Hi Tom, Thanks for your reply!
Yes, we only read digits. We use open CV for filtering, but not for the actual recognition. I was not aware of open CV's recognition abilities. What do you mean with the upstream pipeline? - Increase the images and sort out the whole digit? - Unfortunately we are not able to do that. Thanks Georg Am Montag, 26. August 2013 13:43:43 UTC+2 schrieb georg: > > Hello, > > I have a question regarding language files. > > We have a set of characters, which sometimes has cut off characters. > > It is my understanding that I can not train very different looking > characters in one set, because it causes tesseract to get confused. > > I would like to generate 2 tiffs (one for complete characters and one for > cut off ones) and then do the mft training. > > Is it true that mft training assembles both tiffs in one language file and > runs tesseract twice, first with the tiff for the whole characters and once > for the cut off characters? > > Does tesseract keep the tiffs separate although they are in the same > language file? > > How would you work this problem? - I want to try and keep the training > process as simple as possible (it is already complicated enough). > > Thanks for your help! > > Take care, > > Georg > > > -- -- 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 unsubscribe from this group and stop receiving emails from it, send an email to [email protected]. For more options, visit https://groups.google.com/groups/opt_out.
