Real time sign language recognition and translation using mediapipe ann and lstm

Abstract

This paper presents a real time sign language translation system that converts hand gestures into text and speech. The system uses a webcam, OpenCV, and MediaPipe for hand landmark detection. An Artificial Neural Network recognizes static gestures, while a Long Short Term Memory network recognizes dynamic gestures. Recognized signs are combined into sentences and converted into speech using text to speech. The proposed system provides a low cost and contactless approach for assisting communication between sign language users and non-signers.

Keywords