Real-Time Sign Language Recognition System using Computer Vision and Deep Learning

View at publisher Summarise with VIRAT
Authors: Pranav Shelke, Sanskruti C. Shrirang, Pratham C Durge, Lande M.V, Akshay B. Nagde
Cited by: 0

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Sign language serves as a communication method for individuals who are deaf or mute. Despite this, there are still communication challenges between those with hearing impairments and those without, primarily due to the absence of automated interpretation systems. This project introduces a real-time sign language recognition system that leverages computer vision and machine learning. The system utilizes alive camera feed to capture hand gestures, identifies hand landmarks with Media Pipe, and emp loys a trained Convolutional Neural Network (CNN) model to classifythese gestures. The identified gestures are then translated into text, with suggestions for commonly used wordsprovided to enhance communicat ion efficiency. The system is designed to be user-friendly, affordable, and capable of operating in real time without the need for specialized hardware, thus aiding in closing the communication gap and fostering inclusivity.Key Words:Sign Language Recognition, Hand Gesture Recognition,Machine Learning, Deep Learning, CNN, Computer Vision,Media Pipe

Fields of Study & Subjects

Hand Gesture Recognition Systems Human Pose and Action Recognition Hearing Impairment and Communication

Publication details

Journal / source
International Scientific Journal of Engineering and Management
Volume
05
Issue
03
Pages
1–9
Publication date
31 March 2026
Language
EN