iris and sclera are used as the previous inputs using to recognize the eye with different mechanisms like segmentation combining with different versions. In this paper, entirely biometric-based personal verification and identification methods have gained much interest with an increasing accent on safety. The iris texture pattern has no links with the genetic structure of an individual and since it is generated by chaotic processes externally visible patterns imaged from a distance. Iris patterns possess a high degree of randomness and uniqueness. Here we propose two algorithms they are K-Means algorithm and canny Edge Detection. Totally eight process acting to identify the pupil and also for iris recognition. Comparing images k- means algorithm is to give accurate contest. As a final point it leads to open authentication person details from database. Key words - Median filter, Iris Radius Detection, Iris Unrolling, Iris Recognition, Pupil Detection, Canny edge detection algorithm, K-means algorithm. I. Introduction Recognizing individuals based on biometric systems is increasing rapidly in organizations, industries and others. It mainly focuses on security throughout the world and it is so far increasing. By examining physical or behavioral characters of human beings, biometric systems are reliable [1] which are unique among all individuals. In recognition process biometric systems are deploying and enhancing the security, reliability, convenience and efficiency. Based on uniqueness and stability of the biometrics during human’s lifetime, it has been utilized as an expedient method for the recognizing process for many years. There are few biometric systems are available in world like finger prints, palm, signature, face, DNA, retina, ear and iris. Iris recognition is the process of recognizing a person by analyzing the random pattern of the iris images. The automated method of iris recognition is relatively young, existing in patent only since in 1994.The human iris, an annular region located around the pupil and covered by the cornea, can provide independent and unique information of a person. Among these iris is one of the better authentication method for verification and identification of person in both modes. Iris is a ring like chromatic texture between the black central pupil and white colored sclera in the eye. The inner and outer circular templates in eye are not in a standard circular shape. Complex characteristics exist in iris pattern exhibit the iris as an important, convenient and non- invasive natural identification means. From past years iris is utilized as identification systems rapidly. The existing algorithms are using two circular templates to identify the eye. But they are not in a standard circle shape it leads to iris legacy and difficult to find proper identification. From past iris recognition is proposed as a reliable biometric system in 1987 by L. Form [2]. Although the correlation and the structure of the iris is genetically link, the details of the pattern are not. Iris develops during prenatal growth through a process of tight forming and folding of the tissue membrane. Genetically identical an individual’s irides are unique and structurally distinct, which allows for it to be used for recognizing purposes. Iris based biometric, on the other hand, involves analyze features found in the colored ring of tissue that surrounds the pupil. Identity of verification and authentication increasing day by day to provide security for this iris recognition is more accurate which cannot change by human age. 1.1 Relate Work Daugman developed Daugman's theory using 2-d Gabor filter phase quantification and the code identification system [3, 4]. Wildes given a theory based on the multiscale Gaussian filters for iris identification system [5]. Boles recommended a method based on the wavelet transformation algorithm to iris recognition [6]. Boles and Boashash’s [7] given that iris images are analyzed in a 1-D dyadic wavelet transform in different resolution levels, using wavelet results the feature vector of the iris image was extracted. Junzhou Huang given iris segmentation and Edge extraction is using phase congruency to identify the iris [8]. H. Proenca and L.A. Submitted Date 20 June 2013 Accepted Date: 25 June 2013