On Monday, May 9, 2011 4:01:01 AM UTC-4, Ump wrote:
>
> However, is it possible to specify regions which I want? In that code, 
> it try to make region on every text area in the page. 
>

No, it's not possible, nor do you have to.  What you can do is cut out the 
regions you want and then pass them to the recognizer.

Also, I tried to compile the source code(based on ocropus-pages... 
> modify a bit) on desktop but ocrolib is not found. Do you have any 
> solution of this? 
>

I'm not sure what you mean by "compile".  ocropus-pages is Python code; it 
doesn't need to be compiled.  And ocrolib is a Python library.  If you 
follow the install instructions, it will be installed in the right place. 

And if I have text-image that ready to OCR to plain-text (no need to 
> make segmentation,region etc.), Is there any api-command in python to 
> OCR it directly? 
>

Yes, again have a look at ocropus-pages (in Python); it is commented and 
explains how each part of the process works.

Tom 

-- 
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