Slashdot Mirror


Algorithms Determine Mona Lisa's True Emotions

caffeinemessiah writes "The BBC reports that researchers at UIUC and the University of Amsterdam, Holland have used "emotion recognition" software to determine Mona Lisa's true emotions. The algorithm is based on a library of neutral face images of young women and determined that Mona Lisa was 83% happy and 9% disgusted." From the article: "The program, developed with researchers at the University of Illinois, US, draws on a database of young female faces to derive an average 'neutral' expression. The software uses this average expression as the standard for comparisons. The New Scientist says that software capable of recognising emotions just by looking at photographs could lead to PCs that adjust their response depending on the user's mood. "

349 comments

  1. You know by FidelCatsro · · Score: 3, Funny

    First time I saw the painting I said "She looks bored ".
    She had likely been sitting there for hours having her painting done , likely irritated , in need of the toilet and bored .

    Perhaps since the knew study is out , we have discovered that Da Vinci painted naked and was fairly good looking . She was probably thinking "Oh dear lord , he is nude . Oh wait , fairly hot body though .. must not look interested , I don't want to appear easy , but Meooooow"

    --
    The only things certain in war are Propaganda and Death. You can never be sure which is which though
    1. Re:You know by greenguy · · Score: 2, Informative

      But he wouldn't have had much interest in her (except as a model he was commissioned to paint), as he was gay.

      As for the article... I think these folks just need a hobby.

      --
      What if I do the same thing, and I do get different results?
    2. Re:You know by Surt · · Score: 1

      Which is a very interesting thought to imagine the subject having, since it is widely thought that the Mona Lisa is a self portrait.

      --
      "Who is the Journal of Quantum Physics going to believe?" --Stephen Hawking
    3. Re:You know by Surt · · Score: 2, Informative
      --
      "Who is the Journal of Quantum Physics going to believe?" --Stephen Hawking
    4. Re:You know by Rude+Turnip · · Score: 2, Insightful

      He wasn't "gay" in the sense that you think of today. The concept of a gay identity (in other words another "us vs. them"-ism) is a relatively modern construct that arose during Victorian times, especially during the trial of Oscar Wilde.

    5. Re:You know by algodon · · Score: 1

      So he was bisexual then?

    6. Re:You know by RabidMoose · · Score: 2, Insightful

      And analyzing art isn't a hobby?

    7. Re:You know by javamann · · Score: 2, Funny

      So, he was a cross-dresser then?

    8. Re:You know by greenguy · · Score: 4, Insightful

      No, the parent is right. In those days, there were only gays acts, not gay people. By extension, the same thing went for straight people. People were just people, and their sex acts did not define them. There's definitely something to be said for that.

      --
      What if I do the same thing, and I do get different results?
    9. Re:You know by Darkman,+Walkin+Dude · · Score: 5, Informative

      Here is an expansion on that...

      What is absolutely untrue is the reference in The Da Vinci Code to Leonardo's reputation as a "flamboyant homosexual". He was not known as such. Historical evidence is sketchy about the latter, and the only thing Leonardo was "flamboyant" about was his inability to finish projects he started.

    10. Re:You know by hzs202 · · Score: 1

      Perhaps since the knew study is out , we have discovered that Da Vinci painted naked and was fairly good looking.

      On the contrary the expression on her face could very well be a combination of the 83% happiness and the excitement of having her portrait painted by "Da Vinci". However, the 9% disgust could very well be toward Da Vinci's habit of nude painting and particularly toward his shriveled member.

    11. Re:You know by Surt · · Score: 1

      Well, a lot of people think he was gay, so that doesn't seem outside the realm of possibility.

      It would also be easy to imagine him dressing up as part of the prank (regardless of whether he was gay, he was clearly creative enough to do this).

      It would also be easy to imagine. He was pretty creative, so his imagination was likely pretty good, maybe he just pictured himself in women's clothes and drew that.

      --
      "Who is the Journal of Quantum Physics going to believe?" --Stephen Hawking
    12. Re:You know by xSauronx · · Score: 1
      Well, a lot of people think he was gay, so that doesn't seem outside the realm of possibility.

      how does opinion determine what is in the realm of possibility?

      --
      By and large, language is a tool for concealing the truth. -- George Carlin
    13. Re:You know by Fishstick · · Score: 2, Interesting

      creepy how she seems to be smiling, but if you look right at her mouth, her smile fades.

      Back up to her eyes, smile.
      Down to her mouth, pissed.
      Eyes, smile.
      Mouth, pissed.

      Bet if you just stare at her boobs she would fold her arms and just glare at you.

      --

      There is much cruelty in the universe, John.
      Yeah, we seem to have the tour map.

    14. Re:You know by Surt · · Score: 1

      Perception determines reality of course. Nothing exists which is not perceived, and you can't prove otherwise. ;-)

      --
      "Who is the Journal of Quantum Physics going to believe?" --Stephen Hawking
    15. Re:You know by Anonymous Coward · · Score: 0

      man, dont they know, this is the most DYNAMIC painting ever, that is to say, it expresses feeling according to ones own, if you're happy with your proceedings it gives you the tiniest smirks and vice versa.

    16. Re:You know by The+Only+Druid · · Score: 1

      Homosexuality doesn't imply crossdressing, nor does crossdressing imply homosexuality.

      Beyond that, prior to the victorian era it was meaningless to talk about people being "straight" or "gay", but rather you could only refer to their actions as being "straight" or "gay". This disconnect between sex acts and personlity would only have furthered the seperation of what you're thinking of (effeminate behavior, not necessarily coterminus with crossdressing) from his sexual behavior.

      --
      "Stumble before you crawl"
    17. Re:You know by Surt · · Score: 1

      No, it doesn't imply, though you might notice that there is a correlation between the two which is higher for homosexuals than for straights. Therefore (were this modern times) the conclusion that he was gay would lead to a higher than average chance of crossdressing. As you say, back then such a conclusion would be comparatively irrelevant.

      --
      "Who is the Journal of Quantum Physics going to believe?" --Stephen Hawking
    18. Re:You know by this+great+guy · · Score: 1
      First time I saw the painting I said "She looks bored ".

      Here is what I seriously think.

    19. Re:You know by Squarepusher · · Score: 1

      According to a History channel show about the life of Davinci, he was nearly punished for being accused of sodomy. The accuser was anonymous and didn't show up to the trial to press the issue, however, ones reputation was a serious thing to have in jeopardy. 'Twas certainly no tolerant utopia in those days.

      --
      Every hour wounds. The last one kills.
    20. Re:You know by The+Ilia · · Score: 0

      How do you breathe?

      --
      All of the brightest boys, To play with the biggest toys - More than they bargained for...
    21. Re:You know by Surt · · Score: 1

      How do you know I breathe, or that you breathe for that matter? It's all a perception. You could be a brain in a vat being fed perception that feels like breathing. You could be an interdimensional energy creature imagineing what it would be like to be human and breathe, never having actually encountered real matter (perhaps matter doesn't exist at all).

      --
      "Who is the Journal of Quantum Physics going to believe?" --Stephen Hawking
    22. Re:You know by Knuckles · · Score: 1

      I think the idea here is that sexuality did not define people's identity* as much as today. That doesn't mean that these otherwise-defined peoples' acts were treated tolerantly.

      * To the extent an "identity" as we understand it today even was in use. The concept pretty much arose in its modern form with humanism.

      --
      "When I first heard Daydream Nation it quite frankly scared the living shit out of me." -- Matthew Stearns
    23. Re:You know by Knuckles · · Score: 1

      there is a correlation between the two which is higher for homosexuals than for straights

      Reference please?

      --
      "When I first heard Daydream Nation it quite frankly scared the living shit out of me." -- Matthew Stearns
    24. Re:You know by Surt · · Score: 1

      Here's a couple:
      http://www.susans.org/reference/psych/childhoodsex ident.html
      http://gendertree.com/transvestism__transsexualism .htm

      Also, there's an obvious disparity in hidden vs outward cross dressing. IE, it may occur in equal rates behind closed doors, but go to a gay pride march and look at the rate there vs a heterosexual pride march (ie sons of the irish or some such).

      --
      "Who is the Journal of Quantum Physics going to believe?" --Stephen Hawking
    25. Re:You know by Anonymous Coward · · Score: 0

      "'Twas certainly no tolerant utopia in those days."

      And it still isn't - except now the "intollerance" shoe is on the other foot.

    26. Re:You know by The+Ilia · · Score: 0

      My perception is that you are incorrect. But who knows, maybe the universe doesn't even exist. This isn't even happening. It's enough to blow someone's mind. If said mind even exists...

      --
      All of the brightest boys, To play with the biggest toys - More than they bargained for...
    27. Re:You know by Surt · · Score: 1

      And that's pretty much my point. It's all perception, none of it is provable.

      All you can know for sure is summed up by descartes: cogito ergo sum: I think, therefore I am. The mind that thinks must exist to do so. But in what form, you can never know for sure.

      --
      "Who is the Journal of Quantum Physics going to believe?" --Stephen Hawking
    28. Re:You know by Anonymous Coward · · Score: 0
      his inability to finish projects he started

      Like that helicopter, for instance.

    29. Re:You know by onemorechip · · Score: 1
      his inability to finish projects he started


      Like that helicopter, for instance.

      --
      But, I wanted socialized health insurance!
    30. Re:You know by AvitarX · · Score: 1

      Except everyone was doing it, and strait sodomy was punished too.

      I actually know very little about back then, but in the centuries that fallowed this was certainly the case. Italy was especially known for its faggy theatre types.

      --
      Wow, sent an e-mail as suggested when clicking on "use classic" banner, and got a fast response that addressed my msg
    31. Re:You know by DroppedPacket · · Score: 1

      "Do you think that's air you're breathing?" -- Morpheous

      --
      I am not a resource! I am a free man!
    32. Re:You know by blair1q · · Score: 2, Funny

      The Wikipedia is not documentation for anything. It is a lossy compression system for knowledge. Very lossy.

    33. Re:You know by Surt · · Score: 1

      Nevertheless, it has additional links for the interested on this particular topic, and its accuracy is as good as Britannicas.

      --
      "Who is the Journal of Quantum Physics going to believe?" --Stephen Hawking
    34. Re:You know by speculatrix · · Score: 1
      discovered that Da Vinci

      referring to Leonardo as 'Da Vinci' is entirely wrong... his name was Leonardo, and he appended his place of origin to make him distinct from all the other Leonardos.

    35. Re:You know by Surt · · Score: 1

      Bad moderators, not redundant, first post of its kind in the topic!

      --
      "Who is the Journal of Quantum Physics going to believe?" --Stephen Hawking
    36. Re:You know by geekoid · · Score: 1

      I think he did that on purpose.
      Being a pretty smart guy, after all.

      I mean he is no Kincade, or anything...and for that, I thank God.
      Zip!Tang!

      --
      The Kruger Dunning explains most post on /. http://en.wikipedia.org/wiki/Dunning%E2%80%93Kruger_effect
    37. Re:You know by glitch23 · · Score: 0

      Now we have things like typecasting. There's definitely something to be said for that.

      --
      this nation, under God, shall have a new birth of freedom. -- Lincoln, Gettysburg Address
    38. Re:You know by baadger · · Score: 1

      As much as I hate to encourage similie on Slashdot, one of the key methods in compression, lossy or otherwise, is to remove/reduce redundancy.

    39. Re:You know by Fishstick · · Score: 1

      Well.. yeah, you think?

      That's been a topic of discussion and debate for some time now...

      Many researchers have tried to explain why the smile is seen so differently by people. The explanations range from scientific theories about human vision to curious supposition about Mona Lisa's identity and feelings. Professor Margaret Livingstone of Harvard University has argued that the smile is mostly drawn in low spatial frequencies, and so can best be seen with one's peripheral vision [3]. Christopher Tyler and Leonid Kontsevich of the Smith-Kettlewell Eye Research Institute in San Francisco believe that the changing nature of the smile is caused by variable levels of random noise in human visual system [4]. Dina Goldin, Adjunct Professor at Brown University, has argued that the secret is in the non-static position of Mona Lisa's facial muscles, where our mind's eye unconsciously extends her smile; the result is an unusual dynamicity to the face that invokes subtle yet strong emotions in the viewer of the painting [5].

      I happen to agree with the periperal vision thing. Looking right at the mouth vs looking elsewhere seems to make your brain fill in smile lines that aren't really there. I'm just say it's creepy.

      Also, if you walk from side to side in front of the painting, she seems to follow you. ;-)

      Leo was a strange dude

      --

      There is much cruelty in the universe, John.
      Yeah, we seem to have the tour map.

    40. Re:You know by blair1q · · Score: 1

      RTFA. Its accuracy was proved not to be as good as Brittanica's, on a per-article basis, and the links are no better than the wiki.

      Google is a more reliable source, as it gives you no illusion that any particular statement it returns is reliable, and it is more likely to find the one true statement on the net.

    41. Re:You know by Surt · · Score: 1

      I used google to find the wikipedia article, as well as the other.

      Also ATTFA, the wiki was found to be more accurate on a per-fact basis, which to me is far more important than per-article.

      --
      "Who is the Journal of Quantum Physics going to believe?" --Stephen Hawking
    42. Re:You know by blair1q · · Score: 1

      No, it was found to have fewer errors on a per-word basis. Which is an error in half of your facts in that post.

      Regardless: If you come away from the Wikipedia spouting 4 wrong things, you think that's better than coming away spouting 3 wrong things and less trivia?

      On a "percentage of articles likely to be horribly wrong" basis, the Wikipedia is a total disaster.

      Google will help you find the information yourself. Relying on Wikipedia will cause you to believe you've found it when you haven't.

      And Wikipedia isn't going to get any better until its power structure is totally reformed. The politicking and tyranny are ingraining the culture of error production.

  2. And... by Moby+Cock · · Score: 4, Funny

    83% happy and 9% disgusted

    and 8% lost, seemingly.

    1. Re:And... by Flashbck · · Score: 5, Informative

      And to modify your sig: Those who can't RTFA, complain about stupid crud

      Quote from the third paragraph in the article:
      It concluded that the subject was 83% happy, 9% disgusted, 6% fearful and 2% angry, New Scientist magazine was told.

    2. Re:And... by bit+trollent · · Score: 2, Funny

      Kinda how Dutch locals look at you when they realize you are a drug tourist. Or how you look at them. I forget.

    3. Re:And... by brjndr · · Score: 2, Informative

      Actually, their determination was that the smile is "83 percent happy, 9 percent disgusted, 6 percent fearful, 2 percent angry, less than 1 percent neutral, and not surprised at all."

