has trainable layout recognition been integrated into OCRopus yet?
if so, please share the links to such documentations, tutorials.

if its still under development, can i build a bleeding edge version from 
source code? 

please share the details.

thanks,

On Friday, 11 March 2011 07:19:35 UTC+5:30, Tom wrote:
>
> It can recognize the text pretty well, regardless of layout.  You can also 
> use the XY-cuts or Voronoi layout methods to get blocks.  None of those 
> will reliably give you a tabular structure, however.
>
> We have developed and published trainable layout recognition, but it's not 
> integrated into OCRopus yet.
>
> 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].
To view this discussion on the web visit 
https://groups.google.com/d/msg/ocropus/-/r3by0hLJflEJ.
For more options, visit https://groups.google.com/groups/opt_out.


Reply via email to