ESTUDIO COMPARATIVO DE CLASIFICADORES PARA EL RECONOCIMIENTO DE EXPRESIONES FACIALES (A COMPARATIVE STUDY OF CLASSIFIERS FOR FACIAL EXPRESSION RECOGNITION)
Resumen
Resumen
De acuerdo con el Sistema de Codificación de Acciones Faciales (FACS) de Paul Ekman, las expresiones faciales se originan por la activación de distintos conjuntos de músculos del rostro. En la última década, se han reportado numerosos estudios que intentan reconocer automáticamente emociones en el rostro a partir de expresiones faciales. Sin embargo, para lograr una precisión aceptable, los algoritmos propuestos necesitan entrenamiento específico y en la mayoría de los casos, su ejecución computacional llega a requerir mucho tiempo. En este trabajo presentamos un algoritmo para clasificar expresiones faciales en alguna de las ocho categorías básicas de Paul Ekman: enojo, desprecio, disgusto, miedo, alegría, tristeza, sorpresa y neutral. Utilizando la base de datos de Cohn-Kanade, se han elaborado algoritmos de detección y alineamiento facial mismos que permiten obtener 68 conjuntos de coordenadas correspondientes a puntos específicos del rostro. Dichas coordenadas se han alimentado a distintos clasificadores con el objetivo de comparar su desempeño. Los resultados indican que el clasificador con mejor desempeño es el Perceptrón Multicapa con una precisión del 89%.
Palabras Claves: clasificadores, detección de puntos de interés, perceptrón multicapa, reconocimiento de expresiones faciales, técnicas de aprendizaje supervisado.
Abstract
According to Paul Ekman’s Facial Action Coding System (FACS), facial expressions can be reduced to sets of movements of different facial muscles. During the last decade, a number of studies have attempted to recognize automatically emotions from facial expressions. However, in order to achieve an acceptable precision, the proposed algorithms need specific training and are computationally burdensome. In this paper, we propose an algorithm to classify facial expressions in one of the eight basic categories of Paul Elkman: anger, sadness, happiness, contempt, disgust, surprise, fear and neutral. Using the Cohn-Kanade dataset, we have elaborated face detection and alignment algorithms that allow obtaining a set of 68 face landmarks. Such landmarks are then used to train and test different classifiers. After comparing the results, the multilayer perceptron approach exhibited the best average accuracy (89%).
Keywords: classifiers, detection of interest points, facial expression recognition, multilayer perceptron, supervised learning.
Texto completo:
153-165 PDFReferencias
Abhishree, T.M., Latha, J., Manikantan, K. & Ramachandran, S. Face recognition using Gabor filter based feature extraction with anisotropic diffusion as a pre-processing technique, Procedia Computer Science, Vol. 45, 312-321, 2015.
Ahonen, T., Hadid, A. & Pietikäinen M. Face recognition with Local Binary Patterns. In: Pajdla T., Matas J. (eds), Lecture Notes in Computer Science, Vol. 3021, Springer, Berlin, Heidelberg, 2004.
Álvarez, V.M., Domínguez-Soberanes, J., Sánchez, C., Gutiérrez, S., López, B., Quiroz, R., Mendoza, D., Buendía, H. & Velázquez, R. Consumer acceptances through facial expressions of encapsulated flavors based on a nanotechnology approach, 2018 Nanotechnology for Instrumentation and Measurement (NANOfIM), Mexico City, Mexico, 2018, pp. 1-5.
Álvarez, V.M., Velázquez, R., Gutiérrez, S. & Enríquez-Zarate, J. A method for facial emotion recognition based on interest points, 2018 International Conference on Research in Intelligent and Computing in Engineering (RICE), San Salvador, 2018, pp. 1-4.
Bartlett, M.S., Movellan, J.R. & Sejnowski, T.J. Face recognition by independent component analysis. IEEE Transactions on Neural Networks, Vol. 13, 1450-1464, 2012.
Butalia, M.A., Ingle, M. & Kulkarni, P. Facial expression recognition for security. International Journal of Modern Engineering Research, No. 2, 1449-1453, 2012.
Corcoran, P. & Iancu, C. Hidden Markov Models in automatic face recognition - A review, Reviews, Refinements and New Ideas in Face Recognition, IntechOpen, 2011.
