Beta
×

Welcome to the Slashdot Beta site -- learn more here. Use the link in the footer or click here to return to the Classic version of Slashdot.

Thank you!

Before you choose to head back to the Classic look of the site, we'd appreciate it if you share your thoughts on the Beta; your feedback is what drives our ongoing development.

Beta is different and we value you taking the time to try it out. Please take a look at the changes we've made in Beta and  learn more about it. Thanks for reading, and for making the site better!

Women's Attractiveness Judged by Software

ScuttleMonkey posted more than 6 years ago | from the computers-can-now-tell-you-how-ugly-you-are dept.

Software 348

Roland Piquepaille writes "According to Haaretz, an Israeli team of computer scientists has developed software that ranks facial attractiveness of women. Instead of identifying basic facial characteristics, this software has been designed to make aesthetic judgments — after training. The lead researcher said this program 'constitutes a substantial advance in the development of artificial intelligence.' It is interesting to note that the researchers focused on women only. Apparently, men' faces are more difficult to grade."

cancel ×

348 comments

Sorry! There are no comments related to the filter you selected.

Original Paper & Obvious Criticisms (5, Insightful)

eldavojohn (898314) | more than 6 years ago | (#22924506)

I believe the the original paper can be found here [tau.ac.il] from Dec of 2007.

There are some obvious criticisms:

In the first stage, 30 human participants were asked to rate from 1-7 the beauty of several dozen pictures.
For a masters project (which this was), that's a decent sample size. For research and practice, I do not think that will suffice.

Second, this was done using eigenalysis and principle component analysis. While that's interesting, I have not always found that to be a great approach. Five or six years ago, they were all the rage although I cannot really find anything fruitful that has come from applying this to human faces. This also means that they cannot generate the 'most beautiful' face but if they did, it would simply be the composition of all their eigenvectors (in this case, ghostly looking images of faces) into one representing the highest scoring beauty.

The lead researcher said this program 'constitutes a substantial advance in the development of artificial intelligence.'
Having taken several AI, computer vision & machine learning courses, I don't find this to be at all substantial. An interesting masters project for sure, but several years ago I saw people doing the same things at local universities with the same results.

Why don't they tell us how this scored some celebrities from around the world like say Iman Abdulmajid, Zsa Zsa Gabor & Angelina Jolie? I have a feeling that their system is over-trained and would perform poorly in real life. Facial beauty requires imagination and this system was hand trained on a hundred points. I don't think that's enough but I wish they would have published more results to either prove or disprove my criticisms.

Even beyond that... (5, Interesting)

SatanicPuppy (611928) | more than 6 years ago | (#22924638)

Even beyond the very real problems listed above, I'm not aware of any actual empirical standard of beauty. All you can point to is a general average of perceptions of attractiveness, and even that is far from foolproof as evidenced by the thousands of women who actively try to personify that average, and end up looking subtly hideous (a la Anna Nicole Smith).

In the end, it all comes down to individual perception. Sit ten guys down with thirty pictures, and you're going to get 10 different #1's. Maybe you can teach a program to be able to say who it thinks is hot, whatever use that is. Or you could write a program that would allow a person to rate a hundred or so pictures, so that you could run a dating service that automatically pairs you up with people it thinks you'll find attractive...That's the only use I can come up with.

Re:Even beyond that... (5, Funny)

toddbu (748790) | more than 6 years ago | (#22924666)

In the end, it all comes down to individual perception.

I wonder how the algorithm works after the machine has had a few beers.

Re:Even beyond that... (2)

tekiegreg (674773) | more than 6 years ago | (#22925112)

Obligatory:

Bite my shiny metal *ss

Re:Even beyond that... (1)

pragma_x (644215) | more than 6 years ago | (#22924672)

Well, wouldn't a large sample size (say, tens of thousands) help cancel out most of the individual preferences? At least then, your data would only be skewed by social/cultural preferences of your overall sample group, which may be good enough to get an idea of any underlying (instinctive?) standard of beauty.

Re:Even beyond that... (4, Insightful)

SatanicPuppy (611928) | more than 6 years ago | (#22924740)

Yes and no. Yes, you'll get a more accurate answer, as far as the machine is concerned, but no, in that the answer will be the lowest common denominator of attractiveness.

When you put enough numbers together, all you really get is the sort of bland result that is acceptable to the largest number of people. The female equivalent of McDonald's food, top 40 music, and white bread...No real room in there for the beauty that can occasionally startle you, stop you in your tracks, that we all look for and seldom find on television.

