A Computer Vision and Deep Learning Framework for Sign Language Recognition

Sign language is an important means of communication for Deaf and Hard of Hearing individuals, yet limited knowledge of sign language among hearing people can create substantial communication barriers. This study presents a computer vision and deep learning framework for sign language training and recognition. A custom dataset was developed from 50 selected high-frequency words and a NoSign control class, with image recordings obtained from two signers. MediaPipe Holistic was used to extract facial, pose, and hand landmarks from the captured video.