It might be rash to assume that an OCR package which claims to read
"Greek" can handle polytonic Greek well, unless that specific claim
was made (and that goes for the TEI project, too).
I believe that the Perseus project has done some experiments with
training a commercial OCR package with support for monotonic Greek to
read polytonic (I think FineReader, though I may be wrong). See also
the efforts of Federico Boschetti with Google's OCR
(http://www.himeros.eu/).
Best wishes,
Peter Heslin
On Sat, May 8, 2010 at 7:04 PM, Ricky <[log in to unmask]> wrote:
> Hello,
> I've been told this is just the forum in which to find some insight to the following problem: We have about 270 pages of typewritten and critically edited ancient Greek text that we'd like to scan and digitally edit. It appears that there are several kinds of OCR software available to do this, such as Anagnostis, FineReader and Google's open source OCR. From your own experience in working with these types of manuscripts, do you have a program that you prefer, or perhaps another method to recommend?
>
|