Did you ever find a solution for this, and what trainingset / dataset are you using? :-)
On Friday, October 1, 2010 4:11:15 AM UTC+2, OCR Newbie wrote: > > Hi All, > > Currently I am trying to train 7 segment display by Tesseract, I am using > the training image that has black background and white 7 segment numbers, > when it comes to testing, for black background and red LED display it works > just fine (relatively sharp contrast), but when I want the Tesseract to > detect something like the gray digits and white background lcd display (a > digital watch for instance) , the Tesseract will mistakenly take the > background into part of the recognition process and the result is a mess. > I know I need some pre-processing first, but I am not sure what kind of > pre-processing. > > Thank you!! Any help is appreciated! > -- 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
