Hi Pierpaolo, I've certainly been able to recognise only digits, see the FAQ heading, "How do I recognize only digits?": http://code.google.com/p/tesseract-ocr/wiki/FAQ
That works fine for digits, but I have had problems trying to limit tesseract to a certain set of characters, it seems that the whitelist variable isn't read properly. For example, say I create that text file mentioned in the FAQ and change the content to: tessedit_char_whitelist D123456789 It will still recognise a zero, even though it should use a D instead. So I would guess it's hardcoded somewhere in the source. Hope that helps, Paul. On May 14, 8:36 am, Pierpaolo Monaco <[email protected]> wrote: > I need to process some alphanumeric string. > The main problem is that I have just letter and digit in my imput string but > the result of the ocr process is sometimes a point o a bracket, etc... > Symbols that never will be in my imput domain. > How can I limit the output? > If I want, for example (for semplicity), just digits for result what I have > to do? > Hope somebody can help me. > > Thanks. > > -- > ----------------------------- > Pierpaolo Monaco > ---------------------------- --~--~---------~--~----~------------~-------~--~----~ You received this message because you are subscribed to the Google Groups "tesseract-ocr" group. To post to this group, send email to [email protected] To unsubscribe from this group, send email to [email protected] For more options, visit this group at http://groups.google.com/group/tesseract-ocr?hl=en -~----------~----~----~----~------~----~------~--~---
