Optical character recognition (OCR) is the process of extracting text from images. Even in this digital age a lot of documents are still in printed form. OCR allows digitization of these documents via automation. All you need to do is scan the documents and save it on your computer in an image format. After this, you can feed it to an OCR engine to extract the text content from it. The process is quite compute intensive. Also, the results are not 100% accurate. However, with machine learning the results are becoming better and better.