What it does
This model aims to capture the vicinity of a blind man using a camera and extract the information(name) about all the objects in view in the form of text and finally convert the text into sound. It aims to provide the blind person with a descriptive view of his surroundings by providing him an insight into the objects in his vicinity. Also, it will be able to extract any kind of text, if any, present in the image. To enable blind children learn in a classroom setting where normal children read textbooks, our project will extract all the text present in an image and convert it to braille script (which can be fed to braille printers further) or the text can be read out by our software as per the student requirements. In the COVID scenario where people touching contaminated surfaces are at a high risk of being prone to the virus, visually impaired are at even higher risks as have to touch the surfaces of objects to make out what they are. Through this solution, they will only have to click a picture of the object to make out what it is without having the need to touch it with their hands.