I do not have 3.5 version available, but simple of test image with tesseract v5.0.0-alpha-479-g247c show "some detection" of bold but on wrong places. So I would not suggest to use >=4.x version for this tasks.
Zdenko ut 15. 10. 2019 o 16:52 Ravi Nemala <[email protected]> napísal(a): > > I read tesseract 4.0 does not support wordFontAttributes in LSTM mode. Can > I just use oem 0(Legacy) to identify the bold/italics in my image? > > -- > 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/5d720ed7-2dd4-453d-98da-087c13770b31%40googlegroups.com > <https://groups.google.com/d/msgid/tesseract-ocr/5d720ed7-2dd4-453d-98da-087c13770b31%40googlegroups.com?utm_medium=email&utm_source=footer> > . > -- 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/CAJbzG8waQM_BwweD5ayBKZA3dkNAqFireppsx2L9SiXQpJqTDA%40mail.gmail.com.
This is simple test for bold and imIl'c text
Lnrem lpsum is simply dummy text of die prinu'ng and rypesem'ng industry. Lorem lpsum has been die industry's slandard dummy text ever since die 1500s, when an unknown printer took a galley of type and scrambled it to make a type specimen book It has survived not only five cenuiries, but also die leap inuo electronic rypesem'ng remaining essenu'ally unchanged. It was popularised in die 19605 widi die release of Letraset sheets swimming Lorem lpsum passages, and more recendy widi deskuop publishing sofiware like Aldus PageMaker including versions of Lorem lpsum.
