but it is written in "how to train tesseract ocr-wiki pages" that all the characters of a single font must be there within a single tr file. I've done what you are saying but after training it is not recognizing characters well.
On Wed, Jun 9, 2010 at 3:53 PM, Jimmy O'Regan <[email protected]> wrote: > On 8 June 2010 13:46, Tanmay Kolay <[email protected]> wrote: > > Hi, > > I'm working with tesseract 2.04.I know at least 20 examples of > > each character must be taken for training.But in bengali there are > > almost 290 characters.so for each font i need at least 10 images.so i > > have to cat together the .tr files for each image into a single .tr > > file.I don't know how to do it.can any one help me with this and > > remaining training process. > > You can just specify multiple filenames at the command line. > > > -- > <Leftmost> jimregan, that's because deep inside you, you are evil. > <Leftmost> Also not-so-deep inside you. > > -- > 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]<tesseract-ocr%[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.