Re:Even beyond that... (1)

Otter (3800) | more than 6 years ago | (#22924872)

When you put enough numbers together, all you really get is the sort of bland result that is acceptable to the largest number of people....No real room in there for the beauty that can occasionally startle you, stop you in your tracks, that we all look for and seldom find on television.

You obviously don't watch Univision!!!

Anyway, even if you're completely right, explaining 98% or 99% of beauty still seems like an interesting intellectual exercise.

Re:Even beyond that... (0)

Anonymous Coward | more than 6 years ago | (#22924674)

I thought Anna Nicole Smith was quite beautiful when she stayed in shape and wasn't bloated.

Re:Even beyond that... (3, Insightful)

SatanicPuppy (611928) | more than 6 years ago | (#22924752)

Not me, but that's pretty much my point. You thought she was beautiful and I didn't, and neither of us is objectively right or wrong.

Re:Even beyond that... (2, Insightful)

MarcoAtWork (28889) | more than 6 years ago | (#22924790)

I'm not aware of any actual empirical standard of beauty


you are kidding right? Even programming a very simple algorithm along the lines of

bigger eyes, beauty++
highly symmetrical face, beauty++
triangular or oval shaped face, beauty++
clear skin, beauty++

will give you a pretty good set of matches

Re:Even beyond that... (5, Funny)

SatanicPuppy (611928) | more than 6 years ago | (#22924876)

You just described something [alien.de] out of the x-files...Want to try again?

Re:Even beyond that... (5, Insightful)

timeOday (582209) | more than 6 years ago | (#22924952)

The idea that there are no set standards for beauty is wishful thinking. Every guy wants to find a girl who is beautiful and for some reason nobody else has noticed. In reality this never happens. The next time you see a pretty woman in the airport, don't look at her, look at all the guys as she walks by, it's quite noticeable. Attractive people are treated better from a young age and, knowingly or unknowingly, they leverage this asset to get what they want. This is not some quirk in the study of psychology, it's the driving force behind the behaviors that shape evolution. It's a cruel trick of nature that we are not all created equal, and I'm glad we're civilized enough to moderate some of the resulting inequality.

Re:Even beyond that... (1)

wattrlz (1162603) | more than 6 years ago | (#22924804)

Actually, teaching the program to have an opinion of who it thinks is hot is a far cooler concept in my mind than training a program to analyze picture files to determine which one a group of about thirty people would be more likely to prefer. Though I suppose this would be very useful for a computer dating service.

Re:Even beyond that... (2, Interesting)

gravesb (967413) | more than 6 years ago | (#22924812)

I thought there were studies that show symmetry had a very high impact on attractiveness.

Re:Even beyond that... (1)

SatanicPuppy (611928) | more than 6 years ago | (#22924846)

Well, no doubt most asymmetrical people have trouble dating, so yea, I can see that.

Joking aside, most people already are symmetrical, so it would definitely stand out for people who aren't.

Re:Even beyond that... (1)

erlenic (95003) | more than 6 years ago | (#22924942)

I don't remember where I read this, so take it with the appropriate levels of salt.

The study that I think you're referencing was actually linking symmetry and fidelity. They found that if a man's face was a little bit asymmetrical, his wife/girlfriend was measurably more likely to cheat on him than if he had a symmetrical face. The hypothesized explanation had to do with instinctive sexual selection, so there was an undertone of symmetry = beauty, but they didn't spell it out like that.

The summary I read made no mention of how the symmetry of the woman's face effected the man's fidelity.

Re:Even beyond that... (1)

hardburn (141468) | more than 6 years ago | (#22924864)

Sit ten guys down with thirty pictures, and you're going to get 10 different #1's

True, but all ten will tend to agree on which ones are beautiful and which ones aren't. It's just the #1 position that will be different.

Besides, don't we all dream of the future when robots can sit at bars and say "Hey, checkout the RAM on that baby!" No, I don't either.

Re:Original Paper & Obvious Criticisms (1)

Dachannien (617929) | more than 6 years ago | (#22924730)

Really, identification and characterization of facial features is probably the more interesting (now, anyway) part of this project. Once you figure out how to characterize those features, you can just apply and train a feed-forward neural network based on your training set (decades-old technology now), and Bob's your uncle.

Re:Original Paper & Obvious Criticisms (5, Funny)

coren2000 (788204) | more than 6 years ago | (#22924770)

Out of 7!!! Who the #$%! ever said "Oh that chick is a 7, I need to do her now!"
Software should conform to the normal 10pt ranking scale damnit!

