The momentum map representation of images

Abstract

This paper discusses the mathematical framework for designing methods of large deformation matching (LDM) for image registration in computational anatomy. After reviewing the geometrical framework of LDM image registration methods, a theorem is proved showing that these methods may be designed by using the actions of diffeomorphisms on the image data structure to define their associated momentum representations as (cotangent lift) momentum maps. To illustrate its use, the momentum map theorem is shown to recover the known algorithms for matching landmarks, scalar images and vector fields. After briefly discussing the use of this approach for Diffusion Tensor (DT) images, we explain how to use momentum maps in the design of registration algorithms for more general data structures. For example, we extend our methods to determine the corresponding momentum map for registration using semidirect product groups, for the purpose of matching images at two different length scales. Finally, we discuss the use of momentum maps in the design of image registration algorithms when the image data is defined on manifolds instead of vector spaces.

34 pages, revised version

Cited by in corpus (23)

• Invariant higher-order variational problems
• Multi-component generalizations of the {CH} equation: Geometrical Aspects, Peakons and Numerical Examples
• Solution to the quantum Zermelo navigation problem
• Invariant higher-order variational problems II
• A Geometric Framework for Stochastic Shape Analysis
• Mixture of Kernels and Iterated Semidirect Product of Diffeomorphisms Groups
• A New Riemannian Setting for Surface Registration
• Stochastic Closures for Wave--Current Interaction Dynamics
• Geodesic Warps by Conformal Mappings
• How deep learning works --The geometry of deep learning
• Geometrization of deep networks for the interpretability of deep learning systems
• On the coupling between an ideal fluid and immersed particles
• Spacetime as the optimal generative network of quantum states: a roadmap to QM=GR?
• Geometric dynamics of optimization
• $G$-Strands on symmetric spaces
• Symmetries in LDDMM with higher order momentum distributions
• String Methods for Stochastic Image and Shape Matching
• Multiple Shape Registration using Constrained Optimal Control
• On Hodge decomposition and conformal variational problems
• Clebsch variational principles in field theories and singular solutions of covariant EPDiff equations
• Understanding over-parameterized deep networks by geometrization
• Shape analysis via gradient flows on diffeomorphism groups
• Hamiltonian Coupling of Electromagnetic Field and Matter