Camera-Based Real Time Quran Sign Language Detection System Using LSTM Deep Learning Sequences

Effective communication, vital for expressing emotions, ideas, and resolving conflicts, depends on various forms of language, including written symbols, gestures, and vocalizations. While a shared language often facilitates successful communication, a significant challenge arises between individuals who rely on sign language due to speech impairments and those who use spoken languages. This gap creates barriers to mutual understanding. This study addresses the issue by implementing a proficient deep learning model designed to predict Quranic sign language, aiming to bridge the communication divide between speech-impaired and non-speech-impaired individuals. The research employed a Long Short-Term Memory (LSTM) model, and the results demonstrated that the LSTM model achieved superior performance in recognizing and interpreting Quranic sign language, highlighting its potential as a tool to enhance inclusivity within the community.