Re:Original Paper & Obvious Criticisms (5, Funny)

spun (1352) | more than 6 years ago | (#22924808)

Out of 7!!! Who the #$%! ever said "Oh that chick is a 7, I need to do her now!"
Software should conform to the normal 10pt ranking scale damnit!
This is Slashdot. A seven is more than most of us can ever hope for.

"I've never done a ten, but I did five twos in one night!"
--George Carlin

Re:Original Paper & Obvious Criticisms (1)

Gat0r30y (957941) | more than 6 years ago | (#22925006)

I for one would propose the area code system of ranking... I'll explain

1st number (1-10 scale) facial beauty.
2nd number (binary choice) 1 (would hit that) 0 (wouldn't hit that)
3rd number (1-10 scale) body.

Here's to the 919's out there!

Re:Original Paper & Obvious Criticisms (2, Funny)

coren2000 (788204) | more than 6 years ago | (#22925038)

Call 911, there is a fire in my pants.

Re:Original Paper & Obvious Criticisms (2, Interesting)

Bombula (670389) | more than 6 years ago | (#22924908)

I participated in a psych lab as an undergrad about 10 years ago where the masters students were doing some project like this. We had to rank pictures of women's faces in order of most to least beautiful/attractive. Just faces, black and white against a black bakground, no other context - not even neck. What stood to me was that afterward, when they explained the results, they showed that some astounding percentage of participants - something like 97% - ranked the pictures in identical order. I think there were around 30 faces. There was a very high level of agreement among people over what is and isn't beautiful.

Also noteworthy was that none of the top faces were celebrities. Oh, and the top face was absolutely breathtaking. I mean impossibly beautiful. Several times over the years I've poked around on the internet trying to find it. I remember at the time suspecting it was photoshopped to be perfectly symmetrical, but it was more than that. This face was otherworldly - and to have such an astonishingly perfect face not belong to a celebrity? Weird. Could be some model I'm just unaware of though I guess.

Not to mention... (1)

Jane Q. Public (1010737) | more than 6 years ago | (#22925030)

Then there are such things as racial, regional and cultural variations in ideas of "beauty".

I agree; this does nothing but fancy correlations of faces with judgments of beauty made by a small sample of "instructors". If you were to increase the number of instructors, especially if you made them more diverse (say by region and culture), you would end up with a meaningless hodge-podge... the more meaningless the larger the sample.

Re:Original Paper & Obvious Criticisms (1)

Metasquares (555685) | more than 6 years ago | (#22925094)

The Eigenface people have been doing this stuff for years. I don't see any significant advance in AI, either; it sounds like they're just doing regression, possibly coupled with feature extraction.

Wrong Metric! (5, Insightful)

222 (551054) | more than 6 years ago | (#22924508)

"Apparently, men' faces are more difficult to grade."

Or perhaps their bank accounts are easier to derive a "value" from!

I kid, I kid. I think.

Re:Wrong Metric! (5, Funny)

The Ancients (626689) | more than 6 years ago | (#22924536)

If I had mod points I'd mod you '+1 divorced'

Re:Wrong Metric! (1)

Sciros (986030) | more than 6 years ago | (#22924558)

Yah and that ain't all you can measure.

Speaking of which that goes for boobs, too. I also wonder if this one metric would lead to performance as good as what the research in TFA managed.

As we all know.... (5, Insightful)

EmbeddedJanitor (597831) | more than 6 years ago | (#22924572)

Women are in charge of quality control.

Men will nail anything and the women really control sexual interactions. The cost of mating is far lower for men than for women therefore women are far more choosy.

Not quite (3, Funny)

calebt3 (1098475) | more than 6 years ago | (#22924528)

Apparently, men' faces are more difficult to grade.
Or men are not good at identifying another man as attractive when they are straight.

Re:Not quite (1)

oldhack (1037484) | more than 6 years ago | (#22925080)

Yes, the guys should look at the pics only when they are in homo mode.

requires external criteria (4, Insightful)

jollyreaper (513215) | more than 6 years ago | (#22924532)

"Apparently, men' faces are more difficult to grade."
That's because male attractiveness is graded on a curve, the curve set by wealth, power, and social position. Remove those factors, flattening the curve, and the Cuban pool boy will be ranked at the top once more.

