Sign Language Recognition using Yolo Model

This project presents an innovative approach to real-time Sign Language Recognition using the YOLOv8 (You Only Look Once version 8) object detection algorithm. Aimed at enhancing communication accessibility for individuals with hearing and speech impairments, the system is capable of detecting and recognizing a comprehensive set of American Sign Language (ASL) hand signs, including alphabets (A–Z), numbers (1–9), and commonly used expressions such as "Hello," "Thank You," "Yes," "No," and "I Love You." The dataset used is sourced from Roboflow's sign recognition collection, which provides annotated images of various hand signs. The model is trained in Google Colab for optimized performance and later integrated into a user-friendly Streamlit-based web application. This enables end-users to upload or use real-time camera input for instant sign detection. YOLOv8's advanced architecture ensures high-speed inference and accurate localization, making the system suitable for real-time applications. The framework’s end-to-end design bridges the gap between the deaf community and non-signers by enabling quick interpretation of signs into readable text. This project lays the foundation for future expansion into gesture-based human-computer interaction, education tools, and assistive technologies for differently-abled individuals. 

  Keywords:
YOLOv8, Sign Language Recognition, Streamlit, Real-Time Detection, Assistive Technology.