It seems that tesstrain.sh creates a training file containing most of the bigrams, and then generates tif/box pairs from training file, but never uses the tif/box pairs. Is that intented?
(Also, the comment for the creation of the training file says "Take only the ngrams whose combined weight accounts for 95% of all the bigrams", but the code seems to use 99%.) Thanks, Eric. -- You received this message because you are subscribed to the Google Groups "tesseract-ocr" 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]. Visit this group at http://groups.google.com/group/tesseract-ocr. To view this discussion on the web visit https://groups.google.com/d/msgid/tesseract-ocr/5c2c18e6-e108-4134-ad22-3b03f3eead2a%40googlegroups.com. For more options, visit https://groups.google.com/d/optout.
