Sign language serves as a vital means of communication for individuals with hearing impairments; however, the limited availability of low-cost and scalable interpretation technologies restricts its accessibility in education, healthcare, and workplace settings. This study introduces a real-time American Sign Language (ASL) alphabet recognition system that integrates YOLO-based hand detection with MediaPipe-based hand landmark extraction. YOLOv11 is utilized to precisely detect and localize hand regions, while MediaPipe extracts 21 anatomical hand landmarks, enabling detailed representation of finger movements and hand postures using a conventional webcam. Experimental evaluation indicates high system effectiveness, with a precision of 0.985, recall of 0.981, F1-score of 0.991, and mAP@0.5 of 0.982, alongside a low average inference time of 1.3 milliseconds per frame. The results confirm that the proposed method is suitable for real- time applications and provides an economical assistive communication solution, with scope for future extension to continuous and sentence-level sign language recognition.
Durgesh Gangaram Deore (Sat,) studied this question.