Developing an Intelligent Recognition System for British Sign Language: A Step Towards Inclusive Communication

Effective communication is crucial for ensuring inclusivity, yet the hard-of-hearing community faces significant barriers due to a shortage of qualified interpreters. British Sign Language (BSL), officially recognised in the UK, relies on hand gestures, facial expressions, and body movements. However, limited interpreter availability necessitates technological solutions to bridge the communication gap between signers and non-signers. This study proposes a real-time, vision-based BSL recognition system using computer vision and deep learning to interpret fingerspelling and six commonly used BSL words. The system employs OpenCV for video capture, MediaPipe for hand feature extraction, and Long Short-Term Memory (LSTM) networks for sign classification. A dataset incorporating left- and right-handed signers achieved a 94.23% accuracy rate for 26 fingerspelling gestures and 99.07% for six words. To enhance usability, a graphical user interface was developed, enabling seamless real-time interaction. These findings demonstrate the potential of AI-driven sign language recognition to improve accessibility and foster more inclusive communication for the hard-of-hearing community.