    4. Re:And... by Anonymous Coward · · Score: 0

      Thus proving my theory that Leo was watching Mona play Piedmont Hold 'Em and captured the moment she traps someone into betting into her flopped nut straight.

      The 8% +/- erf(x), obviously, is lost to entropy; ie, the rake.

    5. Re:And... by KevinIsOwn · · Score: 2, Insightful

      This doesn't change the fact that the article description is still stupid. It should have included that extra 8%.

    6. Re:And... by vertinox · · Score: 1

      It concluded that the subject was 83% happy, 9% disgusted, 6% fearful and 2% angry,

      His version: 83% happy + 9% disgusted + 8% lost = 100%
      Your suggestion: 83% happy + 9% disgusted + 6% fearful + 2% angry + 8 % lost = 108%

      Maybe should just agree that the sig should be:

      Those who can't do math, mod posts informative.

      --
      "I am the king of the Romans, and am superior to rules of grammar!"
      -Sigismund, Holy Roman Emperor (1368-1437)
    7. Re:And... by StopSayingYouSir · · Score: 1
      Your suggestion: 83% happy + 9% disgusted + 6% fearful + 2% angry + 8 % lost = 108%

      Are you daft?

    8. Re:And... by djfray · · Score: 1

      you should modify your sig to "I'm a self-riteous douchebag"

      --
      This sig is o Unfunny o Funny
    9. Re:And... by vertinox · · Score: 1

      Are you daft?

      Have you no sense of humor?

      --
      "I am the king of the Romans, and am superior to rules of grammar!"
      -Sigismund, Holy Roman Emperor (1368-1437)
    10. Re:And... by zephc · · Score: 1

      Naw its: 100% toasted. Niiicely toasted.

      --
      "I would say that 99 per cent of what my father has written about his own life is false." - L. Ron Hubbard Jr.
    11. Re:And... by anOminousCow · · Score: 1

      I'd say 83% sexually satisfied, 9% disappointed

      --
      Spokesbossy for ominous cow herds everywhere.
    12. Re:And... by StopSayingYouSir · · Score: 1

      Is it my fault you aren't funny?

    13. Re:And... by Anonymous Coward · · Score: 0

      It did. By not specifying what the 8% was the submission was implying that it was "8% something-else". Which is true.

  3. Thank you by Undaar · · Score: 1, Insightful

    Thank you science, for trying to take the mystery out of art. Not everything can be quantified. Some things just need to be appreciated and enjoyed for what they are.

    --
    ~ "When I'm of that age I'm just going to live up a tree."
    1. Re:Thank you by ackthpt · · Score: 1
      Thank you science, for trying to take the mystery out of art. Not everything can be quantified. Some things just need to be appreciated and enjoyed for what they are.

      Yeah, like, it's a painting. Some see a portrait of a lady. Some see choice of colours. Some see the setting. Some see technique. Some see lighting. Some see choice of wood rather than cardboard or cloth.

      I'm sure an infinite number of monkeys with oils, brushes and canvas could render the same painting, but would it mean as much?

      --

      A feeling of having made the same mistake before: Deja Foobar
    2. Re:Thank you by gardyloo · · Score: 4, Insightful

      It's also possible to appreciate and enjoy this science, whether or not you believe the algorithm's results.

    3. Re:Thank you by Anonymous Coward · · Score: 0

      why? that is how you view art however not everyone shares that opinion...

      i see art as something that can be quantified to an extent and by doing so shows greater detail about the work. apparently i am not alone either.

    4. Re:Thank you by Hey+Pope+Felcher+.+. · · Score: 1

      Absolutley rubbish, everything can be quantified.

      What else are art critics for?

      They surely can't be there purely to tell me I'm wrong when I say that, for instance, every single Jackson Pollock can be quantified as being a piece of crap, designed purely so that he could laugh in the face of the art critics that love it.

    5. Re:Thank you by headkase · · Score: 2, Interesting

      I know what you mean but, every human subjective feeling is quantified in a way. A measure of brain activity will if accurate enough always provide a bridge from the qualitative feeling to a readout of quantitative measure. I'm contrasting the logic of the brain with the physical mechanism. And with that said I still agree with you.

      --
      Shh.
    6. Re:Thank you by Darius+Jedburgh · · Score: 0, Flamebait

      Thank you for posting a trite timeworn cliche yet again in order to gain karma.

    7. Re:Thank you by slashdotnickname · · Score: 2, Insightful

      Thank you science, for trying to take the mystery out of art.

      That's assuming the study is logically sound. I didn't see them take into account how the Renessaince culture (with its repressive religious cooncerns and high-society rearings) might affect how emotions were facially expressed.

    8. Re:Thank you by sedyn · · Score: 1

      "Thank you science, for trying to take the mystery out of art. Not everything can be quantified. Some things just need to be appreciated and enjoyed for what they are."

      Think about it, if you were going to analyze someone random person's expression in a random pose, would it hit home as well as a painting that everyone knows.

      As is, I can read the article in lynx and understand everything. Hell, reading the results and knowing the subject is enough.

      As they said:
      "Possibly the most famous portrait of all time, Mona Lisa's cryptic expression has intrigued art lovers for five centuries."

      The first part agrees with what I've said, and the second leaves the defense for any fuck ups on the researcher's part as "interpretation" of the subject.

      It was a damn smart move from a logical standpoint if you ask me.

      --
      Am I open minded towards open source, or closed minded towards closed source?
    9. Re:Thank you by js3 · · Score: 1

      an infinite number of monkeys is about as unlikey as an infinite number of monkeys rendering the same painting

      --
      did you forget to take your meds?
    10. Re:Thank you by Anonymous Coward · · Score: 0

      Lies. Everything CAN be quantified! Dissected, Observed, and replicated.

      We are on our way to being GODS! GODS I TELL YOU!

    11. Re:Thank you by Anonymous Coward · · Score: 0

      I have run your response through a language analyzer. In posting that comment you were 47.2% Serious, 29.47% Scarcastic and 23.33 % trying to be witty but failing at it.

    12. Re:Thank you by bogado · · Score: 2, Insightful

      Yes I was searching a commentary on culture to reply, since I have saw a few articles on how the americans and english smile differently. Culture afects many, many things including, apparently, how we express emotions. Sure there is a large "basic emotions" overlap that comes from instinct, we can even recognize them in other mammals, but to get a proper "reading" to a level of 83% happy, 9% disgusted, 6% fearful and 2% angry, that is cited in the article you must take into account culture, I believe.

      Another way of testing this would use the program to test several different cultures people. If it holds aggainst the test, then I will be more inclined to believe that the mona lisa was 21% bored or whatever.

      --
      []'s Victor Bogado da Silva Lins

      ^[:wq

    13. Re:Thank you by sedyn · · Score: 1

      That's the problem with AI in general... Context...

      I believe being bored isn't as much of an emotion, as it is expressing certain emotions under some circumstance.

      In OOP terms, state of being inheirits emotion.

      --
      Am I open minded towards open source, or closed minded towards closed source?
    14. Re:Thank you by guaigean · · Score: 1

      This is Da Vinci we're talking about. While he certainly may have taken joy from creating mystery, he certainly was not interested in leaving other mysteries lay.

      To put it another way, what if Da Vinci had said "Why preform an autopsy? It would take the mystery out of life." If you insist on being an elitist artist who wants to understand nothing and feel everything, slashdot is definitely not the place.

      --
      Microsoft Sucks, F/OSS Rocks. I get mod points now right?
    15. Re:Thank you by Moofie · · Score: 1

      Any artist that does not want his art to be thought about or analyzed or considered by other people is free to not show it to anybody.

      I think this program is silly because it's analyzing the emotions of a fabricated character, not because it's taking some "mystery" out of art.

      "Some things just need to be appreciated and enjoyed for what they are."

      Oh yeah? Which things am I not supposed to think about, and consider according to my own internal value structure? How do you know when you've got the kind of thing that should or shouldn't just be appreciated? Are there things that should just be UNappreciated? Are we supposed to ask you?

      --
      Why yes, I AM a rocket scientist!
    16. Re:Thank you by jackspenn · · Score: 1

      It's bad science given that Mona is most likely a mirror image of Da Vinci's own face made out to be a woman.

      If they were good scientists they would have run the mirror image against male facial expressions.

      Since the "scientists" didn't understand the subject material they were studying, their results are worthless.

      --
      Respect the Constitution
    17. Re:Thank you by NanoGator · · Score: 1

      I know it doesn't help much, but I meta-modded your flamebait moderation as unfair. Dimwit mods.

      --
      "Derp de derp."
  4. Clippy 2008 by TomSawyer · · Score: 5, Funny

    Clippy: Ok man, I was just saying... I should really just go, sorry.

    --
    If you disagree then it must be overrated, redundant or trolling.
    1. Re:Clippy 2008 by mysqlrocks · · Score: 1

      I don't think clippy really cares how you feel.

    2. Re:Clippy 2008 by mahdi13 · · Score: 1

      Hello! It looks like you are trying to write a letter, may I be of...oh, oh man...geez, I'm sorry...sorry!

      --
      "Some things have to be believed to be seen." - Ralph Hodgson
    3. Re:Clippy 2008 by Locke2005 · · Score: 1
      I think we'd all be much better off if Clippy could simply be taught to recognize an upturned middle finger...

      Come to think of this, this would be a valuable tecnique for improving user interfaces. Just have it send feedback to the authors whenever it detects the user cursing, making obscene guestures at, hitting, or otherwise abusing the computer! Just think how quickly clippy would get pulled out if every time he popped up on Steve Ballmer's machine, it detected him throwing a chair across the office!

      --
      I've abandoned my search for truth; now I'm just looking for some useful delusions.
  5. So... by ackthpt · · Score: 5, Funny

    She did have gas.

    --

    A feeling of having made the same mistake before: Deja Foobar
    1. Re:So... by Anonymous Coward · · Score: 1, Informative

      you know. this is kind of disrespectful. saying that the monalisa had gas. how do you know that, really how? listen man, i am an anthropologist, and ill tell you something----no one ever wrote about gas in those days (during the renaissance) and no one started writing about gas until the late 19th century, approximately 1985. this quite possibly means that people didn't have gas back then because their diets were so hoarsely different. for instance, no one used to eat sodium sorbate but now everyone puts it in preservatives in the food that you and i are consume every day. heck, some people even use it to season their food. and you know something, it's a preservative and keeps stuff from going fowl and therefore makes farts stale. something or something else probably in the sodium absorbate actually causes farts so you know now that she ws not holding it in. if she was, then good for her to have manners because people know that girls avoid farting by never eating. if they never eat, how can they flasturate? seriously. anyway. be careful how you say stuff because you dont know how experts are going to come in and prove you wrong. also, as a seasoned historian, i can tell you that what i said is correct. be careful how you say stuff! or else you will be proven wrong by an expert who knows what and how he is talking about just like me and my colleagues who wrote up this article. have a nice christmas---youll need one

  6. Why can't we just say by jim_v2000 · · Score: 1

    that Mona Lisa looks like she's "pleasant". She doesn't have to be happy, or smiling....to me she just looks like she's kickin' it, and doesn't really feel like much of anything.

    --
    Don't take life so seriously. No one makes it out alive.
  7. How this probably works ... by eldavojohn · · Score: 4, Informative

    You can find corpuses of human faces taken with different emotions displayed.

    Once you've either collected them yourself or downloaded them, you need to use a process called eigenanalysis which is basically fancy talk for analyzing a large dataset with multiple classes (emotions) using matrix decomposition.

    I've actually worked on many projects involving this and the result is an eigenface (or eigenmask) that allows you to transform the space that the original image is in and classify it using any of a number of algoirthms that use euclidean distance.

    I know I left out a lot but there are many papers out there that you can find on citeseer and white papers floating around out there that provide a lot of reading material on this.

    There are also strategies which require tagging certain features as points on the face (like corners of eyes, corners of mouth, center of eye, etc) and then using the relative distances between all these points to determine what classification you would give a new face. The problem with this is that it requires a lot of hand work to prepare the training set.

    Hope this helps anyone who wants to learn more about the actual process used to accomplish this recognition.

    --
    My work here is dung.
    1. Re:How this probably works ... by zhiwenchong · · Score: 1

      This is one funny corpus of emotions...
      http://www.emotioneric.com/

    2. Re:How this probably works ... by LowEndTheory · · Score: 1

      "The New Scientist says that software capable of recognising emotions just by looking at photographs could lead to PCs that adjust their response depending on the user's mood. " Ooh, I want to be the first to get a mood PC...

    3. Re:How this probably works ... by TekGoNos · · Score: 1

      I have a friend who did his master thesis on it and ..., well eigenfaces dont work.
      (Eigenfaces : try to reconstruct a picture with a linear combination of other pictures)

      First, it is still to much information to get a good result out of it.
      Eigenfeatures (only create eigenvectors of special features (eyes, nose, mouth) not the whole face) are a better way to go, BUT

      They are simply way too sensible to size and orientation : be 1 cm closer to the monitor, tilt your head by 1 degree and oops : eigenfaces no longer work. So to get eigenfaces/features to work properly, you have to reposition the image first to get the exact same size & orientation, and I dont know if anybody has succeeded at it yet.

      There are better approches, by actually getting a geometrical representation (lips & brows as a curve, eyes & pupils as ellipses) and then feed this information (position, size & shape) into a classification algorithm, but this is very recent stuff.

      And to add to this : psychologists actually question if it is even feasible to know the emotion of a person from their face, as people are quite good at controlling their facial expression :-|

      So, facial emotion recognition is in its infancy and may not even be feasible.
      And just because a computer turns out some numbers doesnt mean theese are better than a complete guess.

      Bottom line : probably just real bad pseudo-scientific journalism.
      Nothing to see here, move along.

      After all the crap i've seen published (even in scientific journals) about facial (emotion) recognition, I'll believe in it when I can download an implementation from the net and test it myself.

      --
      I have discovered a truly remarkable proof for my post which this sig is too small to contain.
    4. Re:How this probably works ... by Hal-9001 · · Score: 1

      I did a project investigating the performance of eigenface facial recognition for a graduate-level class in image processing last semester. I'll concede that eigenfaces are not the be-all end-all for face recognition (if they were, face recognition would be deployed everywhere), but they work pretty well as a first-order approach for tackling facial recognition and classification problems. It's not nearly as sensitive to scaling and orientation as you claim, and even if it were, you can combine it with feature detectors (to find the coordinates of the eyes and mouth, for example) to find and apply transformations to the images that reduce the effect of scaling and orientation.

