AN EMOTION ANALYSIS ALGORITHM AND IMPLEMENTATION TO NAO HUMANOID ROBOT

Abstract

Humanoid robots are extensively becoming an essential part of the sociallife.  It is crucial for humanoid robotsto understand the emotions of the people for efficient human-robot interaction.Even though a great number of facial emotion analysis algorithms have beendeveloped and a number of them have been implemented to humanoid robots, thereare still gaps in improving accuracy, computational burden and speed of thesealgorithms.  This paper proposes a4-stage emotion analysis algorithm and then presents its application to NAOhumanoid robot. Initially, the robot detects the face using Viola-Jonesalgorithm. Later, important facial distance measurements are taken withgeometric based facial distance measurement technique. Then, facial actioncoding system technique is used to detect movements of the measured facialpoints. Finally, measured facial movements are evaluated to understand instantemotional properties of the person. Although this algorithm can be implementedto all humanoid robots, in this research, it has been specifically applied toNAO humanoid robot. The reliability of the emotion analysis is verified byanalyzing each terminal decision made based on the facial distancemeasurements. In addition, the accuracy,computational burden and speed of the algorithm are assessed to show theeffectiveness of the algorithm.