We're interested in supporting handwriting recognition in OCRopus, but it won't be based on Tesseract; Tesseract is optimized for printed text and doesn't look like it can be adapted well to handwritten text.
After the release of the new line recognizers (Dec/Jan), the infrastructure will be in place for doing a better job at handwriting recognition. Tom On Fri, Dec 5, 2008 at 04:04, Luke <[EMAIL PROTECTED]> wrote: > > If you end up taking the lead on this (I don't believe anyone else > is), I'd be interested in what you do. I used the Tesseract engine in > a recent project and had reasonable results, but I'm sure there's room > for improvement. I was able to start small with a VERY small > alphabet, which sped up the training process but it also didn't > require any programming. > > Luke > > On Dec 3, 12:26 pm, Denis <[EMAIL PROTECTED]> wrote: > > Hi, > > > > I read on the Projects web page : > > "Adaptation to Handwriting > > The OCRopus system is derived from a handwriting recognition system. > > To restore that functionality requires some programming, training on > > handwriting data, and testing the system." > > > > Did someone look at this problem ? > > Is someone working on it ? > > Does someone know what "some" means in the above description ? > > > > Thanks in advance. > > > --~--~---------~--~----~------------~-------~--~----~ 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 -~----------~----~----~----~------~----~------~--~---
