I need to perform OCR on the a backend of a website on a Linux machine with printed text.
I read the other related questions here, so I tried tesseract, wich is considered as one of the most accurate amongst the open source ones, but it was very inaccurate for me.
I also heard about ABBYY, which is said to be very accurate, but it's extremely expensive. 3500€ for a usage-limited license is way too much for me.
So, here are my requirements:
- I need to be able to work on Linux with the command line.
- I need to recognize Hungarian language documents.
- I do not want to spend more than €1-2k for a licence with unlimited usage on one machine.