i’ve been searching for a while but none of the ones i find are great, the one i landed on hasn’t been updated in over a year

  • Vinny_93@lemmy.world
    link
    fedilink
    English
    arrow-up
    5
    arrow-down
    2
    ·
    7 months ago

    Not particularly Android related but I’m fairly certain you can do some OCR with Python. Question is whether you want to analyse an image file or straight into the camera. The latter might be a challenge.

    • (⬤ᴥ⬤)@lemmy.blahaj.zoneOP
      link
      fedilink
      English
      arrow-up
      11
      ·
      7 months ago

      i have posted this in an android community because i want to do it with an android app :/
      unless there’s a way to easily run a python program with all the necessary dependencies on android this does not help me

    • chrash0@lemmy.world
      link
      fedilink
      English
      arrow-up
      2
      ·
      7 months ago

      no need for Python. there’s a Google SDK, ML Kit, that will do the heavy lifting on this. if that’s not acceptable, TensorFlow, PyTorch, and ONNX support Android, albeit not as nicely integrated.

      your image processing pipeline will be imageSource -> RGB encoding -> OCR -> profit. your OCR just needs an RGB encoded image. doesn’t matter if that’s a JPEG or YUV video feed at the source.

      as for if there’s an app that fits OP’s exact use case, dunno.

      • filister@lemmy.world
        link
        fedilink
        English
        arrow-up
        2
        ·
        7 months ago

        Man, you over complicated this task. OP, in F-Droid there are three apps that are based on a popular OCR Python library called tesseract. Just search for this term on F-Droid and give those apps a try.

        • chrash0@lemmy.world
          link
          fedilink
          English
          arrow-up
          3
          ·
          7 months ago

          i mean, you’re right. i’m just saying it’s a little silly to ship a Python interpreter when there are easier, better supported ways to do the same thing.

          looks like tesseract provides C bindings which are probably being utilized in those apps.