Abstract
In this pilot study, a neural architecture for temporal emotion recognition from image sequences is proposed. The investigation aims at the development of key principles in an extendable experimental framework to study human emotions. Features representing temporal facial variations were extracted within a bounding box around the face that is segregated into regions. Within each region, the optical flow is tracked over time. The dense flow field in a region is subsequently integrated whose principal components were estimated as a representative velocity of face motion. For each emotion a Fuzzy ARTMAP neural network was trained by incremental learning to classify the feature vectors resulting from the motion processing stage. Single category nodes corresponding to the expected feature representation code the respective emotion classes. The architecture was tested on the Cohn-Kanade facial expression database.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Mase, K.: Human reader: A vision-based man-machine interface. In: Cipolla, R., Pentland, A. (eds.) Computer Vision for Human-Machine Interaction, pp. 53–81. Cambridge Univ. Press, Cambridge (1998)
Bascle, B., Blake, A., Morris, J.: Towards automated, real-time, facial animation. In: Cipolla, R., Pentland, A. (eds.) Computer Vision for Human-Machine Interaction, pp. 123–133. Cambridge Univ. Press, Cambridge (1998)
Essa, I.A., Pentland, A.P.: Facial expression recognition using a dynamic model and motion energy. In: ICCV, pp. 360–367 (1995)
Kanade, T., Cohn, J.F., Tian, Y.: Comprehensive database for facial expression analysis. In: Proc 5th IEEE Int. Conf. on Automatic Face & Gesture Recogn., France (2000)
Lucas, B.D., Kanade, R.: An iterative image registration technique with an application to stereo vision. In: Proc. 7th Int. J. Conf. on AI, pp. 674–679 (1981)
Carpenter, G.A., Grossberg, S., Markuzon, M., Reynolds, J.H., Rosen, D.B.: Fuzzy artmap: A neural network architecture for incremental supervised learning of analog multidimensional maps. IEEE Transactions on Neural Networks 3, 698–713 (1991)
Weiss, S.M., Kulikowski, C.A.: Computer Systems that learn, Classification and Prediction methods from Statistics, Neural Nets, Machine Learning and Expert Systems. Morgan Kaufmann Publishers, San Mateo (1991)
Bassili, J.: Facial motion in the perception of faces and of emotional expression. Journal of Experimental Psychology 4, 373–379 (1978)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Schweiger, R., Bayerl, P., Neumann, H. (2004). Neural Architecture for Temporal Emotion Classification. In: André, E., Dybkjær, L., Minker, W., Heisterkamp, P. (eds) Affective Dialogue Systems. ADS 2004. Lecture Notes in Computer Science(), vol 3068. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-24842-2_5
Download citation
DOI: https://doi.org/10.1007/978-3-540-24842-2_5
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-22143-2
Online ISBN: 978-3-540-24842-2
eBook Packages: Springer Book Archive