← Back to team overview

sikuli-driver team mailing list archive

Re: [Question #694279]: Region.text() - number Recognition

 

Question #694279 on Sikuli changed:
https://answers.launchpad.net/sikuli/+question/694279

matteoa posted a new comment:
Hello Javier,
I've had the same problem and I managed to mitigate it with these functions:
        OCR.globalOptions().variable("tessedit_char_whitelist", "PCBU0123456789ABCDEF")
        OCR.globalOptions().variable("tessedit_char_blacklist", "abcdefGgHhIiLlMmNnOopQqRrSsTtuVvZzJjYyKkWw-!|")
        OCR.globalOptions().configs("bazaar")
        OCR.globalOptions().variable("load_system_dawg", "F")
        OCR.globalOptions().variable("load_freq_dawg", "F")   
        OCR.globalOptions().psm(6)
        OCR.globalOptions().variable("user_patterns_file", "C:\\Sikulix\\Util\\OCR.Pattern")   
and the content of the file (strictly tailored for my need) is:
P\n\n\n\n
C\n\n\n\n
B\n\n\n\n
U\n\n\n\n
Here some info I used to get a better OCR:
https://stackoverflow.com/questions/17209919/tesseract-user-patterns
https://github.com/tesseract-ocr/tesseract/blob/master/doc/tesseract.1.asc#config-files-and-augmenting-with-user-data
I said "mitigate" since the problem got better but was not completely solved.
Hope this helps

-- 
You received this question notification because your team Sikuli Drivers
is an answer contact for Sikuli.