FOOD PRODUCT ACCEPTANCE AND PREFERENCE PREDECTION THROUGH AUTOMATED FACIAL EXPRESSION ANALYSIS (MEDICIÓN DE ACEPTACIÓN Y PREFERENCIA DE PRODUCTOS ALIMENTICIOS MEDIANTE ANÁLISIS AUTOMATIZADO DE EXPRESIONES FACIALES)
Resumen
Resumen
Se presenta un sistema para determinar la aceptación y las preferencias de usuarios en productos alimenticios a través del reconocimiento de emociones. Los cambios en expresiones faciales de 80 sujetos mientras probaban cinco distintos productos alimenticios fueron capturados con el sensor Microsoft Kinect. Las expresiones faciales se contrastaron con las evaluaciones sensoriales de los consumidores. Para el reconocimiento de expresiones faciales en cada cuadro del video, se entrenó una red neuronal y se utilizaron diferentes técnicas de aprendizaje supervisado (como máquinas de soporte vectorial, perceptrón multicapa y árboles de regresión) para determinar que sabores podrían ser aceptados y rechazados por el consumidor. Se decidió utilizar la red neuronal, y al observar la matriz de confusión se obtiene un porcentaje de reconocimiento adecuado para las siguientes emociones: neutral 94%, sorpesa 98%, felicidad 99% y disgusto 94%. La aplicación industrial es relevante en el sector de Investigación y Desarrollo de la industria de alimentos.
Palabras Claves: aceptación de consumidores, análisis sensorial, aprendizaje de máquina, expresiones faciales, Kinect, visualización.
Abstract
This paper presents a system for determining consumer acceptance and preferences of food products through emotion recognition. Changes in facial expressions of 80 test subjects while tasting five different food samples were captured using the Microsoft Kinect sensor. The expressions were compared to the consumers’ sensory evaluations. To determine the facial expressions in every video frame, a neural network was trained and different supervised learning techniques (such as support vector machines, multilayer perceptron and regression trees) were used to predict which of the different tastes could be accepted or rejected. A neuronal net was used, when observing the confusion matrix a percentage of adequate recognition was obtained for the following emotions: neutral (94%), surprise (98%), happiness (99%) and disgust (94%). The industrial application of the proposed system is relevant for the Food Industry Research and Development (R&D) by allowing the sampling of a product by potential consumers and analyzing their emotions before launching into market.
Keywords: consumer’s acceptance, sensory analysis, facial expressions, Kinect, machine learning, visualization.
Texto completo:
185-200 PDFReferencias
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.
Alvarez, V.M., Sánchez, C.N., Gutiérrez, S., Domínguez-Soberanes, J. & Velázquez, R. Facial emotion recognition: a comparison of different landmark-based classifiers, 2018 International Conference on Research in Intelligent and Computing in Engineering (RICE), San Salvador, 2018, pp. 1-4.
Crist, C.A., Duncan, S.E., Arnade, E.A., Leitch, L.A., O'Keefe, S.F. & Gallagher, D.L. Automated facial expression analysis for emotional responsivity using an aqueous bitter model, Food Quality and Preference, Vol. 68, 349-359, 2018.
Danner, L., Haindl, S. Joechl, M. & Duerrschmid, K., Facial expressions and autonomous nervous system responses elicited by tasting different juices, Food Research International, Vol. 64, 81-90, 2014.
Donato, G., Bartlett, M.S., Hager, J.C., Ekman, P. & Sejnowski, T.J.,
Classifying facial actions, IEEE Trans. Pattern Anal. Mach. Intell., vol. 21, no. 10, 974–989, 1999.
He, W., Boesveldt, S., de Graaf, C. & de Wijk, R. A. The relation between continuous and discrete emotional responses to food odors with facial expressions and non-verbal reports, Food Quality and Preference, Vol.48, 130-137, 2016.
Juodeikiene, G., Basinskiene, L., Vidmantiene, D., Klupsaite, D. & Bartkiene, E. The use of face reading technology to predict consumer acceptance of confectionery products, 9th Baltic Conference on Food Science and Technology, Latvia, 276-279, 2014.
Jung, H., Lee, S., Yim, J., Park, S., & Kim, J. Joint fine-tuning in deep neural networks for facial expression recognition. In Proceedings of the IEEE international conference on computer vision (pp. 2983-2991), 2015.
Kazemi, V. & Sullivan, J., One millisecond face alignment with an ensemble of regression trees, IEEE Conference on Computer Vision and Pattern Recognition, Columbus, OH, 1867-1874, 2014.
King, D.E., “Dlib-ml: A Machine Learning Toolkit, Journal of Machine Learning Research, Vol. 10, 1755-1758, 2009.
Köster, E. P. Diversity in the determinants of food choice: A psychological perspective, Food Quality and Preference, Vol. 20, No. 2, 70-82, 2009.
Kostyra, E., Rambuszek, M., Waszkiewicz-Robak, B., Laskowski, W., Blicharski, T. & Poławska, E. Consumer facial expression in relation to smoked ham with the use of face reading technology. The methodological aspects and informative value of research results, Meat Sci., vol. 119, 22–31, 2016.
Lagast,S., Gellynck, X., Schouteten, J.J., De Herdt, V. & De Steur, H., Consumers’ emotions elicited by food: A systematic review of explicit and implicit methods, Trends in Food Science & Technology, Vol. 69, Part A, 172-189, 2017.
Leitch, K.A., Duncan, S.E., O'Keefe, S., Rudd, R. & Gallagher, D.L., Characterizing consumer emotional response to sweeteners using an emotion terminology questionnaire and facial expression analysis, Food Research International, Vol. 76, Part 2, 283-292, 2015.
Liu, M., Li, S. Shan, S. Wang, R. & Chen, X. Deeply learning deformable facial action parts model for dynamic expression analysis. In ACCV, 2014, pages 1749–1756. IEEE, 2014.
Littlewort, G. et al., “The computer expression recognition toolbox (CERT), 2011 IEEE International Conference on Automatic Face and Gesture Recognition and Workshops, 298–305, 2011.
Lucey, P., Cohn, J.F., Kanade,T, Saragih, J., Ambadar, Z. and 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, San Francisco, CA, USA, 94-101, 2010.
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.
Rozin, P. & Fallon, A.E. A perspective on disgust, Psychological Review, vol. 94, No. 1, 23-41, 1987.
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.
Sekhon, B.S. Food nanotechnology –an overview, Nanotechnology, science and applications, Vol. 3, 1-15, 2010.
Walsh, A.M., Duncan, S.E., Bell, M.A., O’Keefe, S.F. & Gallagher, D. L. Integrating implicit and explicit emotional assessment of food quality and safety concerns, Food Quality and Preference, Vol. 56, 212-224, 2017.
Wendin, K., Allesen-Holm, B.H. & Bredie, W. L., Do facial reactions add new dimensions to measuring sensory responses to basic tastes?. Food quality and preference, Vol. 22, No. 4, 346-354, 2011.
Zeng, N., Zhang, H., Song, B., Liu, W., Li, Y., & Dobaie, A. M. Facial expression recognition via learning deep sparse autoencoders. Neurocomputing, 273, 643-649, 2018
Zhi, R., Wan, R., Zhang, D. & Li, W., Correlation between hedonic liking and facial expression measurement using dynamic affective response representation, Food Research International, Vol. 108, 237-245, 2018.
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