This research paper focuses on Automatic Sign Language Recognition (SLR), a complex, multidisciplinary field that combines video processing, machine learning, and linguistics. The authors present a model for sign classification that combines diverse features such as position, movement, and hand shape. The model uses a bag-of-words approach and achieves a 97% accuracy rate on an Argentinian Sign Language dataset. The study suggests that sequential ordering may not be essential for recognition, a significant contribution to the field of SLR.
Publication date: 26 Oct 2023
Project Page: https://arxiv.org/abs/2310.17437
Paper: https://arxiv.org/pdf/2310.17437
