Sign Language Recognition
A real-time sign language identification system with machine learning techniques that offers real-time gesture-to-text translation, improving accessibility and communication for users who use sign language.
Abstract
Sign language is a vital communication tool for those who are deaf or hard of hearing.but it confronts numerous challenges as a result of its low level of certification and general awareness. This study recommends developing a real-time sign language identification system with machine learning techniques in order to bridge this communication gap. The system correctly predicts sign language movements from live webcam input by using MediaPipe for a Random Forest classifier trained on a custom dataset of hand motions and hand landmark extraction. For effective management, the program combines an admin panel with a secure user registration and management architecture. The program, which was created using OpenCV and Flask, offers real-time gesture-to-text translation, improving accessibility and communication for users who use sign language. The model's effectiveness in real-time gesture detection is demonstrated by experimental results, highlighting its capacity to promote inclusive communication and assist the deaf community. Keywords: OpenCV, Sign Language, MediaPipe, Random Forest, CNN.