Comparing models for gesture recognition of children's bullying behaviors

Abstract

We explored gesture recognition applied to the problem of classifying natural physical bullying behaviors by children. To capture natural bullying behavior data, we developed a humanoid robot that used hand-coded gesture recognition to identify basic physical bullying gestures and responded by explaining why the gestures were inappropriate. Children interacted with the robot by trying various bullying behaviors, thereby allowing us to collect a natural bullying behavior dataset for training the classifiers. We trained three different sequence classifiers using the collected data and compared their effectiveness at classifying different types of common physical bullying behaviors. Overall, Hidden Conditional Random Fields achieved the highest average F1 score (0.645) over all tested gesture classes.