Hello,
I'm using Tesseract 4.1.0.0 trying to OCR a text field on the target that contains codes that have a pattern ( implemented as pattern file in Tesseract terms): P\n\n\n\n C\n\n\n\n B\n\n\n\n U\n\n\n\n In practice there is a letter that can be P or C, or B or U and then 4 more hex digits. The length is always exactly 5 char in total. So, at least in my intention with this pattern file, correct output would be, as examples: P0123, P2EFD, C12EF, B2BCD and so on. Running the script that does OCR thousands of times I see that the vast majority of the output is as expected but I have also some results like PPB, PFF3,CC3 and so on. Is there a way I can enforce more the adherence to the pattern I setup like this: user_patterns_file=C:\Util\Code_OCR.Pattern tessedit_char_whitelist=PCBU0123456789ABCDEF tessedit_char_blacklist=abcdefGgHhIiLlMmNnOopQqRrSsTtuVvZzJjYyKkWw-!| load_system_dawg=F load_freq_dawg=F Thanks in advance. -- 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/9fe54d32-b055-4237-8749-9f697429de06n%40googlegroups.com.
