Ashwin Krishna Raparthy1, Bhim Prajapati1, Santhi Priya Yalla1, Vigneshkkar Ravichandran1, Enrico De Santis2 and Parisa Naraei3*
1Postgraduate AI Student, Lambton College, Canada
2Machine Learning Engineer and Chief Technology Officer, SisterPomos and Scientific Researcher, Sapienza Università di Roma, Italy
3Professor, Cestar College of Business, Health and Technology, Department of Artificial Intelligence, Lambton College, Applied Researcher, Toronto Metropolitan University Alumni, Canada
*Corresponding Author: Parisa Naraei, Professor, Cestar College of Business, Health and Technology, Department of Artificial Intelligence, Lambton College, Applied Researcher, Toronto Metropolitan University Alumni, Canada.
Received: July 26, 2022; Published: September 23, 2022
Human beings are wonderful creations of nature. People are known for the intelligence they have. Among the various creations of human thoughts, language is also one that human beings use to communicate with each other. But for, differently abled people who cannot hear have a different language to communicate with, called sign language. This type of language is expressed using the physical articulation of the body parts. In this case, it should not be confused with the body language that normal people use. Deaf people primarily use sign language, but people who cannot speak also use this language.
With the evolution of technology and advancement in AI, computers can now process human language using NLP. In this project, we use a deep learning method to predict sign language. We are building a web app through which a sign user can interact with a normal person who cannot understand sign language. We have used a convolutional neural network (CNN) to get the key points of the human body like the face, shoulder, arm, hand, and fingers. Then we used long short-term memory (LSTM) to model the neural network. Our model can predict sign language with an accuracy of 95.8%.
Keywords: Convolutional Neural Network (CNN); Hidden Markov Model (HMM); Artificial Neural Network (ANN)
Citation: Parisa Naraei., et al. “An LSTM Based Sign Language Recognition Model in Support of Patients with Hearing Disabilities". Acta Scientific Computer Sciences 4.10 (2022): 34-39.
Copyright: © 2022 Parisa Naraei., et al. This is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.