Metamorphosis of images in reproducing kernel Hilbert spaces

DOI10.1007/S10444-015-9435-YzbMATH Open1347.65051arXiv1409.6573OpenAlexW2264725480MaRDI QIDQ295375FDOQ295375

Authors: Casey L. Richardson, Laurent Younes 

Publication date: 13 June 2016

Published in: Advances in Computational Mathematics (Search for Journal in Brave)

Abstract: Metamorphosis is a method for diffeomorphic matching of shapes, with many potential applications for anatomical shape comparison in medical imagery, a problem which is central to the field of computational anatomy. An important tool for the practical application of metamorphosis is a numerical method based on shooting from the initial momentum, as this would enable the use of statistical methods based on this momentum, as well as the estimation of templates from hyper-templates using morphing. In this paper we introduce a shooting method, in the particular case of morphing images that lie in a reproducing kernel Hilbert space (RKHS). We derive the relevant shooting equations from a Lagrangian frame of reference, present the details of the numerical approach, and illustrate the method through morphing of some simple images.

Full work available at URL: https://arxiv.org/abs/1409.6573

Recommendations

• Constructing metamorphosis of pixel images for the objects on the basis of solving Euler-Poincaré equations
• Variational problems on flows of diffeomorphisms for image matching
• Time discrete geodesic paths in the space of images
• The Euler-Poincaré theory of metamorphosis
• Image reconstruction through metamorphosis

zbMATH Keywords

variational problemshape analysisalgorithmboundary value problemnumerical exampleinitial value problemshooting methodadjoint methodsdeformable templatesgroups of diffeomorphismsimage metamorphosisnear-diffeomorphic methodsRiemannian geometric framework

Mathematics Subject Classification ID

Numerical aspects of computer graphics, image analysis, and computational geometry (65D18)

Cites Work

• Computing large deformation metric mappings via geodesic flows of diffeomorphisms
• Theory of Reproducing Kernels
• Shapes and diffeomorphisms
• Title not available (Why is that?)
• Optimal Transport
• Title not available (Why is that?)
• Functional analysis, Sobolev spaces and partial differential equations
• Control theory from the geometric viewpoint.
• Sur la géométrie différentielle des groupes de Lie de dimension infinite et ses applications à l'hydrodynamique des fluides parfaits
• Groups of diffeomorphisms and the motion of an incompressible fluid
• Fredholm properties of Riemannian exponential maps on diffeomorphism groups
• On the regularity of the composition of diffeomorphisms
• The Euler-Poincaré equations and semidirect products with applications to continuum theories
• Lectures on Mechanics
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Group actions, homeomorphisms, and matching: A general framework
• Optimal transport, convection, magnetic relaxation and generalized Boussinesq equations
• A fast adaptive multipole algorithm in three dimensions
• A kernel class allowing for fast computations in shape spaces induced by diffeomorphisms
• Computing metamorphoses between discrete measures
• The fast multipole method: Numerical implementation
• Optimal mass transport for registration and warping
• On completeness of groups of diffeomorphisms
• Title not available (Why is that?)
• Variational problems on flows of diffeomorphisms for image matching
• Title not available (Why is that?)
• A Variational Approach to Nonrigid Morphological Image Registration
• The Euler-Poincaré theory of metamorphosis
• Local Geometry of Deformable Templates
• Title not available (Why is that?)
• Fast multipole methods on graphics processors

Cited In (25)

• Splines for image metamorphosis
• Time discrete extrapolation in a Riemannian space of images
• Metamorphoses through Lie group action
• Indirect image registration with large diffeomorphic deformations
• Morphing of manifold-valued images inspired by discrete geodesics in image spaces
• Metamorphic image registration using a semi-Lagrangian scheme
• Metamorphoses of functional shapes in Sobolev spaces
• Constructing metamorphosis of pixel images for the objects on the basis of solving Euler-Poincaré equations
• Geodesic matching with free extremities
• Image extrapolation for the time discrete metamorphosis model: existence and applications
• Matrix-valued kernels for shape deformation analysis
• A generalized model for optimal transport of images including dissipation and density modulation
• Image morphing in deep feature spaces: theory and applications
• An operator-splitting approach for variational optimal control formulations for diffeomorphic shape matching
• Weight metamorphosis of varifolds and the LDDMM-Fisher-Rao metric
• Geometric dynamics of optimization
• Template-based image reconstruction facing different topologies
• Group actions, homeomorphisms, and matching: A general framework
• A kernel class allowing for fast computations in shape spaces induced by diffeomorphisms
• Template-based image reconstruction from sparse tomographic data
• Diffeomorphic matching and dynamic deformable surfaces in 3D medical imaging
• Diffeomorphic image matching with left-invariant metrics
• Convergence of the Time Discrete Metamorphosis Model on Hadamard Manifolds
• Image reconstruction through metamorphosis
• Stochastic metamorphosis with template uncertainties

Uses Software

• ParaView
• SciPy
• Leafsnap

This page was built for publication: Metamorphosis of images in reproducing kernel Hilbert spaces

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q295375)