Hostname: page-component-78c5997874-4rdpn Total loading time: 0 Render date: 2024-11-08T17:33:17.382Z Has data issue: false hasContentIssue false
  • English
  • Français

Principal component analysis for Riemannian manifolds, with an application to triangular shape spaces

Part of: Multivariate analysis Global differential geometry Geometric probability and stochastic geometry

Published online by Cambridge University Press:  01 July 2016

Stephan Huckemann  and
Herbert Ziezold
Stephan Huckemann*
Affiliation:
University of Kassel
Herbert Ziezold*
Affiliation:
University of Kassel
*
∗ Postal address: Department of Mathematics, University of Kassel, D-34109 Kassel, Germany.
∗ Postal address: Department of Mathematics, University of Kassel, D-34109 Kassel, Germany.
Rights & Permissions [Opens in a new window]

Abstract

Core share and HTML view are not available for this content. However, as you have access to this content, a full PDF is available via the ‘Save PDF’ action button.

Classical principal component analysis on manifolds, for example on Kendall's shape spaces, is carried out in the tangent space of a Euclidean mean equipped with a Euclidean metric. We propose a method of principal component analysis for Riemannian manifolds based on geodesics of the intrinsic metric, and provide a numerical implementation in the case of spheres. This method allows us, for example, to compare principal component geodesics of different data samples. In order to determine principal component geodesics, we show that in general, owing to curvature, the principal component geodesics do not pass through the intrinsic mean. As a consequence, means other than the intrinsic mean are considered, allowing for several choices of definition of geodesic variance. In conclusion we apply our method to the space of planar triangular shapes and compare our findings with those of standard Euclidean principal component analysis.

Keywords

Shape analysisprincipal component analysisRiemannian manifoldgeodesic

MSC classification

Primary: 60D05: Geometric probability and stochastic geometry
Secondary: 62H11: Directional data; spatial statistics 53C22: Geodesics
Type
Stochastic Geometry and Statistical Applications
Information
Advances in Applied Probability , Volume 38 , Issue 2 , June 2006 , pp. 299 - 319
Copyright
Copyright © Applied Probability Trust 2006 

References

Bookstein, F. L. (1991). Morphometric Tools for Landmark Data: Geometry and Biology. Cambridge University Press.Google Scholar
Cootes, T. F., Taylor, C. J., Cooper, D. H. and Graham, J. (1992). Training models of shape from sets of examples. In Proc. British Mach. Vision Conf., eds Hogg, D. C. and Boyle, R. D., Springer, Berlin, pp. 9–18.Google Scholar
Dryden, I. L. and Mardia, K. V. (1998). Statistical Shape Analysis. Wiley, Chichester.Google Scholar
Ducham, T. and Stuetzle, W. (1996). Extremal properties of principal curves in the plane. Ann. Statist. 24, 1511–1520.Google Scholar
Fletcher, P. T., Joshi, S., Lu, C. and Pizer, S. (2004). Gaussian distributions on Lie groups and their applications to statistical shape analysis. Preprint.Google Scholar
Fletcher, P. T., Lu, C. and Joshi, S. (2003). Statistics of shapes via principal geodesic analysis on Lie groups. Proc. Computer Vision and Pattern Recognition 2003, Vol. 1, IEEE, Piscataway, NJ, pp. 95–101.Google Scholar
Goodall, C. R. and Lange, N. (1998). Growth curve models for correlated triangular shapes. In Proc. 21st INTERFACE Symp., Interface Foundation, Fairfax Station, VA, pp. 445–454.Google Scholar
Gower, J. C. (1975). Generalized Procrustes analysis. Psychometrika 40, 33–51.Google Scholar
Karcher, H. (1977). Riemannian center of mass and mollifier smoothing. Commun. Pure Appl. Math. 30, 509–541.Google Scholar
Kendall, D. G., Barden, D., Carne, T. K. and Le, H. (1999). Shape and Shape Theory. Wiley, Chichester.Google Scholar
Kent, J. T. (1994). The complex Bingham distribution and shape analysis. J. R. Statist. Soc. B 56, 285–299.Google Scholar
Klassen, E., Srivastava, A., Mio, W. and Joshi, S. H. (2004). Analysis of planar shapes using geodesic paths on shape spaces. IEEE Trans. Pattern Anal. Mach. Intellig. 26, 372–383.Google Scholar
Kobayashi, S. and Nomizu, K. (1969). Foundations of Differential Geometry, Vol. II. Wiley-Interscience, New York.Google Scholar
Kume, A. and Le, H. (2003). On Fréchet means in simplex shape space. Adv. Appl. Prob. 35, 885–897.Google Scholar
Le, H. (2001). Locating Fréchet means with application to shape spaces. Adv. Appl. Prob. 33, 324–338.Google Scholar
Le, H. and Barden, D. (2001). On simplex shape spaces. J. London Math. Soc. 64, 501–512.Google Scholar
Le, H. and Kume, A. (2000). Detection of shape changes in biological features. J. Microscopy 200, 140–147.Google Scholar
Le, H. and Small, C. G. (1999). Multidimensional scaling of simplex shapes. Pattern Recognition 32, 1601–1613.Google Scholar
Nash, J. (1956). The imbedding problem for Riemannian manifolds. Ann. Math. 63, 20–63.CrossRefGoogle Scholar
Small, C. G. (1996). The Statistical Theory of Shape. Springer, New York.Google Scholar
Ziezold, H. (1977). On expected figures and a strong law of large numbers for random elements in quasi-metric spaces. In Trans. 7th Prague Conf. Inf. Theory, Statist. Decision Functions, Random Process., Vol. A, Reidel, Dordrecht, pp. 591–602.Google Scholar
Ziezold, H. (1994). Mean figures and mean shapes applied to biological figure and shape distributions in the plane. Biometrical J.. 36, 491–510.Google Scholar