Slashdot Mirror


Can Machine Learning Guess True Emotions From Facial Microexpressions? (cmu.edu)

jbmartin6 writes: Microexpressions are fast, involuntary facial expressions which other people may not consciously recognize, but arise from our real emotions instead of the face we wish to present to the world. Carnegie Mellon University released an interesting blog entry about new approaches to using computers to recognize these microexpressions with a focus on the security and military applications. If you haven't taped over the cameras on your devices, it might be time to start thinking about it. Just imagine how advertisers would (mis)use this sort of technology.
"Our approach uses machine learning features that treat the whole face as a canvas," writes the lead researcher, adding "One challenge we faced for this project was finding a dataset with accurately labeled data to establish ground truth.

"Few existing databases capture subjects' suppressed reactions...."

55 comments

  1. Lie Detectors by RazorSharp · · Score: 1

    Sounds like lie detectors, with a huge potential for false positives.

    --
    "From the depths of my skeptical and rationalist soul, I ask the Lord to protect me from California touchie-feeliedom."
    1. Re: Lie Detectors by LifesABeach · · Score: 1

      I would be very interested if A.I. Would answer the god dawn question. I get enough liars just watching commercials on TV

    2. Re:Lie Detectors by Anonymous Coward · · Score: 0

      I love what a whiny faggot you have to make yourself on every single technology-related issue. "Oh, how will white hetero men be affected, we're the true victims waaaaaah!" God damn grow a pair, you're pathetic.

    3. Re: Lie Detectors by Anonymous Coward · · Score: 0

      Hi!Cool! I use voiptimecloud.com

    4. Re:Lie Detectors by Anonymous Coward · · Score: 0

      Do you need us to call the waaaahmbulance, snowflake?

    5. Re:Lie Detectors by Anonymous Coward · · Score: 0

      Hahhaha, indeed. But since SJWs are aggressive all the time (one could even argue that SJWs are people that never mastered their aggressions) , this could tragically backfire.

      Non-aggression, the cry of bullies everywhere. Don't hurt me! Whah!

    6. Re:Lie Detectors by Anonymous Coward · · Score: 0

      Persecution complex detected

    7. Re: Lie Detectors by Anonymous Coward · · Score: 0

      Nothing worse than a pussy who has to whine about social justice warriors. Oh no, they are going to get me!

      SJWs are the boogeyman.

    8. Re: Lie Detectors by DCFusor · · Score: 0

      SJWs are assholes and in your face about it. I'd guess a policy of helping Darwin along and murdering them would be worse than whining about them? After all, if just using a wrong pronoun hurts them, it ought to be really easy to just kill them off, right?

      --
      Why guess when you can know? Measure!
    9. Re:Lie Detectors by nospam007 · · Score: 1

      "Sounds like lie detectors, with a huge potential for false positives."

      Easily beaten with a few Botox injections.

    10. Re:Lie Detectors by citizenr · · Score: 1

      or by being a psychopath

      --
      Who logs in to gdm? Not I, said the duck.
    11. Re:Lie Detectors by Anonymous Coward · · Score: 0

      Well of course machine learning can guess your emotions, anyone can do that much.

      The real trick is whether it gets them right and how anyone can prove it.

      Even "lie detectors" aren't. I mean, what is a lie exactly? Merely something that's false? But how can it detect that if you don't know that it's false and honestly believe something true that isn't? You can even reverse that again, for the same lie you believe is true, you "lie" and tell them the truth you don't believe. So you believe you're lying, but the statement itself is true!

    12. Re:Lie Detectors by AHuxley · · Score: 1

      The SJW will use their social media GUI to see every message as its been typed and then corrected. Before been visible on their site.
      Type out a thought crime and expect to have the account banned by SJW.
      Add in a camera to capture the "emotions" of a person wanting to create the social media message.
      Now the SJW social media worker can study a users face and see their emotions as they type, be politically correct and finally use the site to virtue signal .
      The actual emotions and profile of the account user have to match the social media comments and presented profile information, photo.
      1984 telescreens https://en.wikipedia.org/wiki/... with a social media SJW worker to account ratio.

      --
      Domestic spying is now "Benign Information Gathering"
    13. Re: Lie Detectors by Anonymous Coward · · Score: 1

      ...if just using a wrong pronoun hurts them...

