Stories
Slash Boxes
Comments

News for nerds, stuff that matters

Slashdot Log In

Log In

Create Account  |  Retrieve Password

Women's Attractiveness Judged by Software

Posted by ScuttleMonkey on Mon Mar 31, 2008 03:20 PM
from the computers-can-now-tell-you-how-ugly-you-are dept.
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."
+ -
story

Related Stories

This discussion has been archived. No new comments can be posted.
The Fine Print: The following comments are owned by whoever posted them. We are not responsible for them in any way.
 Full
 Abbreviated
 Hidden
More
Loading... please wait.
  • 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... (Score:5, Interesting)

      by SatanicPuppy (611928) * <Satanicpuppy@nOSPaM.gmail.com> on Monday March 31 2008, @03:32PM (#22924638) Journal
      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.
      • by toddbu (748790) on Monday March 31 2008, @03:36PM (#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.

        • by wealthychef (584778) * on Monday March 31 2008, @05:12PM (#22925494)
          I can't believe the algorithm looks at faces. Obviously wasn't designed by a man.
        • by borawjm (747876) on Monday March 31 2008, @05:15PM (#22925524)
          I wonder how the algorithm works after the machine has had a few beers.

          The algorithm works better, but the hardware fails.
        • by Eudial (590661) on Monday March 31 2008, @05:21PM (#22925596)

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

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


          Here's the revised version:


          hotness_t is_good_looking_drunk(void* girl) {
                  return ID_TAP_THAT;
          } // Auxiliary morning after code
          void hangover(void* girl) {
              if(is_slashdotter(this) || girl == NULL) {
                  basement.exit();
                  new breakfast()->eat(); // Sorry, no clean-up
                  throw new moan();
              }

              try {
                  if(memory.search(LAST_NIGHT, "condom") || !is_good_looking_sober(girl)) {
                        exit(EXIT_QUIETLY);
                  } else throw new logic_error("Yeah right"); // Like this ever happens
              } catch (amnesia_error* e) { // Plausible deniability :-D
                      aspirin* a = find(this->apartment(), T_ASPIRIN);
                      if(a == NULL) throw new moan();
                      else this->ingest(a);
              }
          }
      • Re: (Score:3, Insightful)

        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
        • You just described something [alien.de] out of the x-files...Want to try again?
        • by timeOday (582209) on Monday March 31 2008, @04:07PM (#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: (Score:3, Interesting)

            Attractive people are treated better from a young age and, knowingly or unknowingly, they leverage this asset to get what they want.

            All beautiful women who have been stalked, abused, or raped because they are physically attractive, may beg to differ. Also, not being taken seriously because you're a "barbie doll" is a less-than-subtle discrimination permeating Western society. Attractiveness, like all things, has good and bad points. It is fallacious to say it is an asset without costs.

            You may be interested in reading about the "evolutionarily deceptive" teenage years, where soon-to-be-ugly people appear attractive to seduce a mate, and

            • by The-Bus (138060) on Monday March 31 2008, @05:21PM (#22925598) Homepage
              Wow, I may end up being the most handsome man in the world. I've been repelling mates for many years past my teenage years.
            • by kiracatgirl (791797) on Monday March 31 2008, @05:45PM (#22925832)
              I don't believe he ever said or implied that being attractive had no negative points, just that it is an inherent benefit - or perhaps it's better to say weapon - in human social interactions. Somewhat akin to the two-edged sword analogy, it can either help or hurt you. Attractive people either wield their attractiveness knowingly to further their own ends, or unknowingly and to an unknown end. Using it actively can cause unforseen negative repercussions (fanboy stalkers etc.), and using it unknowingly causes all sorts of benefits and detriments to the attractive person and to those around him/her. Being unattractive works in much the same way, albeit with vastly different effects.
                    • by MrNaz (730548) on Monday March 31 2008, @09:24PM (#22927436) Homepage
                      Yes, but there is empirical evidence of highly parallel preferences among males that indicate the presence of common perceptions regarding what constitutes beauty.

                      The fact that there are no empirical standards for beauty is not due to the absence of any common standards for beauty (albeit not universally applicable), rather our inability to represent the metrics of the mind using mathematical or linguistic representations.
      • Re: (Score:3, Interesting)

        I thought there were studies that show symmetry had a very high impact on attractiveness.
        • 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: (Score:3, Interesting)

          What would be useful for a computer dating service would be for you to rate each girl as you see them in terms of attractiveness, similar interests, etc. and use an algorithm like this to then filter out women that you probably wouldn't be interested in. Since each person's definition of beauty differs, it really needs to learn an individual's preference. Ideally, this could be combined with latent semantic analysis of the text that the potential dates typed as part of their profile to further improve mat

    • by coren2000 (788204) on Monday March 31 2008, @03:48PM (#22924770) Journal
      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: (Score:3, Interesting)

      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 th
  • Wrong Metric! (Score:5, Insightful)

    by 222 (551054) <stormseekerNO@SPAMgmail.com> on Monday March 31 2008, @03:22PM (#22924508) Homepage
    "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.
    • by The Ancients (626689) on Monday March 31 2008, @03:24PM (#22924536) Homepage

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

    • As we all know.... (Score:5, Insightful)

      by EmbeddedJanitor (597831) on Monday March 31 2008, @03:27PM (#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.

