Could you please file a bug report and attach the image? This is going to get fixed implicitly in later versions of OCRopus, as we add better text/image segmentation to the pipeline.
For now, we should probably just add a simple check to the deskewer to make sure that it doesn't run if there are too many components overall or too many small components (Faisal?). Tom On Wed, May 13, 2009 at 11:44, kaplun <[email protected]> wrote: > > Dear OCROpus developer, > > I have found an interesting test for the current deskewing process of > OCROpus. > > If you try to run deskewing (tested with OCROpus-0.3.1) on the bzip2ed > picture > I've temporary put at: > > <http://cdsware.cern.ch/tmp/rotated-image-000001.ppm.bz2> > > the deskew process will use an enormous amount of memory. > > This is due to the very bad scanning procedure that has been used to > digitalize the document. > > Is there/will be a way to discover such situation within the deskewing > process > itself? > > Best regards, > Samuele > > > --~--~---------~--~----~------------~-------~--~----~ 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 -~----------~----~----~----~------~----~------~--~---