      And what was it that hurt you snowflake? You're whining a lot more than these SJWs you're afraid of.

  2. Autism by Anonymous Coward · · Score: 0

    How will this handle those autistics who have entirely different body language from the rest of humanity?

    1. Re:Autism by Anonymous Coward · · Score: 0

      It won't, and it will still be good enough for general use. If there are enough autistics to warrant further development, an extension can be made for them at any time.

    2. Re:Autism by Cederic · · Score: 2

      Well, it'll benefit them more than most people, in that many of them struggle to understand facial expressions at any level.

      Sure, it might lead to others misunderstanding them, but fuck it, that already happens.

  3. Quit slashdot by Anonymous Coward · · Score: 0

    WTF?! Heard this was a cool website. There are 20+ trackers on it?! F this, Ima out of here.

  4. No, it cannot by gweihir · · Score: 1

    And the problem starts with establishing ground-truth: Those that are into deception will not give you a sample or will taint the data-set intentionally. From the press, I gather that the average human adult lies once every 10 minutes. Sounds too high to me, but still, almost everybody lies regularly and hence almost everybody has reason to taint the basis for ground-truth.

    But the fascist fuckers that want people to be completely unable to have secrets will keep trying...

    --
    Most ACs are not even worth the keystrokes to insult them. Be generically insulted by this and ignored otherwise.
    1. Re:No, it cannot by Actually,+I+do+RTFA · · Score: 3, Funny

      the average human adult lies once every 10 minutes. Sounds too high to me

      Sounds high to me too. Now, how I am going to kill 9 minutes and 59 seconds.

      --
      Your ad here. Ask me how!
    2. Re:No, it cannot by gweihir · · Score: 1

      Nice!

      --
      Most ACs are not even worth the keystrokes to insult them. Be generically insulted by this and ignored otherwise.
    3. Re:No, it cannot by Nutria · · Score: 0

      From the press, I gather

      The same press that regularly hires "reporters" who commit plagiarism, make up stories from whole cloth to fit their political biases, use "confidential sources" which have their own obvious agendas, and accuse people of rape without a hint of evidence because, you know, All Men Rape?

      That press?

      --
      "I don't know, therefore Aliens" Wafflebox1
    4. Re: No, it cannot by c6gunner · · Score: 1

      From the press, I gather that the average human adult lies once every 10 minutes.

      "The press" reached this conclusion by observing behaviour around their own offices. Unfortunately their approach was deeply flawed since they assumed that press-scum was representative of "the average human".

    5. Re:No, it cannot by Anonymous Coward · · Score: 0

      No one was talking about Breitbart and Gateway Pundit.

    6. Re: No, it cannot by Anonymous Coward · · Score: 0

      Hey Steve Bannon. When did you have enough time in your busy schedule of sucking your own cock to post this?

  5. Perhaps a bit, but... by RyanFenton · · Score: 4, Interesting

    Here's the thing about emotions. They don't mean what you'd expect. Emotions ARE logic to an extent - short-circuited logic, quicker and made with incomplete information. They're the quick-and-dirty half-logic that makes us able to function in a world of unknowns for millions of years as a species.

    They aren't 'serious business' - they're formed and dismissed in fractions of a second, and most of them don't trigger facial emotions - and even then a raised eyebrow muscle can mean confusion, pronounced indifference, mild surprise, or just positioning to move your eyeball, or many other things.

    Like most things, this ain't mindreading - it's just more polygraph logic being applied, ironically like emotion itself is applied - for the basis of 'asperational truth', or bullshit they hope might pan out.

    Ryan Fenton

    1. Re:Perhaps a bit, but... by Anonymous Coward · · Score: 0

      Ever since I first read Hamlet, I was convinced that Claudius' emotional outburst to run out of the room was more out of a fear of being mislabeled a killer than the fact that he was guilty. Hamlet sees a ghost of his late dad and contrives a play to show who the real killer is? I'd say emotion can be both the split second reaction and the enduring drive for years. That's the biggest problem with lie detectors or any attempt to read people: people have their own view of the world, so you're not going to get absolute truth and attempts to infer such are at best guesses.

      So, any sort of AI will need that. Maybe even it should even react on those read emotions as fact as times. But, like you say, logic should win out much more.