Re:requires external criteria (2, Interesting)

Anonymous Coward | more than 6 years ago | (#22924694)

According to some research, people tend to prefer their own race's looks, so Cubans are likely to find cuban pool boys more compelling than Swedes. Obviously there are exceptions for exceptional beauties of both sexes. But, this is a general trend. For instance, I have seen a total of one Indian guy I found hot and one I found attractive. I have dealt with a lot of Indians. I also don't tend to find latinos compelling, but there are always exceptions. I like young white guys the most, and this is likely due to genetics. One study found that people are better at differentiating between the facial features of their racial group. This can be due to increased day-to-day exposure to those features, but also can be due to genes.

Re:requires external criteria (4, Interesting)

jollyreaper (513215) | more than 6 years ago | (#22924882)

According to some research, people tend to prefer their own race's looks, so Cubans are likely to find cuban pool boys more compelling than Swedes. Obviously there are exceptions for exceptional beauties of both sexes. But, this is a general trend. For instance, I have seen a total of one Indian guy I found hot and one I found attractive. I have dealt with a lot of Indians. I also don't tend to find latinos compelling, but there are always exceptions. I like young white guys the most, and this is likely due to genetics. One study found that people are better at differentiating between the facial features of their racial group. This can be due to increased day-to-day exposure to those features, but also can be due to genes.
This can go both ways. While there is a degree of comfort for selecting mates within one's own racial subgroup, there's also a trend towards being attracted to exotics, i.e. those outside of the subgroup. This sort of desire has been postulated as an evolutionary adaptation to keep genes from becoming stagnant. I am not sure if this still in the realm of speculation or if there has been any experimental verification. Of course, culture can also completely fuck up a given subject's appreciation of beauty. Just look at how standard African features have been looked down upon in females. Look at any black couple on television and you'll see that the man may have markedly pronounced African features but the women will always be of mixed race, skin tending towards coffee color but facial features all comfortably Caucasian. I very much doubt this is by chance.

Women are from Venus (0)

Anonymous Coward | more than 6 years ago | (#22924538)

Women less complicated than men, never!

Woman scientists will retaliate... (4, Funny)

Anonymous Coward | more than 6 years ago | (#22924544)

...and generate a manhood-size-prediction algorithm.

Re:Woman scientists will retaliate... (1)

Tablizer (95088) | more than 6 years ago | (#22924706)

...and generate a manhood-size-prediction algorithm.

Their algorithm is much simpler:

    function rankGuy(guy)
    rank = guy.bankAccountAmount / richestDudeBankAmt;
    return(rank);
    end;

Re:Woman scientists will retaliate... (1)

Maxo-Texas (864189) | more than 6 years ago | (#22924884)

Recently lost a girl to just this. Was extremely painful-- loved me to death, he was older, we had great sex-- I truly felt we had a spiritual connection.

He was old... and shorter.. and balding.. and ... wealthy.. and retired... and had a 100 acre ranch.. and a F250.. and horses... and he could spend every afternoon hanging out with her at work and doing little work chores for her. After 9 months, she told me about him and tried to keep both of us.

After three very painful months, I cut off all contact with her. She called me for phone sex two weeks AFTER I cut things off-- apparently he is just not a rocket in the sack and she would have loved to keep sneaking off to see me... while marrying him... after he was "divorcing" his ex-wife to marry her while telling her he was no longer on speaking terms with my ex after his wife got a look at the cell phone bill.

He had stupidly copied his wife on an email before the affair started... and she had stupidly linked her main account to a poetry account I set up. So now he is getting divorced for real. And she still found a stupid pretext to contact me last week.

The only thing I have seen that works is to be a jealous spouse and really check up on them. My friends who do this have vaguely unhappy but surviving marriages while those who do not have either suffered through affairs or ended up with divorces after 8-10 years. Trust but verify. If I had been doing that- I would have caught him 1-2 months in and driven him off.

This article is useless without Pics (4, Funny)

Your.Master (1088569) | more than 6 years ago | (#22924548)

I swore I'd never spout that misogynist meme, but for once it bears a glimmer of truth.

Re:This article is useless without Pics (1)

ari_j (90255) | more than 6 years ago | (#22924742)

It's only misogynist in some applications. Most often, it is at worst superficial. Sometimes, it is completely neutral. I wish that people would do a better job of compartmentalizing these things so as to not blur their meanings.

more average is more attractive (5, Interesting)

Noodles (39504) | more than 6 years ago | (#22924554)

I saw an article in a science journal years ago that showed photos of women averaged together. The more photos in the average, the more attractive the final photo became. The conclusion was the more 'average' the woman looked, the more attractive she was. Makes sense to me.

