mlsanityData to 14 Oct 2026

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

arXiv 2404.17105 ↗First posted 26 Apr 2024cs.CVcited by 5

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 34 of its 97 references that are in the map. First posted on arXiv 26 Apr 2024.

Builds on

34 of 97 references.

References · 34

  1. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
  2. 2016Improved Techniques for Training GANscited by 2,970
  3. 2020Training Generative Adversarial Networks with Limited Datacited by 1,186
  4. 2021Alias-Free Generative Adversarial Networkscited by 1,184
  5. 2019StarGAN v2: Diverse Image Synthesis for Multiple Domainscited by 1,098
  6. 2017StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translationcited by 1,039
  7. 2021Multi-attentional Deepfake Detectioncited by 341
  8. 2018The relativistic discriminator: a key element missing from standard GANcited by 238
  9. 2022Diffusion-GAN: Training GANs with Diffusioncited by 205
  10. 2016View Synthesis by Appearance Flowcited by 172
  11. 2018IntroVAE: Introspective Variational Autoencoders for Photographic Image Synthesiscited by 85
  12. 2023GANDiffFace: Controllable Generation of Synthetic Datasets for Face Recognition with Realistic Variationscited by 49
22 more
  1. 2022PrintsGAN: Synthetic Fingerprint Generatorcited by 30
  2. 2022Synthetic Data in Human Analysis: A Surveycited by 28
  3. 2023Identity-driven Three-Player Generative Adversarial Network for Synthetic-based Face Recognitioncited by 27
  4. 2020D-NetPAD: An Explainable and Interpretable Iris Presentation Attack Detectorcited by 26
  5. 2018Domain-Specific Human-Inspired Binarized Statistical Image Features for Iris Recognitioncited by 24
  6. 2014Deep Representations for Iris, Face, and Fingerprint Spoofing Detectioncited by 21
  7. 2017Synthetic Iris Presentation Attack using iDCGANcited by 17
  8. 2022SpoofGAN: Synthetic Fingerprint Spoof Imagescited by 17
  9. 2023SynthASpoof: Developing Face Presentation Attack Detection Based on Privacy-friendly Synthetic Datacited by 17
  10. 2020CIT-GAN: Cyclic Image Translation Generative Adversarial Network With Application in Iris Presentation Attack Detectioncited by 16
  11. 2019Some Research Problems in Biometrics: The Future Beckonscited by 13
  12. 2023Iris Liveness Detection Competition (LivDet-Iris) -- The 2023 Editioncited by 13
  13. 2022Synthetic Latent Fingerprint Generatorcited by 11
  14. 2018Iris-GAN: Learning to Generate Realistic Iris Images Using Convolutional GANcited by 9
  15. 2019DeepIris: Iris Recognition Using A Deep Learning Approachcited by 8
  16. 2022Controllable 3D Generative Adversarial Face Model via Disentangling Shape and Appearancecited by 8
  17. 2020Generalized Iris Presentation Attack Detection Algorithm under Cross-Database Settingscited by 7
  18. 2018Improving Face Detection Performance with 3D-Rendered Synthetic Datacited by 6
  19. 2020On Loss Functions and Recurrency Training for GAN-based Speech Enhancement Systemscited by 6
  20. 2023Forensic Iris Image Synthesiscited by 5
  21. 2023iWarpGAN: Disentangling Identity and Style to Generate Synthetic Iris Imagescited by 4
  22. 2023StyleGAN3: Generative Networks for Improving the Equivariance of Translation and Rotationcited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 3; 2026: 1.

5 papers.

  1. 2025Synthetic Iris Image Databases and Identity Leakage: Risks and Mitigation Strategiescited by 1
  2. 2025DOOMGAN:High-Fidelity Dynamic Identity Obfuscation Ocular Generative Morphingcited by 1
  3. 2024A Unified Framework for Iris Anti-Spoofing: Introducing Iris Anti-Spoofing Cross-Domain-Testing Protocol and Masked-MoE Methodcited by 0
  4. 2025Gradient-Guided Exploration of Generative Model's Latent Space for Controlled Iris Image Augmentationscited by 0
  5. 2026Generalist Multimodal LLMs Gain Biometric Expertise via Human Saliencecited by 0