https://github.com/tesseract-ocr/tesseract/wiki/Training-Tesseract-3.03%E2%80%933.05#the-unicharambigs-file
On Thursday, January 31, 2019 at 3:52:43 AM UTC-6, 易鑫 wrote: > > Hello,everyone: > > I have trained a new lstm model in my project,but the result is > not so good as I expected. I notice that some characters often mistake in > my result. > I learned that add some rules in .unicharambigs can reduce the mistakes? > > I extract the eng.traineddata and get the eng.unicharambigs file as > follows,but I do not quite understand the meaning? > can anyone help me?Thanks in advance. > > > > v1 > 2 ' ' 1 " 1 > 2 ` ' 1 " 1 > 2 ' ` 1 " 1 > 2 ‘ ' 1 " 1 > 2 ' ‘ 1 " 1 > 2 ’ ' 1 " 1 > 2 ' ’ 1 " 1 > 2 ` ` 1 " 1 > 2 ` ‘ 1 " 1 > 2 ‘ ` 1 " 1 > 2 ` ’ 1 " 1 > 2 ’ ` 1 " 1 > 2 ‘ ‘ 1 “ 1 > 2 ‘ ’ 1 " 1 > 2 ’ ‘ 1 " 1 > 2 ’ ’ 1 ” 1 > 2 , , 1 „ 1 > 1 m 2 r n 0 > 2 r n 1 m 0 > 1 m 2 i n 0 > 2 i n 1 m 0 > 1 d 2 c l 0 > 2 c l 1 d 0 > 2 n n 2 r m 0 > 2 r m 2 n n 0 > 1 n 2 r i 0 > 2 r i 1 n 0 > 2 l i 1 h 0 > 2 l r 1 h 0 > 2 i i 1 u 0 > 2 i i 1 n 0 > 2 n i 1 m 0 > > -- 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 post to this group, send email to tesseract-ocr@googlegroups.com. Visit this group at https://groups.google.com/group/tesseract-ocr. To view this discussion on the web visit https://groups.google.com/d/msgid/tesseract-ocr/1cf3bb61-af26-47d9-aad4-afee8c42aaa0%40googlegroups.com. For more options, visit https://groups.google.com/d/optout.
