Real-time facial expression recognition for natural interaction

The recognition of emotional information is a key step toward giving computers the ability to interact more naturally and intelligently with people. This paper presents a completely automated real-time system for facial expression's recognition based on facial features' tracking and a simple emotional classification method. Facial features' tracking uses a standard webcam and requires no specific illumination or background conditions. Emotional classification is based on the variation of certain distances and angles from the neutral face and manages the six basic universal emotions of Ekman. The system has been integrated in a 3D engine for managing virtual characters, allowing the exploration of new forms of natural interaction.