Please don't use screenshots to represent text. They can't be searched, quoted, edited, and are generally much more difficult for people to deal with.
My results were with -l Arabic. It looks like your Java program is doing the equivalent of -l ara, which isn't the same thing. I suspect that if you use the correct model you'll get the results you desire. Tom On Thursday, November 9, 2023 at 10:22:03 AM UTC-5 mosta....@gmail.com wrote: > Also the same result !! what's wrong with that ?[image: osr1.JPG][image: > osr2.JPG][image: osr3.JPG] > On Wednesday, 8 November 2023 at 18:11:52 UTC+2 tfmo...@gmail.com wrote: > >> On Wednesday, November 8, 2023 at 6:23:46 AM UTC-5 mosta....@gmail.com >> wrote: >> >> That exactly I want, can you share this tessdata model here. >> >> >> tessdata_best is the name of the repo for the standard models and the >> Arabic model contains the language independent Arabic script training. >> >> >> https://github.com/tesseract-ocr/tessdata_best/blob/main/script/Arabic.traineddata >> >> Tom >> > -- 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/cb6cfaaa-f10a-433f-8544-b9e62298314an%40googlegroups.com.
