Hello, I was trying to train Tesseract using tesstrain.sh in order to make it learn a custom font, but I'm struggling right now. I have the right langdata from official repos (with training_text, bigrams, unicharambigs etc...) , I also have the traineddata for the same language wich also comes from official repos. But I don't understand how to use a custom font, by custom font I mean a font for which I only know the name / have real life examples.
I've tried a tutorial following which I had to cut out some text pieces then generate .box files out of these. Then I had to correct box files and give it back to tesseract using *box.train* command. As this method didn't work for me, I've searched another way to do this and I found a way to train using tesstrain.sh but I'm stuck because I don't know how to give my custom font. So if someone could explain me how to do it or has good link that explain I'll be thankfull, I've search in lot of different places and I'm missing something to understand how to give a custom font to train with I followed this tutorial : https://medium.com/apegroup-texts/training-tesseract-for-labels-receipts-and-such-690f452e8f79 and tried using this script : https://github.com/tesseract-ocr/tesseract/wiki/Training-Tesseract-%E2%80%93-tesstrain.sh -- 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/4649d815-d2fe-45ad-9807-ee8e41c442e1%40googlegroups.com. For more options, visit https://groups.google.com/d/optout.
