Hi, I have a similar situation, in my case I "just" need to identify/detect the equation in the picture. I don't need to "read" it. Known the location is enough for me, just like the paper you mentioned "A Simple Equation Region Detector for Printed Document Images in Tesseract <https://www.researchgate.net/profile/Zongyi_Liu/publication/261199419_A_Simple_Equation_Region_Detector_for_Printed_Document_Images_in_Tesseract/links/5c30524f458515a4c70d37d3/A-Simple-Equation-Region-Detector-for-Printed-Document-Images-in-Tesseract.pdf>". However, it seems this feature is OFF by default as said in here -> https://groups.google.com/forum/#!msg/tesseract-ocr/_V7pOll2kPo/JKkJGJMNqUAJ
Did you manage to detect the area of equations in a picture? Kind regards, Em quarta-feira, 27 de maio de 2020 15:25:10 UTC+2, Владимир Калачихин escreveu: > > Heh, "equ" language is not present on language-specific.sh, so training > Tesseract 4 to math symbols impossible. > > Common question: > > Is there a real way to create a language model from scratch? For new, > unknown language? > -- 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/62ad2bf1-b046-4755-9328-8d8fedd4804f%40googlegroups.com.
