I don't know about single or double letters like that, but I use Open Book 9 sold by FreedomScientific.com. It is scanning and OCR software combined. There is a feature such that when a word consistently is recognized incorrectly in a certain way it can be automatically corrected. One goes into the settings of Open Book and types in the incorrect way the word is recognized and then one types in the way it should be recognized. After this is saved the next time the word is recognized incorrectly in that specific way it will be automatically corrected so that the OCR then has it spelled right.
On 1/3/2012 5:49 PM, Laurence Penney wrote: > Great stuff. It looks useful indeed. > > I see in the Thoreau that there are numerous cases where ‘ll’ is mistaken for > ‘U’. It would be splendid if, after just a few of these were fixed manually, > something could suggest performing numerous other replacements — particularly > cases where ‘ll’ was already a candidate for the OCR of that word-part. Is > this something that Abbyy can be induced to do? > > If it’s workable, the same kind of “manually fix a few, then induce an > algorithm to take over” approach would also apply nicely to the long s, at > which Google fails miserably. > > - L > > On 3 Jan 2012, at 22:22, Lee Passey wrote: > >> On Tue, January 3, 2012 1:05 pm, Laurence Penney wrote: >> >>> How about caching results of (at least) these two examples? >> Done: >> >> http://www.ebookcoop.net/ebookcoop/cu31924097556546.html >> >> http://www.ebookcoop.net/ebookcoop/tarzanofapes00burruoft.html >> > _______________________________________________ > Ol-discuss mailing list > [email protected] > http://mail.archive.org/cgi-bin/mailman/listinfo/ol-discuss > To unsubscribe from this mailing list, send email to > [email protected] _______________________________________________ Ol-discuss mailing list [email protected] http://mail.archive.org/cgi-bin/mailman/listinfo/ol-discuss To unsubscribe from this mailing list, send email to [email protected]
