Synthesizing Iris Images using Generative Adversarial Networks: Survey and Comparative Analysis

TL;DR

This paper surveys GAN-based synthetic iris image generation, critically comparing methods for realism, identity uniqueness, and biometric utility in iris recognition and PAD. It analyzes datasets, evaluation metrics (FID, VeriEye rejection rate, ISO Quality), and experiments that assess how synthetic irides aid training and testing. The study finds that iWarpGAN and StyleGAN-3 deliver high realism, with iWarpGAN uniquely enabling fully synthetic identities, while synthetic data bolster PAD and cross-dataset iris recognition. The work highlights practical implications for privacy-preserving data sharing and robust biometric systems, and outlines future directions including fully synthetic ocular images, multi-spectrum synthesis, and diffusion-model approaches.

Abstract

Biometric systems based on iris recognition are currently being used in border control applications and mobile devices. However, research in iris recognition is stymied by various factors such as limited datasets of bonafide irides and presentation attack instruments; restricted intra-class variations; and privacy concerns. Some of these issues can be mitigated by the use of synthetic iris data. In this paper, we present a comprehensive review of state-of-the-art GAN-based synthetic iris image generation techniques, evaluating their strengths and limitations in producing realistic and useful iris images that can be used for both training and testing iris recognition systems and presentation attack detectors. In this regard, we first survey the various methods that have been used for synthetic iris generation and specifically consider generators based on StyleGAN, RaSGAN, CIT-GAN, iWarpGAN, StarGAN, etc. We then analyze the images generated by these models for realism, uniqueness, and biometric utility. This comprehensive analysis highlights the pros and cons of various GANs in the context of developing robust iris matchers and presentation attack detectors.

Figures (17)

• Figure 1: Examples of bonafide irides (green box) and synthetic iris images generated using RaSGAN (red box) yadav2019.
• Figure 2: Examples of synthetically generated iris images using different methods. (i) and (ii) use Texture-based non-deep learning methods from zhou2016 and shah2006. On the other hand, (iii) and (iv) use GAN based methods from yadav2019 and kohli2017, respectively. Former models tasked with producing synthetic biometric samples strive to emulate the distribution of real human biometric data, which inherently ties them to the variability and scope of the training datasets. This can lead to challenges in replicating the intricate variations found in real biometric traits, often yielding a synthetic dataset with a narrow range of diversity. Additionally, certain models may fall short in delivering high-quality and lifelike representations. Nonetheless, Generative Adversarial Networks (GANs) have marked a significant advancement in crafting synthetic images that closely resemble real ones. Yet, these images often bear a strong similarity to the training data that comprises actual human images, meaning that they lack distinctiveness in their identities. Moreover, some of these techniques do not incorporate enough intra-class variation, failing to capture the extensive spectrum of natural differences present in authentic biometric data across real-world settings.
• Figure 3: Some more examples of synthetic irides that are generated using different Generative Adversarial Networks (GANs) for partially and fully synthetic iris images.
• Figure 4: Some examples of real bonafide and PA iris images from MSU-Iris-PA01 yadav2019: (a) bonafide samples and (b) presentation attacks: (i) artificial eye, (ii) & (iii) printed eye, (iv) Kindle display and (v) cosmetic contact lens. yadav2019yadav2020.
• Figure 5: Some examples of partially-synthetic iris PAs (a: Printed eyes, b: artificial eyes and c: cosmetic contact lens) generated using CIT-GAN yadav2023.