What is Face Synthesis

The human face is involved in an impressive variety of different activities. It houses the majority of our sensory apparatus: eyes, ears, mouth, and nose, allowing the bearer to see, hear, taste, and smell. Apart from these biological functions, the human face provides a number of signals essential for interpersonal communication in our social life. The face houses the speech production apparatus and is used to identify other members of the species, to regulate the conversation by gazing or nodding, and to interpret what has been said by lip reading. It is our direct and naturally preeminent means of communicating and understanding somebody’s affective state and intentions on the basis of the shown facial expression (Lewis & Haviland-Jones, 2000). Personality, attractiveness, age, and gender can also be seen from someone’s face. Thus the face is a multisignal sender/receiver capable of tremendous flexibility and specificity. In general, the face conveys information via four kinds of signals listed in Table 1. Automating the analysis of facial signals, especially rapid facial signals, would be highly beneficial for fields as diverse as security, behavioral science, medicine, communication, and education. In security contexts, facial expressions play a crucial role in establishing or detracting from credibility. In medicine, facial expressions are the direct means to identify when specific mental processes are occurring. In education, pupils’ facial expressions inform the teacher of the need to adjust the instructional message. As far as natural user interfaces between humans and computers (PCs/robots/machines) are concerned, facial expressions provide a way to communicate basic information about needs and demands to the machine. In fact, automatic analysis of rapid facial signals seem to have a natural place in various vision subsystems and vision-based interfaces (face-for-interface tools), including automated tools for gaze and focus of attention tracking, lip reading, bimodal speech processing, face/visual speech synthesis, face-based command issuing, and facial affect processing. Where the user is looking (i.e., gaze tracking) can be effectively used to free computer users from the classic keyboard and mouse. Also, certain facial signals (e.g., a wink) can be associated with certain commands (e.g., a mouse click) offering an alternative to traditional keyboard and mouse commands. The human capability to “hear” in noisy environments by means of lip reading is the basis for bimodal (audiovisual) speech processing that can lead to the realization of robust speech-driven interfaces. To make a believable “talking head” (avatar) representing a real person, tracking the person’s facial signals and making the avatar mimic those using synthesized speech and facial expressions is compulsory. The human ability to read emotions from someone’s facial expressions is the basis of facial affect processing that can lead to expanding user interfaces with emotional communication and, in turn, to obtaining a more flexible, adaptable, and natural affective interfaces between humans and machines. More specifically, the information about when the existing interaction/processing should be adapted, the importance of such an adaptation, and how the interaction/ reasoning should be adapted, involves information about how the user feels (e.g., confused, irritated, tired, interested). Examples of affect-sensitive user interfaces are still rare, unfortunately, and include the systems of Lisetti and Nasoz (2002), Maat and Pantic (2006), and Kapoor, Burleson, and Picard (2007). It is this wide range of principle driving applications that has lent a special impetus to the research problem of automatic facial expression analysis and produced a surge of interest in this research topic.