Skin smoothness (5, Interesting)

superstition222 (1019500) | more than 6 years ago | (#22924764)

The theory from some is that this averaging resulted in an illusory correlation between average and beautiful due to the fact that the averaging process improved the appearance/smoothness of skin. People apparently really really like good skin.

Re:Skin smoothness (0)

Anonymous Coward | more than 6 years ago | (#22924868)

One reason is, blemished skin can be a sign of ill health, disease, or bad hygiene. This has both personal safety and reproductive implications. So evolutionarily, we may have come to evaluate smooth skin as desirable because of safety. Heaven knows what effect tattoos will have on human natural selection. But anything that helps trailer trash reproduce can't be good for the species. All tramp stamps should be mandated by law to carry small print saying "Get your herpes here".

Re:more average is more attractive (1)

Tablizer (95088) | more than 6 years ago | (#22924766)

I saw an article in a science journal years ago that showed photos of women averaged together. The more photos in the average, the more attractive the final photo became. The conclusion was the more 'average' the woman looked, the more attractive she was. Makes sense to me.

I've noticed that most of the beauty contest contestants look "bland" to me. Its not that they are ugly, its just that they lack "spice". Throw in a few big booties here and there to mix it up, for example. Add in some round faces and also narrow faces. Women's faces are fascinating. Perhaps this sameness phenom is from supermarket magazines that like to emphasize all deviations/differences as "flaws", perhaps so that they can sell you a "fix".
   

Re:more average is more attractive (1)

Maxo-Texas (864189) | more than 6 years ago | (#22924948)

Watch 1930s-1950s movies... there were many kinds of beauty.

Watch TV & movies today... even the busboys and waitresses all look basically the same beauty level as the leads which is very high.

It's like "middle class" families living in $750k houses in movies and TV shows. And it really screws up our expectations and happiness in real life.

Re:more average is more attractive (0)

Anonymous Coward | more than 6 years ago | (#22924782)

I for one really like tall slender blondes with large hips, breasts, and lips, long hair, eyelashes, and legs, green Asian eyes set wide apart, with IQ over 135... I WISH such women were average, and I think a lot of males would agree with me.

I think the study's effects could be explained by the fact that a lot of minor imperfections and variabilities (pimples, skin deffects, feature dimentions, etc.) are removed once you average multiple images. It's the same reason that airbrushed women look better than their real appearance.

Re:more average is more attractive (3, Insightful)

oni (41625) | more than 6 years ago | (#22924806)

The conclusion was the more 'average' the woman looked, the more attractive she was.

My unscientific opinion is that men tend to rate nearly all women as attractive, and are not very picky beyond that. It's almost a binary, yes/no kind of thing. If pressed a man might be able to say, "this woman is a 6 and this one is a 7" but that rating has no meaning because few, if any, men will pass up the 6 in order to pursue the 7. The male strategy seems to be a shotgun approach - flirt with every woman.

Women on the other hand, seem to rate very few men as attractive, and do seem very picky. A woman will judge a male as "6" and ignore him completely, because she knows a 7 is out there somewhere, if she keeps looking.

In summary, I think that if you picked 10 males and 10 females at random, and then asked 100 or so males to judge the females and vice versa, you would find that the males ranked the majority of the females as attractive, and "in the field" so to speak, you would find the males flirting with all of them. You would find that the females ranked a minority of males as attractive, and "in the field" you would find that those are the only ones they are interested in.

So like you said, an average female face is indeed attractive. This is good news for women. Most of them (and they know this) are attractive to the opposite sex.

Re:more average is more attractive (1)

hcdejong (561314) | more than 6 years ago | (#22924866)

One explanation for this is that we consider symmetrical faces to be attractive (very few people are perfectly symmetrical). Averaging multiple photos will make for a decently symmetrical face.

Re:more average is more attractive (2, Insightful)

russotto (537200) | more than 6 years ago | (#22925040)

One explanation for this is that we consider symmetrical faces to be attractive (very few people are perfectly symmetrical). Averaging multiple photos will make for a decently symmetrical face.


Perhaps, but it turns out if you take one attractive but not perfectly symmetrical face, split it down the middle and combine with its mirror images, the resulting symmetrical faces are not more attractive; they look wrong.

Re:more average is more attractive (0)

Anonymous Coward | more than 6 years ago | (#22924874)

"Average" is not the important thing. Symmetry is the important concept here. Symmetry is an indicator of fitness because fitness is an indicator of good development (I suppose that is a good indicator because is the most improbable thing). By the same reason, the average deletes the existent asymmetries.

