See "baseapi.h", functions TesseractRect() SetImage() (reportedly, Pix* variant is more likely to be supported) SetRectangle()
Then Recognize() or Get*Text() Since your images are binary, use 1 bit per pixel. Having implemented this approach, you will get image passing work extremely fast. Warm regards, Dmitri Silaev On Mon, Mar 28, 2011 at 8:53 PM, zl2k <[email protected]> wrote: > hi, all > > My application will generate bunch of separate binarized characters > and I need to feed the ocr engine for each of them. It will be very > costly if save each of them on disk as a tiff file and then call > tesseract. Is there a by pass so that my application (C++) can > directly call ocr and pass the image to it? Your comments are highly > appreciated. > > zl2k > > -- > 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.
