Are people happy when they smile?: Affective assessments based on automatic smile genuineness identification

抄録

Smiles are one of the most ubiquitous facial expressions. They are often interpreted as a signalling cue of positive emotion. However, as any other facial expression, smiles can also be voluntarily fabricated, masked or inhibited with different communication goals. This review discusses automatic identification of smile genuineness. First, emotions and their bodily manifestation are introduced. Second, an overview of the literature on different types of smiles is provided. Afterwards, different techniques used to investigate smile production are described. These techniques range from human video-coding, bio-signal inspection, and novel sensors that, together with automated techniques using machine learning, aim to investigate facial expression characteristic’s beyond human perception. Next, a general summary on the spatio-temporal shape of a smile is provided. Finally, remaining challenges regarding individual and cultural differences are discussed.