Jacob Whitehill, a computer science Ph.D. student from UC San Diego’s Jacobs School of Engineering can turn his face into a remote control that speeds and slows video playback.
The proof-of-concept demonstration is part of a larger project to use automated facial expression recognition to make robots more effective teachers and explores utility of facial expression as a feedback signal from student to teacher.
It is based on technology for detecting facial expressions being developed at UC San Diego’s Machine Perception Laboratory (MPLab), part of the Institute for Neural Computation, and housed in the UCSD Division of Calit2.
It shows how automatic real-time facial expression recognition can be e ectively used to estimate the level of difficulty, as perceivedby an individual student, of a delivered lecture. It also shows that facial expression data are predictive of an individual student’s preferredrate of curriculum presentation at each moment in time.
Jacob Whitehill - Credit: UC San Diego Jacobs School of Engineering
According to Whitehill:
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.
They investigated whether students’ facial expression can be used to estimate how difficult they find the lecture to be at each moment in time, as well as how fast they would prefer to receive the instruction. In the experiment, each of 8 human subjects watched a recorded video lecture 200 seconds (3 min 20 sec) in length. The lecture video consisted of 7 short video segments concatenated together about a disparate range of topics, including physics, philosophy, math, and teenage gossip.
The results showed that 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.
Whitehill who is leading this project will present it at two peer-reviewed academic conference in June 2008. The work is sponsored in part by UCSD’s Temporal Dynamics of Learning Center (TDLC), an NSF-sponsored Science of Learning Center.
To see video click here.
0 responses so far
There are no comments yet...Kick things off by filling out the form below.
You must log in to post a comment.