Generalized Contact Lens Iris Presentation Attack Detection

Abstract

The high accuracy of iris recognition for person identification has led to its deployment for a variety of applications ranging from border access to mobile unlocking to digital payment. In addition, the commercial success of mobile devices for iris image acquisition enables the easy acquisition of iris images both in an indoor controlled environment as well as an uncontrolled outdoor environment. At the same time, iris recognition systems can easily be attacked using wearable contact lenses. In the literature, several contact lens detection algorithms are proposed; however, the significant drawback is the generalizability under unseen testing domain images. In this research, a novel 3D contact lens iris presentation attack detection algorithm is developed and extensive experiments are performed. The experiments are performed using multiple challenging iris presentation attack databases including the IIITD and LivDet. For the evaluation, we have utilized the experimental protocols, which reflect in-the-wild settings for 3D contact lens iris presentation attack detection where the images belong to both controlled and adverse imaging conditions. The comparison with several state-of-the-art algorithms establishes the effectiveness of the proposed algorithm.