Hi, First of all please make sure you have quality image, check this link <https://tesseract-ocr.github.io/tessdoc/ImproveQuality> for more info.
If you still don't get the required result, the it is suggested to train tesseract with that particular font. And yes, training helps in improved text detection. (Just try to fine tune an existing trained data model) BR\ Piyush On Tuesday, 28 April 2020 10:44:05 UTC+5:30, pranaya mhatre wrote: > > Hi, > > I am using tesseract v4.1.0-bibtag19 in windows 10. I am extracting text > from engineering drawings made in auto cad and the images are clear. but i > am unable to extract all text from drawings and also getting some garbage > text. > > Is it required to train tesseract for engineering drawings font ? fonts > are namely times new roman, romans, simplex, arial. > IS tesseract training helps in text detection also ? > > Please help me. > > Thank you. > > Regards, > Pranaya Mhatre > -- 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/58a82c55-28ff-43c2-9e42-a1b18e903bca%40googlegroups.com.
