Smile Classification

Smile is one of the representative emotional expressions which is observed frequently in daily life and essential for various non-verbal communications. People make spontaneous smiles and intentional ones. It is important to guess properly whether a person is making smile spontaneously or intentionally to understand the meaning of smiles. In this study, we propose a smile classification system with a smart eyewear that equips photo-reflective sensors and examine whether we can distinguish two types of smiles; Natural smiles caused by funny videos and fake smiles evoked by instructions. We extract geometric features: reflection intensity distribution of sensors and temporal features in time axis. By applying Support Vector Machine, we observed 94.6% as the mean accuracy among 12 participants when we used both geometric and temporal features with user dependent training. The result suggested that we can distinguish between natural and posed smile by the sensors embedded with the smart eyewear.