Design and Development of a Compact Communication System for Deaf, Dumb and Blind People

Abstract

Communication is an integral part of our lives as it a mode of sharing and discussing our ideas and thoughts for the betterment of mankind. Unfortunately, some disabled people cannot talk (dumb), see (blind), and hear (deaf); hence facing difficulty in day-to-day chores. It has become a major issue as the World Health Organization states that as many as 28.5 crore persons are blind, 46.6 crore persons are deaf, and 10 lakh persons are vocally impaired, worldwide. This paper proposes a compact communication system that aids the blind, dumb, and deaf people for the purpose of easy communication. Science and technology have rapidly developed making everyday tasks simpler and easier but there still exist some underprivileged people who face difficulty in something as basic and essential as communication. This project focuses on overcoming the gap in communication between the disabled and normal people. Although there already exists devices to help people who are blind, deaf, and dumb individually; to address all the issues within a single compact system is challenging. The final result of this project is a system that provides aid to all the above-mentioned disabilities, in a single compact system. The four objectives of the project are as follows; Text to Speech and Image to Speech for visually impaired people. Speech to Text for deaf people. Gesture to Text for dumb people. The Text to Speech is converted using gTTS API and Play Sound module. Similarly, Speech to Text is converted using URL Speechtexter.com. Image to Speech is converted using the Open-CV and Tesseract OCR software. Gesture to Text is converted using the Open-CV software and Gaussian Algorithm. The design part of our project includes a Raspberry Pi board, Webcam, Speaker, Keyboard, Screen, and Microphone. Raspberry Pi board is a tiny computer that can be connected to a computer screen or television while using keyboard and mouse as input devices. The keyboard is used to provide the input text. Webcam is 25 MP, used for capturing images. It also has an inbuilt sensitive Microphone that is used to record the voice. Speaker is used as an output module to hear the speech that is converted from text and image. For Speech to Text and Gesture to Text, the output text is observed on the screen.