• BoastfulDaedra@lemmynsfw.com
    link
    fedilink
    English
    arrow-up
    9
    arrow-down
    5
    ·
    10 months ago

    You’re very wrong.

    Computer vision is scanning the differentials of an image and determining the statistical likelihood of two three-dimensional objects being the same base mesh from a different angle, then making a boolean decision on it. It requires a database, not a neutral net, though sometimes they are used.

    A neutral net is a tool used to compare an input sequence to previous reinforced sequences and determine a likely ideal output sequence based on its training. It can be applied, carefully, for computer vision. It usually actually isn’t to any significant extent; we were identifying faces from camera footage back in the 90s with no such element in sight. Computer vision is about differential geometry.

    • danielbln@lemmy.world
      link
      fedilink
      arrow-up
      6
      arrow-down
      1
      ·
      10 months ago

      Computer vision deals with how computers can gain high level understanding of images and videos. It involves much more than just object reconstruction. And more importantly, neural networks are a core component is just about any computer vision application since deep learning took off in the 2010s. Most computer vision is powered by some convolutional neural network or another.

      Your comment contains several misconceptions and overlooks the critical role of neural networks, particularly CNNs, which are fundamental to most contemporary computer vision applications.

      • d20bard@ttrpg.network
        link
        fedilink
        arrow-up
        3
        ·
        10 months ago

        Thanks, you saved me the trouble of writing out a rant. I wonder if the other guy is actually a computer scientist or just a programmer who got a CS degree. Imagine attending a CV track at AAAI or the whole of CVPR and then saying CV isn’t a sub field of AI.