Artículos

 

A Fuzzy Reasoning Model for Recognition of Facial Expressions

 

Un modelo de razonamiento difuso para reconocimiento de expresiones faciales

 

Oleg Starostenko¹, Renan Contreras¹, Vicente Alarcón Aquino¹, Leticia Flores Pulido¹, Jorge Rodríguez Asomoza¹, Oleg Sergiyenko², and Vira Tyrsa³

 

¹ Research Center CENTIA, Department of Computing, Electronics and Mechatronics, Universidad de las Américas, 72820, Puebla, Mexico. E–mail: oleg.starostenko@udlap.mx; renan.contrerasgz@udlap.mx; vicente.alarcon@udlap.mx; leticia.florespo@udlap.mx; jorge.rodriguez@udlap.mx

² Engineering Institute, Autonomous University of Baja California, Blvd. Benito Juárez, Insurgentes Este, 21280, Mexicali, Baja California, Mexico. E–mail: srgnk@iing.mxl.uabc.mx

³ Universidad Politécnica de Baja California, Mexicali, Baja California, Mexico. E–mail: vera–tyrsa@yandex.ru

 

Article received on 11/12/2010.
Accepted 05/04/2011.

 

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.

Keywords: Facial expression recognition, emotion interpretation, knowledge–based framework, rules–based fuzzy classifier.

 

Resumen

En este artículo presentamos un sistema de razonamiento difuso capaz de reconocer y medir la intensidad de cualquier expresión facial prototípica o no prototípica. El modelo propuesto utiliza como entrada las deformaciones faciales codificadas ya sea en términos de AUs (Ekman FACS) o FAPs (MPEG–4) y provee reconocimiento de expresiones faciales utilizando una base de conocimiento la cual fue implementada utilizando el sistema de adquisición de conocimiento y editor de ontologías Protégé. Esta base de conocimiento permite, además de la creación de modelos de características faciales obtenidos a partir de parámetros geométricos y codificados en términos de AUs y FAPs, también la definición de las reglas requeridas para la clasificación de las expresiones. En este artículo también se presenta un framework diseñado para codificación de las variables de entrada al clasificador difuso basado en los resultados obtenidos del análisis estadístico de las emociones expresadas en grabaciones de video en base estándar de caras creada por Cohn–Kanade y Pantic. El sistema propuesto fue evaluado con el propósito de analizar su capacidad de detección, indexado, clasificación e interpretación de expresiones faciales.

Palabras clave: Reconocimiento de expresiones faciales, la interpretación de la emoción, conocimiento marco, clasificador difuso basado en reglas.

 

DESCARGAR ARTÍCULO EN FORMATO PDF

 

Acknowledgments

This research is sponsored by Mexican National Council of Science and Technology, CONACyT, Projects: #109115 and #109417.

 

References

1. Black M., Kim, S. & Simeral, J. (2008). Neural control of computer cursor velocity by decoding motor cortical spiking activity, Journal of Neural Engineering, 5, 455–476.         [ Links ]

2. Chakraborty, A. & Konar, A. (2009). Emotion recognition from facial expressions and its control using fuzzy logic, IEEE Transactions on Systems, Man, and Cybernetics–Part A: Systems and Humans, 39(4), 726–743.         [ Links ]

3. Contreras R., Starostenko, O. & Alarcon–Aquino,V. (2009). A Knowledge–based Framework for Analysis of Facial Expressions Using FACS and MPEG–4 Standards, 10th International Conference on Pattern Recognition and Processing, Minsk, Belarus, 251–256.         [ Links ]

4. Ekman, P. & Friesen. W.V. (1978). Facial Action Coding System (FACS). CA, USA: Consulting Psychologists Press.         [ Links ]

5. Esau N., Wetzel, E., Kleinjohann, L. & Kleinjohann, B. (2007). Real–Time Facial Expression Recognition Using a Fuzzy Emotion Model. IEEE International Fuzzy Systems Conference, London, England, 1 –6.         [ Links ]

6. Gomathi, V. & Ramar, K. (2009). Human Facial Expression Recognition using MANFIS Model. World Academy of Science, Engineering and Technology, 50.         [ Links ]

7. Information technology – Coding of audiovisual objects. Part 2: Visual, ISO/IEC14496–2:2001(E), Second edition.         [ Links ]

