Abstract
In elastic shape analysis, a representation of a shape is invariant to translation, scaling, rotation, and reparameterization, and important problems such as computing the distance and geodesic between two curves, the mean of a set of curves, and other statistical analyses require finding a best rotation and reparameterization between two curves. In this paper, we focus on this key subproblem and study different tools for optimizations on the joint group of rotations and reparameterizations. We develop and analyze a novel Riemannian optimization approach and evaluate its use in shape distance computation and classification using two public datasets. Experiments show significant advantages in computational time and reliability in performance compared to the current state-of-the-art method. A brief version of this paper can be found in Huang et al. (Proceedings of the 21st International Symposium on Mathematical Theory of Networks and Systems 2014).
Similar content being viewed by others
References
Absil, P.-A., Mahony, R., Sepulchre, R.: Optimization Algorithms on Matrix Manifolds. Princeton University Press, Princeton, NJ (2008)
Baker, C.G.: Riemannian manifold trust-region methods with applications to eigenproblems. PhD thesis, Florida State University, Department of Computational Science (2008)
Bertsekas, D.P.: Dynamic Programming and Optimal Control. Athena Scientific, Belmont (1995)
Dryden, I.L., Mardia, K.V.: Statistical Shape Analysis. Wiley, Chichester (1998)
Huang, W., Absil, P.-A., Gallivan, K.A.: A Riemannian symmetric rank-one trust-region method. Math. Progr. 150(2), 179–216 (2015)
Huang, W., Gallivan, K.A., Absil, P.-A.: A broyden class of quasi-Newton methods for Riemannian optimization. SIAM J. Optim. 25(3), 1660–1685 (2015)
Huang, W., Gallivan, K.A., Srivastava, A., Absil, P.-A.: Riemannian optimization for elastic shape analysis. In: Proceedings of the 21st International Symposium on Mathematical Theory of Networks and Systems (2014)
Huang, W.: Optimization algorithms on Riemannian manifolds with applications. PhD thesis, Florida State University, Department of Mathematics (2013)
Huang, W., You, Y., Gallivan, K., Absil, P.-A.: Karcher mean in elastic shape analysis. In: Drira, H., Kurtek, S., Turaga, P. (eds.). Proceedings of the 1st International Workshop on Differential Geometry in Computer Vision for Analysis of Shapes, Images and Trajectories, pp. 2.1–2.11. BMVA Press (September 2015)
Kendall, D.G.: Shape manifolds, procrustean metrics, and complex projective spaces. Bull. Lond. Math. Soc. 16(2), 81–121 (1984)
Klassen, E., Srivastava, A., Mio, W., Joshi, S.H.: Analysis of planar shapes using geodesic paths on shape spaces. IEEE Trans. Pattern Anal. Mach. Intell. 26(3), 372–383 (2004). doi:10.1109/TPAMI.2004.1262333
Lahiri, S., Robinson, D., Klassen, E.: Precise matching of PL curves in \(\mathbb{R}^{n}\) in the square root velocity framework, pp. 1–41 (January 2015). arXiv:1501.00577
O’Neill, B.: Semi-Riemannian Geometry. Academic Press Incorporated (Harcourt Brace Jovanovich Publishers), New York (1983)
Qi, C.: Numerical optimization methods on Riemannian manifolds. PhD thesis, Florida State University, Department of Mathematics (2011)
Ring, W., Wirth, B.: Optimization methods on Riemannian manifolds and their application to shape space. SIAM J. Optim. 22(2), 596–627 (2012). doi:10.1137/11082885X
Srivastava, A., Klassen, E., Joshi, S.H., Jermyn, I.H.: Shape analysis of elastic curves in Euclidean spaces. IEEE Trans. Pattern Anal. Mach. Intell. 33(7), 1415–1428 (2011). doi:10.1109/TPAMI.2010.184
Sebastian, T.B., Klein, P.N., Kimia, B.B.: On aligning curves. IEEE Trans. Pattern Anal. Mach. Intell. 25(1), 116–125 (2003). doi:10.1109/TPAMI.2003.1159951
Temple University. Shape similarity research project. www.dabi.temple.edu/~shape/MPEG7/dataset.html
Wu, S.G., Bao, F.S., Xu, E.Y., Wang, Y.-X., Chang, Y.-F., Xiang, Q.-L.: A leaf recognition algorithm for plant classification using probabilistic neural network. In: 2007 IEEE International Symposium on Signal Processing and Information Technology, pp. 11–16 (2007). arXiv:0707.4289v1
You, Y., Huang, W., Gallivan, K.A., Absil, P.-A.: A Riemannian approach for computing geodesics in elastic shape analysis. In: 3rd IEEE Global Conference on Signal and Information Processing (December 2015). To appear
Younes, L., Michor, P., Shah, J., Mumford, D.: A metric on shape space with explicit geodesics. Rendiconti Lincei - Matematica e Applicazioni 9(1), 25–57 (2008). doi:10.4171/RLM/506
Younes, L.: Computable elastic distances between shapes. SIAM J. Appl. Math. 58(2), 565–586 (1998). doi:10.1137/S0036139995287685
Acknowledgments
The authors are grateful to three anonymous referees for the careful reading and helpful comments and suggestions especially, for the suggestion by one referee to include the discussion of the nonuniform-grid Coordinate Descent algorithm.
