I have an OCR built with Pytesseract, where the data is grabbed from a PDF file that's made out of PNG pages, it's converted via poppler and then scanned. The script works well for the most part, but I have an issue with reading strings of characters for car license plates (they are in plain text, as a part of the data). Sometimes the "O" replaces the "0", "Z" replaces "7" and so on.
I've tried changing the config, and binarizing the image but to no avail. Is there something I'm missing here? Let me know what other info could I give out and I'll provide it as soon as I can