Treffer: Wearable sign language detection system by using convolutional neural network.

Being hearing or speech differently-abled may hinder the communication of an individual, thus the goal of the proposed approach is to reduce the communication gap between a differently-abled and a normal person. We aim to develop a hand Glove that can convert sign language to speech, as well as display text on an App. In addition, the App will also be able to do the reverse and convert speech into sign language. To create a complete sign language translator App that can translate sign language into speech and vice versa. The proposed approach is aimed to solve the problems faced by hearing and speech impaired people and enable better communication for them. It is implemented by using Arduino, Convolutional Neural Network (CNN) and Natural Language Processing (NLP). Arduino will be combined with various sensors like flex sensors to get motion data. The image recognizer will be made by the use of CNN in python using Keras. All these will be integrated into a Streamlit App created using the dart programming language. [ABSTRACT FROM AUTHOR]

Copyright of AIP Conference Proceedings is the property of American Institute of Physics and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)