Hello,
i previously was using an older version of tesseract, and i have switched to
svn HEAD. i have an issue i didn't have with the previous version. before each
recognition i'm setting the whitelist parameter to only numerical digits and
"<" and ">". Also, i'm using a trained data i have created from scratch, but
which contains all the alphabet for this font...
The command i use is:
[My stuff...]
_tessApi->setVariable("tessedit_char_whitelist", "><0123456789");
[Start recognition...]
Sample of a result i get:
3000657806S<00S60':0<3000657B0<
As you can notice, the whitelist is completely ignored… On the previous version
it helped tesseract a lot using the whitelist because some characters could not
be "mistaken" for others.
Do you have any idea what i'm doing wrong here?
Thanks a lot for your kind help!
Pierre.
--
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