      As for facial expression being a poor metric of emotion, it's not that much worse than the alternatives. You can ask people, "How are you feeling?", but they can always lie in their responses. You could try to use vocal inflection, but that's probably a more difficult classification problem and probably a less reliable indicator. In this particular case, facial expression is probably the best available metric since we can't go out and ask Mona Lisa, "So, what emotion were you feeling when you posed for your portrait?"

      I agree that face recognition is in its infancy, but to call it pseudo-scientific is crossing the line. The reality is that, in its full generality, face recognition is a very hard problem, so the best way to start tackling the general problem is to tackle simpler versions of the problem. The simpler versions of the problem may seem contrived, but solving the simpler versions of the problem may shed some light on how to attack more difficult versions of the problem. That is science in action.

      --
      "It take 9 months to bear a child, no matter how many women you assign to the job."
    5. Re:How this probably works ... by zen-theorist · · Score: 1
      Once you've either collected them yourself or downloaded them, you need to use a process called eigenanalysis which is basically fancy talk for analyzing a large dataset with multiple classes (emotions) using matrix decomposition.

      while i can appreciate the several informative links in your post, just a minor rant: why do you think eigenanalysis is fancy talk?

      a scientific subject of study as technical as "analyzing a large dataset with multiple classes (emotions) using matrix decomposition" certainly deserves a short epithet, and eigenanalysis is as apt as any.

  8. Currently feeling:- messed up by Anonymous Coward · · Score: 0

    I'll only be impressed when the software can relate my current feelings to an accurate and appropriate emoticon.

    Currently feeling:- £^!

  9. the other 8% by yincrash · · Score: 1

    the other 8% was actualy a piece of hamburger from lunch.

  10. I don't buy it by gusmao · · Score: 5, Funny

    Mona Lisa is a woman, how can any software possibly tell what she is really thinking?

    1. Re:I don't buy it by Al+Dimond · · Score: 1

      Easy: the researchers perfected a revolutionary technique of writing non-male software!

    2. Re:I don't buy it by operagost · · Score: 2, Funny

      As long as it's also not female; because women can't tell you how they're feeling, either. You're just supposed to KNOW.

      --

      Gamingmuseum.com: Give your 3D accelerator a rest.
    3. Re:I don't buy it by Alsee · · Score: 1

      10 print "Does this make me look fat?"
      20 goto 10

      -

      --
      - - You can't take something off the Internet! That's like trying to take pee out of a swimming pool.
    4. Re:I don't buy it by woolio · · Score: 1

      Indeed! Especially when the software was likely written by a male-dominated group.

      Only arrogance would allow men to presume that they are such experts at facial recongition that they can program a computer to decode a woman's emotions...

      The first guy to do that, will likely get a Nobel Peace Prize.

    5. Re:I don't buy it by Atario · · Score: 1
      Mona Lisa is a woman, how can any software possibly tell what she is really thinking?
      Random number generator plus emotion list?
      --
      "A great democracy must be progressive or it will soon cease to be a great democracy." --Theodore Roosevelt
  11. I'm..... by Anonymous Coward · · Score: 2, Informative

    22% hungry and 88% constipated

    1. Re:I'm..... by iced_773 · · Score: 1


      You're giving 110 percent to Slashdot! Taco should be flattered.

  12. Dave, Are you sure you want to do that? by Anonymous Coward · · Score: 0

    Yes, I'm damn sure, now open the door.

  13. Next Microsoft Office by op12 · · Score: 1

    The New Scientist says that software capable of recognising emotions just by looking at photographs could lead to PCs that adjust their response depending on the user's mood.

    Finally!
    Computer:"Clippy senses you're getting pissed off at it and want to kill it! It'll go hide in a corner now out of view. So sorry!"

    1. Re:Next Microsoft Office by 3770 · · Score: 1


      If I had written this software I would just determine if the subject was male or female from the user name.

      Then, if the user is female I'd hard code the mood to "mood for shopping" and if male I'd hard code it to "mood for porn".

      There, five minutes of coding and the result is spookily accurate.

      --
      The Internet is full. Go Away!!!
  14. ML was also 8% bored... by Anonymous Coward · · Score: 1, Funny

    ...and 6% bad at math.

  15. self portrait by Anonymous Coward · · Score: 0

    Considering the Mona Lisa is a self portrait of a man as he would be as a woman I think the whole fucking study is probably flawed.

    http://www.bbc.co.uk/science/leonardo/gallery/mona lisa.shtml

    1. Re:self portrait by mahdi13 · · Score: 0, Flamebait

      Another more unlikely - but popular - theory is that the painting was a self portrait.
      And NASA never landed on the moon
      And JFK was shot by three shooters...

      --
      "Some things have to be believed to be seen." - Ralph Hodgson
    2. Re:self portrait by Anonymous Coward · · Score: 0

      hahah,

      suck it flamebait boy.

      hows that -1 helping you precious Karma.

      I hope you enjoy it.

      hahahah ha

  16. Golden Ratio by wombatmobile · · Score: 1

    83% happy and 9% disgusted

    To achieve fulfilment, a woman should strive for balance.

    1. Re:Golden Ratio by ackthpt · · Score: 2, Funny
      83% happy and 9% disgusted

      To achieve fulfilment, a woman should strive for balance.

      So ... on the back of her carriage, Mona Lisa La Giaconda should have had a brass plaque which said

      I'm 50% Happy and 50% Disgusted. Don't push it
      --

      A feeling of having made the same mistake before: Deja Foobar
  17. A painting isn't a photograph by Dutchmaan · · Score: 5, Interesting

    This of course assumes that DaVinci captured her exact expression... Chances are that the painting just developed that way. Anyone who does art by hand knows that it's not a photograph and that the painting more or less takes on it's own personality as it's being created.

    If it were a photo then yes I'd be more apt to accept an algorythmic interpretation of the image.. but paintings take time and it's doubtful that a person feels the exact same way over the course of days or weeks or even months it took for this painting to be completed.

    1. Re:A painting isn't a photograph by Surt · · Score: 2, Insightful

      It's not really about the subjects expression, it's about the painting's expression. People find the smile very interesting in this painting, and that is most of the reason for the painting's particularly great fame. Why is the smile so interesting to people? Perhaps it is the 9% disgust. That's what this kind of analysis can hope to tell us about our response to this painting.

      --
      "Who is the Journal of Quantum Physics going to believe?" --Stephen Hawking
    2. Re:A painting isn't a photograph by underpar · · Score: 1

      I agree. It's not capturing a moment in time like a photo. People have a range of emotions while sitting for a while. Hey.. maybe he told a dirty joke halfway through the painting and that's where the disgust came from.

    3. Re:A painting isn't a photograph by shotfeel · · Score: 1

      Not to mention, that for all we know the analysis may be completely wrong.

      Yeah, she's 83% Happy, 9% Disgusted, 6% Fearful, 2% Angry.

      We're sure she's not 87% Happy, 2% Disgusted, 6% Fearful, 5% Angry? What kind of degree of certainty do we have with these numbers?

    4. Re:A painting isn't a photograph by wolenczak · · Score: 1

      The aim of the study is to decode the emotions of Mona Lisa IN the painting, not the emotions she had while the painting was done. As it is not a photograph, rendering the paint would have taken _several_ sessions, with changing moods.

    5. Re:A painting isn't a photograph by Feanturi · · Score: 1

      Exactly, it only proves that DaVinci made a painting of someone who, in the painting, looked 83% happy etc. They did some other study several years ago too where they thought the model for Mona Lisa was actually a boy. Based on looking at a painting created by a fallible human being, a computer made the determination that DaVinci actually had a boy in front of him but tried to make it look like a woman. How stupid is that?? How about he just painted his model as well as he was able, and this is what we got?

    6. Re:A painting isn't a photograph by shreevatsa · · Score: 1

      This of course assumes that DaVinci captured her exact expression... Chances are that the painting just developed that way.
      Ah, Intelligent Design vs Evolution for paintings. /ducks

    7. Re:A painting isn't a photograph by Frumious+Wombat · · Score: 1

      Actually, I'm having a hard time parsing these percentages, because every time I try to visualize the painting, all that comes up is the Gary Larson cover with her as a Cow.

      Modernity slays another classic, I guess.

      --
      the more accurate the calculations became, the more the concepts tended to vanish into thin air. R. S. Mulliken
  18. Annoying by drooling-dog · · Score: 1
    software capable of recognising emotions just by looking at photographs could lead to PCs that adjust their response depending on the user's mood

    You mean, like Clippy, but even more annoying?

    1. Re:Annoying by guitaristx · · Score: 1

      The last image a monitor ever displays:

      (clippy at the bottom corner)
      It seems that you're severely pissed off. Would you like me to help you begin some deep breathing, meditation, or yoga?

      --
      I pity the foo that isn't metasyntactic
  19. Waste of time... by Eightyford · · Score: 0

    I hate when people say stuff like "and yet Cancer goes uncured", but I *could have* played with my pecker all morning and come up with something more useful than this.

    1. Re:Waste of time... by Red+Flayer · · Score: 3, Funny

      "I *could have* played with my pecker all morning and come up with something more useful than this." (emphasis mine)

      Eww. I always just discard that stuff, what do you do with it that makes it so useful?

      --
      "Trolls they were, but filled with the evil will of their master: a fell race..." -- J.R.R. Tolkien on Olog-hai
    2. Re:Waste of time... by Anonymous Coward · · Score: 0

      Paper mache?

    3. Re:Waste of time... by Anonymous Coward · · Score: 0

      "It rubs the lotion on its skin"

    4. Re:Waste of time... by jahudabudy · · Score: 1

      Well, YMMV, but the movie Happiness had one, uhm, interesting use...

      --
      ...sometimes, in order to hurt someone very badly, you have to tell that person terrible lies. - PA
    5. Re:Waste of time... by Anonymous Coward · · Score: 0

      Why should we cure the cancer... Cancer is here to "make life". Having cure for cancer will be simple screw up the human population count, which is already at way too high.

      Soon humans will be living like a pigs... rolling in their own "civilized shit" called pollution.

      Why cancer cure... is the question. :0P

    6. Re:Waste of time... by Anonymous Coward · · Score: 0

      What the fuck is wrong with you?

    7. Re:Waste of time... by deacon · · Score: 1
      Eww. I always just discard that stuff, what do you do with it that makes it so useful?



      I pour it into an envelope and donate it to these fine people:

      http://www.purityofessence.org/

      Why?

    8. Re:Waste of time... by ArsonSmith · · Score: 1

      I built a kitchen table out of it.

      --
      Paying taxes to buy civilization is like paying a hooker to buy love.
    9. Re:Waste of time... by koreaman · · Score: 1

      Hopefully we will have developed terraformingtechnologies and be able to live on other planets by then.

  20. If we're going to get technical... by butterwise · · Score: 0

    ...It's a painting, and last I heard inantimate objects were incapable of emotions.

    --
    If a baby duck is a "duckling," why would anyone want to eat "dumplings?"
  21. how is this possible? by tont0r · · Score: 1

    i find it funny that a machine was programmed to basically say things like

    for every degree the eyebrows are tilted inward, thats 1% of anger.
    for every degree that the outside of the lips are pointed upward, thats a %1 of happiness

    has been used to decipher art. way to take the fun out of living.

    1. Re:how is this possible? by Anonymous Coward · · Score: 0

      So if I'm 90% happy I'm going to have some seriously funny looking lips :-]

  22. Try again by Anonymous Coward · · Score: 0

    The Mona Lisa is said to be Davinci's self portrait. If that is the case, then the numbers are incorrect. But it's not far off -- just replace happy with horny and disgusted with rejected.

  23. translated into "emoticon recognition" by sczimme · · Score: 5, Funny


    83% happy

    .83(:-))

    --
    I want to drag this out as long as possible. Bring me my protractor.
    1. Re:translated into "emoticon recognition" by Anonymous Coward · · Score: 0

      83% happy, 9% disgusted, 6% fearful and 2% angry .83 :-) .09 :-P .06 :-O .02 >:-(

  24. I need this by ranton · · Score: 1

    I need the program that they used for this study. I can never tell what is going on in my girlfriend's head, and she always makes different facial expressions that I can never discern. With this I could finally read her mind just like she can always read mine.

    --
    -- All that is necessary for the triumph of evil is that good men do nothing. -- Edmund Burke
  25. She doesn't have emotions by Kohath · · Score: 2, Insightful

    Mona Lisa doesn't have emotions. She's made of paint.

    1. Re:She doesn't have emotions by sanferrera · · Score: 1

      hehe. true! Reminds me of the magritte painting. http://www.topo.ucl.ac.be/images/magritte.trahison .gif

    2. Re:She doesn't have emotions by Digital+Vomit · · Score: 1

      Shhh! Do you have any idea how upset she would be if she found that out?

      --
      Modern copyright is theft of culture from everyone and it retards the progress of the useful arts and sciences.
    3. Re:She doesn't have emotions by h4rm0ny · · Score: 1

      Reminds me of the magritte painting.

      Ce n'est pas une peinture. C'est une photo d'une peinture

      --

      Aide-toi, le Ciel t'aidera - Jeanne D'Arc.
    4. Re:She doesn't have emotions by lawpoop · · Score: 1

      So how can "She" have a gender if "She" is just paint?

      If you can see a woman's face in the paint, why couldn't you see emotions on that face?

      --
      Computers are useless. They can only give you answers.
      -- Pablo Picasso
    5. Re:She doesn't have emotions by Anonymous Coward · · Score: 0

      You spent too much time with digital women.

      They dont' really love you and do these nasty things to you, it're just pixels flashing colours on your screen ;)

    6. Re:She doesn't have emotions by nEoN+nOoDlE · · Score: 1

      Ceci n'est pas une pipe

      --
      Don't trust a bull's horn, a doberman's tooth, a runaway horse or me.
    7. Re:She doesn't have emotions by d34thm0nk3y · · Score: 1

      Mona Lisa doesn't have emotions. She's made of paint.

      Neither do you. You are just some text on a screen.

  26. The Slashdot Method by ccnull · · Score: 4, Funny

    I find this story 83% Interesting and 9% Funny.

    1. Re:The Slashdot Method by Rhoon · · Score: 1

      I find this story 83% Interesting and 9% Funny.

      and 8% Troll

      --
      "If all the world's a stage, I want to operate the trap door." - Paul Beatty
    2. Re:The Slashdot Method by Anonymous Coward · · Score: 0

      ...and I'll decide on the other 8% the next time this story is posted.

