Thanks for this. I used ver 0.4 for my final year dissertation to recognise handwritten historical documents (Gearge Washington's handwriting) but wasn't successful at creating a good character model so recognition rate was close to nil. I had split each word as separate images and had the corresponding ground truth but didn't have enough knowledge of the ocropus libraries to create cseg files for ultimate extraction of chararacters. I plan to give it another go with the new version.
Cheers Raj On Oct 9, 6:03 pm, Tom <[email protected]> wrote: > The code refactoring is finally nearing an end and the next release is > getting closer and closer. > > Part of that is some repository changes. The toplevel "ocropus" repository > now is a repository containing subrepositories. You should be able (on a > recent Ubuntu system) to type: > > hg clonehttps://code.google.com/p/ocropusocropus > cd ocropus > sudo sh install-ubuntu-packages > sh compile-ocropus > > If you still need access to the old ocropus repository, you can pull > fromhttps://code.google.com/p/ocropus.ocroold > > Tom -- 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.