    2. Re:Perhaps a bit, but... by Greyfox · · Score: 1

      Yeah. Often when playing poker, you can tell that your opponent is getting a huge adrenaline rush. But is he getting a huge adrenaline rush because he's bluffing and hopes you'll fold, or because he's sitting on a huge hand and hopes you'll call?

      --

      I'm trying to teach myself to set people on fire with my mind... Is it hot in here?

    3. Re:Perhaps a bit, but... by Anonymous Coward · · Score: 0

      Until someday being unhappy becomes illegal. Make sure to smile (Doctor Who reference):

      https://www.youtube.com/watch?v=xQE2EmZm8f0

    4. Re:Perhaps a bit, but... by Anonymous Coward · · Score: 0

      Hey ... cgjung ...

        emotions and logic === rational, able to judge
      emotions - judge internally/subjectively based on factors including irrationality
      logic - judges externally/objectively based on factors excluding irrationality.

      ok.. now that you grok what he's saying, remove the last bit.
      there' irrationality in anything material externally. the rational-objective-external artifact (speech/books) and the irrational-subjective-external-artifact (form of speech, type of material and so on) .. inside, the will/conceptions/hopes/dreams ... too mangle the terms

      in any case.. glad to see your explanation. it has subjective depths ; ) that makes you a substantive volumetric being ... heh. logic alone has no depth, none of the parallel perception that sensation and emotion offer. its also not inventive.

      and hey, yeah, they are serious in that the micro stuff is how character layers are formed and chosen. you kinda see nature and nurture and play in them all the time. and just being in a reactive place will use a lot of energy/attention. fwiw/fyi/ have fun

  6. Mirror shades by Anonymous Coward · · Score: 0

    The fashionable, practical successor to tin foil hats for today's world, as ppl in one field have already figured out.

  7. How do you feed the engine ? by dargaud · · Score: 1

    Well, even assuming that micro-expressions can indeed reflect some mental state, how would you teach an AI that ? It's not like you can have 10000 pictures of people with a valid set of associated micro-expressions... simply because nobody can accurately recognize micro-expressions except in some edge cases. They are very dynamic too, so a picture won't cut it (a video might).

    And about the taping of video cameras on PCs, why aren't the LEDs hardwired to the camera: if the camera is ON, the LED is too, not relying on some software to turn it on. Seems like a no-brainer.

    --
    Non-Linux Penguins ?
    1. Re:How do you feed the engine ? by AHuxley · · Score: 1

      Why are so many social media sites asking for a baseline profile pic for "reasons" as a baseline.
      The AI knows what a normal user looks like. The AI can be educated by SJW about what past comments got banned and accounts removed.
      Connect up the past images of the banned person as they created the text of the wrong type of comment and thats the SJW AI learning.
      Use that created data set to detect other real time users trying to type messages that SJW want banned.

      The detection of a problematic users face as a not positive movie review is been typed.
      The AI can then look at the words used in the review and look at the face of the user as the review is been created.
      Add the face changes and the type words used and that review will be blocked from been published and the account blocked, reported and reviewed
      No need to just consider the words. The face can show what the user is really thinking.

      --
      Domestic spying is now "Benign Information Gathering"
  8. False positives are the point by rsilvergun · · Score: 1

    you get a false positive out of it and that lets you get the warrant & probable cause to go on the fishing expedition you wanted to.

    --
    Hi! I make Firefox Plug-ins. Check 'em out @ https://addons.mozilla.org/en-US/firefox/addon/youtube-mp3-podcaster/
  9. No ,,, by CaptainDork · · Score: 3, Funny

    ... in some cases, it will return an answer of, "pissed off gorilla."

    --
    It little behooves the best of us to comment on the rest of us.
    1. Re:No ,,, by Anonymous Coward · · Score: 0

      ... in some cases, it will return an answer of, "pissed off gorilla."

      Will this AI be called Ozymadias?

  10. Not yet by tgrigsby · · Score: 2

    Judging from what I saw at NRF in New York City earlier this week the answer is a definite no. Not only did the systems I saw fail to guess my facial emotion but they also decided that I was female. I'm a 53 your old man with short hair and a goatee. It kind of makes you wonder what kind of faces they used to program in what a female face would look like...

    I don't think that we are far off but that conference tends to have some pretty decent cutting-edge systems to show off and we are clearly not there yet.