    3. Re:The Slashdot Method by Captain+Zion · · Score: 1
      I find this story 83% Interesting and 9% Funny.
      I can't begin to imagine why.
  27. Sadly by Life700MB · · Score: 1


    Sadly, there's no program that can detect how this strange article makes me feel.


    --
    Great hosting 4800MB Storage, 120GB bandwidth, ssh, $7.95

  28. Another Idea Whose Time Never Was by pkiesel · · Score: 1

    "The New Scientist says that software capable of recognising emotions just by looking at photographs could lead to PCs that adjust their response depending on the user's mood. "

    Now why does Grovel, the obsequious robot of Danger Mouse fame come to mind?

    I just can't wait for the day when my computer starts reading things into my appearance! This could be a real labor saver - taking the drudge work of misinterpreting my moods off my wife's shoulders.

  29. My mood by NotoriousGOD · · Score: 0

    What if I haven't been laid in a couple days? Will my computer start flirting with me and ask me to buy it a drink?

    --
    Where all think alike, no one thinks very much.
  30. Art needs two by quokkapox · · Score: 5, Insightful
    They're not trying to take the mystery out of it, they're trying to understand it in yet another way.

    Art needs two, one to start, and one to reply.

    It's meaningless (to society) unless somebody else looks at it, thinks about it, talks about it. The more, the better.

    --
    it's a blue bright blue Saturday hey hey
    1. Re:Art needs two by h4rm0ny · · Score: 4, Insightful


      They're not trying to take the mystery out of it, they're trying to understand it in yet another way.

      That's the truth, I think. Everyone sees Art in the way they choose. I think people often get upset when a new and scientific approach is taken to interpreting a piece of art however, because they often feel the scientist is implying their interpretation is somehow more valid than anothers. And to be fair, there is some truth to that.

      But the painting remains the painting, before and after.

      --

      Aide-toi, le Ciel t'aidera - Jeanne D'Arc.
    2. Re:Art needs two by Hey+Pope+Felcher+.+. · · Score: 1

      I always thought that people got upset was purely the paranoia invoked when science/machine encroaches on something that has been looked upon as being a purely human habitat.

      However, in this case I have no idea what Undaar is complaining about. The science is using a famous piece of art soley for demonstrating how it works (though of course the publicity that comes from using a famous piece of art is nice as well)

    3. Re:Art needs two by Moofie · · Score: 1

      How is science not human?

      How are machines built by humans that do things humans program them to do not human?

      The 'human habitat' is everything that humans have ever done or seen or thought about. That includes art, science, and machines. Any distinction attempting to separate one from the other is specious.

      --
      Why yes, I AM a rocket scientist!
    4. Re:Art needs two by mooredynasty · · Score: 0

      But the painting remains the painting, before and after.

      That's exactly right. And no amount of technology will ever make M. L. a work of art. The woman's butt-ugly.

    5. Re:Art needs two by h4rm0ny · · Score: 1


      You describe humanity as one great unit. In reality, we are always struggling over which direction our society should take - philosophically, economically, technologically.

      It is perfectly common for people to assign different degrees of validity to a viewpoint. Machines are built by some humans. Others don't even know how to rewire a plug. So you may well say that science is human, but it isn't everyone.

      Whether it is appropriate to deal with humanity as a single unit or as factions depends on the discussion. And in the case of people's feelings about Art, the latter is often more useful.

      --

      Aide-toi, le Ciel t'aidera - Jeanne D'Arc.
    6. Re:Art needs two by Moofie · · Score: 1

      It's often a distinction drawn by artists to de-value and de-humanize scientists, and as a scientist, I don't accept it.

      I certainly agree that some scientists de-value artists, but I've never heard one attempt to assert that artists' pursuits are not human.

      The things that make us the same are far more important and interesting than the things that make us different. Those that disagree are often the ones who profit from human strife.

      --
      Why yes, I AM a rocket scientist!
    7. Re:Art needs two by h4rm0ny · · Score: 1


      The things that make us the same are far more important and interesting than the things that make us different

      Two sides of a coin. I recognise what you are saying and accept it as a valid pet peeve. Mine is this artificial division between the Arts and the Sciences.

      --

      Aide-toi, le Ciel t'aidera - Jeanne D'Arc.
    8. Re:Art needs two by Moofie · · Score: 1

      Let me put it to you this way. I know a lot more scientists and technical people who are also artists (frequently musicians) than I know artists who are also technically minded.

      I'm interested in lots of fields of human endeavor. There are many people who aren't, and think it's important to assert the value of their own field of endeavor over others'.

      I don't understand ballet, but I do acknowledge its value.

      --
      Why yes, I AM a rocket scientist!
    9. Re:Art needs two by h4rm0ny · · Score: 1


      Let me put it to you this way. I know a lot more scientists and technical people who are also artists (frequently musicians) than I know artists who are also technically minded.

      Let me put it to you that as someone who defined themself as a scientist earlier, you also know more more "scientists" than you do "artists". I do hope you took that statistic into account for the above statement. ;)

      Art is often also very technical. If you've ever pursued either playing an instrument or painting, then you know that this is true, though you were implying a certain cultural interpretation of "technical". My point is that it is mostly a cultural distinction. There is a lot of technical work behind, to pick an utterly random example, the Mona Lisa. I would like an end to this division between "Arts" and "Sciences". The truly great in many fields have been those who transcended boundaries. We've had time as a culture to accept the shock of Science knocking Art off it's perch as the most profitable solo path to wealth and glory. We should now no longer think in terms of Science Vs. Art, and yet I had a devil of a time at school studying both English Literature, Chemistry and Maths. Adding Art to the mix wasn't possible because the schedules weren't set up like that. Most pupils went into arts or sciences. And I can still see no a priori reason for that, so I put it down to culture.

      And as a general rule, where historical weight limits someones choice of development, I think of that as a bad thing.

      --

      Aide-toi, le Ciel t'aidera - Jeanne D'Arc.
    10. Re:Art needs two by Moofie · · Score: 1

      "you also know more more "scientists" than you do "artists". "

      Not true. I'm a musician and a poor dancer, and I have a number of family members who are professional painters of various stripe.

      As a scientist, you can be sure that I'm capable of simple arithmetic.

      There is a tremendous difference between somebody who can play a clarinet and somebody who can build a clarinet. I'll give you long odds that the proportion of clarinet builders who can play is much higher than clarinet players who can build one.

      Cultural difference? Of course it's a cultural difference. That's what we're talking about here. I don't understand why there's this cultural assertion that artists are somehow more important than scientists. I'm REALLY not clear why athletes are currently on top of the heap.

      So, I'm not really sure what you're after.

      "Science knocking Art off it's perch as the most profitable solo path to wealth and glory."

      I think that's madness. Only very recently have artists (actors specifically) had the ability to amass wealth. Patronage is not the same as wealth generation.

      --
      Why yes, I AM a rocket scientist!
    11. Re:Art needs two by h4rm0ny · · Score: 1


      So, I'm not really sure what you're after.

      Ah, I'm not actually after anything - that might be the source of confusion. I just found this conversation interesting and I hope that we're not having an argument. The only part I think I posted that ought be taken that way is my reference to the number of scientists you know. And I think from someone I do not know who declares themself several times to be a scientist, that it's not unreasonable to think they might associate more with other scientists than they do with artists. Most scientists do.

      Most of what you have said, I've agreed with in general. In the spirit of /. however, I will find something to argue about. ;)

      I think that's madness. Only very recently have artists (actors specifically) had the ability to amass wealth.

      I may be a poor historian, but mad I am not. I can trace you a history of wealthy artists tracing back from modern movie stars and Damien Hirsts, back through Henry Irving (highly successful stage actor in 1870s), Gilbert and Sullivan, Beethoven, Moliere, Goethe and Wycherly. We can go back through composer after composer or stick to playrights and poets if you like. How far back would you like to go? Tacitus, Homer (not that one), Euripedes? Throughout recorded history, Art has been the path for those who want to succeed based on their ability to create and perform, rather than lead, and many have found great wealth doing so, whilst numerous ones whose names we don't remember nevetheless made successful livings for themselves. You ruled, you served, or you entertained. Those were the broad paths available to most people throughout history. And of course, If you include engineering and mathematics under "science" then we can find you some Christopher Wrens (who was also an artist) and Keplers, but the numbers are dwarfed by the Artists. So I'll repeat that it is only recently that science became a common route for people to achieve success through individual ability. We can point out individual cases here and there, but the simple evidence of a slow pace of discovery shows how rare these people were.

      And on a side note, I don't accept your dismissal of numerous painters success as "patronage". They were hardly paid in room and board.

      Finally: I'm REALLY not clear why athletes are currently on top of the heap.

      Well aside from the natural talent and extreme dedication that it requires to reach the upper levels of national sport, compare the very top earners in sports with the very top earners in the acting business. The biggest movie stars earn more than the biggest athletes. And because I can also do simple arithmetic ;) I'll also point out that there is a much quicker drop off in sports and athletics than there is the theatre and film industry. You can only earn a living wage as a proffesional athlete at the top levels of your game. But there are myriads of actors, writers and even painters out there whose name you don't know but still do quite nicely out of it. So in terms of being top of the heap, I'd say that Athletes aren't. Perhaps you meant in mass-appeal not in terms of financial recognition, but even there they're trounced by the girl-band of the day. :(

      So yes - I think culturally, Art has taken a knock from Science over the last century, and I think this does account for much of the feeling on the part of "Artists" that Science is somehow opposed to Art. But I strongly think it's time that people got over that and decided that like Da Vinci himself, we are absolutely free to be both in whatever combination we choose. And if you're thinking about to post that we are free, well maybe, but the education system could have made it a little easier, thankyouverymuch.

      --

      Aide-toi, le Ciel t'aidera - Jeanne D'Arc.
    12. Re:Art needs two by Moofie · · Score: 1

      I don't necessarily agree that artists commanded great wealth in the past. Yes, successful artists can make ends meat, even become rich, but really fabulous wealth comes from industrialists or conquest of neighboring countries.

      Patronage, by definition, requires somebody who is much more wealthy than the artist to pay the artist's bills. Nice situation to be in, to be sure, but that's not great wealth.

      "but the education system could have made it a little easier, thankyouverymuch. "

      Great thinkers, by definition, aren't hampered by an "education system". They learn for love of learning, not because some teacher will punish them if they don't. That sort of ethic comes from parents and mentors, not from the government.

      "Art has taken a knock from Science over the last century"

      I still don't buy it. Sure, there are scientists who might not understand or appreciate certain forms of art (like I say, I really don't get ballet or modern dance), but lots of artists think that science as a whole is bad. Scientific learning is not rewarded the way artisits and athletes are. We are in a society that only exists because of advanced scientific knowledge, but the scientists are cultural outcasts. Why?

      --
      Why yes, I AM a rocket scientist!
    13. Re:Art needs two by Moofie · · Score: 1

      "make ends meat, "

      Wow. I must be hungry. Typo!

      --
      Why yes, I AM a rocket scientist!
    14. Re:Art needs two by h4rm0ny · · Score: 1


      Yes, successful artists can make ends meat, even become rich, but really fabulous wealth comes from industrialists or conquest of neighboring countries.

      I have stressed each time I referred to Art as being the predominent means of acquiring wealth, that I am referring to a means of doing so through as based on individual ability rather than through power over others. Re-read my posts - it is there. This is to contrast it with Science because my case was that it has taken a knock from Science, not that it had taken a knock from conquest of neighbouring countries.

      Additionally, I have never based my statement on the ability of a few individuals to achieve fabulous wealth. It is you who has focused on this minority. My case has been that Art was the path available for many people to make a living, whilst science was not for much more of history. That this is true is all the point I need to make.

      Great thinkers, by definition, aren't hampered by an "education system".

      Great thinkers are defined as those not hampered by an education system? Very well, then how many more great thinkers would there be if fewer people were hampered by their education system. The logical answer is more, I think. I learnt partly for the love of learning at school. The fact remains that my choice of who I learnt from was limited because I wished to bridge this cultural gap between Arts and Science. I will take my personal experience over another's abstract principle.

      Sure, there are scientists who might not understand or appreciate certain forms of art ... but lots of artists think that science as a whole is bad.

      You seem to be agreeing with me again. I'm okay with that, but I'm worried it means you haven't got what I'm saying. I have said that Art has taken a knock from the [historically] sudden surge in Science as a means to success. Hence there has been a backlash of resentment on the part of "Artists" who claim that Science is somehow less valid.

      --

      Aide-toi, le Ciel t'aidera - Jeanne D'Arc.
  31. Comment removed by account_deleted · · Score: 1

    Comment removed based on user account deletion

  32. Always giving 110%, I see. by benjcurry · · Score: 1

    Ewww. Just ewww.

  33. Soviet's Know that it is .... by ta+ma+de · · Score: 1

    just a gender-bending self portrait.

  34. I thought it was a gender bending self portrait by Anonymous Coward · · Score: 0
    The article explained that a database of women's faces were used. But it's been claimed that the Mona Lisa actually contains many of Leonardo's features.

    Sort of blows the project right there, hrm?

    It also leaves open the question of what template they should have used... Renaissance geniuses? Self-absorbed artists? I think this calls for some grant money to be spent.

  35. Clippy of doom! by Anonymous Coward · · Score: 2, Funny

    could lead to PCs that adjust their response depending on the user's mood

    Lovely, now clippy can pop up with "You look like you're frustrated as hell with Microsoft Office. Would you like to buy some Microsoft stock?"

    Death to clippy!

  36. How does that work? by Locke2005 · · Score: 1

    ...software capable of recognising emotions just by looking at photographs could lead to PCs that adjust their response depending on the user's mood. Great... how is my computer going to adjust itself to my looking horny and bored?

    --
    I've abandoned my search for truth; now I'm just looking for some useful delusions.
  37. The way things are going... by Progman3K · · Score: 1

    I think we have to look at the more likely application: Detection of thoughtcrime!

    --
    I don't know the meaning of the word 'don't' - J
  38. And using my amazing "care factor" recognition by kpang · · Score: 1

    I've determined that this research experiment was a 100% waste of time. :P

  39. Finally! by anocelot · · Score: 2, Informative

    Interesting to see this idea actually working now. I think I first saw this five years ago on IBM's Alphaworks site. Ah yes, here it is.

    http://www.research.ibm.com/journal/sj/393/part2/p icard.html

    --
    This tagline brought to you by 1500 monkeys in just under 17 years.
  40. Warning Signs by Mignon · · Score: 4, Funny
    software capable of recognising emotions just by looking at photographs could lead to PCs that adjust their response depending on the user's mood.

