Extract highlighted text from images using OCR and CV in your browser
This project is a JavaScript port of my Python app designed to extract highlighted text from book images. It uses OCR (Optical Character Recognition) and image processing techniques to detect and extract highlighted sections from images. See my original post for more information. This JavScript app runs entirely in-browser without the need to download or install any dependencies.
Here is a short demonstration video:
demo.mp4
- Got to zirkelc.github.io/highlights/
- Upload an image containing text with one or more highlighted sections.
- The OCR will start and recognize the text in the image.
- You can then select the color of the highlighted areas by using the color picker on the top-left of the image.
- The OCR will run again, this time the highlighted areas will be displayed in the result.