Hand gesture recognition using hybrid deep learning models for deaf communication support
Journal of Statistics & Management Systems · 2026 · 29 (5) · 529-552
DOI: 10.47974/jsms-1584 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Statistics & Management Systems, 2026. Verfasst von Gautam Govind und 2 weiteren Autor:innen.
Abstract (Originalsprache)
Hand gesture recognition has become an indispensable part of human-computer interaction. It supports intuitive, contactless, and accessible means of communication. This work proposes a robust deep learning-based system for the real-time static recognition of hand gestures to assist communication with the deaf and hard-of-hearing. We propose hybrid architecture that consists of the Swin Transformer for contextual attention, ResNet34 for spatial feature extraction, and a BiLSTM layer for temporal understanding. The model was trained and evaluated using a subset of the HaGRID dataset, consisting of 18 different classes of hand gestures. It achieves a training accuracy rate of 99.3% and a testing accuracy rate of 98.03%, thereby demonstrating its excellence in performance amid different lighting and backgrounds. Our approach proposes a scalable solution that can be integrated into assistive technology for gesture-to-text or gesture-to-speech conversion, thus bridging the communication gap for deaf individuals.
Zitieren
APA
Govind, G., Gupta, D., & Jhajharia, K. (2026). Hand gesture recognition using hybrid deep learning models for deaf communication support. Journal of Statistics & Management Systems, 29(5), 529-552. https://doi.org/10.47974/jsms-1584
Vancouver
Govind G, Gupta D, Jhajharia K. Hand gesture recognition using hybrid deep learning models for deaf communication support. Journal of Statistics & Management Systems. 2026;29(5):529-552. doi:10.47974/jsms-1584
BibTeX
@article{Govind2026,
author = {Govind, Gautam and Gupta, Dhruv and Jhajharia, Kavita},
title = {Hand gesture recognition using hybrid deep learning models for deaf communication support},
journal = {Journal of Statistics & Management Systems},
year = {2026},
volume = {29},
number = {5},
pages = {529--552},
doi = {10.47974/jsms-1584}
}
EUVIMED