I realize that things look pretty quiescent with OCRopus right now,
but we're busy working on the next release.

The biggest change for the release will be that all top-level
functionality will be exposed and programmable from Python.  This
should make customization, documentation, and training significantly
simpler.

We've also developed new training and correction tools (I mentioned
these before) and have been using them for training better character
recognition models.

Support for ligatures and unicode is also coming along.  We'll
probably not finish that before the next release, but we want to
finish the C++ portion of that so that all the remaining logic for
unicode and ligature handling can then be done in Python.

The biggest holdup has still been the delivery of our new compute
servers.   They were supposed to arrive a couple of months ago, but
they're supposedly on their way to us now.  Once they arrive, I expect
a few more weeks of training and testing before we push a functional
release out that people can finally start hacking and building on.

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