I have found that there is a scale-dependency in the curly quotes handling. If I create 300 dpi versions of my scans, then Tess3.01 begins working much better. That is a huge relief and makes tess usable. I wish I could use the 600dpi scans. I have them. Seems like this might be a little bug. Maybe there are some other little bugs that only go away when dpi around 300 is used.
One annoyance: the box maker never joins the double-curly-quotes into a single box. I always have to merge it, and it takes a long time. Finally, even though Tess is usable with 300dpi for the curlys, there is another problem where it occasionally will try to include the right-double-curly-quote into the line above it. Luckily this happens rarely, and is easy-ish to edit to fix the output. But it would be better not to need this. -- You received this message because you are subscribed to the Google Groups "tesseract-ocr" 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/tesseract-ocr?hl=en
