http://groups.google.com/group/tesseract-ocr?pli=1
Someone named Hunter posted about a year ago with a zip file of E13B MICR font training data, and someone else posted about the OCR-A font. Martin Pierre posted about OCR-B but I don't see the solution... --Sven On Wed, May 9, 2012 at 9:31 AM, Franco Giustetto <[email protected]> wrote: > thank you Sven, > I was searching for that, because I suppose (tell me if i'm wrong) that > using specialized training for a single point should improve speed and > accuracy. > 'cause I'm new in both tesseract and google groups maybe I've performed a > wrong search, where I can find the archive you are talking about? > franco > > > > 2012/5/9 Sven Pedersen <[email protected]> >> >> Someone has done training for the OCR-B font -- are you using that >> training data? >> Search the archives and you'll find the files to download. >> --Sven >> >> On Wed, May 9, 2012 at 3:21 AM, [email protected] <[email protected]> >> wrote: >> > Hello, >> > I 'm trying to build up a program to read payment slip. The slip >> > contain a single OCR-B line on the bottom. That line is a record >> > containing some coded information. It is divided in four blocks >> > ( fields) but only three of them are delimited by special character >> > separator and contains a modulo10 control character. >> > In my first try I simply pass a Grayscale cropped image to Tesseract >> > and set in initilization 0123456789>+ as set of allowed char. >> > This gave me 70% of accuracy. >> > I know that for numbers I cannot apply a dictionary (that can boost >> > accuracy to near 99%) but for payments, 70 % of accuracy is not an >> > acceptable result. >> > Does anybody know how could I improve accuracy? >> > >> > thank you very much in advance >> > Franco >> > >> > -- >> > 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 -- 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
