It should be fairly easy to retrain OCRopus for this. There's a little bit of documentation on the Wiki for how to do this. There will probably be some changes to the procedure by the beta release.
Tom On Thu, Aug 27, 2009 at 23:55, Nathaniel Irons<[email protected]> wrote: > > Hello, > > I'm trying to evaluate OCRopus' suitability for reading the MICR strip > of data found on the bottom of printed checks. > > http://en.wikipedia.org/wiki/MICR > > I experimented a little with the TakOCR package, which led to decent > untrained results on miscellaneous printed text, but nonsense when > trying to read the routing/account/check numbers. > > On the plus side, it's a small set of potential characters, almost all > numbers, in a uniform typeface. On the minus side, the characters > which aren't numbers are delimiters not otherwise found in nature, and > apparently the standard E13B typeface is odd enough to stymie most > general-purpose OCR packages. I'd appreciate some guidance before > attempting to bend OCRopus to my will. > > Thanks, > > -nat > > > > --~--~---------~--~----~------------~-------~--~----~ 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 -~----------~----~----~----~------~----~------~--~---
