Downloads: 135 | Views: 235
Research Paper | Computer Science & Engineering | India | Volume 5 Issue 2, February 2016 | Rating: 6.2 / 10
Personal Authentication Based on Iris Recognition
Law Kumar Singh, Praveen Gupta
Abstract: Iris recognition is the process of recognizing a person by analyzing the apparent pattern of his or her iris. Iris recognition is regarded as the most reliable and most accurate biometric identification system available. Algorithms produced by Professor John Daugman [2] have proven to be increasingly accurate and reliable after over 200 billion comparisons [3]. In comparison to face, fingerprint and other biometric traits there is still a great need for substantial mathematical and computer-vision research and insight into iris recognition. Iris recognition is the most accurate and reliable biometric identification system available among other biometrics technique because even the iris of both the eyes of same individual are different. This project basically explains the Iris recognition system and attempts to implement the algorithms in MATLAB. Iris recognition is a biometric system for access control that uses the most unique characteristic of the human body. This paper proposes a personal identification using iris recognition system with the help of five major steps i. e. image acquisition, segmentation is performed using Canny Edge Detection and Hough Transformation, normalization, feature extraction using Local Binary Pattern and matching and also these five steps consists a number of minor steps to complete each step. The pupil and limbic boundaries are detected using Canny Edge Detection and Circular Hough Transformation. Then the iris image is transformed from Cartesian to polar coordinate. We perform feature extraction in which we extract the unique features of the iris image and then perform matching process on iris code using Chi-Square statistics for acceptance and rejection process. We are giving our research papers and our proposed technique works very well and can be easily implemented.
Keywords: Biometrics, Canny Edge Detection, Circular Hough Transformation, Feature Extraction, Chi-square statistics
Edition: Volume 5 Issue 2, February 2016
Pages: 446 - 450