Sensing facial emotions in a continuous 2D affective space

The interpretation of user facial expressions is a very useful method for emotional sensing and it constitutes an indispensable part of affective Human Computer Interface designs. Facial expressions are often classified into one of several basic emotion categories. This categorical approach seems poor to treat faces with blended emotions, as well as to measure the intensity of a given emotion. This paper presents an effective system for facial emotional classification, where facial expressions are evaluated with a psychological 2-dimensional continuous affective approach. At its output, an expressional face is represented as a point in a 2D space characterized by evaluation and activation factors. The proposed system first starts with a classification method in discrete categories based on a novel combination of classifiers, that is subsequently mapped in a 2D space in order to be able to consider intermediate emotional states. The system has been tested with an extensive universal database and human assessment has been taken into consideration in the evaluation of results.