OK. Incidentally, the same training data should be usable with the new 0.7 recognizer. I hope we'll be releasing that before the end of the year. I put up some sample results on ocropus.org
Tom On Wednesday, November 21, 2012 3:33:47 PM UTC+1, MattJ wrote: > > Thanks Tom, training my character model has been fairly successful (~0.1 > edit distance/character in a diverse and degraded document set). Only very > few lines had this problem. -- 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]. To view this discussion on the web visit https://groups.google.com/d/msg/ocropus/-/3VZi7C2A8W4J. For more options, visit https://groups.google.com/groups/opt_out.
