Thanks, Quan! I appreciate you elaborating and including a link. On Friday, May 6, 2016 at 11:56:22 AM UTC-4, Quan Nguyen wrote: > > Specifically, ChoiceIterator. > > https://github.com/tesseract-ocr/tesseract/wiki/APIExample > > On Friday, May 6, 2016 at 10:17:43 AM UTC-5, Tom Morris wrote: >> >> 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/718fef0d-1502-4417-8d25-84845a60a28a%40googlegroups.com. For more options, visit https://groups.google.com/d/optout.
