Iris biometrics is one of the fastest-growing technologies, and it has received a lot ofattention from the community. Iris-biometric-based human recognition does not requirecontact with the human body. Iris is a combination of crypts, wolflin nodules, concen-trated furrows, and pigment spots. The existing methods feed the eye image into deeplearning network which result in improper iris features and certainly reduce the accuracy.This research study proposes a model to feed preprocessed accurate iris boundary intoAlexnet deep learning neural network-based system for classification. The pupil centre andboundary are initially recorded and identified from the given eye images. The iris boundaryand the centre are then compared for the identification using the reference pupil cen-tre and boundary. The iris portion, exclusive feature of the pupil area is segmented usingthe parameters of multiple left-right point (MLRP) algorithms. The Alexnet deep learningmultilayer networks 23, 24, and 25 are replaced according to the segmented iris classes. Theremaining Alexnet layers are trained using the square gradient decay factor (GDF) in accor-dance with the iris features. The trained Alexnet iris is validated using suitable classes. Theproposed system classifies the iris with an accuracy of 99.1%. The sensitivity, specificity,and F1-score of the proposed system are 99.68%, 98.36%, and 0.995. The experimentalresults show that the proposed model has advantages over current model
Available at: http://works.bepress.com/helen-dang/28/