8. Kanade, T., Cohn, J.F. & Yingli, T. (2000). Comprehensive database for facial expression analysis. 4th IEEE Conference on Automatic. Face and Gesture Recognition, Grenoble, France, 46–53.         [ Links ]

9. Khanum, A., Mufti, M. & Javed, M.Y. (2009). Fuzzy case–based reasoning for facial expression recognition. Journal of Fuzzy Sets and Systems, 160(2), 231 –250.         [ Links ]

10. Kharat, G.U. & Dudul, S.V. (2008a). Human Emotion Recognition System Using Optimal SVM. WSEAS Journal Transactions on Computers, 7 (6), 650–659.         [ Links ]

11. Kharat G.U. & Dudul S.V. (2008b). Neural Network Classifier for Human Emotion Recognition. Conference on Emerging Trends in Engineering and Technology, Iran, 1 –6.         [ Links ]

12. Kyoung, S.C., Yong–Guk, K. & Yang–Bok, L. (2006). Real–Time Expression Recognition System Using Active Appearance Model and EFM. Computational Intelligence and Security Conference, Guangzhou, China, 1 –6.         [ Links ]

13. Lin, D.T. (2006). Facial Expression Classification Using PCA and Radial Basis Function Network. Journal of Information Science and Engineering, 22 (5), 1033–1046.         [ Links ]

14. López, J.M., Gil, R. & Cearreta, R. (2008). Towards an Ontology for Describing Emotions. Lecture Notes in Artificial Intelligence, 5288, 96–104.         [ Links ]

15. Maglogiannis, I. et al. (2009). Face detection and recognition of human emotion using Markov random fields. Ubiquitous Computing Journal, 13 (1), 95–101.         [ Links ]

16. Mufti M., & Khanam, A. (2006). Fuzzy Rule Based Facial Expression Recognition, International conference on Computational Intelligence for Modeling, Control and Automation, Sydney Australia, 57.         [ Links ]

17. Muthukaruppan, K., et al. (2007). Development of a Personified Face Emotion Recognition Technique Using Fitness Function. Japan: Springer.         [ Links ]

18. Pantic, M. & Rothkrantz, L.J. (2004). Facial Action Recognition for Facial Expression Analysis from Static Face Images. IEEE Transaction on Systems, Man, and Cybernetics, 34 (3), 1449–1461.         [ Links ]

19. Pantic M., Valstar M.F. & Rademaker R. (2005). Web–based Database for Facial Expression Analysis, IEEE Conference and Expo, Netherlands, 1 –6.         [ Links ]

20. Plutchik R. (2001). The nature of emotions. American Scientist, 89 (4), 344–350.         [ Links ]

21. Protégé. (2009). Ontology editor, Retrieved from: http://protege.stanford.edu/download/download.html        [ Links ]

22. Rizon, M. et al. (2009). Personalized Human Emotion Classification Using Genetic Algorithm. Open International Conference on Visualization, CA, USA, 1–6.         [ Links ]

23. Starostenko O., Contreras, R. & Alarcon–Aquino, V. (2010). Facial Feature Model for Emotion Recognition Using Fuzzy Reasoning. Advances in pattern Recognition. Lecture Notes in Computer Science, 6256, 11–21.         [ Links ]

24. Wood, F. & Black, M. J. (2008). A non–parametric Bayesian alternative to spike sorting, Neuroscience Methods, 173(1) 1 –12.         [ Links ]

25. Young–Joong K. & Myo–Taeg L. (2005). Near–Optimal Fuzzy Systems Using Polar Clustering. Lecture Notes in Computer Science, 3684, 518–524.         [ Links ]

26. Yu, A., Elder, C., Yeh, J. & Pai, N. (2009). Facial Recognition using Eigenfaces. Retrieved from http://cnx.org/content/m33180/latest/.         [ Links ]

27. Zhang, Y. & Ji, Q. (2005). Active Information Fusion for Facial Expression Understanding. IEEE Transactions on Pattern Analysis and Machine Intelligence, 27 (5), 699–714.         [ Links ]

28. Zhou, X. & Huang, X. (2004). Real–time facial expression recognition in the interactive game based on hidden Markov model. Conference on Computer Graphics, Imaging and Visualization, Penang, Malaysia, 1–8.         [ Links ]