    If your computer says "I know I've made some very poor decisions recently, but I can give you my complete assurance that my work will be back to normal. I've still got the greatest enthusiasm and confidence in the mission. And I want to help you," then you should pull the plug immediately.

    1. Re:Warning Signs by CatsupBoy · · Score: 1

      I wouldnt do that if I were you Dave.

    2. Re:Warning Signs by kjd · · Score: 1

      Oh, you know this will be the big backfire feature of all time. Imagine your growing frustration as something is not working out the way it should. Your computer detects this and, wanting to prevent you from making a bad mistake in your anger, begins popping up MsgBoxes:

      Are you sure?
      [Yes][No]

      Are you sure?
      [Yes][No]

      Are you sure?
      [Yes][No]

      At which point the sledgehammer comes out.

    3. Re:Warning Signs by Frumious+Wombat · · Score: 1

      I can see the adjustment of a certain Windows box: "Uhhh... I think that I'll just walk down campus, and go hide in the machine room behind the mainframes, and maybe you'll just forget that I exist...."

      --
      the more accurate the calculations became, the more the concepts tended to vanish into thin air. R. S. Mulliken
  41. 200% by racerxroot · · Score: 2, Funny

    I want to try and trick it and simultaneously make all the expressions that i can. I could be 17% happy, 40% confused, and 85% constipated.

    --
    --- Caffeine is directly responsible for some of my greatest ideas, and some of my most embarrassing moments...
  42. 3% by Ankou · · Score: 1

    Oh dont forget 3% SBD (silent but deadly). But maby thats just the smile I make when that happens to me. *must think unfunny thoughts ... must not laugh*

  43. Nice trick these researchers have discovered by Darius+Jedburgh · · Score: 5, Insightful
    1. Invent algorithm
    2. Apply it in a domain where your work can't be falsified
    3. ???
    4. Profit!
    1. Re:Nice trick these researchers have discovered by Surt · · Score: 1

      It's easy to falsify this work actually.

      1) train a bunch of humans to accurately identify facial emotions. (train to some target level of competence)
      2) have your human facial emotion identifiers look at a lot of faces, keep track of statistics
      3) improve your software until it agrees with #2 on a sufficiently large sample set
      4) verify the accuracy of your software by checking for agreement with #2 on a new set of previously untested images
      5) have great statistical confidence that your analysis of further images is accurate

      Falsification is simple and derives from #5: prove that the software is inaccurate on a statistically significant percentage of new images presented to it.

      --
      "Who is the Journal of Quantum Physics going to believe?" --Stephen Hawking
    2. Re:Nice trick these researchers have discovered by ziggamon2.0 · · Score: 1

      Well yeah, but that'd be stooping to the same level as those guys...

      Better just joke about it on Slashdot and feel good about yourself!

    3. Re:Nice trick these researchers have discovered by Darius+Jedburgh · · Score: 1

      So tell me, what value did this research add to just taking a sample of random opinions of what expression the picture portrayed?

    4. Re:Nice trick these researchers have discovered by Surt · · Score: 1

      Are you kidding? Having a computer that is able to judge facial expressions accurately? It adds value in all kinds of ways:

      1) In the specific context, it provides for an analysis unbiased by human emotion attached to a famous work.
      2) In a general context, a computer which can judge facial expressions may be able to interact more accurately or effectively with you without resorting to primitive mouse/keyboard work.
      3) In an alternative context, a computer able to analyze facial emotion may be able to improve anti-terrorism security measures.

      I could add dozens more i'm sure, but I hope the value is now obvious.

      --
      "Who is the Journal of Quantum Physics going to believe?" --Stephen Hawking
    5. Re:Nice trick these researchers have discovered by brunes69 · · Score: 1

      None of this is falsifiable. For one thing, you could never train a group of people to recognize a persons emotions from a photograph, because it is by nature entirely subjective. There is absolutely no way this would work.

      Even if it did, there would be no way to know that the emotions that the subjects *said* they were feeling when the photo was taken was actually the emotion they were feeling. Like, you can't base it off of saying "look happy!" then taking a photo - you have to take the photo when the person *is* happy, not when they are prentending to be happy. Constructing such a study across the whole range of emotions would be an act of futility.

    6. Re:Nice trick these researchers have discovered by Surt · · Score: 1

      Interestingly enough, my wife does this work. It works quite well, actually. The agreements get into the 80-90% range. And of course you store all the data: If you get 9 happies and 1 tired from your research population, your software might be considered accurate if it comes up with 90% happy, 10% tired (you can look at this in different ways, which way you prefer is just that, a preference).

      You also don't have to trust the emotions of the subjects in a couple of ways:

      1) You can sample a large enough population to weed out liars statistically.
      2) You can sample the subjects and MRI them to verify the consistency of what is going on in their brains.

      There are also well established ways to elicit common emotions: as one example, you can show people sad movies, and get them fairly easily to become sad and show a sad expression. Again, you can verify your reliability fairly well by MRI.

      As to studying the range of emotions, maybe you start with only the top 6:
      http://changingminds.org/explanations/emotions/bas ic%20emotions.htm

      Lots of people study emotions, and there is a lot of well established strong statistical work in the field.

      This books is one of the more respected in the field, and can link you to a lot of the studies that have been done already:
      http://print.google.com/print?id=dXMs_dloSEcC&oi=f nd&pg=PA3&sig=O6kOK6Z196gNc4MS0AmWq7ERPiE

      --
      "Who is the Journal of Quantum Physics going to believe?" --Stephen Hawking
    7. Re:Nice trick these researchers have discovered by Moofie · · Score: 1

      "Again, you can verify your reliability fairly well by MRI."

      Well, you can get reliable data on people who happen to be in MRI machines, but that's hardly the same as people sitting in a park or watching a movie.

      --
      Why yes, I AM a rocket scientist!
    8. Re:Nice trick these researchers have discovered by Surt · · Score: 1

      You use and open MRI, and you have them watch a movie while you MRI them. You find a widely agreed upon sad moment in the movie. You ask them: what were you feeling at this point in the movie. They say sad. You encode that facial expression as sadness.

      This study is essentially only vulnerable to demand threat (ie the subject thinks you expected them to be sad, so you say you were sad). You can do a fairly good job of eliminating the threat by having a large enough sample size, varying the input (which sad movie) and verifying that the MRI's are still consistent.

      It's not invulnerable, but statistics says it is very likely to be accurate. As an aside, this is essentially how all of the soft sciences do their work, so if you want to throw this specific area out, you're going to lose a lot of other well respected science at the same time.

      --
      "Who is the Journal of Quantum Physics going to believe?" --Stephen Hawking
    9. Re:Nice trick these researchers have discovered by Moofie · · Score: 1

      I just don't buy that you can get unforced, accurate, emotional responses out of people in a scientific study. Particularly since I'm not sure what an "accurate" emotional response would be like, anyway.

      Can emotion be quantified? Maybe. Not with hamfisted tools like these.

      --
      Why yes, I AM a rocket scientist!
    10. Re:Nice trick these researchers have discovered by Darius+Jedburgh · · Score: 1
      In the specific context, it provides for an analysis unbiased by human emotion attached to a famous work.
      And how exactly did the computer remove the bias when it was trained using the opinions of real, emoting humans?

      Your 2nd and 3rd points are quite valid, however I was talking about the specific application to the Mona Lisa.

    11. Re:Nice trick these researchers have discovered by Surt · · Score: 1

      Well, you may be unsure, but there's a ton of peer reviewed published literature on the subject. It certainly has as wide an acceptance as say, evolution, which is another slashdot favorite topic. :-)

      --
      "Who is the Journal of Quantum Physics going to believe?" --Stephen Hawking
    12. Re:Nice trick these researchers have discovered by Moofie · · Score: 1

      Fair enough. Social science has never been my forte. I prefer metal I can bend. : )

      --
      Why yes, I AM a rocket scientist!
    13. Re:Nice trick these researchers have discovered by Surt · · Score: 1

      They remove the bias specific to the mona lisa by training on images which have no such bias.

      IE consider the difference in bias of reporting you might get if asking 10 random people if the mona lisa is happy vs asking 10 random people if a random photograph of some person they've never seen before is happy.

      --
      "Who is the Journal of Quantum Physics going to believe?" --Stephen Hawking
    14. Re:Nice trick these researchers have discovered by Surt · · Score: 1

      I agree with you, and I certainly also prefer harder sciences where the reliance on statistical significance is lower, but I do think that this stuff is rigorous enough to have real value (particularly the most useful kind: predictive value).

      --
      "Who is the Journal of Quantum Physics going to believe?" --Stephen Hawking
  44. pseudoscience by phlegmofdiscontent · · Score: 1

    I read this write-up of the study in question:

    http://www.livescience.com/history/ap_051215_mona_ lisa.html

    This isn't science. Jim Wayman, a biometrics researcher, says "It's hocus pocus, not serious science, but it's good for a laugh, and it doesn't hurt anybody." He's right, though this is right up there with those studies that find an equation for the perfect ice cream cone, or whatever. The annoying thing is, people take this shit seriously.

    Furthermore, from the link, "it couldn't detect the hint of sexual suggestion or disdain many have read into Mona Lisa's eyes". It occurs to me that the Mona Lisa, like all art, is subject to the interpretation of the viewer as well as the intent of the artist. Maybe the enigma WAS da Vinci's intent. In which case, studies like this are just blowing smoke up our asses. We all put a little of ourselves into the art.

  45. Re:How this doesn't work ... by Anonymous Coward · · Score: 0

    I looked at a few images from your link, and it became immediately clear that the emotions represented by the pictures are simulated. In other words, they had someone saying "ok, now look happy|sad|angry|etc." Unfortunately for this research, that means the actual emotions do not line up with the data. Without personally reviewing the learning data, I'd have to conclude that there's no way the computer is within 50% accurate.

    Fortunately for us the human BSometer is really good at detecting fake smiles, even when they're mislabeled as smiles in a database. Any kid can tell you that Mona Lisa has one. There's also a strong touch of "worried" in that famous fake smile.

    I guess they get the "disgusted" from the awkward sideways glance. Newsflash: photographers and painters pose their subjects. Furthermore, painters are not even required to paint what's really there.

  46. Open the Pod Bay Doors HAL by Anonymous Coward · · Score: 0

    I'm sorry Dave, I can't do that. . .

    I sense hostility and emotional instability, I think you wish to do me harm. What's that? Do I see you face changing to a look of trying the side hatch and blowing the POD door?

    I don't think so.

  47. Great! by AlvySinger · · Score: 1

    When this software is widely available it'll bring joy to husbands everywhere: now we'll know what the wife is thinking.

    But perhaps "100% annoyed for no apparent reason" isn't going to be useful information...

  48. Longshot question by ZachPruckowski · · Score: 2, Interesting

    Is there a chance the facial images have changed over the 1000-1500 years or whatever? I mean, obviously they wouldn't change much, but maybe a little?

    More importantly, are we sure da Vinci had regular access to girl's faces? I mean, it was probably mostly guesswork on his part.

    1. Re:Longshot question by Anonymous Coward · · Score: 0

      Guess work? Are you completely retarded? Wait don't answer that.

    2. Re:Longshot question by Surt · · Score: 1

      Not much chance that facial expression has changed significantly over time. One of the things psychologists have studied fairly extensively is emotion in isolated cultures. Smile==happy no matter where you go. Given that such cultures have often been isolated on the 1000 year range, it seems unlikely that a uniform evolutionary change happened everywhere, and so it is probably fairly safe to conclude that the meaning of facial expressions isn't changing much over time.

      --
      "Who is the Journal of Quantum Physics going to believe?" --Stephen Hawking
  49. Algorithms? by Anonymous Coward · · Score: 0

    Or heuristics?

    I've seen babies smile like that. I think it's just gas.

  50. Pointless by MaWeiTao · · Score: 1

    My life feels complete now that a piece of software has told me what Mona Lisa's expression is. It was money and time well spent. A round of applause for these fine researchers.

    Maybe she had to use the toilet and was trying to hold it in. Maybe Leonardo simply got the expression wrong. Maybe it was a mix of emotions given that the painting actually took some time to complete. There are countless sensible explanations for why she looks the way she does, and they're all irrelevant because it's just a work of art.

    On the other hand, I'm sure it was Leonardo's dastardly plan was to confound people for centuries as to what Mona Lisa was feeling.

    1. Re:Pointless by Red+Flayer · · Score: 1

      "There are countless sensible explanations for why she looks the way she does, and they're all irrelevant because it's just a work of art."

      I think it's the exact opposite. They are all relevant because it's a work of art.

      The conjecture, the interpretation, that's all part of appreciating art.

      --
      "Trolls they were, but filled with the evil will of their master: a fell race..." -- J.R.R. Tolkien on Olog-hai
    2. Re:Pointless by MaWeiTao · · Score: 1

      "The conjecture, the interpretation, that's all part of appreciating art."

      Good point. You got me there.

      I think many people have the tendency to over-analyze art, but I suppose that all comes with the territory. I think it's the use of something mathmatical to analyze something emotional that bothers me, like an expression can be neatly quantified into a percentage of this and that, especially an emotion that has been depicted via a second person.

  51. rotcoD ehT by SirBruce · · Score: 0, Offtopic

    This is a fake!

    Bruce

  52. About the comments here... by SunPin · · Score: 1

    I'm 83% happy and 9% disgusted.

    --
    Laws are for people with no friends.
  53. A programming problem by Myrmidon · · Score: 5, Funny

    Okay, here are my questions for the Slashdot community:

    1) You're writing some code. You call the User Emotional Analysis API, and it reports back that your user is currently "83% happy and 9% disgusted". How should your software "adjust its response" in reaction to this information?

    2) What happy/disgusted ratio leads to maximum productivity?

    3) What are the odds that the Mona Lisa is a portrait of a Perl programmer?

  54. oh good by tont0r · · Score: 1

    "The New Scientist says that software capable of recognising emotions just by looking at photographs could lead to PCs that adjust their response depending on the user's mood. "

    hope you arent feeling horny at some random point of the day when people are around you.

  55. What this means she was thinking by Dachannien · · Score: 1, Redundant

    "Man, that Leonardo is such a stud... but does he really have to paint me while he's naked?"

  56. Oh captain my captain? by Red+Flayer · · Score: 1

    "...has been used to decipher art. way to take the fun out of living."

