As i understood from wiki, training tesseract lstm requires tiff/box file. I have a dataset which includes small images of text line and texts those images recognized correctly. After researching few tips from tutorials i need to run tesseract with nobatch, makebox options to generate boxfile but it only uses my images to generate box file and can not recognize correct text with it. So i have to edit box file manually using jtessboxeditor even i have already correct text of those images. Is there any possible way to generate box file using image and text file without tesseract command?
-- 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/237ac1d8-ade9-44f3-8e65-f7bbcf0fb496%40googlegroups.com. For more options, visit https://groups.google.com/d/optout.
