GHCLNet: A Generalized Hierarchically tuned Contact Lens detection Network

TL;DR

GHCLNet is a novel deep learning architecture inspired by ResNet-50 that accurately detects contact lenses in iris images without pre-processing, improving biometric security by distinguishing no lens, soft lens, and cosmetic lens.

Contribution

The paper introduces GHCLNet, a hierarchical deep learning model that detects contact lenses directly from raw iris images, eliminating the need for pre-processing or segmentation.

Findings

Outperforms state-of-the-art lens detection algorithms

Works effectively on multiple publicly available datasets

Generalizes well across different iris image datasets

Abstract

Iris serves as one of the best biometric modality owing to its complex, unique and stable structure. However, it can still be spoofed using fabricated eyeballs and contact lens. Accurate identification of contact lens is must for reliable performance of any biometric authentication system based on this modality. In this paper, we present a novel approach for detecting contact lens using a Generalized Hierarchically tuned Contact Lens detection Network (GHCLNet) . We have proposed hierarchical architecture for three class oculus classification namely: no lens, soft lens and cosmetic lens. Our network architecture is inspired by ResNet-50 model. This network works on raw input iris images without any pre-processing and segmentation requirement and this is one of its prodigious strength. We have performed extensive experimentation on two publicly available data-sets namely: 1)IIIT-D 2)ND and on IIT-K data-set (not publicly available) to ensure the generalizability of our network. The proposed architecture results are quite promising and outperforms the available state-of-the-art lens detection algorithms.