Facial expression recognition for robotic teachers

080625073737-large Jacob Whitehill of UC San Diego’s computer science Ph. D program has developed software that recognizes common facial expressions and then translates those expressions into commands that either speed up or slow down the playback of certain video lectures. 

According to Science Daily, “The proof-of-concept demonstration is part of a larger project to use automated facial expression recognition to make robots more effective teachers.” The software can detect when a person is smiling or when their brow is furrowed, for instance. Whitehill also found that people have a tendency to blink less frequently when they’re trying to grasp difficult subject material.

"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.

The software currently appears to work with off-the shelf webcams, which could be used to control the speed of remote lectures. There’s a video located here (sorry, WMV/ASX only) with more information and some demonstrations.