Text Recognition In Images And Converting Recognized Text To Speech

Abstract

Around 285 million people worldwide are visually impaired, including close to 39 million blind people. This has a significant impact on the lives of persons who are blind or visually impaired. Even though numerous attempts have been made to assist those who are blind in seeing objects through alternate senses like touch and sound, text-reading technology is still in its infancy. The system in use right now is either constrained in its application or expensive to maintain. Therefore, we require a system that can automatically recognize and read aloud text to a user base of visually impaired people that is both affordable and truly efficient. The main goal of this research is to develop a program that can identify text characters from turn any natural image into a voice signal. The programmes need to carry out the identical action for any uploaded image and PDF file. The application should also have tools for pace modulation, voice choosing options, and storage capability for image to text output. The target audience for this programme can be expanded to include people with special needs who also have learning impairments, young children, and several other societal groups. The text is extracted from the image using optical character recognition (OCR), and the Windows API is utilised to turn the text into speech. The programming language for digital image processing is MATLAB.