STUDY OF SIGN LANGUAGE USING NEURAL NETWORKS
DOI:
#10.25215/8119070771.14Keywords:
Sign language, Feature Extraction and Representation, Artificial Neural Networks, Convolution Neural Network, TensorFlow, Keras, OpenCV(Open Source Computer Vision).Abstract
Hand gestures, facial expressions, and body language are all used in sign language to communicate. Either word level signs or fingerspelling make up a sign language. For the deaf-dumb community, it is their sole means of communication. However, hearing individuals never attempt to learn sign language. As a result, hearing-impaired people are unable to converse with hearing people without a sign language interpreter. Because of this, deaf persons are socially isolated. Therefore, a system that can decode sign language automatically is required. The execution of such a system gives hearing-impaired people a platform for communication without the help of anyone. One of the most traditional and organic kinds of language for communicating is sign language. Sign language based on fingerspelling technique employing neural networks. Deaf and dumb people use sign language, a kind of nonverbal communication, to communicate. D&M individuals can only communicate through sign languages due to a single communication-related disability that prevents them from utilising spoken languages. Exchanging thoughts and messages through a variety of channels, such as speaking, signalling, behaviour, and visuals, is the act of communication. People (D&M) without hearing or speech use their hands to produce a range of gestures to communicate with others.
Metrics
Published
How to Cite
Issue
Section
License
Copyright (c) 2023 Amal Mathew, Shriya, S. Aravinda Prabhu
This work is licensed under a Creative Commons Attribution 4.0 International License.