Authors:
Roman Gorbunov
;
Emilia Barakova
and
Matthias Rauterberg
Affiliation:
Eindhoven University of Technology, Netherlands
Keyword(s):
Genetic Programming, Hidden Model, Affective Computing, Facial Expressions, Emotions.
Related
Ontology
Subjects/Areas/Topics:
Artificial Intelligence
;
Computational Intelligence
;
Evolution Strategies
;
Evolutionary Computing
;
Genetic Algorithms
;
Informatics in Control, Automation and Robotics
;
Intelligent Control Systems and Optimization
;
Knowledge Discovery and Information Retrieval
;
Knowledge-Based Systems
;
Machine Learning
;
Soft Computing
;
Symbolic Systems
Abstract:
In this paper we demonstrate how genetic programming can be used to interpret time dependent facial expressions in terms of emotional stimuli of different types and intensities. In our analysis we have used video records of facial expressions made during the Mars-500 experiment in which six participants have been isolated for 520 days to simulate flight to Mars. The FaceReader, commercial software developed by VicarVision and Noldus Information Technology, has been used to extract seven time dependent components of facial expressions from the video records. To interpret the obtained time dependent components of facial expressions we have proposed a mathematical model of emotional stimuli assuming that dynamics of facial expressions is determined by emotional stimuli of different types and intensities and facial expression at the moment of the stimuli. Genetic programming has been used to find the locations, types and intensities of the emotional stimuli as well as the way the facial
expressions react on them.
(More)