Ok. I'm OCRing an image I've created. The training it's mine with a special digits font. The ocr works ok if the image has more than 3 digits.
In the last test I just did I see the problem only occurs when I use tesseractdotnet. Using tesseract.exe (with the same image i the same training) works correctly even using several PSM as the "automatic" and the "text line" or "word". With the library tesseractdotnet always returns me "void string" with all I've tried psm. It seems to be a problem tesseractdotnet or at least with the way I use it. Tesseract.exe with the default options works ok but tesseractdotnet does not work well with the same image that contains only 3 digits. Thanks for your help. On Mar 22, 8:55 am, zdenko podobny <[email protected]> wrote: > On Wed, Mar 21, 2012 at 7:22 PM, Jose Garcia <[email protected]> wrote: > > Hello, > > > I've trained tesseract with only this characters: 0123456789-. > > > I used one tiff with this characters, with 6 samples of each. > > > After the successfully training, tesseract only recognize if in the > > input tiff there are more than 3 numbers. With a tiff with, for > > example this numbers 65 it returns nothing but with a tiff with 6565 > > it returns ok, 6565. > > > Some idea? > > > Thanks. > > > What version did you use? > > How did you use tesseract (library or executable)? > What page segmentation did you use? > Where is example image? > > I am sorry but I do not have crystal ball ;-) If you REALLY want help, than > you have to provide details and example. -- 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
