Skip to content

Official repository for the paper: "When Humans Judge Irises: Pupil Size Normalization as an Aid and Synthetic Irises as a Challenge"

Notifications You must be signed in to change notification settings

CVRL/Human-Iris-Judge

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

12 Commits
 
 
 
 
 
 

Repository files navigation

Human Iris Judge

Official GitHub repository for the paper: Mahsa Mitcheff and Adam Czajka, "When Humans Judge Irises: Pupil Size Normalization as an Aid and Synthetic Irises as a Challenge," IEEE Workshop on Manipulation, Generative, Adversarial and Presentation Attacks In Biometrics (MGA-PAD), Tucson, AZ, March 7, 2026 (ArXiv | IEEEXplore)

synthetic_samples ⬆ Sample synthetic image pairs used in a short training phase before the actual experiment. Features labeled A (yellow) and B (green) indicate iris regions relevant for decision-making, whereas the highlighted areas illustrate regions that should be disregarded during evaluation.

Table of contents

Abstract

This paper presents a study that examines human performance in iris verification in two controlled scenarios: (a) under varying pupil sizes, with and without a linear/nonlinear alignment of the pupil size between compared images, and (b) when both genuine and impostor iris image pairs are synthetically generated. The results demonstrate that pupil size normalization carried out by a modern autoencoder-based identity-preserving image-to-image translation model significantly improves verification accuracy. Participants were also able to determine whether iris pairs corresponded to the same or different eyes when both images were either authentic or synthetic. However, accuracy declined when subjects were comparing authentic irises against high-quality, same-eye synthetic counterparts. These findings (a) demonstrate the importance of pupil-size alignment for iris matching tasks in which humans are involved, and (b) indicate that despite the high fidelity of modern generative models, same-eye synthetic iris images are more often judged by humans as different-eye images, compared to same-eye authentic image pairs.

Dataset of Human Judgements

Instructions on how to request a copy of the dataset will be added to the CVRL webpage before the Workshop presentation in March 2026.

Citation

If you find this work useful in your research, please cite the following paper:

@inproceedings{Mitcheff_MGAPAD_2026,
      title={When Humans Judge Irises: Pupil Size Normalization as an Aid and Synthetic Irises as a Challenge}, 
      author={Mahsa Mitcheff and Adam Czajka},
      year={2026},
      booktitle={IEEE WACV Workshop on Manipulation, Generative, Adversarial and Presentation Attacks In Biometrics (MGA-PAD), Tucson, AZ},
}

About

Official repository for the paper: "When Humans Judge Irises: Pupil Size Normalization as an Aid and Synthetic Irises as a Challenge"

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published