Open AccessFacial Action Units Analysis using Rule-Based Algorithm
Author(s) -
Hamimah Ujir,
Irwandi Hipiny,
Dedi Iskandar
Publication year - 2018
Publication title -
international journal of engineering and technology
Language(s) - English
Resource type - Journals
ISSN - 2227-524X
DOI - 10.14419/ijet.v7i3.20.19167
Subject(s) - facial expression , facial action coding system , expression (computer science) , computer science , artificial intelligence , offset (computer science) , active appearance model , face (sociological concept) , coding (social sciences) , consistency (knowledge bases) , property (philosophy) , pattern recognition (psychology) , computer vision , algorithm , mathematics , image (mathematics) , statistics , social science , philosophy , epistemology , sociology , programming language
Most works in quantifying facial deformation are based on action units (AUs) provided by the Facial Action Coding System (FACS) which describes facial expressions in terms of forty-six component movements. AU corresponds to the movements of individual facial muscles. This paper presents a rule based approach to classify the AU which depends on certain facial features. This work only covers deformation of facial features based on posed Happy and the Sad expression obtained from the BU-4DFE database. Different studies refer to different combination of AUs that form Happy and Sad expression. According to the FACS rules lined in this work, an AU has more than one facial property that need to be observed. The intensity comparison and analysis on the AUs involved in Sad and Happy expression are presented. Additionally, dynamic analysis for AUs is studied to determine the temporal segment of expressions, i.e. duration of onset, apex and offset time. Our findings show that AU15, for sad expression, and AU12, for happy expression, show facial features deformation consistency for all properties during the expression period. However for AU1 and AU4, their properties’ intensity is different during the expression period.