Sign Language Recognition System using Machine Learning

Authors: Sakshi Bele, Anish Shinde, Kushal Sharma, Ashwini Shinde

Country: India

Full-text Research PDF File:   View   |   Download

Abstract: Sign language is a vital form of communication for the deaf and hard of hearing community. To bridge the communication gap between sign language users and non-signers, we present a novel system for real-time sign language detection using a standard web camera. This system aims to recognize sign language gestures performed in front of the camera, subsequently converting them into voice output and displaying the corresponding text on screen. The proposed system leverages computer vision techniques, including deep learning models, to capture and analyze sign language gestures. It first identifies the signer’s hand and facial expressions, recognizing key markers that represent signs. The system then employs machine learning algorithms to translate these markers into sign language vocabulary. Upon successful detection and translation of the sign, the system provides simultaneous output in two ways: voice and on-screen text. The voice output enables real-time interpretation for users who may not be familiar with sign language, while the on-screen text serves as a visual reference. This dual output mechanism ensures accessibility and inclusivity for a wider audience. By integrating this system into webcams and other devices with cameras, we aim to enhance the communication capabilities of the deaf and hard of hearing community, enabling them to interact more effectively with hearing individuals. Additionally, this technology can find applications in education, healthcare, and other domains, fostering better understanding and accessibility for sign language users.

Keywords: Sign Language Detection, Deaf and Hard of Hearing, Computer Vision

Paper Id: 230387

Published On: 2023-11-19

Published In: Volume 11, Issue 6, November-December 2023

Share this