It is clear that, out of the box, Abbyy Fine Reader is more accurate. It may well be still more accurate with training, maybe due to post-processing. Many people who produce effective solutions on this list use pre- and post-processing scripts to deal with various common issues. With all that, Tesseract accuracy may be over 96% for normal text (mostly letters, not numbers and punctuation), judging by self-evaluations... --Sven
On Wed, May 23, 2012 at 12:03 PM, Scott Oom <[email protected]> wrote: > We are working on automated testing tools for applications and games. > > We want to be able to verify various text in the UIs in different > languages and have been experimenting with Tesseract OCR and having a > lot of fun with it. > > In 2007, Ray Smith mentioned that "Tesseract is now behind the leading > commercial engines in terms of its accuracy." > > What commercial engines are more accurate than Tesseract and in what > ways? Can Tesseract OCR approach the commercial engines with training > and adjusting of parameters or is it still behind? > > Thanks, > -Scott > -- 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
