AI-Driven Real-Time Sign Language Recognition System

Abstract

Communication is a fundamental human right essential for social inclusion. Individuals with hearing or speech impairments face barriers due to limited understanding of sign language. This project presents an AI-driven real-time sign language recognition system that translates gestures into readable text or speech. The system recognizes both single-hand and dual-hand gestures, including daily expressions and gesture-based computations. It utilizes both Artificial Intelligence (AI) and Computer Vision for accurate gesture interpretation. OpenCV for image preprocessing, and MediaPipe for hand landmark detection. A Flask-based web interface enables real-time interaction, while the gestures are recognized and converted into text. The system operates efficiently with high accuracy and can interpret words like ‘SUN’. This AI-based solution enhances assistive communication and promotes inclusivity in education, healthcare, and accessibility applications.