You don't have to manually create .box files. Use OCR-D for training https://github.com/OCR-D/ocrd-train
In data/ground-truth folder you put tif/gt.txt files and when you run make training it will generate box files. For every tif image you write correct text in gt.txt file, nothing else. Look at the https://github.com/OCR-D/ocrd-train/blob/master/ocrd-testset.zip for example of tif/gt.txt files. -- 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/8d71b79d-0930-4565-8fa0-10b0b101612a%40googlegroups.com. For more options, visit https://groups.google.com/d/optout.
