I plan to do this myself at some point, but thought Skip (or someone else) might want to beat me to it:
Google/UNLV have (re)released an open-source* OCR engine, which they claim is better than any other open-source OCR engine. So it would be interesting to compare the classification with this to that with ocrad. http://google-code-updates.blogspot.com/2006/08/announcing-tesseract- ocr.html =Tony.Meyer * The license is a bit vague, unfortunately. They state it can be freely used/distributed for research/development, and that for commercial use you have to contact the authors. However, they don't cover the middle ground (non-commercial non-research), which SpamBayes falls under. _______________________________________________ spambayes-dev mailing list spambayes-dev@python.org http://mail.python.org/mailman/listinfo/spambayes-dev