We're developing OCRopus primarily for book capture applications, for historical documents, and as a testbed for research ideas. OCRopus used to be developed as a monolithic C++ library and set of commands, but the problems with that were that there are too few good C++ programmers and that C++ lacks good standards for things like images and unicode. Over the last 1.5 years, we converted OCRopus to a collection of Python modules, some with native code some in pure Python. There is full Unicode support now and lots more training and evaluation tools. We're still doing some refactoring of the C++ libraries (mostly removing all the dead code), but the Python code is the new, stable API. We also have new layout analysis, an HMM recognizer, and other tools that are going to be released fairly soon now.
Can you build a Windows product on it? Probably, but you have to use Python in some form or another. That should not be a problem (other products ship that way). 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.
