Visual-Based Emotion Detection for Natural Man-Machine Interaction

Abstract. The demand for humanoid robots as service robots for everyday life has increased during the last years. The processing power of the hardware and the development of complex software applications allows the realization of "natural" human-robot interaction. One of the important topics of natural interaction is the detection of emotions which enables the robot to react appropriate to the emotional state of the communication partner. Humanoid robots designed for natural interaction require a short response time and a reliable detection. In this paper we introduce a emotion detection system realized with a combination of a haar-cascade classifier and a contrast filter. The detected feature points are then used to estimate the emotional state using the so called action units. Final experiments with the humanoid robot ROMAN show the performance of the proposed approach.

• Type: Journal
• Year: 2008
• Where: KI
• Authors: Samuel Strupp, Norbert Schmitz, Karsten Berns
• Keywords: Artificial Intelligence, Emotional State, Humanoid Robot, KI 2008, Natural Interaction