Hi, I am working with OCR to recognize arabic words and numbers(dates) from a scanned pdf (I have done some enhancing on it), but it cant seem to accurately read arabic numbers but it reads the letters properly. what can i do to make this better?
An example of a numbers (in date format) [image: Screen Shot 2020-04-06 at 10.41.21 AM.png] [image: Screen Shot 2020-04-06 at 10.42.42 AM.png] The first one is the input, the second one is the output and it read it as English even though i specify that it is all arabic - when I put the document in google docs and read as a word document, it reads it fine -- 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/5db69553-cde5-4937-ba71-1ff5c2b3bfd4%40googlegroups.com.
