Sign Language Detection and Translation using Machine Learning

This project aims to bridge the communication gap between speech-impaired individuals and the general public by developing a sign language recognition system using Python and OpenCV. The system utilizes computer vision techniques for image acquisition and processing, and a convolutional neural network (CNN) for gesture recognition. Training the model with a dataset of American Sign Language (ASL) gestures, the system translates these gestures into readable text. The primary goal is to make communication accessible for those with speech and hearing impairments, thus aligning with the Sustainable Development Goal (SDG) 10—Reduced Inequalities. This study reviews various gesture recognition techniques, explores their applicability in real-world scenarios, and highlights the robustness and limitations of the proposed system. The results showcase an accuracy rate suitable for practical applications, and potential future enhancements are discussed to further improve gesture recognition accuracy and extend the system's functionality.