    --
    *** *** You're just jealous 'cause the voices talk to me... ***
    1. Re:Not yet by goose-incarnated · · Score: 3, Interesting

      Judging from what I saw at NRF in New York City earlier this week the answer is a definite no. Not only did the systems I saw fail to guess my facial emotion but they also decided that I was female. I'm a 53 your old man with short hair and a goatee. It kind of makes you wonder what kind of faces they used to program in what a female face would look like...

      I don't think that we are far off but that conference tends to have some pretty decent cutting-edge systems to show off and we are clearly not there yet.

      I started getting into ANN and ML recently, just as a hobby. My finding thus far is that the AI we are hearing so much about is nothing more than a sophisticated fuzzy pattern matcher. That's literally all it does: it "learns" by mapping patterns to a limited range of predetermined outputs. The path taken to determine what input should be mapped to what output is reinforced by feeding the machine millions of inputs (and providing the correct output to adjust the weights taken by the path).

      It's sophisticated, computationally expensive, and hilariously nowhere near "intelligence". After seeing how these machines (the ANN) functions I'm pretty certain that we're nowhere close enough to intelligent machines. Sure, we can train a particular NN to beat humans at Go, but the first time we put it in front of another game (recognising pictures) it will lose. Give it enough time and error-correction and it will eventually win that too, but the problem is that there are so many "general" tasks that humans and other animals accomplish with much less training that the machine can never hope to keep up.

      --
      I'm a minority race. Save your vitriol for white people.
    2. Re:Not yet by q4Fry · · Score: 1

      ...also decided that I was female. I'm a 53 year old man with short hair and a goatee. It kind of makes you wonder what kind of faces they used to program in what a female face would look like...

      Ah, but what species did it suggest you are?

  11. Micro-butthurt-expressions by Anonymous Coward · · Score: 0

    I'm detecting some micro-expressions in your's and nutria's posts. Micro-butthurt-expressions that is.

  12. MindReader, $3.99 on the AppStore by Anonymous Coward · · Score: 0

    Can't wait for our dystopian future where everyone has this app on their phone
    It'll feed the data in from a little camera on their wireless earbuds as it analyzes your facial expression in realtime.
    On one hand maybe it will let us discover the sociopaths in our midst, and have a positive effect on society, on the other hand maybe it will let those sociopaths go hog wild as it's another tool to have fun with.

  13. Guess? Sure... by mark-t · · Score: 1

    Guess accurately? That could be interesting...

    How cool would it be to literally have an emoji be part of your password, where the emoji is your literal face, and not some predefined unicode value?

  14. Doubtful. by Anonymous Coward · · Score: 0

    Since most people these days seem to have crippling social anxiety they are almost always going to have a micro expression of being afraid even when they did nothing wrong.

  15. No by Anonymous Coward · · Score: 0

    And even if it could, emotions in the moment are related only to the moment and not really representative of much of anything. I know that nerds are desperate to find a use, any use for this software to justify it. Keep trying.

  16. SJWs... by Anonymous Coward · · Score: 0

    SHWs will warp the program to detect non-existent microaggressions and send them to police

  17. Microexpressions don't exist by maiden_taiwan · · Score: 2

    >Microexpressions are fast, involuntary facial expressions which other people may not
    >consciously recognize, but arise from our real emotions instead of the face we wish to
    >present to the world.

    FYI, that is only a hypothesis, not a universal truth, and there's plenty of evidence against (and debate about) so-called microexpressions and "unconscious emotion." For example, if you place electrodes on people's faces and measure actual muscle movements during emotion, there's tremendous variety, not uniformity. There's also lots of evidence that emotional expressions in the face are neither universal nor innate.

    See the recent TED Talk by neuroscientist Lisa Feldman Barrett for a friendly overview.

    1. Re:Microexpressions don't exist by Anonymous Coward · · Score: 0

      Sure is amusing how often this objection applies to any given machine learning system, even within its own constraints.

      Doubly so that it is then sold *ignoring* those constraints by salesguys who largely don't understand it...

  18. Sounds like a business opportunity by Wizardess · · Score: 1

    Whatever the merits of the situation I see a business opportunity for people who make protective cases for cell phones. Simply build one with an easy to install and easy to pop open attached lens cap. "Let 'em eat darkness."

    {^_-}