A method for synchronizing nods of a CG character and a human using thermal image processing

We have proposed a method for communication between a human and a CG character by exploiting thermal image processing. The CG character can synchronize its nod with a human's nod by predicting his or her nod. We use as a feature parameter the ratio of horizontal length to vertical length of face skin region on a thermal image. The measured parameter is inputted to fuzzy algorithm system to obtain the nod angle of the person in front of an infrared ray camera, then we use moving average model for predicting the nod of person. The average error of the nod angle obtained by the present method was estimated as about 6deg.