There is no table detection or recognition in OCRopus yet. Doing table recognition well is quite tricky, and there are a number of different methods for it.
Table detection, table recognition, math detection, math recognition, and similar tasks are on our to do list, but our primary focus right now is on book OCR. If you want to get started with table recognition, here are some papers: http://scholar.google.com/scholar?num=50&hl=en&lr=&q=table-recognition You can use the character and word bounding boxes that OCRopus yields as a starting point. Tom On Sun, Sep 28, 2008 at 23:55, [EMAIL PROTECTED] <[EMAIL PROTECTED]>wrote: > > Hello forum, > > how would I go about configuring Ocropus to scan a document for three > column tables? > > My documents are financial reports from cooperative owned > apartmentbuildings in Sweden. Each coop have their own layout, but > there all contain a couple of tables that look something like: > > Income > 2005 2004 > > Fees 11000 10000 > Recycling 800 0 > > 11800 10000 > > I never did OCR before and I'm not sure in what end to start but would > like to extract each such table and access the content in structured > form. > > > karl > > > --~--~---------~--~----~------------~-------~--~----~ 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 -~----------~----~----~----~------~----~------~--~---
