I'm trying to do the same thing, and getting similar wrong results. I think the issue for me is the resolution of the image thats being supplied to the ocr.
On Friday, January 11, 2013 9:15:33 AM UTC, sav wrote: > > Dear All, > > I am now needing to OCR the *MRZ* characters on the *Passport*. These > characters are in mostly OCR-B font. > I use two url as a reference : > 1. http://code.google.com/p/tesseract-ocr/wiki/TrainingTesseract3 > 2. > http://michaeljaylissner.com/blog/adding-new-fonts-to-tesseract-3-ocr-engine > Now the problem is that box file is displays all true characters but > when I try to ocr that passport or any other document which has same font > then it was not recognize the all true characters. > Mainly it gives wrong output for O,0,W,M,Z,2,4,V characters. > Can anybody give me some advice on this, or image pre-processing > technique to improve the OCR result? Thank you all! > -- 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
