Hi all, Is the font size important for a training of a new model from scratch? I found that it is not important for the Tesseract v3.0 but I was not able to find anything about Tesseract v.4 and later.
Right now I use default parameters: --xsize 3600 for tesstrain.sh script --ptsize 12 for text2image in tesstrain.sh The net spec is defined like this: '[1,0,0,3Ct3,3,16Mp3,3Lfys64Lfx96Lrx96Lfx192O1c14]' (variable input height and width) Do I need to train the model on multiple font sizes (i.e. by finetunning)? Thanks. Jan -- 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/861486cf-91cc-4b77-8b5c-c398914e03b0%40googlegroups.com.
