Ocrad vs Tesseract OCR

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.