Enhancement of detection accuracy for preventing iris presentation attack

Abstract

A system that recognizes the iris is susceptible to presentation attacks (PAs), in which a malicious party shows artefacts such as printed eyeballs, patterned contact lenses, or cosmetics to obscure their personal identity or manipulate someone else’s identity. In this study, we suggest the dual channel DenseNet presentation attack detection (DC-DenseNetPAD), an iris PA detector based on convolutional neural network architecture that is dependable and effective and is known as DenseNet. It displays generalizability across PA datasets, sensors, and artifacts. The efficiency of the suggested iris PA detection technique has been supported by tests performed on a popular dataset which is openly accessible (LivDet-2017 and LivDet-2015). The proposed technique outperforms state-of-the-art techniques with a true detection rate of 99.16% on LivDet-2017 and 98.40% on LivDet-2015. It is an improvement over the existing techniques using the LivDet-2017 dataset. We employ Grad-CAM as well as t-SNE plots to visualize intermediate feature distributions and fixation heatmaps in order to demonstrate how well DC-DenseNetPAD performs.