Have you had any luck training tesseract for arabic letters or numbers? On Sunday, November 25, 2018 at 9:09:33 AM UTC+1, [email protected] wrote: > > Hi Marwa M. Khan > > Have you generated any tessdataa for arabic-indian number ? > > I'm trying to generate one but JTessBoxEditor does not take > arabic-indian numbers, how to fix it ? > > On Thursday, July 19, 2018 at 12:52:24 PM UTC+3, Marwa M. Khan wrote: >> >> Hello, >> >> I am trying to train the Tesseract 4.0 with LTSM on Arabic/Hindi >> Digits in windows OS. I found that I need to create box file. Thus, I'm >> using JTessBoxEditor 2.0 for creating tiff and box files. However, it fails >> when I used JTessBoxEditor 2.0 to generate the .traindata file. Note that >> I choose combine_tessdata.exe as tesseract executable, ara.arial.exp0.box >> as training data, and training with existing box as a training mode. >> >> >> The output is the followings: >> >> esseract Open Source OCR Engine v4.0.0-beta.1-108-gf291 with Leptonica >> Page 1 >> Bad box coordinates in boxfile string! ١ ٤٥٤ ٣١٦٣ ٤٦٣ ٣١٩٠ ٠ >> >> Bad box coordinates in boxfile string! ٢ ٤١٣ ٣١٦٣ ٤٢٨ ٣١٩٠ ٠ >> >> Bad box coordinates in boxfile string! ٣ ٣٧٣ ٣١٦٣ ٣٩٣ ٣١٩٠ ٠ >> >> Bad box coordinates in boxfile string! ٤ ٣٣٨ ٣١٦٣ ٣٥٠ ٣١٩٠ ٠ >> >> Bad box coordinates in boxfile string! ٥ ٢٩٨ ٣١٦٨ ٣١٤ ٣١٨٥ ٠ >> >> Bad box coordinates in boxfile string! ٦ ٢٥٨ ٣١٦٣ ٢٧٣ ٣١٩٠ ٠ >> >> Bad box coordinates in boxfile string! ٧ ٢١٩ ٣١٦٣ ٢٣٨ ٣١٩٠ ٠ >> >> Bad box coordinates in boxfile string! ٨ ١٨٠ ٣١٦٣ ٢٠٠ ٣١٩٠ ٠ >> >> Bad box coordinates in boxfile string! ٩ ١٤٥ ٣١٦٣ ١٥٩ ٣١٩٠ ٠ >> >> Bad box coordinates in boxfile string! ٠ ١٠٩ ٣١٦٧ ١١٧ ٣١٧٨ ٠ >> >> Bad box coordinates in boxfile string! ١ ٤٥٤ ٣٠١٥ ٤٦٣ ٣٠٤٢ ٠ >> >> Bad box coordinates in boxfile string! ٢ ٤١٣ ٣٠١٥ ٤٢٨ ٣٠٤٢ ٠ >> >> Bad box coordinates in boxfile string! ٣ ٣٧٣ ٣٠١٥ ٣٩٣ ٣٠٤٢ ٠ >> >> Bad box coordinates in boxfile string! ٤ ٣٣٨ ٣٠١٥ ٣٥٠ ٣٠٤٢ ٠ >> >> Bad box coordinates in boxfile string! ٥ ٢٩٨ ٣٠٢٠ ٣١٤ ٣٠٣٧ ٠ >> >> Bad box coordinates in boxfile string! ٦ ٢٥٨ ٣٠١٥ ٢٧٣ ٣٠٤٢ ٠ >> >> >> Could you please tell me where I did wrong or how to fix this error? >> >> >> Best Regards, >> Marwa M. Khan >> >
-- 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 post to this group, send email to [email protected]. 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/3d1aa31a-6af2-4b90-a1e6-b93f9b792de9%40googlegroups.com. For more options, visit https://groups.google.com/d/optout.
