back to article People outperform computer programs for 'compressing' pix

For all the fuss over algorithms and machine learning, computation can't quite compete with people when it comes to lossy image compression, it is claimed. Comp-sci boffins from Stanford University and student interns from three San Francisco Bay Area high schools in the US devised a system to assess how code instructions …

  1. Anonymous Coward
    Anonymous Coward

    At least!

    ...a scientific explanation for the appallingly low quality of my collection of free-to-web grumble.

    Although I'm not sure HOW people would compress a movie?

    1. Anonymous Coward
      Anonymous Coward

      Re: At least!

      'Although I'm not sure HOW people would compress a movie?' - you get loads of people to do it each 1 frame at a time and then have a human multiplexing system.....Oh, you wanted real time GOPs and I, B and P frames?......ah.

      Joking aside - reminds me that the first 'computers' were good fast human mathematicians if I've heard the story correctly.

      1. Claptrap314 Bronze badge

        Re: At least!

        The were not mathematicians--they were in fact the 'programmers'. (Or engineers were, I presume.) The "programmer' was someone who broke a complex computation down for for the 'computers'--who were generally high school educated (when that counted for something). My understanding is that the programs were executed multiple times and the (intermediate) results cross-checked.

    2. Paul Kinsler

      Re: not sure HOW people would compress a movie?

      You get them to watch it, and then ask them what they thought.

      Even if they produce a ten page essay, that's going to be a pretty good compression ratio. :-)

  2. J.G.Harston Silver badge

    I'm surprised they actually got real work out of Mechanical Turk. I was registered on there for ages and all I got was spam.

    1. Pascal Monett Silver badge
      Trollface

      Don't worry, you'll still get spam.

  3. Anonymous Coward
    Anonymous Coward

    I do not understand this article.

    Based on the headline I figured there was some sort of AI that was trying to squeeze down pics using whatever AI magic it had and that this was then compared to human-written compression schemes like JPEG and the like.

    But then the article starts going on about about high school students editing photos of giraffes and I lost the plot.

    Can anyone explain better?

    1. Jamie Kitson

      Re: I do not understand this article.

      Ah, this sentence from the summary on their website is helpful:

      > In this work, we perform compression experiments in which one human describes images to another, using publicly available images and text instructions.

    2. diodesign (Written by Reg staff) Silver badge

      Re: "Can anyone explain better?"

      Here's how it works: take an image, then have one person describe to another person what can be removed or reduced from the image without turning it into garbage. This works better than have a computer compress the image using an algorithm.

      Just added a bit more to the piece to explain it.

      C.

      1. Anonymous Coward
        Anonymous Coward

        Re: "Can anyone explain better?"

        I went ahead and read the entire paper the whole thing still makes absolutely no sense.

        They took a reference image and had a human manually recreate the reference image's composition using bits from other photos. They refer to this process as "human compression." This is not, under any definition I'm aware of, "compression."

        Compression takes an image and reduces the number of bytes needed to store it and in the case of lossy compression it does this by discarding some of the information in the original. Reconstructing the image, on the other hand, creates a new and separate image that bears a superficial resemblance to the original but does not contain any information from the original image.

        What they appear to be getting at is that you might be able to "compress" images by working out a way to *describe* the image such that a computer program can assemble bits of *other* pre-existing images into something that kinda sorta maybe resembles the original - like some sort of automatic digital collage. Which even if possible is pointless - nobody wants to have images that sort of look like a thing, they want images that look exactly like the thing.

        1. diodesign (Written by Reg staff) Silver badge

          Re: "the whole thing still makes absolutely no sense."

          Ah well, thanks for the feedback. It's just research we thought people would find interesting. To be fair, we do say it is impractical - it's just an amusing way to 'compress' images.

          I've added more background to the piece to it's more obvious to folk who don't read the paper or the code.

          C.

  4. The Nazz Silver badge

    What's a Giragge?

    Just asking.

    line 12 of the excerpt.

    1. Sceptic Tank
      Terminator

      Re: What's a Giragge?

      It's part of the "lossy compression" experiment, and how (some) humans can recover from such errors?

POST COMMENT House rules

Not a member of The Register? Create a new account here.

  • Enter your comment

  • Add an icon

Anonymous cowards cannot choose their icon

Biting the hand that feeds IT © 1998–2019