Re:more average is more attractive (0)

Anonymous Coward | more than 6 years ago | (#22924880)

I saw an article in a science journal years ago that showed photos of women averaged together. The more photos in the average, the more attractive the final photo became. The conclusion was the more 'average' the woman looked, the more attractive she was. Makes sense to me.

Averages are also called means. So what you are saying is that the more "mean" a woman looks the more attractive she is.

Makes sense, huh?

In any case, men's faces are harder to rate for attractiveness because all men are pretty similar in what they find attractive, whereas women tend to far greater extremes. What one woman finds extremely attractive another will find positively ugly. Men have far less variance in this, as in so many things, which is why men have always been favoured as the go-to gender for one-size-fits all cannon-fodder and other uniformed jobs.

schmaverage (1)

rodentia (102779) | more than 6 years ago | (#22924938)

From TFA:

The research revealed that faces considered beautiful are average - with no extreme facial characteristics.

The procedure would seem to eliminate edge cases offensive to some. Sort of begs the question of semantics of beauty don't it? What could possibly be beautiful in any true sense about an average.

Middlebrow is not the same as tasteful and inoffensive is not the same as impressive.

Re:more average is more attractive (3, Informative)

LaskoVortex (1153471) | more than 6 years ago | (#22925104)

This [nih.gov] is the paper. There were several faces more attractive than the average. So, a conclusion from that paper was that you can't do wrong with average, but you can do better on occasion.

Women don't like men (-1, Flamebait)

Anonymous Coward | more than 6 years ago | (#22924570)

Only gay men like men.

Women like money.

Why do we need software for this? (5, Funny)

$RANDOMLUSER (804576) | more than 6 years ago | (#22924576)

I thought that's what beer was for.

Re:Why do we need software for this? (1)

DickBreath (207180) | more than 6 years ago | (#22924754)

I need software to help me judge the attractiveness of women. Like other software that performs an important but infrequently used function, I would have to study the man pages and figure out the options on those rare occasions when I need to know if a woman is attractive.

Re:Why do we need software for this? (1)

Tablizer (95088) | more than 6 years ago | (#22924796)

I thought that's what beer was for.

But the score always approaches "10" as consumption approaches 8 cans.
   

Re:Why do we need software for this? (0)

Anonymous Coward | more than 6 years ago | (#22924844)

Which is why you need this software on your cell phone - take a pic of the chick you want to hit on and let it tell your drunk ass whether or not to proceed based on the minimum score you set when you were sober. Beer goggles solved.

Re:Why do we need software for this? (1)

wattrlz (1162603) | more than 6 years ago | (#22924918)

Actually, I think this software might be very useful to quite a few people after a large quantity of beer. Just port it to your camera phone and suddenly you've got a portable second opinion of who you should leave with.

In other news (1)

evolvearth (1187169) | more than 6 years ago | (#22924596)

In other news: Researchers on the project were forced to cooperate with woman researchers in fear of being accused of homosexuality.

fixup (0)

Anonymous Coward | more than 6 years ago | (#22924620)

Apparently, men' faces are more difficult to grade.
Apparently, nobody cares about men's faces.

There, fixed that for you.

Missing Word (5, Funny)

Kyont (145761) | more than 6 years ago | (#22924624)

Women's Attractiveness Judged by Software Engineers

There, fixed that title for you...

Knees (2, Funny)

kevin_conaway (585204) | more than 6 years ago | (#22924626)

I thought the true measure of a womans attractiveness was the pointiness of her knees

HotOrNot Turing test (1)

Nimey (114278) | more than 6 years ago | (#22924632)

Think about that.

Re:HotOrNot Turing test (1)

SatanicPuppy (611928) | more than 6 years ago | (#22924690)

I'd actually though about that when I first heard of the website...That's a lot of interesting data being collected.

Still, the lack of any demographic information on the reviewers makes the rest of the data much less useful.

Re:HotOrNot Turing test (1)

vita10gy (932040) | more than 6 years ago | (#22924702)

If it were going to use hot of not as any basis they would need to detect if the girl was blond and subtract 2 if she was and detect if there's at least a hint of cleavage in the photo and subtract 1 to 3 depending on exposure level. Otherwise the hot or not rankings are so skewed they are useless.

