Enhancing human iris recognition performance in unconstrained environment using ensemble of convolutional and residual deep neural network models

Abstract

Despite the prominent advancements in iris recognition, unconstrained image acquisition through heterogeneous sensors has been a major obstacle in applying it for large-scale applications. In recent years, deep convolutional networks have achieved remarkable performance in the field of computer vision and have been employed in iris applications. In this study, three distinct models based on the ensemble of convolutional and residual blocks are proposed to enrich heterogeneous (cross-sensor) iris recognition. In order to analyze their quantitative performances, extensive experiments are carried out on two publicly available iris databases, ND-iris-0405 dataset and ND-CrossSensor-Iris-2013 dataset. Further, the final model has been scrutinized based on the least error rate and then fused using score-level fusion with two preeminent feature extraction methods, i.e., scale-invariant feature transform and binarized statistical information features. The resultant model is examined for cross-sensor iris recognition and reported the top two error rates as 1.01% and 1.12%. It infers that the proposed approach constitutes vital discerning iris features and can recognize that the micro-patterns exist inside the iris region. Furthermore, a comparative study is carried out with the state of the art, where the proposed approach obtains significantly improved performance.