Tesseract still threshold before recognition. You need a really good adaptive thresholding, possibly combined with prescaling.There would have to be a lot of major changes to support "native" greyscale recognition. Ray.
On Sun, Jun 14, 2009 at 1:25 PM, nguyenq <nguyen...@gmail.com> wrote: > > You can try VietOCR, a frontend program to Tesseract OCR engine. > > http://vietocr.sf.net > > On Jun 14, 8:00 am, eddiec <edwardch...@gmail.com> wrote: > > Hi, > > > > I have some scanned images I am trying to OCR. The images are > > grayscale and scanned from microfilm. The packages I have tried to OCR > > the images with first convert the images to black and white and then > > OCR. The problem is that the B&W images are far less legible than the > > grayscale images and therefore the OCR has a low accuracy rate. > > > > Is there any way to OCR a grayscale image natively? > > > > TIA > > > > eddiec :-) > > > --~--~---------~--~----~------------~-------~--~----~ You received this message because you are subscribed to the Google Groups "tesseract-ocr" group. To post to this group, send email to tesseract-ocr@googlegroups.com To unsubscribe from this group, send email to tesseract-ocr+unsubscr...@googlegroups.com For more options, visit this group at http://groups.google.com/group/tesseract-ocr?hl=en -~----------~----~----~----~------~----~------~--~---
