Robot Mimics Facial Expressions

clipped from technology.newscientist.com

Mummy, that robot is making faces at me

Robotics engineers at the University of Bristol, UK, have been grimacing a lot recently, thanks to their copycat robotic head, Jules, which can mimic the facial expressions and lip movements of a human being.

Jules is an animatronic head produced by US roboticist David Hanson, who builds uniquely expressive, disembodied heads with flexible rubber skin that is moved by 34 servo motors.

Human face movements are picked up by a video camera and mapped onto the tiny electronic motors in Jules' skin.

The Bristol team developed its own software to transfer expressions recorded by the video camera into commands to make those servos produce similarly realistic facial movements.

clipped from www.brl.ac.uk

clipped from www.brl.uwe.ac.uk

Humanoid Robotics and Social Interaction

BRL is now engaged in research into how humans and robots interact and exploit representations of ‘emotional’ state using visual and physical cues as well as non-verbal

Related:
Mummy, that robot is making faces at me - robots - 29 October 2008 - New Scientist Tech
Bristol Robotics Laboratory
Video Articles - Pg1 - New Scientist
BBC NEWS | England | Bristol | Probe into domestic robot usage
Special Report on Robots - New Scientist Tech

Facial Expression Recognition Software

Researchers have developed an algorithm which is capable to recognize and categorize a persons facial expressions.

clipped from www.sciencedaily.com Facial Expression Recognition Software Developed ScienceDaily (Feb. 25, 2008) — Researchers at the Department of Artificial Intelligence (DIA) of the Universidad Politécnica de Madrid’s School of Computing (FIUPM) have, in conjunction with Madrid’s Universidad Rey Juan Carlos, developed an algorithm that is capable of processing 30 images per second to recognize a person’s facial expressions in real time and categorize them as one of six prototype expressions: anger, disgust, fear, happiness, sadness and surprise. Applying the facial expression recognition algorithm, the developed prototype is capable of processing a sequence of frontal images of moving faces and recognizing the person’s facial expression. The software can be applied to video sequences in realistic situations and can identify the facial expression of a person seated in front of a computer screen. Although still only a prototype, the software is capable of working on a desktop computer or even on a laptop.