Hi, i'm trying to fine tune tesseract for my docs but dont really understand a couple of things: - i'm planning to use tesseract on colorized inmages with thresholding_method=2. It seems to me that i should train the model and evaluate quality on the files that were binarized the same way. - I tried to set thresholding_method in data\langdata\mymodel\mymodel.config file but it doesnt seem to affect the behavior. Even if i intentionally pass wrong params to the config the result is exactly the same. - should i instead prepare my ground truth files with the same thresholding method before training?
-- 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 tesseract-ocr+unsubscr...@googlegroups.com. To view this discussion on the web visit https://groups.google.com/d/msgid/tesseract-ocr/fcb94b1c-edc3-444f-a2d2-d3c8ae859873n%40googlegroups.com.
