With an ever-increasing role of computers and other digital devices in our society, one of the main foci of the research in Artificial Intelligence is on Impacts of Emerging Human-Machine Systems. A related, crucial issue is that of Human-Machine Interaction (HMI). A long-term goal in HMI research is to approach the naturalness of human-human interaction. This means integrating "natural" means that humans employ to interact with each other into the HMI designs. With this motivation, automatic speech recognition and synthesis have been the topics of research for decades. Recently, other human interactive modalities such as body and facial gestures have also gained interest as potential modes of HMI. The objective of the symposium proposed here is to review recent advances in automatic facial expression analysis and synthesis and their potential applicability to natural HMI.

Facial expression is one of the most cogent, naturally preeminent means for human beings to communicate emotions, to clarify and stress what is said, to signal comprehension, disagreement, and intentions, in brief, to regulate interactions with the environment and other persons in the vicinity.
Automated analyzers and synthesizers of facial expressions have, therefore, numerous applications in behavioral science, medicine, security, and HMI. They form the essence of automated tools for lip reading, bimodal speech analysis, videoconferencing, face and visual speech animation, virtual character animation, affective computing, etc. In the robotics area, the facial expression is also very important for natural/comfortable man-machine interaction. KISMET (AI Lab., MIT) and Face Robot Science University of Tokyo) are good examples.

Although several promising approaches have been reported in the literature in the last ten years, automatic detection, interpretation and synthesis of human facial expressions remain rather difficult to achieve. The proposed symposium represents an internationally respected scientific forum for presenting and discussing different approaches to automatic facial expression detection, analysis, synthesis, and their applications to the field of HMI.

We believe that the proposed symposium on Automatic Facial Expression Analysis and Synthesis will induce an extension of the state of the art in the field in the following two ways: