Abstract

2,3 Abstract: An authentic personal identification infrastructure is required to control the access in order to secure areas or materials. Biometric technology is based on physiological or behavioral characteristics of a human body. Iris recognition system consists of image acquisition, localization, normalization, features extraction and encoding, and classification. Iris images are downloaded from CASIA Iris V1.0 database for study. To separate the iris region from the eye image, Hough transform is used. Circular Hough transform is used to localize circular iris and pupil region while parabolic Hough transform is used to enhance the occluding eyelids and eyelashes. Daugmans rubber sheet model is used to normalize the extracted iris region into a rectangular block with constant polar dimensions. After normalization, 2D Gabor filter is employed to extract the important features from iris. Iris provides texture information which is unique, universal and contains high randomness. Feature extraction is performed by convolving the normalized iris region with 2D Gabor filter which gives the phase information. The phase data represented by a data set is utilized as input for classifiers. The classifiers used in this study are Artificial Neural Networks (ANN) and Support Vector Machines (SVM). This study shows that Support Vector Machines gives higher recognition rate than Artificial Neural Networks.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call