You'll need to use the API to get that level of control. On Thursday, May 5, 2016 at 8:22:54 AM UTC-4, [email protected] wrote: > > I want to use tesseract to convert images of a single Chinese/Japanese > character which will be handwritten by a client-side user on an html5 > canvas. > > > After several tests, I find Tesseract's recognition of handwritten chinese > characters to be very good, but sometimes the result is slightly off. > Sometimes I get the correct 木 character as output, but sometimes I get the > slightly different 本 character. > > > How can I make Tesseract output something like a list of top 10 best > matches, one of which will likely be the desired result, instead of just > outputting one incorrect result? > > > I want it to do something like: > > > Command: tesseract tree.gif out -psm 10 -l jpn ----> Output (best > matches): 本, 木, 休, 十, 八, 六,.......etc > > > An example image I'm using is below. > > > <https://lh3.googleusercontent.com/-wEN7FNMLGbc/VysTLEjen-I/AAAAAAAAAAM/iR2d7jORK4MjZuCgQGhqZIUc7_0dEyC5ACLcB/s1600/tree.gif> > >
-- 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 https://groups.google.com/group/tesseract-ocr. To view this discussion on the web visit https://groups.google.com/d/msgid/tesseract-ocr/d6a1fd59-7d8b-425f-b621-9599f10f03ab%40googlegroups.com. For more options, visit https://groups.google.com/d/optout.
