This paper discusses the problem of creating a multimodal dataset based on MediaPipe technology for automatic translation of Uzbek sign language into text and speech. Due to the multifaceted nature of sign language hand movements, facial expressions, body posture, and gaze direction the technical, linguistic, and ethical aspects of dataset preparation are analyzed. Using MediaPipe, key points of the hands, face, and body are extracted, and experiments are conducted with GRU, LSTM, and BiLSTM models. Comparative analysis demonstrates the efficiency and resource-saving capability of the GRU model, while LSTM and BiLSTM show advantages in processing complex sequences. Thus, the multimodal dataset developed in this study provides a reliable foundation for the development of real-time sign language recognition systems.
| Mualliflar | Джураев, Д.Б. |
|---|---|
| Jurnal | Рақамли технологияларнинг назарий ва амалий масалалари |
| Nashr sanasi | 2025-09-15 |
| Jild | 8 |
| Son | 3 |
| Betlar | 82-93 |
| Til | Rus |
| DOI | 10.62132/ijdt.v8i3.290 |
DOI: 10.62132/ijdt.v8i3.290 · Maqolaning asl sahifasi
жестовый язык, MediaPipe, мультимодальный датасет, RNN (GRU, LSTM, BiLSTM), компьютерное зрение, обработка естественного языка (NLP), искусственный интеллект, sign language, MediaPipe, multimodal dataset, RNN (GRU, LSTM, BiLSTM), computer vision, natural language processing (NLP), artificial intelligence
To effectively detect and prevent DDoS (Distributed Denial-of-Service) attacks, it is necessary to use various datasets. This article analyzes the most popular datasets for DDoS attack detection, including CIC-DDoS2019…
To study unsteady filtration and fluid displacement in multilayer porous systems, a self-similar solution has been obtained. From its form, it follows that by a special selection of parameters it is possible to ensure…
The article presents a theoretical and practical comparative analysis of four important methods related to feature extraction and dimensionality reduction: Fisher Discriminant Analysis (FDA), Canonical Correlation…
This article improves the mathematical model of the process of pollutant distribution in the atmospheric air taking into account their physical and mechanical properties - particle diameter, diffusion coefficient…
Drug development is a central topic at the intersection of structural biology, biochemistry, and medicine, associated with significant challenges such as high cost (billions of dollars), low success rates (less than…
Using the Duhamel-Neumann relationship and the equations of motion, the Saint-Venant compatibility conditions, are written as a system of six dynamic equations with respect to strains. It is shown that, unlike the…
This paper argues that advances in fuzzy reasoning systems in healthcare are critical for patient data, requiring innovative methodologies that combine the interpretive capabilities of artificial intelligence with…
The quality of historical documents related to fields such as art, architecture, mathematics, astronomy, astrology, law, music, and medicine, which were written hundreds of years ago and are still preserved by libraries…
This review systematizes how machine learning (ML) can be integrated into Lagrangian particle dispersion models (LPDM: FLEXPART, HYSPLIT, STILT, NAME) as a physics-consistent augmentation rather than a replacement of…
This article introduces an advanced speech signal protection technology aimed at safeguarding radio communication systems against information leakage. The proposed technology provides a reliable means of securing radio…
Рақамли технологияларнинг назарий ва амалий масалалари — barcha maqolalar