Proceedings of the First International Conference on Advances in Computer Vision and Artificial Intelligence Technologies (ACVAIT 2022)

<Previous Article In Volume
Next Article In Volume>

A CNN-LSTM Model for Arabic Sign Language Recognition

Authors
Basel Dabwan1, *, Mukti Jadhav2
1Department of Computer Science, Dr. Babasaheb Ambedkar Marathwada University, Aurangabad, India
2Shri Shivaji Science and Art College, Chikhali District, Buldhana, India
*Corresponding author. Email: baseldbwan@yahoo.com
Corresponding Author
Basel Dabwan
Available Online 10 August 2023.
DOI
10.2991/978-94-6463-196-8_35How to use a DOI?
Keywords
CNN; LSTM; Sign Language; Deep Learning; Machine Learning
Abstract

Gesture-based communication is a correspondence of nonverbal sort that involves the utilization of additional body parts. Demeanours of the face alongside Hand, eye, and lip movement is used for passing on data in correspondence with sign language. Individuals with hearing impairment or discourse are significantly dependent on gesture-based communication as a kind of association in their day-to-day existence. Few of the studies dealt with Arabic sign language, so in this work, we developed applied research with its video-based Arabic sign language recognition system that helps deaf and dumb people in the Arabic community. We developed our sign language model by a combination of Long Short Term Memory (LSTM) and Convolutional Neural Networks (CNN), with two distinct neural network architectures. The first architecture is ConvLSTM and the second one LRCN. We used these two algorithms for extracting spatial and temporal features. The first model achieved a training accuracy of 99.66% and validation accuracy of 95%, and the second model achieved 99.5% training accuracy and 93.33% validation accuracy. We tested the performance of these two models in recognition between 28 classes of Arabic sign language.

Copyright
© 2023 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

<Previous Article In Volume
Next Article In Volume>
Volume Title
Proceedings of the First International Conference on Advances in Computer Vision and Artificial Intelligence Technologies (ACVAIT 2022)
Series
Advances in Intelligent Systems Research
Publication Date
10 August 2023
ISBN
10.2991/978-94-6463-196-8_35
ISSN
1951-6851
DOI
10.2991/978-94-6463-196-8_35How to use a DOI?
Copyright
© 2023 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Cite this article

risenwbib
TY  - CONF
AU  - Basel Dabwan
AU  - Mukti Jadhav
PY  - 2023
DA  - 2023/08/10
TI  - A CNN-LSTM Model for Arabic Sign Language Recognition
BT  - Proceedings of the First International Conference on Advances in Computer Vision and Artificial Intelligence Technologies (ACVAIT 2022)
PB  - Atlantis Press
SP  - 459
EP  - 470
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6463-196-8_35
DO  - 10.2991/978-94-6463-196-8_35
ID  - Dabwan2023
ER  -