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

TL;DR

This paper reviews and compares state-of-the-art GAN-based methods for synthetic iris image generation, assessing their realism, diversity, and utility for biometric systems and attack detection.

Contribution

It provides a comprehensive survey and analysis of various GAN models for iris synthesis, highlighting their strengths and limitations for biometric applications.

Findings

StyleGAN and StarGAN produce highly realistic iris images

Different GANs vary in their ability to generate diverse iris patterns

Synthetic iris data can improve training for recognition and attack detection

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.