Pan-Art Pedagogy. Theory & Practice Philology. Theory & Practice Manuscript

Archive of Scientific Articles

ISSUE:    Pan-Art. 2026. Volume 6. Issue 4
COLLECTION:    Architecture and Design

All issues

License Agreement on scientific materials use.

The application of generative neural networks in the inclusive design of web infographics for users with visual impairments

Danila Denisovich Likhovtsov
The Kosygin State University of Russia, Moscow

Nadezhda Alekseevna Korobtseva
The Kosygin State University of Russia, Moscow
Submitted: October 12, 2026
Abstract. The aim of the study is to determine the possibilities and prospects of using generative neural networks in the inclusive design of web infographics for users with visual impairments. The article examines the principles of inclusive design, taking into account the requirements of WCAG 2.1 – specifically, Success Criteria 1.3.1, 1.4.3, and 1.4.11 (W3C) – and GOST R 52872-2019. The work also provides recommendations and describes the risks and prospects associated with the use of generative neural networks. The experiment was conducted on 30 infographics generated with and without an inclusive prompt. The results were evaluated according to WCAG criteria. The study’s scientific novelty lies in identifying the limited effect of an inclusive prompt on the accessibility parameters of web infographics created using generative neural networks. The results demonstrate that generative neural networks provide high text-to-background contrast but do not guarantee compliance with WCAG requirements for icon contrast in cases involving color vision deficiency. The use of an inclusive prompt does not provide a consistent advantage across all accessibility criteria; in some cases, a deterioration in performance was observed. This finding supports the need for a designer to participate in evaluating the generated results.
Key words and phrases:
инклюзивный дизайн веб-инфографики
нейросети для веб-инфографики
пользователи с нарушениями зрения
принципы инклюзивного дизайна веб-инфографики
inclusive design of web infographics
neural networks for web infographics
users with visual impairments
principles of inclusive design of web infographics
Reader Open the whole article in PDF format. Free PDF-files viewer can be downloaded here.
References:
  1. Волкова А. А. Влияние методов инклюзивного проектирования цифровых интерфейсов на пользователя // Будущее экономики в эпоху технологических изменений: роль искусственного интеллекта и инноваций. Актуальные практики бизнес-трансформации: технологические и управленческие аспекты: сборник тезисов докладов XIV Конгресса молодых ученых (г. Санкт-Петербург, 07-11 апреля 2025 г.). СПб.: Университет Информационных технологий, механики и оптики, 2025.
  2. Anschütz M., Sylaj T., Groh G. Images Speak Volumes: User-Centric Assessment of Image Generation for Accessible Communication // Proceedings of the Third Workshop on Text Simplification, Accessibility and Readability (TSAR 2024) (Miami, November, 2024). Miami: Association for Computational Linguistics, 2024. https://doi.org/10.18653/v1/2024.tsar-1.4
  3. Campoverde-Molina M., Lujan-Mora S. Artificial intelligence in web accessibility: A systematic mapping study // Computer Standards & Interfaces. 2026. Т. 96. Art. 104248.
  4. Chandrasekera T., Hosseini Z., Perera U. Can artificial intelligence support creativity in early design processes? // International Journal of Architectural Computing. 2024. Vol. 23. No. 1.
  5. Gurita A. E., Vatavu R. D. Insights and Implications of Evaluating Accessibility Compliance in AI-Generated Web Interfaces // Companion Proceedings of the ACM Web Conference 2025 (Sydney, April, 28 – May 2, 2025). N. Y.: Association of Computing Machinery, 2025. https://doi.org/10.1145/3701716.3715552
  6. Gutflaish E., Kachlon E., Zisman H., Hacham T., Sarid N., Visheratin A., Huberman S., Davidi G., Bukchin G., Goldberg K., Mokady R. Generating an Image From 1,000 Words: Enhancing Text-to-Image With Structured Captions // arXiv. 2025. November 10. https://doi.org/10.48550/arXiv.2511.06876
  7. Miranda-Pena C., Reeson A., Paris C., Poon J., Kummerfeld J. K. Do LLMs Generate Creative and Visually Accessible Data Visualisations? // Proceedings of the 22nd Annual Workshop of the Australasian Language Technology Association (Canerra, December, 02-04, 2024). Canberra: Association for Computational Linguistics, 2024.
  8. Moreno Martinez C., Piorno J. R., Escribano Otero J. J., Guijarro Mata-Garcia M. Responsive inclusive design (RiD): a new model for inclusive software development // Universal Access in the Information Society. 2023. Vol. 22.
  9. Shen Y., Zhang H., Shen Y., Wang L., Shi C., Du S., Tao Y. AltGen: AI-Driven Alt Text Generation for Enhancing EPUB Accessibility // AICI 25: Proceedings of the 2025 International Conference on Artificial Intelligence and Computational Intelligence (Kuala Lumpur, February 14-16, 2025). N. Y.: Association for Computing Machinery, 2025. https:///doi.org/10.1145/3730436.3730449
  10. Srivatsan N., Samaniego S., Florez O., Berg-Kirkpatrick T. Alt-Text with Context: Improving Accessibility for Images on Twitter // Proceeding of the International Conference on Learning Representations (ICLR) (Vienna, May 7, 2024). Vienna, 2024. https://arxiv.org/html/2305.14779v3
  11. Zhang T., Wang X., Lu Li, Tai Z., Chi J., Tian J., He H., Wang S. STRICT: Stress Test of Rendering Images Containing Text // Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing (Suzhou, 2025). Suzhou: Association for Computational Linguistics, 2025. https://doi.org/10.18653/v1/2025.emnlp-main.1070
All issues


© 2006-2025 GRAMOTA Publishing