Hot or Not (0)

Anonymous Coward | more than 6 years ago | (#22924636)

I think there should be a few years of hotornot data to seed the AI system. Of course that might not jibe with actual beauty and may reflect more on the relative states of undress of the aspirant "hotties."

Screenshot (1)

Paul Slocum (598127) | more than 6 years ago | (#22924640)

Here's [lemon64.com] a screenshot from the main UI.

Digital Misogyny (3, Funny)

crymeph0 (682581) | more than 6 years ago | (#22924646)

On the bright side, this should encourage more women to enter the science and engineering fields, if for no other reason than to crack into this system and perform the digital equivalent of dumping your cocktail on your head. I think training it to rank goatse as aesthetically pleasing would do the trick.

Intelligence (1)

sveard (1076275) | more than 6 years ago | (#22924654)

That's artificial, superficial intelligence

That's odd (1)

Tablizer (95088) | more than 6 years ago | (#22924664)

80% of the code is devoted to breast measurements ;-P

Honestly, I don't see what's difficult (1)

evolvearth (1187169) | more than 6 years ago | (#22924668)

From my understanding, according to various comments from different women, male attractiveness stems from just a few factors: sharp facial features instead of rounded features tend to be more attractive, as well as tanned skin and light facial hair. Apparently, the butt chin is also seen as very masculine and attractive.

Strong Genetic Diversity? (1)

Prien715 (251944) | more than 6 years ago | (#22924686)

I would assume that, evolutionarily speaking, one strong criterion for a perspective mate is finding a partner to provide offspring with different genetic material. Since I assume facial characteristics are a result of genes, I'd assume that different people would find people attractive differently based on their own set of genes. To use a never-before-used analogy, finding the "best" woman is like finding the "best" wine for a given meal -- it all depends on what you're eating.

OR As Paul Graham Noted In ANSI Common Lisp (0)

Anonymous Coward | more than 6 years ago | (#22924688)


artificial stupidiy.

Sincerely,
Kilgore Trout, Just Another Lisp Hacker

Symmetry (5, Interesting)

Reality Master 101 (179095) | more than 6 years ago | (#22924692)

I read an article a while back that made the point that one of the biggest factors in attractiveness was symmetry. The "perfect" face doesn't have any features out of alignment. There was another study that made the point that "averaging" faces produced more attractiveness, but this was actually the wrong conclusion. It was the averaging process that smoothed out features into perfect alignment.

Symmetry actually makes sense. The more messed up someone's face is from ideal, the worse their genetics could be. Of course, there are other factors such as shiny hair, clear skin, sharp cheekbones, fitness, which all factor back to health.

What I'm interested in (1)

lyml (1200795) | more than 6 years ago | (#22924720)

Is there anywhere where one could get ahold of the sourcecode to this software, or even a binary. How can this be news for nerds without a proper link to the source? ;)

Re:What I'm interested in (1)

mapleneckblues (1145545) | more than 6 years ago | (#22924784)

It was an MS funded project.

Far more useful than the face... (1)

Dan Posluns (794424) | more than 6 years ago | (#22924724)

Do some basic curve fitting of a woman's front and profile to a couple of splines and I'll write you software to measure the number of beers it will take either me or her...

Has it already judged (1)

Lewrker (749844) | more than 6 years ago | (#22924726)

all Miss World contestants as horrible abominations ?

Was the computer gay? (1)

PC and Sony Fanboy (1248258) | more than 6 years ago | (#22924744)

So, was this a study to determine if the women were attractive to men? Or if they were attractive in general? And do men and queer women look for the same qualities in women? (hint: they don't) ... so ... I guess this computer is straight.

The big question, what if the computer doing the rating was a fruit?

Re:Was the computer gay? (1, Funny)

Anonymous Coward | more than 6 years ago | (#22924840)

... so ... I guess this computer is straight.

The big question, what if the computer doing the rating was a fruit?


Then it would prefer bananas over a lovely pair of coconuts.

However, software suffered from a fatal bug... (1)

Maxo-Texas (864189) | more than 6 years ago | (#22924788)

They couldn't get it to actually look up at women's faces whenever they wore an open top.

Old news (2, Funny)

mcpkaaos (449561) | more than 6 years ago | (#22924824)

Men have been judging women by their software for ages.

