Abstract
The capability of replicating experiments and comparing results is a basic premise for scientific progress. Thus, it is imperative that the conduction of validation experiments follow transparent methodological steps and be also reported in a clear way to allow accurate replication and fair comparison between results. In 3D facial expression recognition, the presented results are estimates of performance of a classification system and, therefore, have an intrinsic degree of uncertainty. Because of that, the reliability of a measure for evaluation is directly related to the concept of stability. In this work, we examine the experimental setup reported by a set of 3D facial expression recognition studies published from 2013 to 2018. This investigation revealed that the concern with stability of mean recognition rates is present in only a small portion of studies. In addition, it demonstrates that the highest rates in this domain are also, potentially, the most unstable. Those findings lead to a reflection on the fairness of comparisons in this domain.
This study was financed in part by the Coordenação de Aperfeiçoamento de Pessoal de Nível Superior - Brasil (CAPES) - Finance Code 001.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
- 2.
- 3.
For the complete list of those studies, please see the supplementary material available in https://goo.gl/JUP1cM.
References
Azazi, A., Lebai Lutfi, S., Venkat, I., Fernández-Martínez, F.: Towards a robust affect recognition: automatic facial expression recognition in 3D faces. Expert Syst. Appl. 42(6), 3056–3066 (2015). https://doi.org/10.1016/j.eswa.2014.10.042
Azazi, A., Lutfi, S.L., Venkat, I.: Analysis and evaluation of SURF descriptors for automatic 3D facial expression recognition using different classifiers. In: 2014 4th World Congress on Information and Communication Technologies, WICT 2014, pp. 23–28. IEEE, December 2014. https://doi.org/10.1109/WICT.2014.7077296
Gong, B., Wang, Y., Liu, J., Tang, X.: Automatic facial expression recognition on a single 3D face by exploring shape deformation. In: ACM International Conference on Multimedia, pp. 569–572 (2009)
Bousquet, O., Elisseeff, A.: Stability and generalization. J. Mach. Learn. Res. 2(3), 499–526 (2002). https://doi.org/10.1162/153244302760200704
Duda, R.O., Hart, P.E., Stork, D.G.: Algorithm-independent machine learning. In: Pattern Classification, pp. 453–516. Wiley, New York (2012). Chap. 9
Jan, A., Meng, H.: Automatic 3D facial expression recognition using geometric and textured feature fusion. In: 2015 11th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (FG), vol. 05, pp. 1–6. IEEE, May 2015. https://doi.org/10.1109/FG.2015.7284860
Lemaire, P., Ardabilian, M., Chen, L., Daoudi, M.: Fully automatic 3D facial expression recognition using differential mean curvature maps and histograms of oriented gradients. In: 2013 10th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (FG). pp. 1–7. IEEE, April 2013. https://doi.org/10.1109/FG.2013.6553821. http://ieeexplore.ieee.org/document/6553821/
Li, H., Sun, J., Xu, Z., Chen, L.: Multimodal 2D+3D facial expression recognition with deep fusion convolutional neural network. IEEE Trans. Multimed. 19(12), 2816–2831 (2017). https://doi.org/10.1109/TMM.2017.2713408
Li, H., et al.: An efficient multimodal 2D + 3D feature-based approach to automatic facial expression recognition. Comput. Vis. Image Underst. 140(C), 83–92 (2015). https://doi.org/10.1016/j.cviu.2015.07.005
Li, Q., An, G., Ruan, Q.: 3D Facial expression recognition using orthogonal tensor marginal fisher analysis on geometric maps. In: 2017 International Conference on Wavelet Analysis and Pattern Recognition (ICWAPR), vol. 35, pp. 65–71. IEEE, July 2017. https://doi.org/10.1109/ICWAPR.2017.8076665
Li, X., Ruan, Q., An, G.: 3D facial expression recognition using delta faces. In: 5th IET International Conference on Wireless, Mobile and Multimedia Networks (ICWMMN 2013), pp. 234–239. Institution of Engineering and Technology (2013). https://doi.org/10.1049/cp.2013.2415
Li, X., Ruan, Q., An, G., Jin, Y., Zhao, R.: Multiple strategies to enhance automatic 3D facial expression recognition. Neurocomputing 161(C), 89–98 (2015). https://doi.org/10.1016/j.neucom.2015.02.063
Savran, A., et al.: Bosphorus database for 3D face analysis. In: Schouten, B., Juul, N.C., Drygajlo, A., Tistarelli, M. (eds.) BioID 2008. LNCS, vol. 5372, pp. 47–56. Springer, Heidelberg (2008). https://doi.org/10.1007/978-3-540-89991-4_6
Yang, X., Huang, D., Wang, Y., Chen, L.: Automatic 3D facial expression recognition using geometric scattering representation. In: 2015 11th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (FG), pp. 1–6. IEEE, May 2015. https://doi.org/10.1109/FG.2015.7163090
Yin, L., Wei, X., Sun, Y., Wang, J., Rosato, M.J.: A 3D facial expression database for facial behavior research. In: FGR 2006: Proceedings of the 7th International Conference on Automatic Face and Gesture Recognition 2006, pp. 211–216 (2006). https://doi.org/10.1109/FGR.2006.6
Zeng, W., Li, H., Chen, L., Morvan, J.M., Gu, X.D.: An automatic 3D expression recognition framework based on sparse representation of conformal images. In: 2013 10th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (FG), pp. 1–8. IEEE, April 2013. https://doi.org/10.1109/FG.2013.6553749
Zhen, Q., Huang, D., Wang, Y., Chen, L.: Muscular movement model-based automatic 3D/4D facial expression recognition. IEEE Trans. Multimed. 18(7), 1438–1450 (2016). https://doi.org/10.1109/TMM.2016.2557063
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Alexandre, G.R., Thé, G.A.P., Soares, J.M. (2019). Reliability of Results and Fairness in the Comparison of Rates Among 3D Facial Expression Recognition Works. In: Vento, M., Percannella, G. (eds) Computer Analysis of Images and Patterns. CAIP 2019. Lecture Notes in Computer Science(), vol 11678. Springer, Cham. https://doi.org/10.1007/978-3-030-29888-3_31
Download citation
DOI: https://doi.org/10.1007/978-3-030-29888-3_31
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-29887-6
Online ISBN: 978-3-030-29888-3
eBook Packages: Computer ScienceComputer Science (R0)