I'm actually training with several other TIFF images which contain the "Circle M" symbol (uppercase M inside a circle). In all cases, tesseract reports the error message "Couldn't find a matching blob". So I think the issue is something fundamental with the algorithm rather than just an anomaly with the image I posted. I suspect that the circle around the M might have something to do with it but I don't know enough about tesseract's algorithm to know how it handles this situation. Are there any parameters I could use that would instruct tesseract to use the raw image as-is rather than trying to match blobs?
On Sunday, May 27, 2018 at 8:07:13 AM UTC-6, Quan Nguyen wrote: > > You need a much larger sample, in the range of hundreds or at least > several dozens, so that even though some symbols could experience "Couldn't > find a matching blob" errors, other samples would get picked up. > > > -- 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]. To post to this group, send email to [email protected]. Visit this group at https://groups.google.com/group/tesseract-ocr. To view this discussion on the web visit https://groups.google.com/d/msgid/tesseract-ocr/a480d0b9-8764-4f35-ab39-fcc318ca42ad%40googlegroups.com. For more options, visit https://groups.google.com/d/optout.