We knew that (2, Interesting)

Anonymous Coward | more than 6 years ago | (#22924828)

What we're looking for is a healthy specimen to breed with. We will judge the health of said specimen based on our own body type. For instance, if we have long fingers, we will find long fingers attractive and vice versa. There really isn't a godlike ideal that we strive for. We just want someone healthy who can give us healthy children. In that regard, the way the body curves is just as important as the face, if not more so. Somehow we think that judging beauty based on the face is pure while judging on the basis of other bodily characteristics is less pure. Not so. When us guys get all excited about a woman's secondary sexual characteristics, we're just thinking about the good of the children.

Now all we need (1)

Hesperus (16733) | more than 6 years ago | (#22924856)

...is software that can drink beer, and listen to music for us. While we're at it let's code up something that can relieve us of our tedious skiing, flying, and reading habits.

Of course (0)

Anonymous Coward | more than 6 years ago | (#22924870)

Apparently, men' faces are more difficult to grade.

That's because in most pictures of men's faces, you can't see their wallet.

Silly Guys (1)

iark (1169713) | more than 6 years ago | (#22924890)

This whole men's attractiveness would be sorted in a jiffy if they had some GAY SCIENTISTS on board! I can recommend a few able-bodies in Tel-Aviv.

Face? (1)

PPH (736903) | more than 6 years ago | (#22924902)

Wrong anatomical part.

Money spent better elsewhere... (0)

Anonymous Coward | more than 6 years ago | (#22924904)

Why are we wasting this money on researching this when we could be using this money on research to make women prettier.

Or better yet, use this money at the gentleman's club. ;-)

Shallow HAL? (2, Funny)

OutSourcingIsTreason (734571) | more than 6 years ago | (#22924916)

They made a movie [wikipedia.org] about it.

Something ommitted (5, Interesting)

Pojut (1027544) | more than 6 years ago | (#22924936)

Something I have noticed is that the more intelligent a woman is, the more attractive she looks when showing certain emotions.

An intelligent woman looks highly attractive when confused...you can almost see the gears working in her head, trying to figure it out. An unintelligent woman just has a dumb confused look on her face.

From what I have seen, intelligent women tend to not necessarily have more attractive facial features, but a more attractive way of showing their emotion and reaction to things. Not something that is commonly thought about.

Vast systems already exist to grade men. (1)

netsavior (627338) | more than 6 years ago | (#22924964)

Apparently, men' faces are more difficult to grade."


Most computer programmers find it trivial to take the short-cut and run a credit score and bank account balance. This is a much more accurate portrayl of men's attractiveness anyway.

How abt feeding Hillary's pic into it? (1)

theneb (732287) | more than 6 years ago | (#22924986)

I want to use it to judge her electability. Hopefully the software wont try to "steal" memory from other "resources" and in the process "crash" the whole system.

WOOHOO! SWEET! (0)

Anonymous Coward | more than 6 years ago | (#22925018)

With my trusty computer to help me, I'll never have to be burdened with looking at women again!!!

Wait ...

Oh Dear.

<cry>

Beauty (1)

gsmraxe (442187) | more than 6 years ago | (#22925042)

Beauty is only skin deep...But ugly goes straight to the bone!

Men Obsolete (0)

Anonymous Coward | more than 6 years ago | (#22925070)

What good are men now that computers can do the one thing they were good at, picking out attractivce women?

What is the purpose of this? (1)

yurivr (1252248) | more than 6 years ago | (#22925086)

I understand that this is an interesting research topic but is there some type of use that can be derived from this in the real world. Why would an AI care how statistically attractive you are, and whu would we want an AI evaluating our appearance? After all, I thought the purpose of aesthetic beauty was to help you find a mate... so the robotic equation does not really... compute. (que fembot jokes) "Robot, Robot, in the server [wall]... who is the statistical outlier among them all?"

Why men's faces are more difficult to grade (0, Redundant)

spazoid12 (525450) | more than 6 years ago | (#22925090)

"Apparently, men' faces are more difficult to grade."

This is because you can't typically see a man's wallet in a photo of his face.

Needs a date (1)

msgtomatt (1147195) | more than 6 years ago | (#22925096)

Seriously, stop humping your keyboard and get a date! (algorithm: Locate eyes, look ~17inches down, score proportional to size of round bulges)
Load More Comments
Slashdot Login

Need an Account?

Forgot your password?

Submission Text Formatting Tips

We support a small subset of HTML, namely these tags:

  • b
  • i
  • p
  • br
  • a
  • ol
  • ul
  • li
  • dl
  • dt
  • dd
  • em
  • strong
  • tt
  • blockquote
  • div
  • quote
  • ecode

"ecode" can be used for code snippets, for example:

<ecode>    while(1) { do_something(); } </ecode>