Human Emotion Recognition Using Body Expressive Feature

Abstract

Recognition of emotions from human plays a vital role in our day-to-day life and is essential for social communication. In many application of human–computer interaction using nonverbal communication like facial expression, body movements, eye movements and gestures are used. Among these methods, body movement method is widely used because it predicts the emotions of human. In this paper, body expressive features (angle, distance, velocity and acceleration) are proposed to recognize the emotion from human body movements. The GEMEP corpus (straight view) videos are used for this experiment. The 12-dimensional features were extracted from the head point, left-hand point and right-hand point of body movements of the human present in the frame. The features are given to the random forest (RF) classifier to predict the human emotions. The performance measure can be calculated using qualitative and quantitative analyses.