Hello Tom, I checked the new ocropus version, and the recognition results are fine, see http://art1pirat.blogspot.de/2013/04/ocropus-07-erste-tests.html (in German). But I have two questions.
First, if I remember me correctly, previous versions of ocropus were able to use tesseract 3.02 training files. Is it possible to train ocropus0.7 with these files, too? Second, the fraktur example does not support 'long-s', therefore words like 'Wachstube' vs. 'Wachſtube' could be problematic in historical texts. Because in my personal project I digitize a book from 20th century with fraktur I could send you some full corrected wordlists and pages. Please send me anote, if this could be helpful With best regards Andreas -- 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/-/tgCF8l8dNC0J. For more options, visit https://groups.google.com/groups/opt_out.
