Generating a Biometrically Unique and Realistic Iris Database

2025-03-15

AI Summary

To address the scarcity of real iris data in biometric research—due to privacy and ethical constraints—this paper introduces the first synthetic colored iris image generation method based on open-source diffusion models. We propose a conditional diffusion framework that jointly models iris textural patterns and full-spectrum pigment distribution, producing anonymized images with high visual fidelity and biometric uniqueness. The synthesized images yield no matches in mainstream iris recognition systems and comprehensively cover natural iris pigment phenotypes, empirically satisfying both unlinkability (i.e., inability to re-identify individuals) and realism. To our knowledge, this is the first systematic application of diffusion models to iris synthesis. Our approach provides a reproducible, privacy-compliant, and high-fidelity data alternative for sensitive biometric research, enabling rigorous algorithm development and evaluation without compromising subject confidentiality.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Privacy
• Humans and AI: AI for Accessibility

Application Category

• Security and Privacy: Data transparency and provenance
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Web Mining and Content Analysis: Web data generation and simulation

Abstract

The use of the iris as a biometric identifier has increased dramatically over the last 30 years, prompting privacy and security concerns about the use of iris images in research. It can be difficult to acquire iris image databases due to ethical concerns, and this can be a barrier for those performing biometrics research. In this paper, we describe and show how to create a database of realistic, biometrically unidentifiable colored iris images by training a diffusion model within an open-source diffusion framework. Not only were we able to verify that our model is capable of creating iris textures that are biometrically unique from the training data, but we were also able to verify that our model output creates a full distribution of realistic iris pigmentations. We highlight the fact that the utility of diffusion networks to achieve these criteria with relative ease, warrants additional research in its use within the context of iris database generation and presentation attack security.

Problem

• Creating a realistic, biometrically unidentifiable iris image database.
• Overcoming ethical barriers in acquiring iris image databases for research.
• Utilizing diffusion models for generating unique iris textures and pigmentations.

Innovation

• Uses diffusion model for iris image generation
• Creates biometrically unique, realistic iris textures
• Ensures full distribution of iris pigmentations