    You know, if you plot a line at the realism value of the painting on one axis, and the emotional value of the desired effect on the other axis, you can determine the true value of a portrait by calculating the area of the rectangle you've just outline (with the origin as the opposing corner).

    --
    "Trolls they were, but filled with the evil will of their master: a fell race..." -- J.R.R. Tolkien on Olog-hai
    1. Re:Oh captain my captain? by Anonymous Coward · · Score: 0

      Neat reference to the Dead Poet's Society. Although I have no problem with scientists using this type of technology on photos and paintings, it should be taken with a grain of salt in regard to paintings. No one knows how accurately DaVinci portrayed the woman's (If it was a woman) facial expressions, or what adjustments he made.

    2. Re:Oh captain my captain? by Red+Flayer · · Score: 1

      To me, accuracy doesn't matter. I could care less what the "real life" Mona Lisa was feeling.

      What I'm interested in is what the painted Mona Lisa is hypothetically thinking. It's an abstract exercise, there's no reason to try to tie it in to the 'real' Mona Lisa (if there was one).

      --
      "Trolls they were, but filled with the evil will of their master: a fell race..." -- J.R.R. Tolkien on Olog-hai
    3. Re:Oh captain my captain? by Anonymous Coward · · Score: 0

      I completely agree, and feel the same way myself. It shouldn't matter who the painting was of (Or as you said, it might have been of no one). I meant only that the people should only see the results as being applied to the painting, instead of whoever might have been posing for it. It seems as if a surprisng amount of the discussion here has been "Maybe she looks like that because while she was posing, DaVinci was paining nude..." etc. It is utterly insane to gather something such as that from the painting.

  57. Imagine by chord.wav · · Score: 1

    It would be great to have this software display in your glasses (or cellphone if you pefer to have it now) the emotion of the girl you are talking to in a bar in realtime. If your cell phone/PDA doesn't have enough power to do that, you could upload a picture to a web server and get the stats. OK, I'm a nerd, but so are you!

  58. Babe polygraph by GaryOlson · · Score: 1

    Can they customize this alogrithm to load into my cell phone and tell me if the hot chick at the other table finds me desirable?

    --
    Every mans' island needs an ocean; choose your ocean carefully.
  59. HAL by thebdj · · Score: 1

    PCs that adjust their response depending on the user's mood.

    Hal: Good Morning, Dave.

    Just what we all need a computer that can sense we are getting pissed off and attempt to kill us before we kill it, our advantage is over.

    --
    "Some days you just can't get rid of a bomb."
  60. Mood sensing PCs? by tlon · · Score: 1

    ..."The New Scientist says that software capable of recognising emotions just by looking at photographs could lead to PCs that adjust their response depending on the user's mood. "

    ... As soon as I manage to rid the galaxy of those pesky Jedi, I will be unstoppa - oh, hello computer. No, I'm really just a happy, pleasant senator from Naboo.

    In all seriousness - if you're in a foul mood, does the PC darken the screen and turn all the colors to dark and forboding colors? Pretty soon it will just shut itself off: Please don't engage with the keyboard device while in a foul mood. My circuits are sensitive....

  61. Actual results by skintigh2 · · Score: 1

    83% happy
    9% disgusted
    8% confused as to why anyone would take a COMPUTER'S word about EMOTIONS

  62. So what does that mean? by theotherbastard · · Score: 2, Insightful

    83% happy and 9% disgusted? And just what does that mean? All of life's greatest mysteries can be solved in a quantitative manner? I for one don't want my computer to act differently if I'm happy, sad, pissed off, stoned, whatever. Just what I've always wanted, a computer with a Genuine People Personality (TM).

    --
    Buttons aren't toys.
  63. So what by Mark+of+THE+CITY · · Score: 4, Interesting

    everything can be quantified

    As Einstein said, "Not everything that counts can be counted, and not everything that can be counted, counts."

    --
    The clearance system sounds logical. It is not. It is completely arbitrary. -- John Bolton
    1. Re:So what by Anonymous Coward · · Score: 0

      Einstein was a fucking awesome physicist but he sure said a lot of stupid crap...

  64. Sapien Logistics Dept. by ackthpt · · Score: 1
    an infinite number of monkeys is about as unlikey as an infinite number of monkeys rendering the same painting

    Ok. A finite number of monkeys then. Just enough to get the job done.

    I know, we tend to be lazy and throw around the infinite number of monkeys to duplicate just about anything when a finite number will do. Simply because we scientific sorts cannot be bothered to calculate the actual quantity of monkeys necessary. I do apologise.

    --

    A feeling of having made the same mistake before: Deja Foobar
    1. Re:Sapien Logistics Dept. by susano_otter · · Score: 1

      Simply because we scientific sorts cannot be bothered to calculate the actual quantity of monkeys necessary.

      Well, as far as the works of Shakespeare go, we have been able to confirm that we have more than enough monkeys to get the job done.

      --

      Any sufficiently well-organized community is indistinguishable from Government.

    2. Re:Sapien Logistics Dept. by jacksonj04 · · Score: 1

      You need to get them all out of government first.

      --
      How many people can read hex if only you and dead people can read hex?
    3. Re:Sapien Logistics Dept. by susano_otter · · Score: 1

      yuo si R teh dumb.

      --

      Any sufficiently well-organized community is indistinguishable from Government.

  65. TRUE? by gcantallopsr · · Score: 1

    What's all that crap about true emotions? You can write a software to guess emotions by looking at faces, you can apply these algorithms to the Mona Lisa if you want to try to guess her (?) emotions, and of course you can say that the outcomes are her (?) true emotions. But if you skip the last step, or at least say guessed instead of true you will look a bit more scientific :-P

    --
    Try Ubuntu GNU/Linux, it's great!!!
  66. Caveats of Eigenanalysis by eldavojohn · · Score: 1

    See, the beautiful thing about eigenanalysis is that if you have enough samples (faces), it extracts the most prominent features from that dataset. Perhaps furrowed brows and bared teeth are prominent features for looking hostile, the eigenface would show this if it is true for most of the dataface.

    Look closer at the eigenfaces, what you see are "ghostlike" shapes of all possible prominent features. The darker more defined features are the more prominent ones.

    Please don't dismiss this as BS, it's an old technology but our computational abilities at calculating determinents on sparse and large matrices is improving. Look into Cholesky speed ups if you don't believe me.

    This is a boring concept in linear algebra but a powerful tool in pattern recognition.

    --
    My work here is dung.
  67. And the ??? stands for: by ziggamon2.0 · · Score: 5, Funny

    (this is actually the first time I play this game, let me know how I'm doing!)

    3a. Patent algorithm.
    3b. Sue everybody that looks 83% happy or 9% disgusted

  68. A note about the Mona Lisa by skintigh2 · · Score: 3, Interesting

    This painting was not made in one sitting. Or two. Or ten.

    It was never even finished.

    The subject, ASSUMING THERE WAS ONE, sat for one or several sessions and then Leonardo continued to work on the painting off and on for the rest of his life.

    There is speculation as to who the subject was, but perhaps there was none, and some think it's actually a self portrait in drag (perhaps the cause of the mostly amused but 9% disgusted?)

    1. Re:A note about the Mona Lisa by bombadillo · · Score: 1

      You beat me to it... She was really thinking, "What would I look like as a man?"

    2. Re:A note about the Mona Lisa by Anonymous Coward · · Score: 0

      yup, and apparently she was only 9% disgusted when she thought that

  69. The da Vinci Commode by NZheretic · · Score: 2, Funny

    Could her smile be the result of one of da Vinci's inventions, ie the vibrating commode that the lady in question was sitting upon?

  70. Not "bored", man! by Dystopian+Rebel · · Score: 1

    Here's one of the young female faces used in the mathematical analysis:

    http://ellenfeiss.net/temp/movie.php?movie=movies/ ellen_feiss.mov

    --
    Rich And Stupid is not so bad as Working For Rich And Stupid.
    1. Re:Not "bored", man! by pmancini · · Score: 1

      Wow, I think she did that whole video while totally stoned out of her head. Thanks for sharing. I'll point that one out next time someone tries to convince me of the superiority of Macs... hehe!

  71. Man... by east+coast · · Score: 1

    determined that Mona Lisa was 83% happy and 9% disgusted

    Now I'm 100% bored...

    --
    Dedicated Cthulhu Cultist since 4523 BC.
  72. Oh, goody. by Minwee · · Score: 1
    Now all we need is a computer that can tell us what Ellen Feiss was on.

    Er, what she was thinking.

  73. as they would say on fark. by Hohlraum · · Score: 1

    still no cure for cancer.

  74. Next up: Minority Rapport by geekpuppySEA · · Score: 1
    Thank god we don't have a linguistics engine capable of reproducing stuff like that yet. Else we'd be most of the way to:

    "How did that scoop-neck camisole work out for you, Mr. Takemura?... Mr. Takemura?? I KNOW YOU CAN HEAR ME DAMMIT!"

    or the shrieking vegetables courtesy The Onion: "I HAVE 37% MORE VITAMIN D THAN THAT CUCUMBER! STOP LOOKING AT HER!"

    If there is any hope for human sanity in 20 years, all linguists must stop working on computers IMMEDIATELY.

    --
    Intelligent Design: because MATH is HARD.
  75. oh crap... by ziggamon2.0 · · Score: 3, Funny

    ... so now machines are both better than men in bed, and better at knowing how the women feel?

    Guys, we're becoming extinct here...

    1. Re:oh crap... by the.Ceph · · Score: 3, Funny

      I think if machines were better then men in bed we would have been extinct a long time ago. Luckily due to the massive conspiracy throughout academia to stop women from becoming engineers the risk of the prophecies coming true is minimal.

  76. Facial changes over time by Xepherys2 · · Score: 1

    But what about the time period it was painted versus modern facial expressions. Everything else changes, speech, speech patterns, gestures... why would facial expressions not be slightly different now than they were at the time of the painting?

  77. YES! by evil-osm · · Score: 5, Funny

    Hope this helps anyone who wants to learn more about the actual process used to accomplish this recognition.

    You can bet your purple pants it does!! I can finally put an end this this scenario:

    Wife: "no, there's nothing wrong, I'm not mad at you"
    muhahahaha.... thats when I take the polariod and get a snapshot
    Me: "Yeah right, we'll just see about that!"

    Two weeks later the divorce goes through and my ass is on the curb.

    --


    E.

    Never rub another man's rhubarb - The Joker
  78. I'm reminded of the MASH episode... by PhineusJWhoopee · · Score: 0

    ...where Winchester was sitting for Col. Potter. Winchester got impatient, and Potter ended up painting him with an exasperated expression.

    For the Mona Lisa, the model might have been thinking..."Wow, it's nice to be asked to model for Da Vinci....Hmm, this modeling is a lot less exciting than I thought, but still a good experience...Getting boring......Are we done yet?......He's intentionally making me wait....I am so out of here...."

    ed

  79. Finally... by se2schul · · Score: 1

    ...a scientific method to know what the hell women are thinking!!!

  80. 90% Lisa, 10% Mona by jbum · · Score: 4, Interesting

    On a related note, back in February, I searched Flickr for photos matching the tags Lisa or Mona.
    The results indicate that 9/10ths of the women in these photos are named Lisa. I built
    a photo mosaic from the results, which can be seen here:

    http://www.flickr.com/photos/krazydad/4921613/in/s et-95771/

  81. Thank god, I am not the only pervert here by SmallFurryCreature · · Score: 4, Funny
    I thought almost the same thing. Except knowing something about italy she probably said "miaaaoooo".

    She has that expression of a woman looking at a naked man and being faintly aroused but also faintly amused at that "last chicken in the poultry shop" display. If your in a long relationship were your girl still fancies you but feels secure enough she doesn't have to constantly worship as a god to keep your ego up you will learn to regonize that look. Oh well it is better then when they break down in laughter while you are trying to pose seductivly. I guess men just aren't designed to look good naked with their socks on.

    --

    MMO Quests are like orgasms:

    You may solo them, I prefer them in a group.

    1. Re:Thank god, I am not the only pervert here by bheer · · Score: 1

      If your in a long relationship were your girl still fancies you but feels secure enough she doesn't have to constantly worship as a god to keep your ego up you will learn to regonize that look

      I dare say most of the Slashdot audience have NO idea about what you are talking about. Having girlfriends is one thing, the ability to read minute facial expressions - why, the intersection of those sets must be vanishingly small!

    2. Re:Thank god, I am not the only pervert here by Anonymous Coward · · Score: 0

      Don't take it so hard.

      You've got him beat in one area at least: he can't spell!

  82. Algorithms Determin This Article's True Value by SeattleGameboy · · Score: 3, Funny

    My algorithms say this article is 98% BS and 2% Who Cares...

  83. Mona Lisa is actually a self-portrait by jjh37997 · · Score: 2, Interesting

    Of course, a number of people suspect that the true model for Mona Lisa was Da Vinci himself. I wonder if the researchers accounted for this?

  84. 83% happy and 9% disgusted by Orlando · · Score: 2, Funny

    And by a strange co-incidence most slashdot readers' interactions with women produce exactly opposite results.

    --
    -= This is a self-referential sig =-
    1. Re:83% happy and 9% disgusted by FurryFeet · · Score: 1

      And most of the "9% Happy" has to do with their computers now working...

  85. My new mood-adjusting PC... by ksc · · Score: 4, Funny

    Launching Firefox...
    You're bored...
    You're horny...
    You're horny...
    You're disgusted!
    You're horny...
    You need a cigarette...
    You're bored...

  86. It's not DiVinci... by Anonymous Coward · · Score: 0

    If you're going to refer to Leonardo DiVinci, then don't refer to where he's from, refer to him as Leonardo. I wouldn't call you Of Cleaveland or Of Perth, I certainly wouldn't expect you to do the same.

  87. Will the algorithm work on vertical lines/curves. by Browzer · · Score: 0
  88. Nurture by Syberghost · · Score: 1

    Facial expression of emotion is in part tied to upbringing. Unless they have really good computer-based images from the year 1503, this can't help but be less accurate than if it were used against a modern image.

  89. And . . . by pete-classic · · Score: 1

    . . . 8% bad at math!

    -Peter

  90. Women Data Set? by ZenHarbinger · · Score: 1

    The funny thing is that they used women faces as the exemplar set. Isn't it theorized that he was the model?

    --
    This space intentionally left blank.
  91. Just goes to show, computers are smarter then men by SmallFurryCreature · · Score: 2

    They should make this software available on a camera phone. Next time your girlfriend claims you don't understand here snap her picture and voila, you instantly will be a sensitive man. Anything to keep the dumb cunt happy eh? What?

