Super User is a question and answer site for computer enthusiasts and power users. It's 100% free, no registration required.

Sign up
Here's how it works:
  1. Anybody can ask a question
  2. Anybody can answer
  3. The best answers are voted up and rise to the top

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, wich is told to be very accurate, but it's extremly 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 languaged documents.
  • I do not want to spend more than 1-2k € for a licence with unlimited usage on one machine.
share|improve this question
Thanks for the edit, and sorry for the mistakes. – mimrock Aug 25 '12 at 13:26
What exactly are you trying to OCR, printed text? handwriting? – ewanm89 Aug 26 '12 at 12:01
Printed text. Actually receipts. – mimrock Aug 26 '12 at 12:31

Your Answer


By posting your answer, you agree to the privacy policy and terms of service.

Browse other questions tagged or ask your own question.