GHCLNet: A Generalized Hierarchically tuned Contact Lens detection Network

10/14/2017
by   Avantika Singh, et al.
0

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.

READ FULL TEXT

page 3

page 8

research
11/18/2018

Iris Presentation Attack Detection Based on Photometric Stereo Features

We propose a new iris presentation attack detection method using three-d...
research
10/25/2020

Generalized Iris Presentation Attack Detection Algorithm under Cross-Database Settings

Presentation attacks are posing major challenges to most of the biometri...
research
03/14/2023

Eliciting Latent Predictions from Transformers with the Tuned Lens

We analyze transformers from the perspective of iterative inference, see...
research
07/02/2021

LensID: A CNN-RNN-Based Framework Towards Lens Irregularity Detection in Cataract Surgery Videos

A critical complication after cataract surgery is the dislocation of the...
research
02/06/2014

Multispectral Palmprint Encoding and Recognition

Palmprints are emerging as a new entity in multi-modal biometrics for hu...
research
05/09/2020

Domain-specific loss design for unsupervised physical training: A new approach to modeling medical ML solutions

Today, cataract surgery is the most frequently performed ophthalmic surg...
research
12/20/2021

State-of-the-Art in Smart Contact Lenses for Human Machine Interaction

Contact lenses have traditionally been used for vision correction applic...

Please sign up or login with your details

Forgot password? Click here to reset