Deep learning for iris recognition: A survey

K Nguyen, H Proença, F Alonso-Fernandez - ACM Computing Surveys, 2024 - dl.acm.org
In this survey, we provide a comprehensive review of more than 200 articles, technical
reports, and GitHub repositories published over the last 10 years on the recent …

CYBORG: Blending human saliency into the loss improves deep learning-based synthetic face detection

A Boyd, P Tinsley, KW Bowyer… - Proceedings of the …, 2023 - openaccess.thecvf.com
Can deep learning models achieve greater generalization if their training is guided by
reference to human perceptual abilities? And how can we implement this in a practical …

The value of ai guidance in human examination of synthetically-generated faces

A Boyd, P Tinsley, K Bowyer, A Czajka - Proceedings of the AAAI …, 2023 - ojs.aaai.org
Face image synthesis has progressed beyond the point at which humans can effectively
distinguish authentic faces from synthetically-generated ones. Recently developed synthetic …

Human-aided saliency maps improve generalization of deep learning

A Boyd, KW Bowyer, A Czajka - Proceedings of the IEEE …, 2022 - openaccess.thecvf.com
Deep learning has driven remarkable accuracy increases in many computer vision
problems. One ongoing challenge is how to achieve the greatest accuracy in cases where …

Human saliency-driven patch-based matching for interpretable post-mortem iris recognition

A Boyd, D Moreira, A Kuehlkamp… - Proceedings of the …, 2023 - openaccess.thecvf.com
Forensic iris recognition, as opposed to live iris recognition, is an emerging research area
that leverages the discriminative power of iris biometrics to aid human examiners in their …

Cyborg: Blending human saliency into the loss improves deep learning

A Boyd, P Tinsley, K Bowyer, A Czajka - arxiv preprint arxiv:2112.00686, 2021 - arxiv.org
Can deep learning models achieve greater generalization if their training is guided by
reference to human perceptual abilities? And how can we implement this in a practical …

Misclassifications of contact lens iris PAD algorithms: Is it gender bias or environmental conditions?

A Agarwal, N Ratha, A Noore… - Proceedings of the …, 2023 - openaccess.thecvf.com
One of the critical steps in biometrics pipeline is detection of presentation attacks, a physical
adversary. Several presentation (adversary) attack detection (PAD) algorithms, including iris …

Model focus improves performance of deep learning-based synthetic face detectors

JC Piland, A Czajka, C Sweet - IEEE Access, 2023 - ieeexplore.ieee.org
Deep learning-based models generalize better to unknown data samples after being guided
“where to look” by incorporating human perception into training strategies. We made an …

Deformirisnet: An identity-preserving model of iris texture deformation

SK Khan, P Tinsley, A Czajka - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
Nonlinear iris texture deformations due to pupil size variations are one of the main factors
responsible for within-class variance of genuine comparison scores in iris recognition. In …

Training Better Deep Learning Models Using Human Saliency

A Boyd, P Tinsley, KW Bowyer, A Czajka - arxiv preprint arxiv:2410.16190, 2024 - arxiv.org
This work explores how human judgement about salient regions of an image can be
introduced into deep convolutional neural network (DCNN) training. Traditionally, training of …