Interesting . . . looks really hard to make!
more info here:http://www.calinon.ch/showVideo.php?video=5
When the robot recognizes a face in its field of view, it first grabs a snapshot of this face and
extracts the relevant features and contours characterizing it. The robot then grabs a pen and start
drawing the user's portrait, starting from the rough contours and adding details iteratively.