A Comparative Study of Deep Learning Models for American SL Recognition

American SL (ASL) is a natural language employed by the deaf community in the United States as well as in some areas of Canada. ASL is a visual language that makes use of facial expressions, hand signs, and body language as means of communication, effectively conveying meaning to its users. In this research paper, we performed a comparative study of various deep learning approaches with the aim of accurately recognizing hand gestures in ASL. To conduct our comparative study, we created a comprehensive dataset of ASL hand gestures from A to Z, excluding J and Z, and trained each model on this dataset, it also included images from many sources with a range of backgrounds, lighting, and other environmental factors, making the dataset more resilient and adaptable. The models we evaluated included RNN, ConvNeXt, and Vision Transformer, as well as a computer vision-based approach. We assessed the accuracy of each model on each alphabet and the overall accuracy of each model across all alphabets. Our results shows that ConvNeXt achieve the highest overall accuracy of 99.670%, followed by RNN with 96.6664% accuracy and Vision Transformer with 95.2464% accuracy. These findings highlight the importance of using diverse deep-learning models and comprehensive datasets to accurately recognize ASL hand gestures.