Sign Language to Text Conversion using CNN

Abstract

Sign language is a communication strategy used by those who are unable to hear. So those people who know sign language can communicate with people who are deaf. But a majority of our people don’t know sign language therefore there comes a communication gap between the ones who know sign language and others who don’t know. This project’s major purpose is to bridge this gap by developing a system that recognizes multiple sign languages and translates them into text in real-time. We use machine learning technologies to construct this system especially, convolutional neural networks (cnns), which are used to recognize and translate American Sign Language (ASL) into text by capturing it using a webcam. The transformed text is then presented on the screen by which individuals can comprehend and communicate with those who use sign language. The system’s performance is evaluated on a dataset of ASL gestures, attaining excellent accuracy and indicating its potential for practical usage in enhancing communication accessibility for the deaf and hard-of-hearing community.