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.
  • 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 clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.