An Inclusive AI-Based Game for LIBRAS Learning Developed Through University Extension

• Italo Firmino da Silva Universidade Federal de Santa Catarina (UFSC)
• João José Sebastião Universidade Federal de Santa Catarina (UFSC)
• Ruan Pablo da Silva Soares Universidade Federal de Santa Catarina (UFSC)
• Beatriz Schuelter Tartare Universidade Federal de Santa Catarina (UFSC)
• Gabriel Feltes dos Santos Universidade Federal de Santa Catarina (UFSC)
• Maria Eduarda Winkel de Mello Vianna Universidade Federal de Santa Catarina (UFSC)
• Sheila Filipe Pereira Oliveira Universidade Federal de Santa Catarina (UFSC)
• Talita Alves Borges Caneda Universidade Federal de Santa Catarina (UFSC)
• Alison R. Panisson Universidade Federal de Santa Catarina (UFSC)

DOI: https://doi.org/10.5753/sbsc.2026.20041

Resumo

This paper presents IRIS, a university extension project developed within a Computer Engineering program that explores the use of artificial intelligence in the development of educational and inclusive digital games. As part of the project, students design and implement games that apply AI techniques to socially relevant contexts. This paper focuses on one of the project outcomes: an inclusive game inspired by the traditional Hangman game aimed at supporting the learning of Brazilian Sign Language (LIBRAS). The game employs computer vision and artificial intelligence to recognize LIBRAS signs captured by a camera, enabling sign-based interaction instead of text input. The paper describes the main technical aspects of this game and the associated extension activities, highlighting the potential of AI-driven game development in Computer Engineering education and inclusive learning initiatives.

Palavras-chave: AI-Based Game, LIBRAS, University Extension

Referências

Alaghband, M., Maghroor, H. R., and Garibay, I. (2023). A survey on sign language literature. Machine Learning with Applications, 14:100504.

Brasil (2018). Lei geral de proteção de dados pessoais (lgpd) – lei nº 13.709. Brazilian General Data Protection Law.

Brito, C. C. d. et al. (2024). Gamificação: uso de estratégias de ensino/aprendizagem na educação de pessoas surdas.

Brito, L. F. (2010). Por uma gramática de línguas de sinais. TB - Edições Tempo Brasileiro, Rio de Janeiro, 2. ed. edition. Originalmente publicado em 1995.

CNE (2018). Resolução Nº 7, de 18 de dezembro de 2018: Estabelece as Diretrizes para a Extensão na Educação Superior Brasileira. Diário Oficial da União, Brasília, 19 de dezembro de 2018, Seção 1, pp. 49-50.

Filho, R. R., Bittencourt, L. F., Porter, B., and Costa, F. M. (2022). Exploiting the potential of the edge-cloud continuum with self-distributing systems. In 2022 IEEE/ACM 15th International Conference on Utility and Cloud Computing (UCC), pages 255–260.

Gimenez, A. M. N., de Oliveira Gavira, M., and Bonacelli, M. B. M. (2024). The three fundamental university missions: Brazilian challenges. International Higher Education, (120).

Gou, J. et al. (2021). Knowledge distillation: A survey. International Journal of Computer Vision, 129:1789–1819.

Hidayat, E. W. et al. (2015). Increasing vocabulary mastery of the seventh grade students through hangman game. Unpublished Thesis. Palu: Universitas Tadulako.

Hinton, G., Vinyals, O., and Dean, J. (2015). Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531. Accessed: 2026-02-03.

Jordan, M. I. and Mitchell, T. M. (2015). Machine learning: Trends, perspectives, and prospects. Science, 349(6245):255–260.

Lee, C. K., Ng, K. K., Chen, C.-H., Lau, H. C., Chung, S. Y., and Tsoi, T. (2021). American sign language recognition and training method with recurrent neural network. Expert Systems with Applications, 167:114403.

Li, H.-H. and Hsieh, C.-C. (2025). Dynamic hand gesture recognition using mediapipe and transformer. Engineering Proceedings, 108(1):22.

LIBRAS-Roboflow (2025). Alfabeto em libras. [link]. Acessado em 10 de setembro de 2025. Licença: CC BY 4.0. Alfabeto em LIBRAS com as letras que não apresentam movimento.

Lugaresi, C., Tang, J., Nash, H., McClanahan, C., Uboweja, E., Hays, M., Zhang, F., Chang, C.-L., Yong, M. G., Lee, J., Chang, W.-T., Hua, W., Georg, M., and Grundmann, M. (2019). Mediapipe: A framework for perceiving and processing reality. arXiv preprint arXiv:1906.08172.

Medronha, A., Lima, L., Claudio, J., Kupssinskü, L., and Barros, R. C. (2024). Lermo: A novel web game for ai-enhanced sign language recognition. The Thirty-Eighth AAAI Conference on Artificial Intelligence (AAAI-24), 38:23352–23359.

Morett, L. M. (2015). Lending a hand to signed language acquisition: Enactment and iconicity enhance sign recall in hearing adult american sign language learners. Journal of Cognitive Psychology, 27(3):251–276.

Munikasari, M., Sudarsono, S., and Riyanti, D. (2021). The effectiveness of using hangman game to strengthen young learners’vocabulary. Journal of English Education Program, 2(1).

Oliveira, D. d. S., Bernet, R., and Hoyos, D. d. M. (2024). The transformative integration of university extension and education in communities. Seven Editora, 576:82.

Papadimitriou, K., Potamianos, G., Sapountzaki, G., Goulas, T., Efthimiou, E., Fotinea, S.-E., and Maragos, P. (2025). Greek sign language recognition for an education platform. Universal Access in the Information Society, 24(1):51–68.

Rego, R. C., de Morais, L. M., and Almeida, W. M. (2025). Brazilian sign language recognition using deep learning based on fast fourier transform and kinematic features. IEEE Access, 13:202875–202892.

Ruiz, D. S., Olvera-López, J. A., and Olmos-Pineda, I. (2023). Word level sign language recognition via handcrafted features. IEEE Latin America Transactions, 21(7):839–848.

Santana, D. J., Batista, D. M., et al. (2022). A gamificação no processo de ensino-aprendizagem de libras com l1: vivências no campo de estágio.

Schultes, M.-T., Graf, D., Holzer, J., Schober, B., and Spiel, C. (2025). Implementation and evaluation of service learning at higher education institutions. Evaluation and Program Planning, 112:102622.

Silva, L. G. d. et al. (2023). Gamificação e o impacto no ensino-aprendizagem de libras para surdos e ouvintes.

Soukaina, C. M., Mohammed, M., and Mohamed, R. (2025). Geometric feature-based machine learning for efficient hand sign gesture recognition. Statistics, Optimization & Information Computing, 13(5):2027–2043.

Voulodimos, A. et al. (2018). Deep learning for computer vision: A brief review. Computational Intelligence and Neuroscience, 2018.