When Humans Judge Irises: Pupil Size Normalization as an Aid and Synthetic Irises as a Challenge

2026-01-11

arXiv.org

AI Summary

This study addresses the impact of pupil size variation and high-fidelity synthetic irises on human experts’ accuracy in forensic iris comparison. It presents the first systematic evaluation of pupil size normalization for improving human performance in iris verification, proposing an identity-preserving image translation model based on an autoencoder that integrates both linear and nonlinear methods to align pupil sizes and generate high-quality synthetic same-eye iris images. Experimental results demonstrate that the proposed normalization strategy significantly enhances human verification accuracy. Furthermore, while human examiners can effectively distinguish between real and synthetic images from different eyes, they exhibit notable judgment bias when comparing real irises against high-fidelity synthetic counterparts from the same eye.

Technology Category

• Computer Vision: Bias, Fairness & Privacy
• Humans and AI: Interaction Techniques and Devices
• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Security and Privacy: Large-scale security measurements
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

Iris recognition is a mature biometric technology offering remarkable precision and speed, and allowing for large-scale deployments to populations exceeding a billion enrolled users (e.g., AADHAAR in India). However, in forensic applications, a human expert may be needed to review and confirm a positive identification before an iris matching result can be presented as evidence in court, especially in cases where processed samples are degraded (e.g., in post-mortem cases) or where there is a need to judge whether the sample is authentic, rather than a result of a presentation attack. 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. We offer data and human judgments along with this paper to allow full replicability of this study and future works.

Problem

• iris recognition
• human verification
• pupil size variation
• synthetic irises
• forensic biometrics

Innovation

• pupil size normalization
• synthetic iris images
• human iris verification
• identity-preserving image translation
• biometric forensics