A Fuzzy Reasoning Model for Recognition of Facial Expressions

Abstract

Abstract. In this paper we present a fuzzy reasoning model and a designed system for Recognition of Facial Expressions, which can measure and recognize the intensity of basic or non-prototypical emotions. The proposed model operates with encoded facial deformations described in terms of either Ekman´s Action Units (AUs) or Facial Animation Parameters (FAPs) of MPEG-4 standard and provides recognition of facial expression using a knowledge base implemented on knowledge acquisition and ontology editor Protégé. It allows modeling of facial features obtained from geometric parameters coded by AUs - FAPs and from a set of rules required for classification of measured expressions. This paper also presents a designed framework for fuzzyfication of input variables of a fuzzy classifier based on statistical analysis of emotions expressed in video records of standard Cohn-Kanade’s and Pantic´s MMI face databases. The proposed system designed according to developed model has been tested in order to evaluate its capability for detection, indexing, classifying, and interpretation of facial expressions.