Hello, I would like to train tesseract on some sample images of text that I have. When training tesseract on images, should I pre-process them as I would normally to improve inference, i.e. using black text on white background and binarization via thresholding? Also can I reuse the pre-trained data for the training? If so, do you advise me to process the images? (and in which way?)
Thank you for your interest. -- 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/f29886a1-a736-453b-a850-ffa62a108d54%40googlegroups.com.
