This paper presents a novel approach to the recognition of Latin alphabet characters in Uzbek Sign Language (UzSL). The primary aim is to develop an effective algorithm and mathematical model that accurately identifies and translates these characters, facilitating communication for individuals with hearing impairments. Our methodology involves capturing the precise positions of each finger joint to extract coordinate data and generating angle features from these coordinates. We utilize a deep learning framework, leveraging Convolutional Neural Networks (CNNs) to enhance the recognition accuracy. The proposed approach is validated through extensive experimentation, demonstrating superior performance in comparison to traditional methods. This study highlights the potential of advanced neural network techniques in improving sign language recognition systems, providing a robust tool for real-time communication support in the Uzbek context.

Uzbek sign language (UzSL), Latin alphabet recognition, neural network, convolutional neural networks (CNN), deep learning, sign language recognition, angle feature extraction.

World Health Organization. Safe Listening Devices And Systems: A Who‑Itu Standard; World Health Organization: Geneva, Switzerland, 2019; p. 10.

Japan Hearing Instruments Manufacturers Association. Japantrak 2022; Jhima: Tokyo, Japan, 2022; p. 99.

Jiang, S.; Sun, B.; Wang, L.; Bai, Y.; Li, K.; Fu, Y. Skeleton Aware Multi‑Modal Sign Language Recognition. In Proceedings Of The

2021 Conference On Computer Vision And Pattern Recognition (Cvpr), Nashville, Tn, Usa, 19–25 June 2021.

Hezhen, H.; Wengang, Z.; Houqiang, L. Hand‑Model‑Aware Sign Language Recognition. In Proceedings Of The 35th Aaai Conference On Artificial Intelligence, Virtual, 2–9 February 2021; Volume 35, Pp. 1558–1566.

Kayumov, O., Kayumova, N., Rayxona, A., & Madina, Y. L. (2023). The Strategic Significance Of Human Resource Management In Uzbekistan Enterprises On The Basis Of Artificial Intelligence. International Journal Of Contemporary Scientific And Technical Research, 268-272.

Turakulov, O. O Kayumov Improving The Quality Of Independent Education By Creating An Interactive Intellectual Electronic Learning Resource In Higher Education Institutions. International Journal Of Contemporary Scientific And Technical Research.

Kayumov, O., Sayfullayeva, I., & Rustamov, I. (2023, May). Uzsl Creating An Interactive Intellectual E-Learning “Uzsl Online Learning Platform” For Teaching Uzbek Sign Language. In International Scientific And Practical Conference On Algorithms And Current Problems Of Programming.

Kayumov O, Kayumova N, Xodjabekova D. OʻZbek Imo-Ishora Tilida Lotin Alifbosini Tanib Olishning Barmoq Boʻg‘Imi Va Bilak Koordinatalaridan Olingan Burchak Belgilari Asosidagi Modeli

Kayumov, O., & Kayumova, N. (2023). Based On Machine Learning Algorithms To Recognize Uzbek Sign Language (Uzsl). International Journal Of Contemporary Scientific And Technical Research, 1(2), 58-68.

Саидова, Х., Каюмов, О., & Каюмова, Н. (2024). Tasvirlarni Tanib Olish. Новый Узбекистан: Наука, Образование и Инновации, 1(1), 676-679.

XolboʻTayevich, T. O., Achilovich, K. O., & Rashitovna, K. N. (2022). OʻZbekistonda Raqamli Iqtisodiyot Sohasini Rivojlantirish Davrida Korxonaning Intelektual Resurslarini Boshqarish. International Journal Of Contemporary Scientific And Technical Research, 65-68.

Ahmad, A., Kayumov, O., & Kayumova, N. (2023). Artificial Intelligence In The Management Of Intellectual Resources Of Enterprises In The Conditions Of The Digital Economy In Uzbekistan. Scientific-Theoretical Journal Of International Education Research, 1(1), 106-116.