mArSL is an isolated Arabic sign language (ArSL) dataset consisting of 6,748 samples representing 50 signs of Arabic sign language. The dataset’s signs were performed by four signers. Each sign was repeated by each signer several times at different sessions. All signers are male with different skin colors. The signers’ ages range between 21 and 30 years old. The main focus of this dataset was to record signs that require facial expressions (non-manual gestures) to study the importance of this component for sign language recognition.
mArSL dataset was recorded using a Kinect V2 camera that provides three types of information (color, depth, and skeleton joint points) recorded simultaneously for each sign.
If you use mArSL dataset, we kindly ask you to cite Towards Hybrid Multimodal Manual and Non-Manual Arabic Sign Language Recognition: mArSL Database and Pilot Study
@Article{electronics10141739,
AUTHOR = {Luqman, Hamzah and El-Alfy, El-Sayed M.},
TITLE = {Towards Hybrid Multimodal Manual and Non-Manual Arabic Sign Language Recognition: mArSL Database and Pilot Study},
JOURNAL = {Electronics},
VOLUME = {10},
YEAR = {2021},
NUMBER = {14},
ARTICLE-NUMBER = {1739},
ISSN = {2079-9292},
DOI = {10.3390/electronics10141739}
}
The dataset is available in three modalities:
To download the dataset, please send an email to hluqman@kfupm.edu.sa
For more information, contact Hamzah Luqman (hluqman@kfupm.edu.sa)