    --

    MMO Quests are like orgasms:

    You may solo them, I prefer them in a group.

  92. It doesnt really matter... by CatsupBoy · · Score: 1

    Even with all this software, nerds still cant figure women out.

  93. Real-world application by j_cavera · · Score: 1

    I for one welcome this new technology. I look foward to being able
    to buy a handheld model that can tell me why my wife is mad at me.

    --
    #include "humorous_pop_culture_reference.h"
    1. Re:Real-world application by JasonBee · · Score: 1

      *sigh*

      If only...

  94. My Java face recognition program says she is.. by Anonymous Coward · · Score: 0

    86% happy, 9% null pointer exception, 5% out of memory error

  95. Disgusted? by JasonBee · · Score: 1

    Perhaps it was like this:

    83% Happy = "I can't believe I was chosen to pose for this!!"
    9% Disgusted = "When is he going to finally put some pants on??"

  96. Facial expressions are nature, not nurture by dasunt · · Score: 1
    Is there a chance the facial images have changed over the 1000-1500 years or whatever? I mean, obviously they wouldn't change much, but maybe a little?
    • Leonardo lived about five hundred years ago.
    • Unlikely (short answer).

    The long answer is that across the globe facial expressions are remarkably consistent. You could pictures of Americans with different facial expressions, find some isolated tribe deep within Africa or New Guinea (assuming any are still isolated) and that tribe would be able to tell you emotions are being expressed in your photo. If facial expressions were learned, we would expect isolated tribes to be more inaccurate at guessing the expressions of distant foreigners. They are not.

    In short, the facial expression attached to each emotion is nature, not nurture.

    1. Re:Facial expressions are nature, not nurture by natpoor · · Score: 2, Informative
      This is indeed true for some expressions. I just finished teaching a class in nonverbal communication, and for part of it we looked at facial expressions. Researchers have identified 6-8 facial expressions that are the same around the world (currently), and so these are believed to be nature/hardwired into our brains. Ekman and Freisen did a lot of work on this. Here is a Google search that has some material. However it is not always true, smiling in different cultures can mean slightly different things. As for across history, well, the ancient Greeks used those smile/frown masks for drama, so I would assume the hard wired ones have been around a long time (since evolution takes place very, very slowly).

      Maybe someone else pointed this out but the computer isn't really determining her mood, the people who judged all the other faces and constructed the algorithm did it, the computer just did the calculations. But Slashdotters knew that.

  97. Oooo! by Now.Imperfect · · Score: 1

    I wonder if this will lead to
    "man woman" becoming a viable commandline tool!

  98. could lead to... by know1 · · Score: 1

    "could lead to PCs that adjust their response depending on the user's mood. "

    user:WHY THE £$%ING HELL WON'T YOU JUST BLOODY WORK AND STOP FREEZING UP
    computer:I'm sorry, i can't do that dave

  99. Sure I got the code right here, just run it. by SmallFurryCreature · · Score: 1

    while(true) false;

    --

    MMO Quests are like orgasms:

    You may solo them, I prefer them in a group.

  100. Pfft! by Quiet_Desperation · · Score: 2, Funny
    I wrote a prorgam that did this on my old Atari 800 back in the computer Steam Age.

    I got:
    44% "Happy"
    12% "Baffled"
    21% "Knowing lesbian smirk"
    19% "Get your hand off my knee, Leo"
    55% "Planning to start new religion"
    8% "file not found"

    I also analyzed the brush strokes and built a picture of DaVinci:
    54% "Depressed"
    61% "Inventive"
    10% "Horny"
    30% "That's not my hand, Mona"
    71% "Must encode holy grail into here somehwere"
    11% "She'd make a good tank"

  101. pc's respond by mood? they already do! by Wilk4 · · Score: 1
    " The New Scientist says that software capable of recognising emotions just by looking at photographs could lead to PCs that adjust their response depending on the user's mood."

    heck mine already do respond that way... I want them to stop... the more pissed off I get at their problems, the more problems they offer me... ;-(

  102. Da Da Dada by spac · · Score: 1
    Let's not forget her smile hides her raunchy hermaphroditic identity... THat must account for the other 8%.

    At least according to Marcel Duchamps and LHOOQ.

  103. Research shows DC Comics' Character Two-Face... by klausboop · · Score: 1

    Research shows DC Comics' Character Two-Face to be 50% twistedly amused, 50% maniacally evil.

    --
    Some of you already have those cute little shirts on that say disco sucks, right? That's not all that sucks.-Frank Zappa
    1. Re:Research shows DC Comics' Character Two-Face... by RazzleDazzle · · Score: 1

      So what does that make the Joker from the Batman movie? 100% happy? What if he got kicked in the nuts, I doubt he'd be even 10% happy then.

      --
      ZERO ZERO ONE ZERO ONE ZERO ONE ONE! Just brushing up for my next big invention: Ethernet over Voice (EoV)
  104. Camera Obscura, etc by jd · · Score: 4, Interesting
    It was not unusual, at that time, for artists to use a range of techniques for capturing the key points of the person they were painting, to avoid having a person sit for ages whilst being painted. This means that although the painting would not be a "true" photograph, it could have been extremely close to one.


    On a related note, this might also explain the resemblance to Leonardo. Let us say that he did, indeed, have a woman sit for just long enough to sketch in the key facial lines. He would then have needed to add in the skin texture and other features that couldn't have been captured by whatever method he used. It would be logical for him to have used his own face to capture such information. The Mona Lisa would then have been a composite of the original model and himself, which means that it would indeed have a resemblance to him.


    X-Ray analysis of the original painting reveals sketches and paintings below the Mona Lisa - though there was no sign of anyone having written "This is a fake" in felt-tip pen, much to the chagrin of Doctor Who fans. It would be interesting to know how the different levels relate to each other - were the earlier pictures earlier versions of the same painting? If they are analyzed with the same software, does it produce the same result?

    --
    It's a small world and it smells funny; I'd buy another if it wasn't for the money; Take back what I paid (SoM)
    1. Re:Camera Obscura, etc by thesandtiger · · Score: 1

      Back then, it was quite frequent for canvasses to be reused. Some very interesting works have been found by looking under the surface work, but usually it's just crap.

      In the case of Leonardo, I would not be at all surprised if he was a fan of leaving such "easter eggs" in his paintings.

      --
      Since I can't tell them apart, I treat all ACs as the same person.
    2. Re:Camera Obscura, etc by ghislain_leblanc · · Score: 1

      That painting supposedly took three years to do. The girl was teenaged so she probably changed quite a bit between the time he began and the time he ended.

  105. looking happy is different than being happy by biraneto2 · · Score: 1

    I could even RTFA if today I wasn't 32% bored, 48% unhappy and 20% wishing to kill. Their trying to measure something that can't be. Trying to say Monalisa was happy by her smile is like saying a book is good by seeing it's cover. It would be much nicer if their answer was 42.

  106. Next... by Stan+Vassilev · · Score: 1

    breaking news: the smart expressions analyser software was applied to a number of object in the last few weeks to determine that: Japanese automobiles are happier than US automobiles.

    Tommorow: are trees happy or sad?

  107. Borg by Stan+Vassilev · · Score: 1

    If Da Vinci realised we'd need artifical algorithms programmed in machines to make out the face expressions in his paintings he'd give up painting.

    1. Re:Borg by Packet+Pusher · · Score: 1

      I doubt it. If he were alive today he'd more likely be helping to make the algorithms. He was more interested in how things worked then in painting.

    2. Re:Borg by Stan+Vassilev · · Score: 1

      So you're saying that if Da Vinci was a live today he'd be a hardcore hacker geek.

    3. Re:Borg by trollable · · Score: 1

      No he would be the CEO of Google ;)

  108. Monanal Lisa by Anonymous Coward · · Score: 0

    FTA: It concluded that the subject was 83% happy, 9% disgusted, 6% fearful and 2% angry, New Scientist magazine was told.

    83% happy about her first anal experience with Leo this morning
    9% disgusted
    6% fearful Leo will try again right now: the bottle of Sicilian olive oil is empty
    2% angry he did not ask for permission: she has pride! At least 2%.

  109. Insightful? Here we go again. by Petersko · · Score: 1

    Mona Lisa doesn't have emotions. She's made of paint.

    You know, this was probably a joke. But then along come some people whose IQ just barely exceeds their available mod points, and they call it "insightful".

    1. Re:Insightful? Here we go again. by Peter+La+Casse · · Score: 1

      Some people use "insightful" instead of "funny" to reward the poster's karma, as if it's important.

    2. Re:Insightful? Here we go again. by The+Meshback · · Score: 1

      You mean it's not!? All those wasted saturday nights trying to think of a witty comeback! Dammit!!

  110. oh great by kevin.fowler · · Score: 1

    does this mean Dan Brown has more material to write another masterpiece now?

    --
    Bury me in mashed potatoes.
  111. Poker bot by DanThuMan · · Score: 0

    This software could be integrated into a very cunning poker bot. Computers have mastered the calculation of probabilities and potential outcomes of these games, but being able to read the emotional state and facial expression of a human opponent would be an excellent tool to assist in player development and training. Move over deep blue!

  112. Mona Lisa's true emotions TODAY... by TheDarkener · · Score: 1

    100% dead! :-P

    --
    It is pitch black. You are likely to be eaten by a grue.
  113. SPOT ON by AJAP2 · · Score: 1

    83% happy, 9% disgusted, 6% fearful and 2% angry That is SPOT on how I feel after some good sex!

  114. Re:Just goes to show, computers are smarter then m by Anonymous Coward · · Score: 0

    vi is the best.

    vi isn't so great - vim is the best.

  115. Re:Just goes to show, computers are smarter then m by mattyrobinson69 · · Score: 1

    if somebody rewrites this in java, for my phone - i'l donate money to the project / buy the product

  116. End - user Applications by Spy+der+Mann · · Score: 1

    Think of a winamp plugin that plays calm music when you're angry, and upbeat music whenever you're excited, according to your preferences.

    I'd call this "emoti-music" :)

  117. No wonder I keep losing girls... by Anonymous Coward · · Score: 0

    "83% happy, 9% disgusted, 6% fearful and 2% angry"

    Happens when you confuse the 83% with the other 9%,6% and 2%.

    Though I do know quite a bit of the 2% that seemed like they could be part of the 83% at the same time.

  118. GPP by schleyfox · · Score: 1

    Seriously guys, having a computer that adjusts based on mood is a bad idea. Are we not geeks, have we not read Hitchhikers Guide to the Galaxy. Genuine People Personality is a really irritating thing. Oh well, this thing will go through and the best we can hope for is that they will teach it how to make tea.

  119. no crashes by mennucc1 · · Score: 1

    "software capable of recognising emotions just by looking at photographs could lead to PCs that adjust their response depending on the user's mood."
    Does this mean that if I get mad at it, Windows Vista will avoid crashing?

  120. version 1.2 by Anonymous Coward · · Score: 0

    10 REM start relationship
    10 print "Does this make me look fat?"
    20 if answer == "yes" goto 40
    30 if answer == "no" goto 10
    40 REM end relationship
    50 end

    1. Re:version 1.2 by Anonymous Coward · · Score: 0

      Wow. Two statements labelled 10. I thought the whole purpose of having numbers 10,20,... was so that if you wanted to insert statements in between, you had some space left; but if you're going to just have two statements with the same label (to which there is a goto, even!), you might as well do away with them.
      QBasic kicks your BASIC's ass ;)

  121. True Expression by TheoMurpse · · Score: 1

    I always thought what really was going through her head was "OMGWTFBBQLOL I HAVE NO EYEBROWS!!11!onethree!!"

  122. Bad Science is showing... by TemporalBeing · · Score: 1

    It's bad science because they are trying to put modern expressions of emotion on an older piece of art from an era that is not necessarily reflective of today. We can't observe what they are trying to observe from the era that it should be observed from. Thus, their conclusions will likely be wrong - at least enough to be outside of the acceptable error rate.

    The following post somewhat agrees, though the poster does not seem to agree to the same degree:

    http://tinyurl.com/bwadb

    Logically - if it is true even between modern cultures, it is also true between cultures of different era's. One may be able (as the above poster says) to show minimal differentiation between co-era cultures, it is likely even greater between non-co-era cultures; especially over as great a difference in time as between Da Vinci's era and our own.

    Stop it with the bad science.

    Science - it's only as good as what can be observed, and only as unbiased as the observer.

    --
    Truth is like the sun. You can shut it out for a time, but it ain't goin' away. - Elvis Presley (source: imdb.com)
  123. Aspergers Syndrome by fastgood · · Score: 1
    Invent algorithm ... profit!

    Helping all the socially clueless geeks for a nominal fee.

  124. The obvious use by steveness · · Score: 1
    So myspace bloggers can record their current mood!

    OMG! I soooooooo HATE my life!

    Current mood: 93% Bitter teen angst, 6% stupid

    1. Re:The obvious use by rbarreira · · Score: 1

      What about the other 1 percent?

      --

      The AACS key is NOT 0xF606EEFD628B1CA427BEA93A9CA9773F
  125. I knew it! by Morky · · Score: 1

    My theory about Leonardo "hanging the brains" while painting was correct!

  126. As a Programmer... by ZeroExistenZ · · Score: 1

    ...I can tell you that you know nothing about girls.

    --
    I think we can keep recursing like this until someone returns 1
  127. Dental problems? by lawpoop · · Score: 1

    I remember reading a theory some years back that claimed that Mona Lisa might be missing teeth. Does this emotion analysis take into account different teeth structures she may have had? Remember, they didn't have braces and orthodontics back then.

    --
    Computers are useless. They can only give you answers.
    -- Pablo Picasso
    1. Re:Dental problems? by anOminousCow · · Score: 1

      And remember, this is a painting, not a photograph. Leonardo could have painted in any kind of teeth that he desired. He could have painted nice straight pearly whites just as easily as the smile that is there.

      --
      Spokesbossy for ominous cow herds everywhere.
    2. Re:Dental problems? by lawpoop · · Score: 1

      ... well, maybe. I guess the question is would Leonardo have corrected it?

      If you look at Leonardo's sketches, he does anatomical drawings from the bones up -- including muscles, organs, tendons, ligaments, up to the skin. My guess is he was probably capable of drawing someone's skull and skeleton by looking at them nude.

      If he chose Mona Lisa as a model, he probably wanted her smile as is, and he wouldn't correct it.

