Slashdot Mirror
Averaging Inanimate Objects Together Produces a Very Human Face
StartsWithABang writes: It's well known that by aligning and averaging a wide variety of human faces together, an eerie "average" human face can be arrived at. But we see faces in things all the time, from natural scenes like terrain to artificial ones like cars, coffeemakers and combination locks. For the first time, someone averaged together a large number of images of objects appearing to have faces, and the result, strikingly, was an eerily human face. You'd think this might say more about the algorithm than the images themselves, but when noise was used, no human face emerged at all.
So, average a bunch of things that only have their resemblance to a human face in common, and you end up with a human face? I didn't see that coming.
You'd think this might say more about the algorithm than the images themselves, but when noise was used, no human face emerged at all.
Wait, so, when images that looked more like faces were used, the average looked more like a human face? Just crazy.
It's cute, but I'm not sure it's particularly profound.
Your blogspam links to Forbes is offensive.
Stop linking a website that is designed to broke hyperlinks and to force through an ad page.
Did the rest of the world suddenly get dumb?
Here averaging is basically:
What's common amongst all/most of these images that look like a face?
Yes, it's something that looks like a face. Shocked, I tell you.
there's this facebook thing, too. when you gaze long into an average......
man that is one F'ed up site that i can not get past the ADVERTISING 3 second countdown
that is royally F'ED UP
"I don't pitch OpenSUSE Linux to my friends, i let Microsoft do it for me
Pick 15 things that look like a face
average them together
result looks like a face
What is happening to Slashdot?
STOP . AMERICA . NOW
Whenever I see a Forbes link redirect to forbes.com/forbes/welcome, I click back (page doesn't even need to fully load) and click the link again. The second time it goes straight to the target. Works with both Firefox and Chrome w/ ABP.
Combinging 50 sounds which sound like a bird might not sound very birdlike. You might end up with some kind of white noise.
Probably true but I bet if you took images of human faces which were not already aligned and not all zoomed to a similar size then that too would generate noise. The only reason the averaging works is because people naturally take photos with the face the right way up and zoomed to a similar size. I bet if you were allowed to do the same alignment and scaling for bird song you could average the now aligned audio to get something like birdsong.
This is why this result is so obvious and not at all what it says. These are not random face-like images but ones with the same alignment and comparable zoom factor. If I did the same for any shape I would get the same result: the details of the shape would blur but the basic shape would remain the same because they are all aligned and have similar sizes. Someone should nominate this for an ignobel prize.
Post by me. Wasn't logged in. Screw being AC.
I really hate to contribute to the hate noise the haters bring, but I really hate to visit websites that hate to let me see the site without allowing scripting I hate from dozens of hated sources.
Could we get some kind of automated indicator when a link points at a site that just won't load with NoScript?
I don't think I am a tinfoil hat paranoid, I just don't like to have to allow 17 different sites to run scripts in my browser just to read an article. After reading a few comments it looks like I didn't miss much this time.
"Proximity to wonder has blunted our perception and appreciation of it" --Tim Hartnell in 'Exploring ARTIFICIAL INTELLI
Next thing you'll be telling me that when you average 50 photos of assholes you'll come up with something that looks remarkably like [pick your favourite politician].
I've just averaged all the human faces together and got an early '60s Jaguar E-Type:
http://image.motortrend.ca/f/1...
You are welcome on my lawn.
I'm no expert in human cognition or neural nets, but it seems to me that if, on average, something looks like a human face to the average human, then it must share regular correspondences to a human face. Take a few of these that vary in one way or another but all share such average correspondences and average them together, one would expect to get a human face.
I don't know, the obviousness factor is just still there for me. Maybe the profundity escapes me.
STOP . AMERICA . NOW
Well, obviously: If you're averaging many real numbers between 41 and 43, you'll get a number close to 42. If you're averaging many "objects that look like human faces" you'll get something that looks like a human face. What did they expect ? White Noise ? A porcupine ? 7 ?
It got a real scam site ... "continue to article in 3 2 1 ...". Are we talking about a warez site or a news site? Would not click again.
