OCR, Translation and Text to Speech to Aid Illiterate Drivers

Abstract

People travel to different places every day. Most of them travel to new places as a part of profession. Drivers move from one state to another and they need to understand languages of other states. A person can’t understand all the languages and a lot of them can’t read their own language. This article addresses these issues by taking the picture of unknown language script, translate it into the required language and give speech output of the translated text. The captured image is pre-processed using OpenCV, the text is extracted using Google Vision, the extracted text is translated using Google Translator and the speech output is obtained through Google text to speech.