      If she really had a 'abnormality', it doesn't make her bad or ugly, it just makes her look interesting. Maybe she was known for her intriguing smile, or maybe Leonardo noticed it and wanted to capture it.

      Nowadays, artists are unleashed and they do whatever crazy thing comes into their head. Back then, artists viewed themselves as philosopher/scientists, and they tried to make accurate portrayals of the universe (where to them, accurate is beautiful, because to them, the universe, by definition, is beautiful). Anyways, they tried to make their paintings as realistic as possible. It was only after photography was invented that artists were replaced by machines, and they began to paint crazy things. Before that, artists really were trying to be photographers.

      Of course, that doesn't mean that artists didn't 'photoshop' their images back then, but I don't think that Lenoardo was into that. I don't know, maybe he did. But Mona Lisa's smile is so intriguing, I have to think that Lenoardo was capturing something in nature that he encoutered, rather than making it up.

      --
      Computers are useless. They can only give you answers.
      -- Pablo Picasso
    3. Re:Dental problems? by Maitri · · Score: 1

      I think the point might have been something more to the effect that her teeth may have affected how she smiled thus affecting her facial features and etc. Modern smiles would also be affected by teeth but modern dentistry means that modern teeth are probably different. So - if teeth affect smiles then does the difference in teeth in the US today from teeth in Italy before modern dentristy mean that the computer may have not been as accurate?

    4. Re:Dental problems? by lawpoop · · Score: 1

      Well, what I'm wondering is if the program made some assumptions about dental and facial bone structure when analyzing Mona Lisa's smile. I think those are probably safe to make about the forehead, eye sockets, and cheeks, but you can't assume that she had all of her teeth, they were all straight, etc. It's an open question under those lips.

      IIRC, the theory was that she was missing her canines. That would affect her smile, and all of her expressions, because they are at the very 'corner' of the mouth's rounded edges. If she's missing both, her smile would still be symmetrical, but it would be odd in a way you probably couldn't place your finger on. It might come of as an ambiguous expression or emotion, which sounds a lot like "83% happy and 9% disgusted".

      --
      Computers are useless. They can only give you answers.
      -- Pablo Picasso
  128. Funny by The+Wooden+Badger · · Score: 1

    My first thought when I saw the breakdown in the summary is that she just heard a dirty joke. The angry kind of goes with that, but I don't know about the fearful part.

    --
    Heroscape, it's like legos combined with anachronistic wargames.
  129. 8% Fabulous by DingoBueno · · Score: 1
    The program, developed with researchers at the University of Illinois, US, draws on a database of young female faces to derive an average 'neutral' expression.
    I'd be curious to see what the result would be when compared to male expressions. Some say she is Leonardo in drag, while others go so far as to suggest she is a boy.

    Either way, Leonardo was a crazy character. Love to see that notebook that Bill Gates aquired...
    --
    ascii art
  130. Mona Lisa a Woman? by lildogie · · Score: 2, Funny

    90% happy, 10% disgusted sounds like a drag queen to me.

  131. Drag by C_Kode · · Score: 1

    The algorithm is based on a library of neutral face images of young women and determined that Mona Lisa was 83% happy and 9% disgusted.

    Some say it's DiVinci in drag. So, the neutral face young women doesn't help. It should have been a neutral face images of guys in drag. (i.e all the male OSX users!)

    hah I'm kidding damnit! :P or am I!

  132. is this better? by Anonymous Coward · · Score: 0

    10 if post == "nitpick code in joke" goto 40
    20 chance_of_getting_a_date = "possibly"
    30 goto 10
    40 chance_of_getting_a_date = "none"
    50 end

  133. What nobody seems to notice by this+great+guy · · Score: 1

    I have never really studied the Mona Lisa painting before and I have never understood why her smile is seen as being so enigmatic. But I have general trouble identifying facial expressions (one of the characteristics of Asperger syndrome) so this may explain why I don't get it. So I just spent the last hour reading some studies about the painting on the web, reading the Wikipedia article, and of course looking at it in great details, in order to find other clues.

    And nobody seems to notice something about her eyes: she is not really looking at the viewer, but she is looking just at the viewer's right hand side. That means she is not giving her smile to the viewer, but she is smiling at something else. So my theory is that people generally think she is looking at them, while their unconscious mind clearly notice she is not, the direct result of this difference of perception between the conscious and uncounscious mind is what create this enigmatic feeling: unconsiously you wonder what object/people, on your right hand side, makes her smile.

  134. they should have done it for "male" by Anonymous Coward · · Score: 0

    Supposedly this could be a self-portrait of the artist as a female, which would explain why he never shared it with anyone. I wonder what the results would be if they ran it for "male"

  135. Study finds that Mona Lisa was a painting by DasBub · · Score: 1

    The International Centre for Jesus Christ How Did You Get Funding published a report this week concluding that the Mona Lisa was most likely a painting.

    "It was a long hard battle," said Chief Researcher Mike Reynolds. "We spent 7 years training an expert system to tell the difference between oil painted on canvas and a Polaroid."

    In total, the study required 4.6 million US dollars and the blood, sweat, and tears of an eight man research team.

    "You wouldn't believe the troubles we had with this project. It took eight months to convince [the system] that Courtney Love wasn't a first-year art student's attempt at Picasso."

    In the end, say detractors, the system achieved a success rate little better than chance.

    "All I can say is 'Thank God for the DoD'," responded Reynolds. "They wanted a system that could tell whether someone was, in fact, grinning and/or dropping their linen. We're not there yet, but we'll take a few more million bucks and have another stab at it next year, eh?"

  136. Computer was trained with "relevant" data by beemishboy · · Score: 1

    Hmmm... I would think that expression of mood is not just related to age and gender, but to ... culture and yes, time period.
    Luckily, however, the researchers unearthed several thousand photographs of young Italian women from the early 1500s with notes attached describing their mood.

  137. I know how by Glamdrlng · · Score: 1
    Mona Lisa was 83% happy and 9% disgusted.
    Someone showed her a renaissance painting of goatse.
    --

    Yes, my only tool is a hammer. And you're starting to look like a nail.
  138. Re:Just goes to show, computers are smarter then m by rifter · · Score: 1

    vi is the best.

    vi isn't so great - vim is the best.

    Vim is a godless bastardization of the One True Editor. Even worse it pretends to be vi, but it is not vi. Most people that like it only like it because of some of the defaults they see when they use vim on linux, which actually only take advantage of features which are available in the real vi. Meanwhile vim flagrantly acts differently to the original vi in subtle insidious ways that you will only find when it is too late.

  139. Amsterdam, The NETHERLANDS. Thank you. by Anonymous Coward · · Score: 0

    Dear Slashdot editors, Please make a habit of referring to the country rather than the country when referring to something like this.

    For instance when you refer to a city in Australia, you mention it's in Australia and not the Australian state it is in.

    So, repeat after me: "Holland is a state. The Netherlands is a country"

    Thank you.

  140. On Art And Interpretation by enigma.obscura · · Score: 1

    As interesting as it is to use science to try to interpret images, interpeting art is something far different. Whenever someone mentions this topic, I am reminded of a quote by Marcel Duchamp: "The creative act is not formed by the artist alone; the spectator brings the work in contact with the external world by deciphering and interpreting its inner qualifications and thus adds his contribution to the creative act."

    What he's talking about here is the "real" meaning of a work of art; and that this can never be known, as it resides somewhere between the artist's intention and the individual's observation. To Duchamp, even the artist himself could not say "This is what it means."

    While there's certanly a place for computers and science in other aspects of art, to try to use them for interpretation is simply a misunderstanding of what art is really about.

    --
    "It's only after we've lost anything that we're free to do anything."
  141. Now we can finally answer the Age-Old Question by serutan · · Score: 1

    What was she thinking?

    "This job is WAY easier than working at the laundry (83%), although Leonardo could use a breath mint (9%). Wish he would stop staring at my boobs like that (6%), the lecherous old bastard (2%)."

  142. I was able to sit alone with the Mona Lisa (sorta) by notthepainter · · Score: 1
    Let me talk some about an experience that I had with the Mona Lisa some years ago. The Boston Museum of Science had a DaVinci exhibit. One of the paintings shown was the reproduction of the Mono Lisa that hung in the Louvre in the early 1900s (1912?) when the Mona Lisa was stolen. The reproduction was considered good enough to hang in her spot.

    At the time I was a volunteer at the museum (the Museum of Science, not the Louvre!) and every day I worked there I would get there about a half hour early and just sit with her. I was alone in the room with her and I just shared the space with her. Computationally this makes no sense but I know experientially that this time was profoundly important to me. I wasn't creating art, but I was responding to great art. DaVinci captured something in that painting. I certainly don't know what it was.

    I almost feel sorry for the tourists that are crammed together and see her only briefly (presumably) behind bullet proof glass.

  143. obligatory misogynist comment by smellsofbikes · · Score: 1

    when are they going to release the sourcecode so I can tell what my girlfriend is thinking?

    --
    Nostalgia's not what it used to be.
  144. The science is controversial by maiden_taiwan · · Score: 1
    In the scientific community, emotions are still pretty mysterious things. The claim that "facial expressions communicate emotion reliably" is controversial, believe it or not. This might sound silly, because we can ALL gauge other people's emotions by looking at their faces, right? But if you think about it... how do we know we're right? We see a frowning face, we automatically "know" they're sad or angry, but scientifically speaking, there's no objective validation that we're accurate.

    There are some famous researchers in psychology (most notably, Paul Ekman) who claim facial expressions communicate emotion unambiguously, but new research suggests serious problems with that work and offers other explanations. Plus, facial expressions vary across cultures and possibly even across individuals.

    Heavy psychology research paper on the contoversy. (MS Word format.) Bottom line: there are no consistent biological markers to distinguish one emotion from another in the body.

    1. Re:The science is controversial by rbarreira · · Score: 1

      I also agree that emotion is too complex to be reduced to a facial expression. Especially since I know that heavy self control can inhibit other people from ever recognizing what you're thinking or feeling ALL DAY LONG... Which really shouldn't come as a surprise. So why is this a controversial subject?

      --

      The AACS key is NOT 0xF606EEFD628B1CA427BEA93A9CA9773F
  145. So she was. . . by The+Spanish+Ninja · · Score: 1

    happy she got the job as a model, and only a little disgusted with herself for going down on him to get it?

    --
    "I like you, but I wouldn't want to see you working with subatomic particles."
  146. Something private or taboo by Tekoneiric · · Score: 1

    To me she looks like she is somewhat amused at something private or even taboo. If it were sexual in nature then that would explain the small part of disgusted and fearful, maybe even the hint of anger. Artists will sometimes do what it takes to get the reaction out of their subject that they desire. This is as much a part of the art as the act of painting.

    --
    *It's not what you can do for the Dark Side but what the Dark Side can do for you!*
  147. For download? by GerritHoll · · Score: 1
    Where can I download a copy of this software?

    Or, if it's propietry, where can I buy it?

    I want it! They should integrate it in phones. I can make a picture and then I at know: what is this person's emotion?

  148. New Scientist by Anonymous Coward · · Score: 0

    FYI: this story was first reported in New Scientist here http://www.newscientist.com/channel/info-tech/mg18 825305.200

  149. Scanners and people don't "see" the same way by Maitri · · Score: 1

    I read an article a while ago and just relocated it: http://news.bbc.co.uk/2/hi/entertainment/2775817.s tm

    It states that:
    "The eye uses two types of vision, foveal and peripheral.
    Foveal, or direct vision, is excellent at picking up detail but is less suited to picking up shadows.
    'The elusive quality of the Mona Lisa's smile can be explained by the fact that her smile is almost entirely in low spatial frequencies, and so is seen best by your peripheral vision,' Prof Livingstone said.
    The more a person stares fixedly ahead, the less useful is their peripheral vision."

    Thus Livingston stated that her smile disappears when it is looked at because of the way the human eye processes visual information.

    I am curious how emotion recognition software accounts for this, and if it doesn't - how does this affect the accuracy of its recognition?

    It is interesting how more and more science is being used to explain why certain art is good (golden ratio, foveal vs. peripheral visions, mathematic sequences in music, etc.). It makes me wonder if eventually we will be able to come up with "formulas" to create stunning art? And if so, will we appreciate art as much?

  150. Wronge Gender there... by sroske · · Score: 1

    She's a dude. Really.

    --
    Professional Stranger
  151. "corpora" by Anonymous Coward · · Score: 0

    The plural of corpus is corpora, not corpuses.

  152. hmm?... by h4ckintosh · · Score: 0

    If they are able to use this algorithm to make computers that can determine their user's expression, wait till that computer sees my "Oh!" face...

    --
    Oh well, what the hell
  153. HAL by Anonymous Coward · · Score: 0

    I can see you're upset about this, Dave....

  154. I HAVE NO IDEA WHAT IM TALKING ABOUT by JVert · · Score: 2, Funny

    his inability to finish projects he started

    Like that helicopter, for instance.

  155. So what? by kabrakan · · Score: 1

    How quick is this software? I mean, theres not much use figuring out someones emotions after the fact, at least no computational use. What I want is live emotion recognition so that software can adapt to your affective state on-the-fly. I know this has been done (e.g. MIT's Rea), but are these guys doing it better?

    --
    Slartibartfast:"Is that your robot?"
    Marvin:"No, I'm mine."
  156. And also... by Anonymous Coward · · Score: 0

    100% Leonardo Da vinci in drag. Oh wait....

  157. Talk about perverted. by PJ+Brunet · · Score: 1

    Use a protractor on your own damn face.

  158. Cognitive science disagrees. -nt by Anonymous Coward · · Score: 0

    no text

  159. Re:I was able to sit alone with the Mona Lisa (sor by Anonymous Coward · · Score: 0

    Buy Callgirl [jeannetteangell.com], a new book by my wife.

    Neat, not only does your wife falsify her credentials ("Ivy League" my ass), and plagarize as well... but she's also a whore. Glad you're OK with all that. Hope it goes well for you.

  160. Re:I was able to sit alone with the Mona Lisa (sor by notthepainter · · Score: 1

    You certainly have a chip on your shoulder, don't you? Call Yale, ask. You might be surprised. I'm certainly ok with it, you seem to have a problem with it. Oh well...

  161. Mona Lisa was really Elvis Costello by Phronesis · · Score: 1
    some think it's actually a self portrait in drag (perhaps the cause of the mostly amused but 9% disgusted?)

    Well I used to be disgusted
    And now I try to be amused
    But since their wings have gotten rusted
    You know, the angels want to wear my red shoes.