July 2022
·
175 Reads
·
4 Citations
This paper presents an iris recognition framework to recognize irises from distantly acquired face images using image gradient-based feature extraction and K-Nearest Neighbor with various distance classifiers. The work herein applies the gradient local auto-correlation descriptor to extract discriminative features from the iris images and to reduce feature dimensionality by optimizing some parameters. Several distance metrics are applied in the iris classification stage to reduce computational complexity and build the classification models. The proposed framework effectively handles the noisy artefacts, rotation, occlusion, and illumination variation challenges. The experiments are carried out on a publicly accessible CASIA-V4 distance database to ascertain the effectiveness of distant iris recognition and to compare the efficacy of several existing distant classifiers. The experimental results justify that distance metrics influence the recognition outcomes of the classifier significantly, and the recognition performance of the Correlation distance metric is better than the other distance classifiers for iris gradient features.