Utilizing Convolutional Neural Networks to Create a Wearable Sign Language Detection System with the Internet of Things

Because having hearing or speech impairments might make it more difficult for an individual to communicate, the objective of the strategy that has been offered is to narrow the gap in communication that exists between a person with a disability and a typical person. Our goal is to create a hand glove that is capable of not only translating sign language into voice but also displaying text on an app. Additionally, the application will be able to do the task in reverse, translating spoken words into sign language. To develop a full sign language translator app that is capable of translating speech into sign language and sign language into speech vice versa. The technique that has been suggested is intended to help persons with hearing and speech impairments overcome the challenges they experience and improve their ability to communicate with others. Arduino, Convolutional Neural Network (CNN), and Natural Language Processing are the technologies that are used to accomplish it (NLP). In order to get data on motion, Arduino will be paired with a number of other sensors, such as flex sensors. The convolutional neural network (CNN) will be implemented in Python by making use of the Keras library. All of them will be combined into a single application called Streamlit, which will be developed using the dart programming language.