I noticed that, for some pages, the ocropus deskewing does not work
well; most of the time it does work well.  An example of a page, and
its deskewing by ocropus and by omnipage15 is visible at
http://jfunderburk3.com/ocropusexamples/deskew1/.

Is there a way to 'tinker' with how the ocropus deskewing works.  Can
ocropus generate a statistic for a given image which could be used to
describe the quality of the deskewing?

Below is the log.txt file from the web reference that describes the
situation.

The example deskew1.lua just uses one method (cleanup) of
'make_DeskewPageByRAST'. What should I look at to learn what other
methods are available?  I am particularly interested in knowing how to
use more of the layout analysis capabilities of ocropus.

Thanks.

log.txt:

An example of a page which where the deskewing of a scanned
image is visibly better by the commercial program omnipage 15
than by ocropus.  Two questions are
1. Why is omnipage better than ocropus for this page?
   For other similar pages I have examined, ocropus and omnipage
   provide results difficult to distinguish by visual inspection.
2. Is there a way to generate a statistic in ocropus that would
 measure how good the deskewing of a given page is? By examining
 such a statistic, one could have some confidence that a page
 is deskewed adequately or poorly.

The files are:
 wil-020-original.jpg   the original scanned image found in nature.
 wil-020-omnipage.jpg   the result of omnipage15 deskewing.
 wil-020-ocropus.jpg    the result of ocropus 3.1 deskewing
 deskew1.lua            ocropus script used to deskew

http://jfunderburk3.com/ocropusexamples/deskew1/
--~--~---------~--~----~------------~-------~--~----~
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