Quote/Cytat - Nick White <[email protected]> (Tue 15 Apr 2014
05:14:15 PM CEST):
Hi Janusz,
On Tue, Apr 15, 2014 at 01:31:16PM +0200, Janusz S. Bien wrote:
I use tesseract from ocrodjvu and get this message in the context
when it doesn't seem to be appropriate.
I don't think the params model does what you think it does. I hadn't
looked at it before, but I think its concern is with weighing of
some features of a language. As the code comment says, there are
times when those weighings aren't directly comparable, so it's best
to give up on that optimisation when doing multilingual OCR.
The details of the word model features are not something I know much
about at the moment, but I think that's approximately the answer. So
it doesn't mean "using default language", but rather "not using
certain features of each language, as they wouldn't work well in
multilingual mode".
Thank you very much for the explanation.
Best regards
Janusz
--
Prof. dr hab. Janusz S. Bień - Uniwersytet Warszawski (Katedra
Lingwistyki Formalnej)
Prof. Janusz S. Bień - University of Warsaw (Formal Linguistics Department)
[email protected], [email protected], http://fleksem.klf.uw.edu.pl/~jsbien/
--
--
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
---
You received this message because you are subscribed to the Google Groups "tesseract-ocr" group.
To unsubscribe from this group and stop receiving emails from it, send an email
to [email protected].
For more options, visit https://groups.google.com/d/optout.
