JUMLA-QSL-22: A Novel Qatari Sign Language Continuous Dataset

This paper proposes the first large-scale and annotated Qatari sign language dataset for continuous sign language processing. This dataset focuses on phrases and sentences commonly used in healthcare settings and contains 6300 records of 900 sentences. The dataset collection process involves diverse participants, including both hearing-impaired individuals and sign interpreters, to capture variations in signing styles, speeds, and other linguistic nuances. The data collection setup integrates advanced technology, including true depth cameras, to comprehensively record signing movements from various angles. The collected dataset is rich in content, encompassing different signing variations and linguistic intricacies. The dataset is publicly available in IEEE Dataport. The paper also analyzes the data captured to understand the trends and patterns within the data. As the global population with hearing difficulties continues to grow, there is a pressing need for effective sign language recognition systems to bridge the communication gap between the deaf and non-deaf communities and the introduction of the JUMLA-QSL-22 dataset constitutes a significant stride toward addressing this imperative need.