Slashdot Mirror

← Back to Stories (view on slashdot.org)

Google Unveils Neural Network With Ability To Determine Location of Any Image (technologyreview.com)

Posted by BeauHD on from the neural-networking dept.

schwit1 writes: Here's a tricky task. Pick a photograph from the web at random. Now try to work out where it was taken using only the image itself. If the image shows a famous building or landmark, such as the Eiffel Tower or Niagara Falls, the task is straightforward. But the job becomes significantly harder when the image lacks specific location cues or is taken indoors or shows a pet or food or some other detail. Nevertheless, humans are surprisingly good at this task. To help, they bring to bear all kinds of knowledge about the world such as the type and language of signs on display, the types of vegetation, architectural styles, the direction of traffic, and so on. Humans spend a lifetime picking up these kinds of geolocation cues. So it's easy to think that machines would struggle with this task. And indeed, they have. Today, that changes thanks to the work of Tobias Weyand, a computer vision specialist at Google, and a couple of pals. These guys have trained a deep-learning machine to work out the location of almost any photo using only the pixels it contains.

12 of 116 comments (clear)

  1. Can it figure out where goatse was taken? by Anonymous Coward · · Score: 4, Insightful

    Can it figure out where the notorious goatse photo was taken?

    1. Re: Can it figure out where goatse was taken? by johnsnails · · Score: 3, Funny

      Not where bit it can determine it was taken after the London 2012 Olympics as it depics one of the finalist logos. https://encrypted-tbn1.gstatic...

  2. Almost all = not that many by gweihir · · Score: 2

    In mathematics, "almost all" means "all, except for a finite number". As the number of pictures in this universe is finite, this could even mean this "magic" machine cannot do it at all. I guess the headline was written in this spirit.

    --
    Most ACs are not even worth the keystrokes to insult them. Be generically insulted by this and ignored otherwise.
    1. Re:Almost all = not that many by ClickOnThis · · Score: 2

      In mathematics, "almost all" means "all, except for a finite number". As the number of pictures in this universe is finite, this could even mean this "magic" machine cannot do it at all. I guess the headline was written in this spirit.

      I'm not sure the author was using the phrase in a mathematical sense. More likely it was in the probabilistic sense of a very high percentage of successes in a number of finite trials.

      BTW, "almost all" in mathematics (specifically, real analysis) can also mean "all, except for a set of zero measure." Consider for example, the Cantor set which has an uncountably infinite number of members lying in the interval [0,1], yet it has measure 0. So, if you construct a function f(x) on [0,1] that has the value 1 at values of x in the Cantor set, but 0 otherwise, then you can say f(x) = 0 at almost all values of x.

      --
      If it weren't for deadlines, nothing would be late.
    2. Re:Almost all = not that many by squiggleslash · · Score: 2

      On Slashdot, "almost all" and "all" are actually synonyms, which is why you'll get flamed if you say something like "Almost all Foobar widgets cost over $10" by people complaining that they found a single Foobar widget for $9.

      --
      You are not alone. This is not normal. None of this is normal.
  3. False Title by OpinOnion · · Score: 2

    It can't possibly determine the location of any image. Many will simply have too little location data to form a reasonable guess.

  4. Try it yourself by mobby_6kl · · Score: 4, Interesting

    Well the "Guess the location" thing, not the NN :)

    There's a site that basically opens StreetView at random around the world and asks you to place it on the world map. As the summary explains, you can use a number of clues to generally place photos surprisingly accurately. Used to play this occasionally at work, we really liked that it challenged you to think about all these things that you know about the countries and regions around the world.

    https://geoguessr.com/

  5. Almost any photo = 10.1% by ebcdic · · Score: 4, Informative

    According to the article, it can identify 10.1% of the Flickr images it was tested on at "city-level" accuracy.

    1. Re:Almost any photo = 10.1% by thegarbz · · Score: 2

      Compared to a human that's pretty dam good.

  6. Uh oh by rampant+mac · · Score: 2

    Guess us old-timers will finally find out where the goatse guy is hiding out. :(

    --
    I like big butts and I cannot lie.
  7. Great! by Black+Parrot · · Score: 2

    Now, where does it say the moon landings were filmed?

    --
    Sheesh, evil *and* a jerk. -- Jade
  8. Artists can sense location by the quality of light by dsmatthews9379 · · Score: 4, Interesting

    Perhaps not all of them but it is a thing many talk about, that different locations have a distinct quality to the natural light there. Not just location either, but seasonal variation too. It would not surprise me if the NN was also sensitive to these clues. Which makes me wonder can Weyand el al get their NN to tell them additional things about the image such as time of day and day of year, perhaps even in some cases actual year because it can cross reference images in the same location with known dates against an image that it has geo-located and know what the weather (lighting conditions) were for that point in time near that location.