American Sign Language Recognition and Translation using Deep Learning and Computer Vision

Chandrasekaran, Sruthi (2021) American Sign Language Recognition and Translation using Deep Learning and Computer Vision. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration manual) Download (1MB) | Preview

Abstract

Humans communicate using the language that they are familiar with. There are people who have hearing impairment and speaking issues. Its not necessary that everyone should know sign language and communicate in sign language. The Recognition and Translation of Sign Language in real-time would benefit people to have a effective communication and bridges the communication gap between people who do not know sign language. This work addresses the issue of ” sign language recognition and sign language translation”. The dataset used here is American Sign Language(ASL) Alphabets, which contain 26 letters and 3 special characters that are space, delete and nothing. These special characters help in real-time recognition. Convolutional Neural Network(CNN) was chosen for the ASL recognition and Translation. Since the dataset is images, Image augmentation, color conversion, size reduction are implemented. The model could predict the letter and display in text and convert to audio with the help of python library called ’gTTs’(Google Text to Speech). The CNN model with Image Augmentation have achieved an accuracy of 94% with 10 epochs. In terms of accuracy the model is compared with all other ASL translation techniques, where most of them are using glove and sensors. However the model is overfit, and future work should address this while improving.

Item Type:	Thesis (Masters)
Subjects:	P Language and Literature > P Philology. Linguistics Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > QA Mathematics > Computer software T Technology > T Technology (General) > Information Technology > Computer software P Language and Literature > P Philology. Linguistics > Language Services
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Clara Chan
Date Deposited:	15 Nov 2021 16:42
Last Modified:	21 Feb 2022 15:36
URI:	https://norma.ncirl.ie/id/eprint/5140

Actions (login required)

View Item