Abstract
The problem of isometry-invariant representation and comparison of surfaces is of cardinal importance in pattern recognition applications dealing with deformable objects. Particularly, in three-dimensional face recognition treating facial expressions as isometries of the facial surface allows to perform robust recognition insensitive to expressions.
Isometry-invariant representation of surfaces can be constructed by isometrically embedding them into some convenient space, and carrying out the comparison in that space. Presented here is a discussion on isometric embedding into \(\mathbb{S}^{\rm 3}\), which appears to be superior over the previously used Euclidean space in sense of the representation accuracy.
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
Bronstein, A., Bronstein, M., Kimmel, R.: Expression-invariant 3D face recognition. In: Proc. Audio and Video-based Biometric Person Authentication, pp. 62–69 (2003)
Bronstein, A., Bronstein, M., Kimmel, R.: Three-dimensional face recognition. Technical Report CIS-2004-04, Dept. of Computer Science, Technion, Israel (2004)
Elad, A., Kimmel, R.: Bending invariant representations for surfaces. In: Proc. CVPR, pp. 168–174 (2001)
Schwartz, E.L., Shaw, A., Wolfson, E.: A numerical solution to the general- ized mapmaker’s problem: attening nonconvex polyhedral surfaces. IEEE Trans. PAMI 11, 1005–1008 (1989)
Grossman, R., Kiryati, N., Kimmel, R.: Computational surface attening: a voxel-based approach. IEEE Trans. PAMI 24(4), 433–441 (2002)
Zigelman, G., Kimmel, R., Kiryati, N.: Texture mapping using surface attening via multi-dimensional scaling. IEEE Trans. Visualization and computer graphics 9(2), 198–207 (2002)
Elad, A., Kimmel, R.: Spherical attening of the cortex surface. In: Malladi, R. (ed.) Geometric methods in bio-medical image processing, vol. 2191, pp. 77–89. Springer, Heidelberg (2002)
Walter, J., Ritter, H.: On interactive visualization of high-dimensional data using the hyperbolic plane. In: Proc. ACM SIGKDD Int. Conf. Knowledge Discovery and Data Mining (2002)
Bronstein, A., Bronstein, M., Gordon, E., Kimmel, R.: Fusion of 3D and 2D information in face recognition. In: Proc. ICIP (2004) (to appear)
Borg, I., Groenen, P.: Modern multidimensional scaling - theory and applications. Springer, Heidelberg (1997)
Bronstein, A., Bronstein, M., Gordon, E., Kimmel, R.: High-resolution structured light range scanner with automatic calibration. Technical Report CIS-2003-06, Dept. of Computer Science, Technion, Israel (2003)
Sethian, J.A.: A review of the theory, algorithms, and applications of level set method for propagating surfaces. Acta numerica, 309–395 (1996)
Kimmel, R., Sethian, J.A.: Computing geodesic on manifolds. In: Proc. US National Academy of Science, vol. 95, pp. 8431–8435 (1998)
Spira, A., Kimmel, R.: An efficient solution to the eikonal equation on parametric manifolds. Interfaces and Free Boundaries (2004) (to appear)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Bronstein, A.M., Bronstein, M.M., Kimmel, R. (2005). Isometric Embedding of Facial Surfaces into \(\mathbb{S}^{\rm 3}\) . In: Kimmel, R., Sochen, N.A., Weickert, J. (eds) Scale Space and PDE Methods in Computer Vision. Scale-Space 2005. Lecture Notes in Computer Science, vol 3459. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11408031_53
Download citation
DOI: https://doi.org/10.1007/11408031_53
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-25547-5
Online ISBN: 978-3-540-32012-8
eBook Packages: Computer ScienceComputer Science (R0)