If you can afford adding a border then you certainly can use e.g. Photoshop or ImageMagick to remove the bottom dark line. Most likely this will suffice, but also you might need to adjust the contrast/brightness to make the image look more like a normal paper image. Then Tesseract should work fine.
Warm regards, Dmitri Silaev www.CustomOCR.com On Mon, Nov 14, 2011 at 7:35 PM, Rick Appleton <[email protected]> wrote: > Hello, > > I hate to do this, but I'm out of ideas. I have an image from which I'm > trying to recognize text. The image in question is attached to the post, or > you can view the image at > http://imageshack.us/photo/my-images/855/photo1ws.jpg/ > > I'm unable to recognize the text with sufficient quality using Tesseract. > One of the things previously suggested to me was adding a border around the > image. That doesn't help in this case. > > http://www.onlineocr.net is able to correctly recognize the text with only a > single character error (the 'c' is recognized as an 'r'), so I'm hoping I > could tweak some of Tesseract's settings. > > I've done little to no pre-processing on the image, as that has usually led > to worse results in the past. > > I hope someone here can give me some pointers. > > Kind regards, > Rick Appleton > > -- > 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
