SPEECH CONVERSION FROM THE EXTRACTED TEXT OF IMAGE FOR BLIND PEOPLE

This paper is about a device that is used to convert image text into voice. Language is one of the main problems in communication. The primary motivation of this project is to provide a user friendly interface for blind people. Input is text for books, papers, magazines, etc., output is in speech form. This system is for blind people. Whatever the input given to the device, the output is produced in speech. Optical Character Recognition (OCR) engine is mainly used for conversion process. Python coding is used for conversion process. The main components are raspberry pi, camera module, headphones or speaker. Worldwide many people are blind and unable to read the text present in papers; this is the system very useful for blind people for knowing information in papers.