Real-Time Sign Language Interpretation Using CNN and LSTM Networks
International Journal of Emerging Technologies and Innovative Research · 10.04.2026 · 105
DOI: 10.48175/ijetir-9220 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Emerging Technologies and Innovative Research, online erschienen am 10.04.2026. Verfasst von Divya U H und 5 weiteren Autor:innen. Die Arbeit nennt 12 Literaturangaben.
Abstract (Originalsprache)
For those with speech and hearing problems, sign language is an essential communication tool. Nonetheless, there is a substantial barrier separating sign language users from non-signers, which restricts accessibility in everyday interactions, healthcare, and education. The DL (deep learning)-based sign language interpretation system described in the present paper utilises LSTM (Long Short-Term Memory) networks for dynamic sequence classification, CNNs (Convolutional Neural Networks) for static gesture identification. The system has a user-friendly interface utilizing Streamlit for smooth interaction and uses Mediapipe for real-time hand landmark detection. Conventional rule-based recognition systems are outperformed by experimental evaluations, which show an accuracy of 88% for dynamic sequences and 92% for static gestures. The suggested method improves accessibility and inclusivity by offering real-time gesture translation into text, facilitating efficient communication for the community of people who are hard-of-hearing and deaf.
Zitieren
APA
H, D. U., Kousar, D. H., V, R. T., R, H., C, C. V., & S, D. (2026). Real-Time Sign Language Interpretation Using CNN and LSTM Networks. International Journal of Emerging Technologies and Innovative Research, 105. https://doi.org/10.48175/ijetir-9220
Vancouver
H DU, Kousar DH, V RT, R H, C CV, S D. Real-Time Sign Language Interpretation Using CNN and LSTM Networks. International Journal of Emerging Technologies and Innovative Research. 2026:105. doi:10.48175/ijetir-9220
BibTeX
@article{H2026,
author = {H, Divya U and Kousar, Dr. Heena and V, Rashmi T and R, Harshitha and C, Chandu V and S, Divya},
title = {Real-Time Sign Language Interpretation Using CNN and LSTM Networks},
journal = {International Journal of Emerging Technologies and Innovative Research},
year = {2026},
pages = {105},
doi = {10.48175/ijetir-9220}
}
EUVIMED