Iris Localization and Recognition Using Second Gradient Norm Features

Abstract

Iris is regarded as the most reliable and accurate biometric identification system available. In this paper, we propose a novel system for iris recognition composed of image preprocessing including (segmentation, normalization, eyelashes and eyelids detection, enhancement), features extraction and classifier design. Iris feature extraction is based on using second order gradient images operator that will be robust against the variations may occur in iris's contrast or illumination because of lightening differences and camera changes. The low order norms of gradient components are used to establish the feature vector. The experimental results indicated that the efficiency of our proposed method when tested on the CASIA v1 and CASIA v4-Interival image database is promising, it achieves nearly perfect high recognition rate.