      • by xPsi (851544) * on Monday March 31 2008, @06:19PM (#22926126)

        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.

        Probably for most of our 100000+ years as a species this was true. But with birth and disease control advances in the past 50 years, great strides have been made to allow the relative coupling risks for women to drop considerably, at least in principle. Some men and women embrace this sexual symmetry by choice and this has given women more sexual freedom than ever before in history (i.e. they don't have to be so choosy), but for many, I guess old evolutionary habits are (understandably) hard to break since certain behaviors are essentially embedded in our wetware.
  • Not quite (Score:3, Funny)

    by calebt3 (1098475) on Monday March 31 2008, @03:24PM (#22924528)

    Apparently, men' faces are more difficult to grade.
    Or men are not good at identifying another man as attractive when they are straight.
  • by jollyreaper (513215) on Monday March 31 2008, @03:24PM (#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.
    • by value_added (719364) on Monday March 31 2008, @04:37PM (#22925212)
      That's because male attractiveness is graded on a curve, the curve set by wealth, power, and social position.

      I'm not an expert of male attractiveness, nor do I play one on Slashdot, but I imagine similar factors (absence of damage, proportionality of features, symmetry on the vertical plane, etc.) would play a similar enough role. That said, there have been plenty of studies showing that the "attractiveness" of a male's face corresponds to the menstrual cycle of the female: during ovulation, the "rugged and handsome" look is preferrable to "nice and well-shaved" whereas the inverse is generally true at other times.

      As for "wealthy and powerful", I guess that could similarly depend on the financial and social status of the female. I prefer to consider it a truism in the same way that in the wild, it's typically the biggest, strongest, or the one with the most goodies that gets the opportunity to mate.

      A side note for anyone cherishing the notion that everything is relative or personal, and there can be no standard of attractiveness. Even across disparate cultures where such things can run into the extremes, the attractiveness value of facial symmetry, to take one example, remains universal. I remember a PBS program on the subject years back that examined the faces of famous movie stars. Turns out by taking a ruler to the face of someone like Brad Pitt or Angelina Jolie, you'll discover both have nearly perfectly symmetrical faces. I imagine one could conclude there's some form of Golden Ratio [wikipedia.org] that applies, particularly to body shapes like those of Angeline Jolie. ;-)
      • by jollyreaper (513215) on Monday March 31 2008, @04:01PM (#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.
  • by Anonymous Coward on Monday March 31 2008, @03:25PM (#22924544)
    ...and generate a manhood-size-prediction algorithm.
          • by Maxo-Texas (864189) on Monday March 31 2008, @05:29PM (#22925678)
            Your theory sounds lovely-- I'm just saying what I've seen in practice.

            It takes time to build a friendship, then a sexual interest, then a romantic relationship-- the guys I know who have stable relationships do not let their women hang around alone with other men. When their feelers go up they chase the guy off- usually just by saying very mildly that they are not comfortable with the situation.

            In my case, they had a business relationship first.. then started meeting for lunch-- then I stopped being copied on emails-- then his wife stopped being copied on emails-- then they acknowledged something deeper than friendship (this is about 5 months in-- like I said, I got to read every email from both of them once I stopped the blind trust thing), then they started having sex-- then she had some work conferences (i.e. trips to his ranch)-- (now we are at 7 months)-- then they had a full out affair- he dropped hundreds if not thousands on jewelry, flowers, dinners and THEN he found out about me (she told him there was no one else-- he was married so there was no conflict right away) -- THEN she fought him for three months to keep both of us-- finally she told me and tried to keep both of us but as you would imagine, she was 60% him / 40% me and sliding towards him by then or else she would have cut him off instead of trying to keep both of us.

            You are right- we are all individuals who control our own destinies and we have no strong control others. But it take time to slide from loving someone to being willing to lie and betray them. If you catch them early, then you can stop things before they are too far along.

            If he had not been so damn wealthy I do not think it would have been an issue. It was like the second sentence out of her mouth when she broke the news to me. The universe had sent a wealthy man to take care of her. It was right after she said crying that she had had an affair with someone and she didn't want to lose me.