Donato, G., Bartlett, M.S., Hager, J.C., Ekman, P. & Sejnowski, T.J. Classifying facial actions, Transactions on Pattern Analysis and Machine Intelligence, Vol. 21, No. 10, 974–989, 1999.
Hamm, J., Kohler, C.G., Gur, R.C. & Verma, R. Automated Facial Action Coding System for dynamic analysis of facial expressions in neuropsychiatric disorders, Journal of Neuroscience Methods, 237-256, 2011.
Kar, N.B., Babu, K.S. & Jena, S.K. Face expression recognition using histograms of oriented gradients with reduced features, Advances in Intelligent Systems and Computing, Vol. 460, 209-219, 2017.
Kazemi, V. & Sullivan, J. One millisecond face alignment with an ensemble of regression trees, IEEE Conference on Computer Vision and Pattern Recognition, Columbus, Ohio, 1867-1874, 2014.
King, D.E. Dlib-ml: A Machine Learning Toolkit, Journal of Machine Learning Research, vol. 10, 1755-1758, 2009.
Krithika, L.B. & Lakshmi, P.G., Student Emotion Recognition System (SERS) for e-learning Improvement based on learner concentration metric, Procedia Computer Science, 85, pp. 767-776, 2016.
Lucey, P., Cohn, J. F., Kanade, T., Saragih, J., Ambadar, Z. & Matthews, I. The Extended Cohn-Kanade Dataset (CK+): A complete dataset for action unit and emotion-specified expression, IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Workshops, San Francisco, 94-101, 2010.
Mehrabian, A. Communication without words. Psychology Today, Vol. 2, No. 4, 53-56, 1968.
Nefian, A.V. Embedded Bayesian networks for face recognition, IEEE International Conference on Multimedia and Expo, 133-136, 2002.
Paul, L.C. & Sumam, A.A. Face recognition using Principal Component Analysis Method, International Journal of Advanced Research in Computer Engineering & Technology, Vol. 1, No. 9, 135-139, 2012.
Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O. & Vanderplas, J. Scikit-learn: Machine learning in Python. Journal of machine learning research, 2011.
Pissaloux, E., Maybank, S. & Velázquez, R. On Image Matching and Feature Tracking for Embedded Systems: A State of the Art. In: A. Chatterjee, H. Nobahari & P. Siarry (Eds.), Advances in Heuristic Signal Processing and Applications, Springer-Verlag (Berlin-Heidelberg), 2013, pp. 357-380.
Sánchez, C., Rivera, M. & Velázquez, R. Robust multiband image segmentation method based on user clues, 2017 IEEE 37th Central America and Panama Convention (CONCAPAN XXXVII), Managua, 2017, pp. 1-6.
Santillana, A., Delgado-Mata, C., & Velázquez, R., Training a single-layer perceptron for an approximate edge detection on a digital image, 2011 International Conference on Technologies and Applications of Artificial Intelligence, Taiwan, pp. 189-193, 2011.
Tong, Y., Chen, R. & Cheng, Y. Facial expression recognition algorithm using lgc based on horizontal and diagonal prior principle. Optik-International Journal for Light and Electron Optics Vol. 125, 4186-4189, 2014.
Tsai, H.H. & Chang, Y.C. Facial expression recognition using a combination of multiple facial features and support vector machine, Soft Computing, 1-17, 2017.
Wang, S., Li, W., Wang, Y., Jiang, Y., Jiang, S. & Zhao, R. An improved difference of gaussian filter in face recognition, Journal of Multimedia, 6, 429-433, 2012.
Zhang, Z. & Zhang. J. A new real-time eye tracking for driver fatigue detection. ITS Telecommunications Proceedings, 8-11, 2011.
URL de la licencia: https://creativecommons.org/licenses/by/3.0/deed.es
Pistas Educativas está bajo la Licencia Creative Commons Atribución 3.0 No portada.
TECNOLÓGICO NACIONAL DE MÉXICO / INSTITUTO TECNOLÓGICO DE CELAYA
Antonio García Cubas Pte #600 esq. Av. Tecnológico, Celaya, Gto. México
Tel. 461 61 17575 Ext 5450 y 5146
pistaseducativas@itcelaya.edu.mx