[spambayes-dev] Ocrad vs Tesseract OCR

[skip at pobox.com]

    Tony> I plan to do this myself at some point, but thought Skip (or
    Tony> someone else) might want to beat me to it:

    Tony> Google/UNLV have (re)released an open-source* OCR engine, which
    Tony> they claim is better than any other open-source OCR engine.  So it
    Tony> would be interesting to compare the classification with this to
    Tony> that with ocrad.

    Tony> http://google-code-updates.blogspot.com/2006/08/announcing-tesseract-ocr.html

Thanks, I'll try to take a look when I get a chance.  Alas, the SF link is
currently giving an Internal Server Error message.  (Jeez, what are the
chances???)

    Tony> * The license is a bit vague, unfortunately.  They state it can be
    Tony> freely used/distributed for research/development, and that for
    Tony> commercial use you have to contact the authors.  However, they
    Tony> don't cover the middle ground (non-commercial non-research), which
    Tony> SpamBayes falls under.

I suppose we ought to contact the authors, just to be on the safe side.

Skip