OCRopus is set up for recognizing books and journal articles--pages consisting of blocks of horizontal text lines plus rectangular images.
Recognizing magazines, comics, manga, etc. requires telling OCRopus that text can occur at other orientations, and using other kinds of analysis algorithms. Some of those algorithms are already in OCRopus (e.g., the Voronoi page segmenter), but others haven't been integrated yet. Tom On Mon, Feb 16, 2009 at 09:04, Dummey <[email protected]> wrote: > > Having an issue trying to run ocroscript recognize on <http:// > www.onemanga.com/Naruto/435/006/>. > > dum...@dummey-desktop:~/Desktop$ ocroscript recognize 006.jpg > ocroscript: /usr/local/share/ocropus/scripts//recognize.lua:113: > CHECK ./ocr-utils/ocr-utils.cc:833 background_seems_white(a) > > Is this an error on the programs part or on my part by giving it a bad > image? > > > --~--~---------~--~----~------------~-------~--~----~ 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 -~----------~----~----~----~------~----~------~--~---
