Development of a humanoid robot for emotion recognition

Abstract

This paper deals with a humanoid robot system of recognizing human's expression from a detected human's face and then showing human's emotion. A face detection method is as follows. First, change RGB color space to CIElab color space. Second, extract skin candidate territory. Third, detect a face through facial geometrical interrelation by face filter. Then, the position of eyes, a nose and a mouth which are used as the preliminary data of expression recognition are distinguished using geometrical features. Usually, when a person shows expression, he uses eyebrows, eyes and a mouth. In this paper, the change of eyebrows and a mouth are used as feature values of expression recognition. Feature values which are gained in this way are sent to a robot through serial communication. Then the robot operates a motor that is installed and shows human's emotion. The result of experiments on 60 persons shows 77.9% accuracy.