Self-Learning Facial Emotional Feature Selection Based on Rough Set Theory

Emotion recognition is very important for human-computer intelligent interaction. It is generally performed on facial or audio information by artificial neural network, fuzzy set, support vector machine, hidden Markov model, and so forth. Although some progress has already been made in emotion recognition, several unsolved issues still exist. For example, it is still an open problem which features are the most important for emotion recognition. It is a subject that was seldom studied in computer science. However, related research works have been conducted in cognitive psychology. In this paper, feature selection for facial emotion recognition is studied based on rough set theory. A self-learning attribute reduction algorithm is proposed based on rough set and domain oriented data-driven data mining theory. Experimental results show that important and useful features for emotion recognition can be identified by the proposed method with a high recognition rate. It is found that the features concerning mouth are the most important ones in geometrical features for facial emotion recognition.

[1]  Setsuo Ohsuga.  Knowledge Discovery as Translation , 2005, Foundations of Data Mining and knowledge Discovery.

[2]  Yi Zhang,et al.  RIDAS - a rough set based intelligent data analysis system , 2002, Proceedings. International Conference on Machine Learning and Cybernetics.

[3]  Rosalind W. Picard.  Affective computing: challenges , 2003, Int. J. Hum. Comput. Stud..

[4]  David E. Goldberg,et al.  Genetic Algorithms in Search Optimization and Machine Learning , 1988 .

[5]  Wang Guo,et al.  Decision Table Reduction based on Conditional Information Entropy , 2002 .

[6]  Sui-Xue,et al.  Online Processing of Facial Expression Recognition , 2007 .

[7]  Guoyin Wang.  Introduction to 3DM: Domain-Oriented Data-Driven Data Mining , 2008, RSKT.

[8]  Chen Shi-fu,et al.  An Approach for Reduction of Continuous-Valued Attributes , 2005 .

[9]  Zdzislaw Pawlak,et al.  Rough Set Theory and its Applications to Data Analysis , 1998, Cybern. Syst..

[10]  Qiang Shen,et al.  Tolerance-based and Fuzzy-Rough Feature Selection , 2007, 2007 IEEE International Fuzzy Systems Conference.

[11]  Guoyin Wang,et al.  Feature Selection in Audiovisual Emotion Recognition Based on Rough Set Theory , 2007, Trans. Rough Sets.

[12]  Rosalind W. Picard.  Affective Computing , 1997 .

[13]  Goldberg,et al.  Genetic algorithms , 1993, Robust Control Systems with Genetic Algorithms.

[14]  Ian H. Witten,et al.  WEKA: a machine learning workbench , 1994, Proceedings of ANZIIS '94 - Australian New Zealnd Intelligent Information Systems Conference.

[15]  Zdzislaw Pawlak,et al.  Rough classification , 1984, Int. J. Hum. Comput. Stud..

[16]  Guoyin Wang,et al.  Facial Expression Recognition Based on Rough Set Theory and SVM , 2006, RSKT.

[17]  M. White,et al.  Effect of Photographic Negation on Matching the Expressions and Identities of Faces , 2001, Perception.

[18]  Jennifer Healey,et al.  Toward Machine Emotional Intelligence: Analysis of Affective Physiological State , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[19]  Miao Duo,et al.  A HEURISTIC ALGORITHM FOR REDUCTION OF KNOWLEDGE , 1999 .

[20]  Guoyin Wang,et al.  3DM: Domain-oriented Data-driven Data Mining , 2009, Fundam. Informaticae.

[21]  Guoyin Wang,et al.  An Emotion Recognition System Based on Rough Set Theory , 2006, AMT.

[22]  Guoyin Wang,et al.  Speech Emotion Recognition Based on Rough Set and SVM , 2006, 2006 5th IEEE International Conference on Cognitive Informatics.

[23]  Andrzej Skowron,et al.  A rough set-based knowledge discovery process , 2001 .

[24]  Andrzej Skowron,et al.  Rough set methods in feature selection and recognition , 2003, Pattern Recognit. Lett..