Author information
Authors and Affiliations
Corresponding author
Appendix: Proofs
Appendix: Proofs
Proof of Theorem 1
Proof
By definition, for any \(\tilde{q} \in [q]_{{{\mathrm{\mathrm {SO}}}}(n) \times {\varGamma }_s^o}\), there exist \(\tilde{O} \in {{\mathrm{\mathrm {SO}}}}(n)\) and \(\tilde{\gamma } \in {\varGamma }_s^o\) such that \(\tilde{q} = \tilde{O} (q, \tilde{\gamma })\). It follows from [12, Lemma11] that there exists a sequence \(\{\gamma _i\} \subset {\varGamma }^o\) such that \((q, \gamma _i) \rightarrow (q, \tilde{\gamma })\) with respect to the \(\mathbb {L}^2\) metric. Since \({{\mathrm{\mathrm {SO}}}}(n)\) is isometric for \(\mathbb {L}^2\), we have \(\tilde{O} (q, \gamma _i) \rightarrow \tilde{O} (q, \tilde{\gamma })\), which implies that \(\tilde{q} \in \overline{[q]}\). Therefore, we obtain \([q]_{{{\mathrm{\mathrm {SO}}}}(n) \times {\varGamma }_s^o} \subseteq \overline{[q]}\). We finished proving the first statement.
For any \(v \in \overline{[q]}\), there is a sequence of \(\{O_i\}\) and \(\{\gamma _i\}\) such that \(O_i (q, \gamma _i) \rightarrow v\) with respect to the \(\mathbb {L}^2\) metric. Since \({{\mathrm{\mathrm {SO}}}}(n)\) is a compact set, there exists a convergent subsequence of \(\{O_i\}\), i.e., \(\{O_{i_j}\} \subseteq \{O_i\}\) and \(O_{i_j} \rightarrow \tilde{O}\) with respect to 2-norm. Let \(\tilde{q}\) denote \(\tilde{O}^T v\). It follows that \(O_{i_j} (q, \gamma _{i_j}) \rightarrow \tilde{O} \tilde{q}\). We have
It follows that
which implies \((q, \gamma _{i_j}) \rightarrow \tilde{q}\). Since \(q^{-1}(0_n)\) has measure zero, it follows from [12, Corollary 3] that there exists \(\tilde{\gamma } \in {\varGamma }_s^o\) such that \(\tilde{q} = (q, \tilde{\gamma })\). Therefore, \(v = \tilde{O} (q, \tilde{\gamma }) \in [q]_{{{\mathrm{\mathrm {SO}}}}(n) \times {\varGamma }_s^o}\), which implies \(\overline{[q]} \subseteq [q]_{{{\mathrm{\mathrm {SO}}}}(n) \times {\varGamma }_s^o}\). \(\square \)
Proof of Theorem 2:
Proof
By definition, for any \(\tilde{q} \in [q]_{{{\mathrm{\mathrm {SO}}}}(n) \times {\varGamma }_s^c}\), there exist \(\tilde{O} \in {{\mathrm{\mathrm {SO}}}}(n)\) and \((\tilde{m}, \tilde{\gamma }) \in {\varGamma }_s^c\) such that \(\tilde{q} = \tilde{O} ((q, \tilde{m}), \tilde{\gamma })\). It follows from [12, Lemma 11] that there exists a sequence \(\{\gamma _i\} \subset {\varGamma }^o\) such that \(((q, \tilde{m}), \gamma _i) \rightarrow ((q, \tilde{m}), \tilde{\gamma })\) with respect to the \(\mathbb {L}^2\) metric. Since \({{\mathrm{\mathrm {SO}}}}(n)\) is isometric for \(\mathbb {L}^2\), we have \(\tilde{O} ((q, \tilde{m}), \gamma _i) \rightarrow \tilde{O} ((q, \tilde{m}), \tilde{\gamma })\), which implies that \(\tilde{q} \in \overline{[q]}\). Therefore, we obtain \([q]_{{{\mathrm{\mathrm {SO}}}}(n) \times {\varGamma }_s^o} \subseteq \overline{[q]}\). We finished proving the first statement.
