Iris Recognition using Secant Lines Segments Histogram

Abstract

Biometrics is a method for recognizing based on physiological and behavioral characteristics. Iris recognition is one of the robust biometric technologies used for authentication applications. An iris recognition system is composed of segmentation, normalization, feature extraction and matching. The performance of iris recognition system depends on the selection of iris features. Most commercial iris recognition systems used patented algorithms developed by Daugman’s Gabor filter for feature extraction. These methods have large computation. To overcome this problem, a new effective method, Secant Lines Segments Histogram, is proposed for extracting features of iris. In this paper, Hough Transform is applied for localizing the iris region. The segmented iris is normalized using Daugman’s Rubber Sheet Model. For extracting iris features, Secant Lines Segments Histogram is used. The two iris feature vectors are matched using Euclidean Distance. The proposed iris recognition system reduces the computation and time load for extracting features of the iris.