> Is there a way to customize column space?  (I hit a "MAX COLUMNS"
> error during the translate as well).

You can change the page segmenter to a different segmenter
(SegmentPageBy1CP, SegmentPageByRAST1).

> Also, has anybody had any luck in restricting ocropus to just
> interpreting numbers? (i.e. alot of zeros come out at O's) .

Without retraining, you can create a new language model.  For that,
you need to generate a model un OpenFST format (a generalization of
regular expressions).  You can use pyopenfst to do that.

http://code.google.com/p/pyopenfst/

You probably also need to retrain the character shape model for better
performance.  The good news is that there is a set of good tools for
that now, but it needs to be documented.

Tom

-- 
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