I found Adobe acrobat was good at ocr but I’m on Linux now.

  • e0qdk@reddthat.com
    link
    fedilink
    arrow-up
    3
    ·
    edit-2
    19 hours ago

    You can use tesseract -l jpn input.png - on the command line to have it print out the text from input.png into the console if you’ve got the language files for Japanese installed. (There’s also language files for vertical text and a few others for script in my package manager.) Alternatively give the filename (w/o extension) instead of - to write the output into a .txt file.

    On Mint, I think I did sudo apt install tesseract-ocr tesseract-ocr-jpn to get it working for the simple case of horizontal text; been a while though.