Hi Tom,

Thanks for help me clarify "style violation message".

Please help me on another question.

I would like to use Tesseract engine to do text line recognition and after
that use OCRopus language model to do spelling correcting.

I wonder if I can do that because:

Slide 45 @ http://www.slideshare.net/tmbdev/2008-03-million-books-2
show that Tesseract by pass WFST language model.

And in one of your paper you said that:
" Tesseract does not attempt to estimate character likelihoods, posterior
probabilities, or probabilistic segmen-
  tation costs, but does return "match scores". Tesseract also does not
compute a complete segmentation graph
  for the input. Both of these factors limit the ability to use Tesseract
with the statistical natural language models
  used by OCRopus."

Could you show me how can I use Tesseract with OCRopus statistical natural
language module?

Thank you very much,

-- 
Tien Dung
+65 8136 3969
http://free-and-happy.com/

--~--~---------~--~----~------------~-------~--~----~
You received this message because you are subscribed to the Google Groups 
"ocropus" 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/ocropus?hl=en
-~----------~----~----~----~------~----~------~--~---

Reply via email to