Indeed - I am experiencing illegal box coordinates in about 40% of the
images I scan (I am using Tesseract 3.0). You can find such an example
on:
http://www.scanbizcards.com/IMG_0735.JPG
and the resulting boxes (after reducing image size by 2 along X and Y
dimension) on:
You can get the compiled assembly here
http://www.pixel-technology.com/freeware/tessnet2/bin.zip
You can get sample project TesseractOCR.csproj here
http://www.pixel-technology.com/freeware/tessnet2/dotnet.rar
If you don't know how to add the tessnet2 assembly reference in
TesseractOCR project,
hi, i was wondering how can i train tesseract with a new font.
i need to add the tahoma font in the italian language.
how can i see if there is already in (i think not, since pages with
this font are little weird)?
i read the wiki, but how can i add a new font, not a new language?
thanks in
Hi,
I'm doing a project in openCV(with visual studio 2008). I need to identify
serial numbers as a part of the project. So I was trying to configure
tesseract 2.04. But I wasn't successful.If anyone can give me a guide to
configure this,that will be a great.
thanks in advance
--
.Irusha
4 matches
Mail list logo