The latest version of OCRopus (0.7) has a new recognizer based on recurrent neural networks.
It should be easy to train for printed materials, but it probably isn't so good for handwritten inputs in the current release. Tom On Sunday, February 24, 2013 2:19:56 PM UTC-8, [email protected] wrote: > > Hello all, > > I have been to the painful job of training tesseract and learn about it > just to be quite disappointed. > > I am hoping that OCROPUS is easier. > > First question I would like to ask is to learn about any kind of > documentation on how to train it for handwritten recognition. > > Has anyone tried it? I need a OCR engine that can do both handwritten and > normal typewriter recognition from older forms. > > Also, is there any image preparation that I need to go over before using > the engine? > > As I am new to it, I appreciate any pointers specially those related to > handwritten recognition. > > Thanks. > -- You received this message because you are subscribed to the Google Groups "ocropus" group. To unsubscribe from this group and stop receiving emails from it, send an email to [email protected]. To post to this group, send email to [email protected]. To view this discussion on the web visit https://groups.google.com/d/msg/ocropus/-/vgk49cNkRqYJ. For more options, visit https://groups.google.com/groups/opt_out.
