Hi everyone! I've got a lot of scanned documents with a font type and font size combination the tesseract recognizes with very bad quality. The documents are authored by a governmental office, so the obvious solution isnt work (to recreate with other font type) I decided to train the tesseract, but any articles I found lacks steps, explains or something what essential to the success. Is there any comprehensive tutorial or step-by-step guide for training you can advice?
environment: tesseract4.1 on ubuntu focal, everything is installed from distrib repository. thanks in advance Istvan -- 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 view this discussion on the web visit https://groups.google.com/d/msgid/tesseract-ocr/e4db6202-7007-45a3-a709-6f911a756739n%40googlegroups.com.
