The OCRopus 0.4.1 release is up.  It fixes the problem that made
training fail.  There's also quite a few changes behind the scenes,
including a new string class that rationalizes Unicode handling
(written by Matthias Reif), a new abstraction for book level OCR
(IBookStore), and multipage TIFF support.  OpenMP has been disabled by
default since it made debugging too hard; however, you can re-enable
it if you need the performance (3-4x faster on a four core machine).

It's not a downloadable tar file, but simply a Mercurial tag (to
encourage use of Mercurial and also because we probably need to make
small updates anyway).  Please follow the instructions on ocropus.org
for obtaining it.

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