Video-Based Sign Language Digit Recognition for the Thai Language: A New Dataset and Method Comparisons

Wuttichai Vijitkunsawat, Teeradaj Racharak, Chau Nguyen, Nguyen Minh

2023

Abstract

Video-based sign language recognition aims to support deaf people, so they can communicate with others by assisting them to recognise signs from video input. Unfortunately, most existing sign language datasets are limited to a small vocabulary, especially in low-resource languages such as Thai. Recent research in the Thai community has mostly paid attention to building recognisers from static input with limited datasets, making it difficult to train machine learning models for practical applications. To overcome this limitation, this paper originally introduces a new video database for automatic sign language recognition for Thai sign language digits. Our dataset has about 63 videos for each of the nine digits and is performed by 21 signers. Preliminary baseline results for this new dataset are presented under extensive experiments. Indeed, we implement four deep-learning-based architectures: CNN-Mode, CNN-LSTM, VGG-Mode, and VGG-LSTM, and compare their performances under two scenarios: (1) the whole body pose with backgrounds, and (2) hand-cropped images only as pre-processing. The results show that VGG-LSTM with pre-processing has the best accuracy for our in-sample and out-of-sample test datasets.

Paper Citation

in Harvard Style

Vijitkunsawat W., Racharak T., Nguyen C. and Minh N. (2023). Video-Based Sign Language Digit Recognition for the Thai Language: A New Dataset and Method Comparisons. In Proceedings of the 12th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-758-626-2, pages 775-782. DOI: 10.5220/0011643700003411

in Bibtex Style

@conference{icpram23,
author={Wuttichai Vijitkunsawat and Teeradaj Racharak and Chau Nguyen and Nguyen Minh},
title={Video-Based Sign Language Digit Recognition for the Thai Language: A New Dataset and Method Comparisons},
booktitle={Proceedings of the 12th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2023},
pages={775-782},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011643700003411},
isbn={978-989-758-626-2},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 12th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - Video-Based Sign Language Digit Recognition for the Thai Language: A New Dataset and Method Comparisons
SN - 978-989-758-626-2
AU - Vijitkunsawat W.
AU - Racharak T.
AU - Nguyen C.
AU - Minh N.
PY - 2023
SP - 775
EP - 782
DO - 10.5220/0011643700003411