IMAGE TO SPEECH CONVERSION USING DIGITAL IMAGE PROCESSING

There are close to 39 million blind people and around 285 million visually impaired people globally. There is a huge impact on the lives of visually disabled people due to this. Although there have been several attempts made for helping visually disabled to see objects via other alternating means such as sound and touch, the development of text reading device is still at a nascent stage. The system currently in existence either has a limited scope or requires a heavy investment. Therefore, we need a cost effective and truly efficient system that will be able to automatically identify and recite text aloud to visually challenged user base. The main purpose of this project is to create an application to recognize the text character from any natural image and convert it into speech signal. The application should do the same for any PDF document and uploaded image. Along with this the application should also provide features for pace modulation, voice selection options dictionary and image to text output saving capabilities. The scope of this application can be widened to specially-abled people with learning disabilities, young children and various other segments of society. Optical Character Recognition (OCR) is used to extract text from image and Windows API to convert this text into speech. MATLAB is used as the programming language for Digital Image Processing.