This system uses computer vision and machine learning to detect and translate Pakistan Sign Language (PSL) gestures in real-time — helping bridge the communication gap between the deaf and hearing communities.
Webcam-based detection runs at up to 30 FPS, recognising hand gestures with sub-second latency using MediaPipe hand landmarks.
A Multi-Layer Perceptron trained on 42 landmark coordinates achieves 98.6% test accuracy across 37 Urdu letters.
Detected signs are spoken aloud in Urdu using pre-recorded audio, making the system accessible without reading.