Hello everybody, I want to recognize a random combination of numbers and letters string in OCR A font. I did not had any luck with that so I tried to recognize reference texts with the same font and got surprised: The "normal" text got recognized without a problem, while my desired string is wrongly interpreted. Searching through the web lead me to disable the dictionaries used by Tesseract to match common words in the config file. Unfortunately that didn't help either.
Furthermore I tried the same text with a different font (CourierNew) and I was able to detect my desired string. So I would assume it has something to do with the font. String I want to detect: 0300FY9N457 My machine is Win10 and the output of "tesseract --version" is: tesseract v5.0.0-alpha.20191030 leptonica-1.78.0 libgif 5.1.4 : libjpeg 8d (libjpeg-turbo 1.5.3) : libpng 1.6.34 : libtiff 4.0.9 : zlib 1.2.11 : libwebp 0.6.1 : libopenjp2 2.3.0 Found AVX2 Found AVX Found FMA Found SSE Found libarchive 3.3.2 zlib/1.2.11 liblzma/5.2.3 bz2lib/1.0.6 liblz4/1.7.5 Attached is the input- and outputfile, as well as the configfile and the generated .tif. The cmd line used for generating the outputfile was: tesseract OCRA_Reference.jpg test [PATH]\config.txt All kinds of help/suggestions are much appreciated. Best regards Alex -- 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/6bdfe9df-7550-4cb1-b8f6-ae02b75a5acb%40googlegroups.com.
tessedit_write_images true load_system_dawg false load_freq_dawg false
OCR A Std Regular the quick brown fox 1234567690 O300FY9N457 O30 OF YOUNAS 7 THE QUICK BROWN FOX JUMPS OVER TI
