A Proposed Biometric Technique for Improving Iris Recognition

Abstract Recently, the Iris Recognition system has been considered an effective biometric model for recognizing humans. This paper introduces hybrid technique combining edge detection and segmentation, in addition to convolutional neural network (CNN) Hamming Distance (HD), extracting features classification. The proposed is applied different datasets, which are CASIA-Iris-Interval V4, IITD, MMU. For validating results of models, detailed modeling simulation procedures took place using mentioned three datasets. A comparison between obtained from current work published open literature was carried out as well. Proposed Biometric Technique showed desirable recognition accuracies 94.88% based on applying HD CASIA, 96.56% CNN 98.01% illustrated superiority such a classifier compared other classifiers used literature.