Real Time Implementation of Image Recognition and Text to Speech Conversion

This paper introduces an innovative, efficient and realtime cost beneficial technique that enables user to hear the contents of documents/text images instead of reading through them. It combines the concept of Optical Character Recognition (OCR) and Text to Speech Synthesiser (TTS) in MATLAB R2011b. This kind of system enables visually impaired people to interact with computers effectively through vocal interface. It also enables users to listen the audio created from the contents of web pages, e-books, documents and almost all electronically available data thereby enhancing the human-computer interactions. It is used to develop a system which extracts text data from images containing horizontally aligned text using Optical Character Recognition (OCR) and speaks out the extracted text data using Text to Speech synthesizer (TTS).