Cross-database evaluation for facial expression recognition
We present a system for facial expression recognition that is evaluated on multiple databases. Automated facial expression recognition systems face a number of characteristic challenges. Firstly, obtaining natural training data is difficult, especially for facial configurations expressing emotions like sadness or fear. Therefore, publicly available databases consist of acted facial expressions and are biased by the authors’ design decisions. Secondly, evaluating trained algorithms towards real-world behavior is challenging, again due to the artificial conditions in available image data. To tackle these challenges and since our goal is to train classifiers for an online system, we use several databases in our evaluation. Comparing classifiers across data-bases determines the classifiers capability to generalize more reliable than traditional self-classification.
KeywordsFacial expression recognition machine learning computer vision
Unable to display preview. Download preview PDF.
- 1.J. Ahlberg, “Candide-3 — an updated parameterized face,” Tech. Rep. LiTH-ISY-R-2326 (Linköping Univ., 2001).Google Scholar
- 2.K. Khnlenz, B. Radig, C. Mayer, and S. Sosnowski, “Towards robotic facial mimicry: system development and evaluation,” in Proc. Int. Symp. in Robot-Human Interactive Communication (Atlanta, 2011).Google Scholar
- 4.P. Ekman, “Universals and cultural differences in facial expressions of emotion,” in Proc. Nebraska Symp. on Motivation 1971, Ed. by J. Cole (Univ. Nebraska Press, Lincoln, NE, 1972), Vol. 19, pp. 207–283.Google Scholar
- 5.P. Ekman and W. Friesen, The Facial Action Coding System: A Technique for The Measurement of Facial Movement (Consulting Psychologists Press, San Francisco, 1978).Google Scholar
- 9.A. A. Livshin and X. Rodet, “The importance of cross database evaluation in musical instrument sound classification: a critical approach,” in Proc. Int. Symp. on Music Information Retrieval (ISMIR 2003) (Baltimore, 2003).Google Scholar
- 10.M. G. Frank, C. Lainscsek, I. R. Fasel, M. S. Bartlett, G. C. Littlewort, and J. R. Movellan, “Automatic recognition of facial actions in spontaneous expressions,” J. Multimedia 1(6) (2006).Google Scholar
- 11.C. Mayer, M. Wimmer, F. Stulp, Z. Riaz, A. Roth, M. Eggers, and B. Radig, “A real time system for model-based interpretation of the dynamics of facial expressions,” in Proc. Int. Conf. on Face and Gesture Recognition (Amsterdam, 2008).Google Scholar
- 12.M. Pantic, M. F. Valstar, R. Rademaker, and L. Maat, “Web-based database for facial expression analysis,” in Proc. IEEE Int. Conf. Multmedia and Expo (ICME’05) (Amsterdam, 2005).Google Scholar
- 17.F. Wallhoff, The Feedtum Database (2006). http://cotesys.mmk.etechnik.tu-muenchen.de/isg/content/feeddatabase. [Accessed June 13, 2011].Google Scholar
- 18.P. Watzlawick, J. B. Bavelas, and D. D. Jackson, Pragmatics of Human Communication: A Study of Interactional Patterns, Pathologies, and Paradoxes (W. W. Norton and Co, New York, 1967).Google Scholar