One big problem, You dio not stil a a PG or DP text ebook. You do have any markup what so even! Plus, what happens if you give them the Google scan sets!! I have work with OCR that will get me 100% text accuracy, but it took a hell alot of training, aka human interaction. Also, OCR today achieves their accuracy from dictionaries and guessing at the correct spelling. Which under many circumstances this type of heuristics causes a quite a few errors. regards Keith. Am 04.03.2010 um 16:02 schrieb Michael S. Hart:
BB if it was realistic I would take you up on your bet. In 50 years their will not be a system finished that will do job of creating proper output anything above 95% fully automatically That is without any human interaction whatsoever..
_I_ will take that bet!!!
Even thought there are no realistic odds I will be here to collect.
I will be only too glad to have the proceeds go to PG, or In Memoriam.
The bet is that a Xerox machine type of scanning and OCR will produce a 95% accurate copy of certain pages selected from an average set of books, magazines, etc. Just go to a library and ask for samples.
Fair enough???
Michael
_______________________________________________ gutvol-d mailing list gutvol-d@lists.pglaf.org http://lists.pglaf.org/mailman/listinfo/gutvol-d