Синтез изображений радужной оболочки глаза с использованием генеративно-состязательных сетей

Авторы: Коннова Н.С., Мартынов С.М.
Опубликовано в выпуске: #5(100)/2025
DOI:
Раздел: Информатика, вычислительная техника и управление | Рубрика: Информационные технологии. Компьютерные технологии. Теория вычислительных машин и систем
Ключевые слова: генеративно-состязательная сеть, синтетические радужки глаза, глубокое обучение, биометрические системы, системы распознавания, распознавание радужной оболочки глаза
Опубликовано: 17.10.2025

В работе рассмотрены актуальные проблемы, связанные с разработкой и тестированием систем распознавания радужной оболочки глаза. Также исследованы проблемы, связанные с ограниченными наборами данных для обучения данных систем. В качестве возможного решения проведен обзор современных методов генерации синтетических изображений радужной оболочки глаза на основе GAN, анализ их сильных сторон и ограничений в создании реалистичных изображений. Представлены различные методы, применяемые для синтетической генерации радужной оболочки глаза, в частности, рассмотрены модели на основе StyleGAN, RaSGAN, CIT-GAN, iWarpGAN, StarGAN. Изображения, сгенерированные этими моделями, проанализированы на предмет реалистичности. Результаты исследования могут быть использованы при разработке, обучении и тестировании систем распознавания радужной оболочки глаза.

Литература

[1] Vatsa N.M., Singh R. Ocular biometrics: A survey of modalities and fusion approaches. Information Fusion, 2015, vol. 26, pp. 1–35.

[2] Gent E. A cryptocurrency for the masses or a universal ID? Worldcoin aims to scan all the world

[3] Perala. Princeton identity tech powers galaxy s8 iris scanning. URL: https://mobileidworld.com/princeton-identity-galaxy-s8-iris-003312 (accessed 16.11.2024).

[4] Ross A., Banerjee S., Chen C., Chowdhury A., Mirjalili V., Sharma R., Swearingen T., Yadav S. Some research problems in biometrics: The future beckons. Proc. of 12th IAPR International Conference on Biometrics (ICB). Crete, Greece, 2019, pp. 1–8.

[5] Voigt P., Von dem Bussche A. The EU General Data Protection Regulation (GDPR). A Practical Guide. Cham, Springer International Publishing, 2017, chapters 10 (3152676). https://doi.org/10.1007/978-3-031-62328-8

[6] Wyzykowski A.B.V., Jain A.K. Synthetic latent fingerprint generator. Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2023, pp. 971–980.

[7] Zhu T., Chen J., Zhu R., Gupta G. StyleGAN3: Generative networks for improving the equivariance of translation and rotation. arXiv preprint arXiv:2307.03898, 2023. https://doi.org/10.48550/arXiv.2307.03898

[8] Fang M., Huber M., Damer N. SynthASpoof: Developing face presentation attack detection based on privacy-friendly synthetic data. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 1061–1070.

[9] Taherkhani F., Rai A., Gao Q., Srivastava S., Chen X., de la Torre F., Song S., Prakash A., Kim D. Controllable 3D generative adversarial face model via disentangling shape and appearance. Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2022, pp. 826–836.

[10] Dankar F.K., Ibrahim M. Fake it till you make it: Guidelines for effective synthetic data generation. Applied Sciences, 2021, vol. 11 (5), art. no. 2158.

[11] Drozdowski P., Rathgeb C., Busch C. Sic-gen: A synthetic iris-code generator. IEEE International Conference of the Biometrics Special Interest Group (BIOSIG). Darmstadt, Germany, IEEE, 2017, pp. 1–6. https://doi.org/10.23919/BIOSIG.2017.8053520

[12] Khade S., Ahirrao S., Phansalkar Shr., Kotecha K. et al. Iris Liveness Detection for Biometric Authentication: A Systematic Literature Review and Future Directions. Invention, 2021, vol. 6.65. https://doi.org/10.3390/inventions6040065

[13] Joshi I., Grimmer M., Rathgeb C., Busch C., Bremond F., Dantcheva A. Synthetic data in human analysis: A survey. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024, vol. 46 (7), pp. 4957–4976.

[14] Grosz S.A., Jain A.K. SpoofGAN: Synthetic fingerprint spoof images. IEEE Transactions on Information Forensics and Security, 2022, vol. 18, pp. 730–743.

[15] Daugman J. New methods in iris recognition. IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 2007, vol. 37 (5), pp. 1167–1175.

[16] Nguyen K., Fookes C., Ross A., Sridharan S. Iris recognition with off-the-shelf CNN features: A deep learning perspective. IEEE Access, 2017, vol. 6, pp. 18848–18855.

[17] Shah S., Ross A. Generating synthetic irises by feature agglomeration. IEEE International Conference on Image Processing. Atlanta, 2006, pp. 317–320.

[18] Wood E., Baltrusaitis T., Morency L.P., Robinson P., Bulling A. A 3D morphable model of the eye region. Optimization, 2016, vol. 1:0, pp. 1–17.

[19] Cardoso L., Barbosa A., Silva F., Pinheiro A.M., Proenca H. Iris biometrics: Synthesis of degraded ocular images. IEEE Transactions on Information Forensics and Security, 2013, vol. 8 (7), pp. 1115–1125. https://doi.org/10.1109/TIFS.2013.2262942

[20] Bamoriya P., Siddhad G., Kaur H., Khanna P., Ojha A. DSB-GAN: Generation of deep learning based synthetic biometric data. Displays, 2022, vol. 74, art. no. 102267.

[21] Bhuiyan R.A., Czajka A. Forensic Iris Image Synthesis. IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW). Waikoloa, HI, USA, IEEE, 2014, pp. 1015–1023.

[22] Yadav S., Chen C., Ross A. Synthesizing iris images using rasgan with application in presentation attack detection. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops. Long Beach, USA, 2019, pp. 10–20.

[23] Choi Y., Uh Y., Yoo J., Ha J.-W. StarGAN v2: Diverse image synthesis for multiple domains. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2020, arXiv:1912.01865v2.

[24] Karras T., Laine S., Aila T. A style-based generator architecture for generative adversarial networks. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 4401–4410.

[25] Choi Y., Choi M., Kim M., Ha J.-W., Kim S., Choo J. StarGAN: Unified generative adversarial networks for multi-domain image-to-image translation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 8789–8797.

[26] Yadav S., Ross A. CIT-GAN: Cyclic image translation generative adversarial network with application in iris presentation attack detection. Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2021, pp. 2412–2421.

[27] Karras T., Aittala M., Laine S., Harkonen E., Hellsten J., Lehtinen J., Aila T. Alias-free generative adversarial networks. Advances in Neural Information Processing Systems (NIPS), 2021, pp. 852–863.

[28] Yadav S., Ross A. iWarpGAN: Disentangling identity and style to generate synthetic iris images. IEEE International Joint Conference on Biometrics (IJCB), 2023, pp. 1–10.

[29] Salimans T., Goodfellow I., Zaremba W., Cheung V., Radford A., Chen X. Improved techniques for training GANs. Advances in Neural Information Processing Systems (NIPS), 2016, pp. 2234–2242.

[30] Yadav S., Ross A. Synthesizing Iris Images using Generative Adversarial Networks: Survey and Comparative Analysis. arXiv:2404.17105v2, 2024, pp. 1–25.

[31] ISO/IEC 29794-6. Information Technology – Biometric sample quality – Part 6: Iris image data. 2015.