            And I make a good income and wasn't stingy on sharing it and had proposed. She was gloriously happy while at the same time she was being a complete skank. She and he started out with the idea that it would be a discrete little side thing that they would do during the day and "no one would get hurt". His family is hurt... I'm torn all to hell... his wife is hurt. The two of them lied to everyone. I damn near had a nervous breakdown over it because there was almost no warning. I knew she was under stress and consoled her and she told me it was about her business- I trusted her completely at that point. The stress was apparently really that she was fighting with him to keep it all secret and under wraps.

            I wouldn't be posting but she tried to open up contact with me again last week after I had successfully ended contact with her for several weeks and that attempt opened up all the pain again.

  • by Your.Master (1088569) on Monday March 31 2008, @03:25PM (#22924548)
    I swore I'd never spout that misogynist meme, but for once it bears a glimmer of truth.
  • by Noodles (39504) on Monday March 31 2008, @03:26PM (#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 (Score:5, Interesting)

      by superstition222 (1019500) on Monday March 31 2008, @03:48PM (#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.
    • by oni (41625) on Monday March 31 2008, @03:52PM (#22924806) Homepage
      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.
        • by oni (41625) on Monday March 31 2008, @07:31PM (#22926728) Homepage
          The entire philosophy is completely alien to me.

          Well, I think that a lot of it is basic, sexual-species instinct. A male who is too picky leaves fewer offspring than a male that is less picky. Thus, we all have the genes of those less picky males, and thus we are less picky. Conversely, a woman makes a huge investment in a child. At least several months and as much as three or four years. A woman who is less picky might get pregnant by a beta male, and then tomorrow, when that alpha male comes along, she can't take advantage of his genes. She loses. So as a result, the more picky females left more fit offspring, and as a result we all carry the genes for picky females.

          Contraceptives and abortion haven't been around long enough to change those instincts.

          Layered on top of that is our cultural programming, but its effect seems small, often invisible. Culture tells men to commit to one woman and buy her a giant diamond ring, but most men don't (or they do but they cheat) and women complain that men are "afraid of commitment" but that's like saying a bear is afraid to stay awake all winter. Culture tells women - actually, not even culture, most women are smart enough to realize that an average guy with a steady job and no major vices like alcoholism or violence will give them a happier life, but it's just so hard to resist the instinct that says, "bang the dirty guy from the biker gang." LOL!

          It's *very* difficult to overcome instinct, especially when you deny that the instinct exists. That's what we do. We pretend that we're special, that we're the only animal without these instincts.
    • by ABoerma (941672) on Monday March 31 2008, @04:07PM (#22924954)
      You can test it for yourself at http://www.faceresearch.org/demos/average [faceresearch.org].
    • by LaskoVortex (1153471) on Monday March 31 2008, @04:24PM (#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.
      • Re: (Score:3, Insightful)

        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.
  • by $RANDOMLUSER (804576) on Monday March 31 2008, @03:27PM (#22924576)
    I thought that's what beer was for.
  • by Kyont (145761) <kyont@mindsDEGASpring.com minus painter> on Monday March 31 2008, @03:31PM (#22924624)
    Women's Attractiveness Judged by Software Engineers

    There, fixed that title for you...
  • Knees (Score:3, Funny)

    by kevin_conaway (585204) on Monday March 31 2008, @03:31PM (#22924626) Homepage
    I thought the true measure of a womans attractiveness was the pointiness of her knees
  • by crymeph0 (682581) on Monday March 31 2008, @03:34PM (#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.
  • 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.

  • Old news (Score:3, Funny)

    by mcpkaaos (449561) on Monday March 31 2008, @03:55PM (#22924824)
    Men have been judging women by their software for ages.
  • Something ommitted (Score:5, Interesting)

    by Pojut (1027544) on Monday March 31 2008, @04:06PM (#22924936) Homepage
    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.
  • what of love? (Score:5, Insightful)

    by Anonymous Coward on Monday March 31 2008, @04:25PM (#22925118)
    I fell in love, unexpectedly, with a woman who was not a classic beauty.

    Within a handful of months, I noticed I was finding women with facial and body characteristics similar to hers more attractive than the magazine beauties I normally ogled. Indeed, the model types started looking odd to me.

    Now add in cultural and racial preferences and this "breakthrough" starts sounding like "bullshit".
  • by religious freak (1005821) on Tuesday April 01 2008, @01:05AM (#22928416)

    Apparently, men's faces are more difficult to grade.
    Rather, what kind of dude wants to (or perhaps is even able to) code for MALE face attractiveness? I can't help but think the guys coding this said "hey let's do the women faces first, because I don't mind looking at chicks all day", rather than it being too hard.

    Yes, I'm assuming the team was mostly male... hopefully I don't offend anyone with this obvious assumption.