Future of Engineering
Saturday, June 28, 2008
Face Acts As Remote Control, Speeds and Slows Video Playback
A computer science Ph.D. student Jacob Whitehill can turn his face into a remote control that speeds and slows video playback.
The inception of online teaching has drastically changed the education field. Face-to-face interaction is minimised in this approach. Robotic technology hopes to take it one step further by introducing robotic teachers.
The only drawback is that a robot cannot understand the expressions of a confused student.It would go on teaching even if the student looks puzzled with the lesson. In order to tackle this Whitehall's pilot study explores the utility of facial expression as a feedback signal from student to teacher.
To achieve this he has studied the facial expressions of people who participate in a lecture. Using video conferencing software he collects the facial expressions of the students.
From here, Whitehill would then 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.
Their results have shown that automatic facial expression recognition is already a useful feedback signal for intelligent tutoring systems for two concrete tasks:perceived difficulty estimation, and preferred speed prediction. As expression recognition technology improves, its usefulness in ITS will continue to grow.
The work is being presented in June 2008 at the Intelligent Tutoring Systems conference and at the IEEE International Workshop on Computer Vision and Pattern Recognition for Human Communicative Behavior Analysis.
Read the Abstract of the project here.
Image Credit: UC San Diego Jacobs School of Engineering
The inception of online teaching has drastically changed the education field. Face-to-face interaction is minimised in this approach. Robotic technology hopes to take it one step further by introducing robotic teachers. The only drawback is that a robot cannot understand the expressions of a confused student.It would go on teaching even if the student looks puzzled with the lesson. In order to tackle this Whitehall's pilot study explores the utility of facial expression as a feedback signal from student to teacher.
To achieve this he has studied the facial expressions of people who participate in a lecture. Using video conferencing software he collects the facial expressions of the students.
From here, Whitehill would then 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.
Their results have shown that automatic facial expression recognition is already a useful feedback signal for intelligent tutoring systems for two concrete tasks:perceived difficulty estimation, and preferred speed prediction. As expression recognition technology improves, its usefulness in ITS will continue to grow.
The work is being presented in June 2008 at the Intelligent Tutoring Systems conference and at the IEEE International Workshop on Computer Vision and Pattern Recognition for Human Communicative Behavior Analysis.
Read the Abstract of the project here.
Image Credit: UC San Diego Jacobs School of Engineering
Labels: Automation, Robotics
PermaLink - Face Acts As Remote Control, Speeds and Slows Video Playback posted by Vanessa : 4:23 AM
