🔒 Tesseract not reading properly | Python | Page 1

tepid vale Apr 21, 2024, 11:45 AM

#

Hi, some of the tesseract output for this type of image (which is a preprocessed version) is

2QBBETRAVALOFREINFORCEMENTS 507 BEoss90xBEiPoo
2TormenroFPecuLiaRrty SF025Fo2s0mfFoa Bo
1BucHt SE043BoseoeBoeRo
16INcURSIONOFTNVASION SF033BFo2soxHBo26o```

While even Gemini / some random OCR's on the internet got it 100% accurate. I tried different flags for engines/dpi/character whitelists but it's either this or worse. Do I have to preprocess it in a different way or is something else wrong?

livid ivyBOT Apr 21, 2024, 11:45 AM

#

tepid vale Hi, some of the tesseract output for this type of image (which is a preprocessed...

#

@tepid vale

Python help channel opened

Remember to:

Ask your Python question, not if you can ask or if there's an expert who can help.
Show a code sample as text (rather than a screenshot) and the error message, if you've got one.
Explain what you expect to happen and what actually happens.

:warning: Do not pip install anything that isn't related to your question, especially if asked to over DMs.

tepid vale Apr 21, 2024, 11:46 AM

#

deep pewter Apr 21, 2024, 11:51 AM

#

What was the "random OCRs"? easyocr is usually less fragile, AFAIK

tepid vale Apr 21, 2024, 11:52 AM

#

one of the first google results, soda PDF i think

#

i'll try easyocr

#

it's actually like 90% accurate on the names

#

the numbers are a bit off but i'll try figuring it out, thanks a lot ❤️

livid ivyBOT Apr 21, 2024, 11:59 AM

#

Python help channel closed

This help channel has been closed and it's no longer possible to send messages here. If your question wasn't answered, feel free to create a new post in #1035199133436354600. To maximize your chances of getting a response, check out this guide on asking good questions.

#

🔒 Tesseract not reading properly

#🔒 Tesseract not reading properly