I only have a limited number of samples, but that seems to be enough for now (100% detection rate for everything i have). If I can collate a few more then i shall retrain and post the updated language files and maybe a T3 compiled file.
I have posted the source files and the compile T2 language files on my site: http://beanland.net.au/Programming/dotnet/TesseractMICR.zip If you have any feedback, more samples etc, please send them to me (my email is in the readme.htm file of the zip) On May 28, 7:08 am, Dmitri Silaev <[email protected]> wrote: > Agree. We can make ready version 3.0x traineddata files from box/tiff > pairs community provides, crediting the commencement to Hunter. > > Warm regards, > Dmitri Silaevwww.CustomOCR.com > > > > > > > > On Fri, May 27, 2011 at 1:32 PM, Sven Pedersen <[email protected]> > wrote: > > Me too. I've worked with MICR fonts before, and I'd like to see high > > quality support for them in tesseract. I could spearhead a movement to > > get them working properly. I believe most people have wanted to do it > > commercially and have not shared their info, but if we did it as a > > community it could yield much better recognition quality. > > Thanks, > > Sven > > > On Fri, May 27, 2011 at 7:08 AM, Dmitri Silaev <[email protected]> > > wrote: > >> I'd appreciate having box/tiff pairs. > >> Thanks in advance! > > >> -- > >> Dmitri > > >> On Fri, May 27, 2011 at 5:11 AM, Hunter <[email protected]> wrote: > >>> I bit the bullet and did my own training - it wasn't as bad as i > >>> thought. I didn't include all of the control chars in the spec - just > >>> the ones i found on my cheque samples. Seems to detect all my cheques > >>> perfectly - so far. If any wants my training files or tessdata (v2) > >>> files, let me know. > > >>> On May 26, 5:04 pm, Hunter <[email protected]> wrote: > >>>> Does anyone have a MICR language file they are willing to share? > > >>>> I need to use Tesseract 2 (via TessNet2) to read cheque details. > >>>> Tesseract has a lot of difficultly reading the MICR font on the bottom > >>>> of the cheque so it will need to be trained. Rather than wasting a day > >>>> attempting to do this, it would be very cool if someone has this > >>>> already done. Even the box file would be a huge help. > > >>>> Thankyou in advance! > > >>> -- > >>> 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 > > > -- > > ``All that is gold does not glitter, > > not all those who wander are lost; > > the old that is strong does not wither, > > deep roots are not reached by the frost. > > From the ashes a fire shall be woken, > > a light from the shadows shall spring; > > renewed shall be blade that was broken, > > the crownless again shall be king.” > > > -- > > 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
