Leptonica is used only for text/image segmentation, that is if there are images (half-tones, graphics) in your documents and tesseract outputs a large number of garbage characters originating from these images then text/image segmentation with leptonica will help you in removing those images before feeding the document to tesseract. For normal documents containing only text, you don't need leptonica.
Cheers, Faisal On Tue, Nov 25, 2008 at 4:19 PM, Andrew <[EMAIL PROTECTED]> wrote: > > > > On Nov 25, 8:28 am, "Thomas Breuel" <[EMAIL PROTECTED]> wrote: > > We'll try to come up with a workaround. > > > > Generally, Leptonica will likely be dropped as a requirement for OCRopus > > when the built-in text/image segmentation catches up with Leptonica; that > > will simplify builds and configuration. > > > > How essential is Leptonica to the accuracy of the recognition quality > (or speed?) of this software? > > I currently have a (presumably) working version of ocropus, compiled " > --without-fst --without-leptonica ". Should I persist in integrating > FST and Leptonica into my build? (I say "presumably" because it > currently complains about my tesseract not being trained/configured > (with box pairs?)) > > Thanks > andrew > > > --~--~---------~--~----~------------~-------~--~----~ 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 -~----------~----~----~----~------~----~------~--~---
