Forgot to mention: I'm using Ubuntu 8.04, commandline tesseract.
Jon wrote:
> Hi all,
>
> I'm still in the progress of training tessearct for a specific Hebrew
> font.
> It's quite advanced, but I ran into a problem with a certain letter
> that keeps being interpreted as the numeric digit 1.
> The said Hebrew letter is the letter Vav, that kind of looks like an
> upper case i .
>
> So, the problem is that the word HESHBONIT (spelled here in English
> characters, but it's actually in Hebrew) is being rendered as
> HESHBON1T.
>
> I've added the word HESHBONIT to freq-dawg and user-words.
> I've also added the following to DangAmbigs:
>
> 1[tab]1[tab]1[tab]I
>
> To indicate that "I" may be incorrectly recognized as 1.
>
> But after all of these, it's still comes out HESHBON1T.
>
> Anything I missed?
>
> Thanks
--~--~---------~--~----~------------~-------~--~----~
You received this message because you are subscribed to the Google Groups
"tesseract-ocr" group.
To post to this group, send email to [email protected]
To unsubscribe from this group, send email to
[email protected]
For more options, visit this group at
http://groups.google.com/group/tesseract-ocr?hl=en
-~----------~----~----~----~------~----~------~--~---
