Hi all,

I have a page from a camera. Here is a sample line from the page:

http://halfbakedmaker.org/wp-content/uploads/2010/04/original.png

And here is the result from book2pages:

http://halfbakedmaker.org/wp-content/uploads/2010/04/binarized.png

After pages2lines, I get these two files for this particular line:

http://halfbakedmaker.org/wp-content/uploads/2010/04/01000a.png
http://halfbakedmaker.org/wp-content/uploads/2010/04/01000a.rseg.png

Neither of those lines is of very good quality compared to the full-
page binarized version from book2pages. So what should I be using for
training? I'm worried that if I segment the binarized version myself
and train on that, OCRopus will still fail because it seems to take a
totally different direction when it breaks the page into lines.

Any ideas?

Thanks,

--Rob

-- 
You received this message because you are subscribed to the Google Groups 
"ocropus" 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/ocropus?hl=en.

Reply via email to