For any \(v \in \overline{[q]}\), there is a sequence of \(\{O_i\}\), \(\{m_i\}\) and \(\{\gamma _i\}\) such that \(O_i ((q, m_i), \gamma _i) \rightarrow v\) with respect to the \(\mathbb {L}^2\) metric. Since \({{\mathrm{\mathrm {SO}}}}(n)\) and [0, 1] are compact sets, there exists a convergent subsequence of \(\{O_i\}\) and \(m_i\), i.e., \(\{O_{i_j}\} \subseteq \{O_i\}\) and \(O_{i_j} \rightarrow \tilde{O}\) with respect to 2-norm and \(\{m_{i_j}\} \subseteq \{m_i\}\) and \(m_{i_j} \rightarrow \tilde{m}\). Let \(\tilde{q}\) denote \(\tilde{O}^T (v, - \tilde{m})\). It follows that \(O_{i_j} ((q, m_{i_j}), \gamma _{i_j}) \rightarrow \tilde{O} (\tilde{q}, \tilde{m})\).
Proceeding as (21), we have
It holds that
Since q is absolutely continuous, \(m_{i_j} \rightarrow \tilde{m}\) implies \(\Vert (q, m_{i_j}) - (q, \tilde{m})\Vert _{\mathbb {L}^2} \rightarrow 0\). Therefore, using (22) and (23) yields \(((q, \tilde{m}), \gamma _{i_j}) \rightarrow (\tilde{q}, \tilde{m})\). Since \(q^{-1}(0_n)\) has measure zero, \((q, \tilde{m})^{-1}(0_n)\) also has measure zero. It follows from [12, Corollary 3] that there exists \(\tilde{\gamma } \in {\varGamma }_s^o\) such that \((\tilde{q}, \tilde{m}) = ((q, \tilde{m}), \tilde{\gamma })\). Therefore, \(v = \tilde{O} ((q, \tilde{m}), \tilde{\gamma }) \in [q]_{{{\mathrm{\mathrm {SO}}}}(n) \times {\varGamma }_s^c}\), which implies \(\overline{[q]} \subseteq [q]_{{{\mathrm{\mathrm {SO}}}}(n) \times {\varGamma }_s^c}\). \(\square \)
Proof of Lemma 2:
Proof
The cost function L(O, m, l) is equal to
Consider the cost function defined on the embedding manifold
The gradient for the variable O is
The gradient for the variable m is
The gradient for the variable l is not easy to compute directly. First, consider the directional derivative along \(v \in {{\mathrm{\mathrm {T}}}}_{l} \mathcal {L}\).
Simplifying, we have
If
then
Since the gradient is the vector that satisfies
we obtain
Finally, the Riemannian gradient is given by projecting each component of \(\bar{L}(O, m, l)\) to its associated manifold. \(\square \)
Rights and permissions
About this article
Cite this article
Huang, W., Gallivan, K.A., Srivastava, A. et al. Riemannian Optimization for Registration of Curves in Elastic Shape Analysis. J Math Imaging Vis 54, 320–343 (2016). https://doi.org/10.1007/s10851-015-0606-8
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10851-015-0606-8