An Intelligent Text Reader based on Python

Abstract

As per the World Health Organization (WHO), 285 million people are visually impaired of whom 39 million are completely blind. Though there exist enough remedies to the problems of assisting individuals who are visually impaired to read, there is a requirement for an intelligent text reader which is economical, accurate and easily accessible in order to help them read for day to day activities. This paper proposes an intelligent text reader using python. This product is built on a Raspberry Pi module connected with camera that is used to capture the input image. The input image is enhanced using Image processing techniques. The Tesseract OCR (Optical Character Recognition) engine embedded in the Raspberry Pi searches for the text in an improved image and converts it into digital document. The digital document is then analyzed using semantic check module. After the analysis, text is converted to speech by a Python based TTS (text to speech) conversion unit embedded in the Raspberry Pi. Finally, the audio output is given to the Audio Amplifier for it to be read out.