Hi again, On Fri, Jul 20, 2012 at 09:46:37AM -0700, Nikola Ivanovic wrote: > With increased resolution of image to 2000px I'm getting even better results, > with command > > tesseract ocr1.png outtest2 -psm 6
Great :) > But still there're some issues: > - after unpacking eng.traineeddata where can I find components of it? They're > not in Tesseract directory. It will be in the directory you ran the combine_tessdata program from. If you're on Windows I guess that might be your "My Documents" folder? I'm not sure, though, I'm not very familiar with Windows. > - can I somehow edit my boxfile in boxeditor for characters that I'm not > satisfied with? The reason this is a bad idea is that you can't just train a few characters that get poor results and combine it with an existing training. So you would have to train for all characters you might need, and it would probably take a while. > - is there a way to preserve original table layout? or artificaly get one: > define large blank spaces as TAB space, etc? > - can I save file as cvs or similar, or just as .txt? Search the archives. I haven't done this myself, and I don't think it's very easy to do, but there have certainly been people keen to do that in the past. > Thank you all for helping. You're welcome! Nick -- 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
