Abstract
It has recently been shown that the facial expression space as a psychophysical image space is a Riemann space where the metric tensor is defined by the JND (Just-Noticeable-Difference) discrimination thresholds at every point in the space. The major obstacle to understand this space is how to estimate the metric tensor in high dimensions which requires an inaccessible number of psychophysical experiments. In this paper we address two fundamental issues: methods to estimate the Riemann metric tensor in a high dimensional space and how to define and to determine the effective dimensions of Riemann spaces and psychophysical spaces. We introduce new definitions for these dimensions and novel algorithms for estimating the high dimensional Riemann metric tensor and for dimension reduction to low dimensional subspaces. We then apply these algorithms to the facial expressions space. The Riemann metric tensor of the high dimensional facial expression space is estimated from psychophysical measurements of JND data. We apply these methods to investigate the facial expression space. We describe our experiments to estimate the effective dimension (together with upper and lower bounds) of Riemann manifolds and psychophysical spaces.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Kambhatla, N., Leen, T.K.: Dimension reduction by local principal component analysis. Neural Comput. 9(7), 1493–1516 (1997)
Richardson, M.W.: Multidimensional psychophysics. Psychol. Bull. 35(9), 659–660 (1938)
Tenenbaum, J.B., De Silva, V., Langford, J.C.: A global geometric framework for nonlinear dimensionality reduction. Science 290(5500), 2319–2323 (2000)
Gorban, A.: Principal Manifolds for Data Visualization and Dimension Reduction. Springer, Heidelberg (2007). https://doi.org/10.1007/978-3-540-73750-6
Ma, Y., Fu, Y.: Manifold Learning Theory and Applications. CRC Press, Boca Raton (2011)
Goh, A.: Riemann manifold clustering and dimension reduction for vision-based analysis. In: Wang, L., Zhao, G., Cheng, L., Pietikäinen, M. (eds.) Machine Learning for Vision-Based Motion Analysis, pp. 27–53. Springer, London (2011). https://doi.org/10.1007/978-0-85729-057-1_2
Brun, A., Westin, C.-F., Herberthson, M., Knutsson, H.: Fast manifold learning based on Riemannian normal coordinates. In: Kalviainen, H., Parkkinen, J., Kaarna, A. (eds.) SCIA 2005. LNCS, vol. 3540, pp. 920–929. Springer, Heidelberg (2005). https://doi.org/10.1007/11499145_93
Lin, T., Zha, H.: Riemannian manifold learning. IEEE Trans. Pattern Anal. Mach. Intell. 30(5), 796–809 (2008)
Ekman, P., Friesen, W.V.: Facial Action Coding System: A Technique for the Measurement of Facial Movement. Consulting Psychologists Press, Palo Alto (1978)
Russell, J.A., Bullock, M.: Multidimensional scaling of emotional facial expressions: similarity from preschoolers to adults. J. Pers. Soc. Psychol. 48(5), 1290–1298 (1985)
Young, A.W., Rowland, D., Calder, A.J., et al.: Facial expression megamix: test of dimensional and category accounts of emotion recognition. Cognition 63(3), 271–313 (1997)
Calder, A.J., Burton, A.M., Miller, P., Young, A.W., Akamatsu, S.: A principal component analysis of facial expressions. Vision Res. 41(9), 1179–1208 (2001)
Benitez-Quiroz, C., Srinivasan, R., Martinez, A.M.: EmotioNet: an accurate, real-time algorithm for the automatic annotation of a million facial expressions in the wild. In: Proceedings of IEEE-CVPR (2016)
3DScanStore. https://www.3dscanstore.com/. Accessed 2 Feb 2020
Sumiya, R., Lenz, R., Chao, J.: Measurement of JND thresholds and Riemannian geometry in facial expression space. In: Kurosu, M. (ed.) HCI 2018. LNCS, vol. 10901, pp. 453–464. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-91238-7_37
Sumiya, R., Chao, J.: Transform facial expression space to Euclidean space using Riemann normal coordinates and its applications. In: Kurosu, M. (ed.) HCII 2019. LNCS, vol. 11567, pp. 168–178. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-22643-5_13
Shinto, M., Chao, J.: How to compare and exchange facial expression perceptions between different individuals with Riemann geometry. In: Kurosu, M. (ed.) HCII 2019. LNCS, vol. 11567, pp. 155–167. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-22643-5_12
MacAdam, D.L.: Visual sensitivities to color differences in daylight. JOSA 32, 247–273 (1942)
Brown, W., MacAdam, D.: Visual sensitivities to combined chromaticity and luminance differences. JOSA 39, 808–823 (1949)
Chao, J., Lenz, R., Matsumoto, D., Nakamura, T.: Riemann geometry for color characterization and mapping. In: Conference on Colour in Graphics, Imaging, and Vision, IS&T, pp. 277–282 (2008)
Chao, J., Osugi, I., Suzuki, M.: On definitions and construction of uniform color space. In: CGIV, IS&T, pp. 55–60 (2004)
Suzuki, M., Chao, J.: On construction of uniform color spaces. IEICE Trans. Fundam. E85-A(9), 2097–2106 (2002)
Ohshima, S., Mochizuki, R., Chao, J., Lenz, R.: Color reproduction using Riemann normal coordinates. In: Trémeau, A., Schettini, R., Tominaga, S. (eds.) CCIW 2009. LNCS, vol. 5646, pp. 140–149. Springer, Heidelberg (2009). https://doi.org/10.1007/978-3-642-03265-3_15
Mochizuki, R., Kojima, T., Lenz, R., Chao, J.: Color-weak compensation using local affine isometry based on discrimination threshold matching. JOSA 32(11), 2093–2103 (2015)
Oshima, S., Mochizuki, R., Lenz, R., Chao, J.: Modeling, measuring, and compensating color weak vision. IEEE Trans. Image Process. 25(6), 2587–2600 (2016)
Tasaki, H., Lenz, R., Chao, J.: Simplex-based dimension estimation of topological manifolds. In: Proceedings of ICPR, pp. 3598–3603. IEEE (2016)
Tasaki, H., Lenz, R., Chao, J.: Dimension estimation and topological manifold learning. In: Proceedings of IJCNN, Budapest, 14–19 July 2019. IEEE (2019)
Do Carmo, M.P.: Riemannian Geometry. GTM, vol. 171. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-26654-1_9
Petersen, P.: Riemannian Geometry. GTM, 3rd edn. Springer, New York (2006). https://doi.org/10.1007/978-3-319-26654-1
Acknowledgment
This research is supported by the MIC/SCOPE #181603006.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Shinto, M., Lenz, R., Chao, J. (2021). Definition and Estimation of Dimension in Facial Expression Space. In: Kurosu, M. (eds) Human-Computer Interaction. Theory, Methods and Tools. HCII 2021. Lecture Notes in Computer Science(), vol 12762. Springer, Cham. https://doi.org/10.1007/978-3-030-78462-1_47
Download citation
DOI: https://doi.org/10.1007/978-3-030-78462-1_47
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-78461-4
Online ISBN: 978-3-030-78462-1
eBook Packages: Computer ScienceComputer Science (R0)