Hi Arthur, first of all I want to say thanks for sharing the trained data files to us. But I found that the "7" digit data I have is different like your trained data. My "7" digit has one more segment in the left top. So I was thinking to train by myself. But I got problem when I follow training instruction from here https://code.google.com/p/tesseract-ocr/wiki/TrainingTesseract3 especially in "Run Tesseract for Training" part. It did not give me *.tr file. Can you give me a clear instruction how did you train your data? Thank you in advance!
Sabrina. On Friday, 4 July 2014 08:13:12 UTC+8, Artur wrote: > > Hi Nick, > > I've just pushed the training data to my project page! > > https://github.com/arturaugusto/display_ocr/tree/master/training_source > > If someone come with improvements as you told, I will be accepting pull > requests. > > Artur > > > > 2014-07-03 18:47 GMT-03:00 Artur Augusto <[email protected] > <javascript:>>: > >> And thats why I created a project that uses OpenCV so user can real time >> control the erosion.. >> >> >> 2014-07-03 18:45 GMT-03:00 Artur Augusto <[email protected] >> <javascript:>>: >> >> Sure, just need some time to compile all stuff in a more organized way >>> and document it. >>> >>> I needed to apply some erosion to preprocess the font because of the >>> problem to recognize segmented fonts. >>> >>> My trained data only works with erosion. >>> >>> I will do that as soon as I can. >>> >>> 2014-07-03 18:27 GMT-03:00 Nick White <[email protected] >>> <javascript:>>: >>> >>> Hi Artur, >>>> >>>> On Wed, Jul 02, 2014 at 10:18:55PM -0300, Artur Augusto wrote: >>>> > As many people ask about how to use tesseract to read 7 segments >>>> display, I >>>> > decided to publish an open source sample project. >>>> > >>>> > If someone wanna check it: >>>> https://github.com/arturahttps://github.com/ >>>> > arturaugusto/display_ocrugusto/display_ocr >>>> >>>> Awesome, thanks so much for sharing! I was about to add it to the >>>> 3rdParty wiki page, but Zdenko beat me to it :) >>>> >>>> Can you share the source files for your training somewhere too >>>> (image and box files), so people can potentially improve on / add to >>>> the training themselves? >>>> >>>> Nick >>>> >>>> -- >>>> 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] <javascript:>. >>>> To post to this group, send email to [email protected] >>>> <javascript:>. >>>> 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/20140703212755.GB19831%40manta.lan >>>> . >>>> For more options, visit https://groups.google.com/d/optout. >>>> >>> >>> >> > -- 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/73052430-a525-4bbd-a177-a15e0bc55a9b%40googlegroups.com. For more options, visit https://groups.google.com/d/optout.
