A Knowledge-base Framework for Analysis of Facial Expressions Using FACS and MPEG-4 Standards

Abstract

This paper presents the development of a knowledge-base framework that supports creation of quantitative models for recognition of basic and non-prototypical emotion using Ekmanґs Facial Action Coding System (FACS) as well as animation and definition parameters (FAPs and FDPs) of MPEG-4 standard. Among the well-known approaches adopted in the automatic emotion detection system, the rule-based fuzzy classification approach has been proposed for recognition of emotions and their intensities. The designed system that consists of the knowledge-base framework implemented using the ontology editor Protйgй and fuzzy classifier, has been tested in order to evaluate its capability for detection, indexing, classifying, and interpretation of facial expressions. This proposal permits to create novel models for precise facial feature detection as well as recognition and interpretation of basic and non-prototypical. These types of systems may be used in medicine, security, psychology and psychiatry, robotics, distance education, human-computer interaction, and others.