Description

Our project is made using python, and uses a GUI made from pyqt5. The project has three main phases, or steps; the image upload and processing, the extraction of text from an image, and finally the conversion of text to displayed words on a GUI. Our project works with a user submitted image, which is then processed using the pillow library. The image is made more clear, and a gaussian blur effect is applied to make it easier to extract text from. The text is extracted using the pytesseract, which is split into words. The split words are displayed on a GUI, according to a reading speed of 250 (Adjustable) words per minute. This is an optimal reading speed, and can help people with dyslexia read much faster, since the words are being displayed once at a time.