RISA: A Real-Time Interactive Shadow Avatar

Abstract

As Webcams become an important factor in the PC environment, many camera-based communication techniques have been developed. Among them, gesture-based communication is attracting attention. In this paper, we propose a real-time interactive shadow avatar (RISA) which can express facial emotions by changing as response to the user's gestures. The avatar's shape is a virtual shadow constructed from a real-time sampled picture of user's shape. Several predefined facial animations overlap on the face area of the virtual shadow, according to the types of hand gestures. We use the background subtraction method to separate the virtual shadow, and a simplified region-based tracking method is adopted for tracking hand positions and detecting hand gestures. In order to achieve a smooth change of emotions, we use a refined morphing method which uses many more frames in contrast to traditional dynamic emoticons. Through our experiments, we found that in the cases where there was enough distance between a camera and a user, the accuracy was higher than in the cases where the distance between them was very close. We have found RISA to be very useful in simple online chatting and PC game environments and it was also highlighted in a real media art exhibition.