I'm looking at possibly using tesseract 4 for license plate recognition. Currently I've use downloaded the trained English database - from https://github.com/tesseract-ocr/tessdata/ - and limited returns to numbers and capital letters only. It still isn't very good, but that's probably because there is a lot of handwritten stuff in there that I don't need. I'm wondering if someone already has a trained set for license plate characters? I've looked at the training documentation but it looks horrendous, but I possibly could use something others have written to streamline this a little (I found some links earlier). But to train tesseract (v4 in particular) apparently I will need a lot of training data as well, which I don't particularly have much of, so a traineddata file with only A-Z & 0-9 would be helpful.
-- 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/118e9b74-6ec1-4d3d-a490-3c26a57f7c1d%40googlegroups.com. For more options, visit https://groups.google.com/d/optout.
