From: David Starner (prosfilaes@gmail.com)
Date: Tue Jan 31 2006 - 17:32:54 CST
On 1/31/06, Kent_Spielmann@sil.org <Kent_Spielmann@sil.org> wrote:
> Does anyone know of OCR software solution that permits mapping to the full
> Unicode character set as output from the character recognition process?
> This needs to include mapping to base character+combining character
> combinations.
This may not be the solution for you, but I've used Finereader to OCR
such texts by training it to use ASCII sequences like [3] and [4] for
the tresillo and cuatrillo. Then I can simply search and replace (or
sed) the output to get Unicode text.
This archive was generated by hypermail 2.1.5 : Tue Jan 31 2006 - 17:44:59 CST