Publication

Abstract : American Sign Language recognition is a crucial technology that aims to improve accessibility and communication for the deaf and hard-of-hearing community. This research aims to convert ASL gestures into text or speech by analyzing and interpreting them using gesture recognition in sign language. This study compares different deep learning algorithms for sign language identification to overcome communication difficulties that deaf or hard-of-hearing people face. Three models—VGG16, ResNet, and AlexNet—were created and trained using a dataset of hand motions. The findings show that all three models have excellent accuracy, with AlexNet performing the best at 99.87%, ResNet coming in second at 98.9%, and VGG16 third at 98.2%.