On May 14, 3:23 am, Tom <[email protected]> wrote:
> OCRopus provides page segmentation algorithms that do just this.
>
> The C++ and Python interface is called ISegmentPage. The command line
> tool is called ocropus-pseg (you probably need to call ocropus-
> binarize first). It outputs a color image that assigns a different
> color to each region. There are multiple algorithms implementing page
> segmentation; not all algorithms work for all page types.
>
I managed to compile the entire ocropus suite now, but I noticed
that after running :-
$ ocropus-pseg mypic.png
It will output a file mypic.pseg.png, but when I view the file, it's
quite far away
from what I want to accomplish, basically it did not put the few
rectangular
area of text into different colors.
Viewing mypic directory, it shows a few pictures inside, but each
picture contains
of one line element, which is not what I am looking for. Because in
the original
picture, it contains multi-line segment ( such as a postal address ),
I want to group
them together.
Is it the limitation of the algorithm ? Is there a quick way for me to
try different algorithms ?
--
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.
