Slashdot Mirror
Lost the Remote? Use Your Face
coondoggie writes "A researcher has discovered a way to use facial expressions to speed and slow video playback.
By using a combination of facial expression recognition software and automated tutoring technology Jacob Whitehill, a computer science Ph.D. student from UC San Diego's Jacobs School of Engineering, is leading the project that ultimately is part of a larger venture to use automated facial expression recognition to make robots more effective teachers.
The researchers recently conducted a pilot test with 8 people that demonstrated information within the facial expressions people make while watching recorded video lectures can be used to predict a person's preferred viewing speed of the video and how difficult a person perceives the lecture at each moment in time."
... or just look between the couch cushions.
I have Bell's Palsy you insensitive clod!
So, whenever you were constipated, your movie would start rewinding?
The obvious use for this technology is, of course, pornography. When it detects a look of boredom it knows to fast-forward through the plot bits. When it detects a relaxed-but-slightly-guilty look, it knows to stop the video and clear your browsing history.
What about when it sees my O face. You know, Oh Oh Oh...
Great. Then you'll know when the kids who grew up with this technology get bored -- they'll subconsciously start to make the "fast forward" facial expression.
And when they mishear something, they'll make the "rewind" face.
I can't wait. It'll be hilarious.
can do this. I've noticed bad college professors just keep plowing through the subject. The best ones will look at the students faces and say, "Lets back up a little," when they see blank stares from their pupils.
I don't think the ability to determine how difficult a concept is to grasp is the breakthrough here. I think it's the fact that a machine can do it.
One of our competitors trademarked the term "hypothesis". From now on, we will call them "boneheaded ideas".
Has anyone heard of a company making good headway in this department?
CS: It is all sink or swim...oh and did I mention there are sharks in that water?
Next, they'll be teaching computers to read lips. Anyone who has seen 2001: A Space Odyssey knows that this is a bad idea.
If it can recognize my "Stupid TiVo!" face when TiVo starts playing back one minute after (or before) I press the play button when rewinding (or fast-forwarding), well, we've got a winner here. Or at least recognize what I mean when I'm screaming "Not there! THERE! Ya piece of junk!"
Prisencolinensinainciusol. Ol Rait!
A researcher has discovered a way to use facial expressions to speed and slow video playback.
By using a combination of facial expression recognition software and automated tutoring technology Jacob Whitehill, a computer science Ph.D. student from UC San Diego's Jacobs School of Engineering, is leading the project that ultimately is part of a larger venture to use automated facial expression recognition to make robots more effective teachers.
The researchers recently conducted a pilot test with 8 people that demonstrated information within the facial expressions people make while watching recorded video lectures can be used to predict a person's preferred viewing speed of the video and how difficult a person perceives the lecture at each moment in time.
"If I am a student dealing with a robot teacher and I am completely puzzled and yet the robot keeps presenting new material, that's not going to be very useful to me. If, instead, the robot stops and says, 'Oh, maybe you're confused,' and I say, 'Yes, thank you for stopping,' that's really good," said Whitehill in a release.
Recent advances in the fields of pattern recognition, computer vision, and machine learning have made automatic facial expression recognition in real-time a viable resource for intelligent tutoring systems (ITS), researchers added. As facial expression recognition technology improves in accuracy, the range of its application will grow. One particular application we are currently developing is a \smart video player" which modulates the video speed in real-time based on the user's facial expression so that the rate of lesson presentation is optimal for the current user, researchers said.
In the pilot study, researcher said the facial movements people made when they perceived the lecture to be difficult varied widely from person to person. Most of the 8 test subjects, however, blinked less frequently during difficult parts of the lecture than during easier portions of the lecture, which is supported by findings in psychology.
One of the next steps for this project is to determine what facial movements one person naturally makes when they are exposed to difficult or easy lecture material. From here, researchers could train a user specific model that predicts when a lecture should be sped up or slowed down based on the spontaneous facial expressions a person makes.
The goal of UC San Diego's Machine Perception Laboratory is to gain insights into how the brain works by developing systems that perceive and interact with humans in real time using natural communication channels. Researchers are also developing algorithms for robots that develop and learn to interact with people on their own. Applications include personal robots, perceptive tutoring systems, and system for clinical assessment, monitoring, and intervention.
Interested in hypermiling?
Oh, oh, facial recognition. That makes a lot more sense. When I read the headline, I first thought it was going to suggest that if you lose the remote, get up and bash the buttons on the DVD player with your forehead or something.
A similar system applied to computer keyboards would certainly make IT and data entry more interesting professions...
Demanding constant attention will only lead to attention.
When our name is on the back of your car, we're behind you all the way!
Until we develop a neural link, all other interfaces will be poor substitutes. Of course there are drawbacks like the possibility that it will become The Matrix. Even if it worked, it might work too well:
[Average male watching TV]
[Average Male thought]: Hey! Football is on.
[Neural Link switches to football]
[Average Male thought]: Damn, a commercial. What else is on?
[Neural Link begins switching channels at a breathtaking rate. Epilleptics in room start convulsing]
[Average Male thought]: Is the game back on?
[Neural Link switches back to football]
[Average Male thought]: Damn, another commercial. Hey that girl is hot!
[Neural Link switches to Playboy channel and dims lights]
[Male's Significant Other stares at him in disgust]
Well, there's spam egg sausage and spam, that's not got much spam in it.
So when you are nodding off late at night, what happens? Does the volume go up and down? That could create an infinite loop. I bet if my neighbor's wife looked at the TV it would change the channel to the Sci-fi network.
> The next Slashdot story will be ready soon, but subscribers can beat the rush and see it early!
...
*look of boredom*
Nope, didn't help
Bark less. Wag more.
Cool! We could apply this to computers and do away with the mouse...
Typical day at the support desk:
Support: "Hello, how can I help you?"
User: "Hi, I can't see how to open an application"
Support: "OK, you need to look at the application you want to open"
User: "OK"
Support: "Now, double blink with your left eye"
User: "Hey! That did it!"
Support: "Great, is there anything else I can help you with?"
User: "Yeah, sometimes I'll be doing stuff and the popup menu will appear, it's quite annoying"
Support: "Hmmm, perhaps you suffer from a nervous twitch"
User: "Actually, I do have a problem in my right eye, that's probably it!"
Support: "Thanks for calling, bye now."
Summation 2
go threw it?
my mind explodes and i cringe
the clip fast forwards
WARNING: Smartphones have side effects--most of them undocumented.
Flipping through the channels is gonna get ugly.
Hand gesture recognition makes a lot more sense.
Engineering is the art of compromise.