Essentially, this method should show what kind of traits look like faces to us rather than what real human faces look like. It's exploring properties of the psychovisual system of humans, not properties of face detection algorithms or statistical human faces.
2spooky4me Usually average faces are considered attractive, not eerie. And of course they're just called eerie in the Slashdot summary, not the article.
They consciously trained their algorithms to do what babies do: pan, and zoom/frame-in-software until facelike features emerge. But what is more interesting, the research relies on YOU to take the last, great leap.
They present the results --- the one from merged faces and the one from objects --- as a 'face'. But is it really a face? Ask yourself, if you were walking outside under perfect lighting conditions and someone with the precise blurred faces shown as their result approaches you. What would your reaction be? Calm and casual recognition or astonished horror? The Uncanny Valley represents the confusion we experience when our facelike scanning apparatus returns a high score but we do not perceive other cues necessary for casual recognition such as limb movement or fluidity of expression.
We now grow up in a sea of photographs and paintings. Try to imagine a time in history when naturally vivid artwork of human figures and faces was first presented to other humans, who until then had only seen actual people resembling people The synchronous echo of "Is a person!" and "Is not a person!" in their minds, depending on their temperament and personal experience, could result in anything from euphoric wonder to a panic of paranoid discomfort.
At times naturally occurring phenomenae we encounter 'seem' intelligently designed -- faces on Mars, crystalline growth, beacon-like pulsars. But that is because they are being intelligently observed. In the early days of ether -- hearing odd radio emissions was thought by some to be 'ample evidence' that there must be a message, was someone talking, we just weren't clever enough to parse the language.
As a kid I first learned that a portion of the static that embodies the white noise between FM stations, and the 'snow' on empty analog TV channels is actually an energy remnant of the Big Bang -- I was hooked. I found an empty channel and watched a lot of snow, just in the wild wild wonder of it all. And after awhile I did begin to see things! Shapes! Hear voices! Coherent slime, oozing out from my TV set. Yet, even as it happened -- one of the intelligent avatars in my seething mind was working in tandem, pursuing its own dream... suggesting to me perhaps, perhaps. The whisper of an alternative theory for these 'visitations'. A flat-fact, I have decided -- I was shaping the static into the familiar by the very mechanisms of my own thought and perception. Aliens and dragins within. That so fit, I wrapped static into a concept, turned off the set and embarked on a fascinating trek of learning about sensory deprivation, the human mind's insatiable lust to find patterns, anywhere! Everywhere!, the mystery of how children 'bootstrap' language, acquiring it by some algorithmic neural osmosis.
Then 'modern' TVs were designed that blank that wild and beautiful analog static, which we once called snow. Then they were all changed again over to digital, so now we are shown our coherent signals, or ABSOLUTELY NOTHING. You could say that at one time there was a bit of the Big Bang in every living room but now it has been banished to the laboratory... appearing most often as a little squiggles on a graph. I feel a sense of loss in this.
I have kept an analog television just so I can turn it on from time to time and see that the static is still there.
And there will come a day when the static is still there but I will be gone, along with all analog televisions.
It will be a whole world of everything or nothing, all noise squelched or designed out or shouted over.
No sublime cosmic mystery in your own living room left to gaze into.
A dark age of total enlightenment.
<blink>down the rabbit hole</blink>
Yes.
Maybe if you averaged the song of many birds of the same species you could get some kind of recognizable song out.
Exactly - but that is what they are doing for faces. They are not averaging human, ape, bird, spider, insect etc. faces but the faces of a single species: humans. So by analogy it is perfectly reasonable to specify the same species of bird and then adjust the frequencies to match (since size variation will affect the frequency) and then add an appropriate delay so they all start the same part of the tune at the same time. This is exactly what the OP did with the images and I would agree that with the same approach adapted for audio there is probably a good chance that you'll get a recognizable song too.
The same phenomenon is observed when looking at the stars - we find shapes and call them constellations.
It's easier to navigate by the stars if you can visualize them as a series of distinct pictures rather a random mass of bright dots.
To have a right to do a thing is not at all the same as to be right in doing it