I just pushed a whole lot of new revisions to OCRopus.  All the
(supported) OCRopus APIs are available from Python using native Python
datatypes.  This means that you can now easily use a very large
collection of image and pattern recognition libaries with OCRopus.

The Python APIs also document all the supported OCRopus APIs (you can
extract documentation using standard Python documentation extraction
tools), addressing the need for better API documentation.

All the toplevel commands have also been converted to Python and
should support Unicode and ligatures.  (In fact, Unicode and ligature
support was one of the main reasons behind the refactoring and binding
to Python, because doing that in C++ and/or Lua would have been much
harder.)

What remains to be done is to port over some recognition strategies
that aren't in the Python version of the line recognizer yet, and then
finally train some better models.

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