Re: Optical Character Recognition (OCR)

Hi,

Don't know if it'll be of help.

Check out, where Rhys Davids Pali English Dictionary is
the guys who did the input / conversion and the technical aspects,
http://dsal.uchicago.edu/dictionaries/contact.html
http://dsal.uchicago.edu/dictionaries/techinfo.html
http://www.inputcenter.com/PAGES/EXAMPLE.HTM
http://www.inputcenter.com/PAGES/SERV.HTM

teruvan saranayi,
Aruna

--- In Pali@yahoogroups.com, Walter <walter@...> wrote:
> I'm wondering if anyone has found an OCR package that can
> successfully scan a printed Pali text, complete with all
> diacritics (dots, bars, retroflex(?) markers, etc.). With my
> existing software (FineReader), I seem to be able to scan all
> of the characters except 'm with dot beneath', and 'd with
> dot beneath', as these do not occur in the Unicode
> ( http://www.unicode.org/ ) standard on which the software
> is based, except through 'combining' characters which it
> doesn't seem to scan properly.
>
> Therefore, this is just a quick request to see if anyone's
> had any success with alternate packages.
>
> Regards,
> Walter