SIGN LANGUAGE TO TEXT CONVERTOR

Sign language is a vital form of communication for the Deaf and Hard of Hearing community, yet there remains a significant barrier in real time interaction with non-sign language users. This project proposes the development of a Sign Language to Text Converter, an innovative system designed to translate sign language gestures into written text. The goal of the system is to produce an accessible real-time tool that transcends the communication gap between the Deaf people and those who are not familiar with sign language, thus enhancing interaction in diverse spheres such as education, healthcare, and social settings. This system will utilize techniques such as computer vision and machine learning in recognizing and interpreting hand gestures. The system processes real-time video input using OpenCV for image processing and MediaPipe for hand and pose detection, extracting key features such as hand positions, movements, and orientations. These features are then fed into a Convolutional Neural Network (CNN) trained to classify individual sign language gestures. The output is translated to text, which can either be displayed on a screen or used with the text-to-speech systems to provide an auditory output.