Geometrical facial modeling for emotion recognition

Abstract

Facial expressions are the facial changes in response to a person's internal emotional states, intentions, or social communications. Facial expression analysis has been an active research topic for behavioral scientists since the work of Darwin in 1872. It includes both measurement of facial motion and recognition of expression. There are two different ways to analyze facial expressions: one considers facial affect (emotion) and the other facial muscular movements. Many researchers argue that there is a set of basic emotions which were preserved during evolutive process because they allow the adaption of the organisms behavior to distinct daily situations. This paper discusses emotion recognition based on analysis of facial elements. Different feature sets are proposed to represent the characteristics of the human face and their performance is evaluated using Machine Learning techniques. The results indicate that the selected facial features represent a valid approach for emotion identification.