Matrix-valued kernels for shape deformation analysis
From MaRDI portal
Publication:2018097
Hilbert spaces with reproducing kernels (= (proper) functional Hilbert spaces, including de Branges-Rovnyak and other structured spaces) (46E22) Groups of diffeomorphisms and homeomorphisms as manifolds (58D05) Image processing (compression, reconstruction, etc.) in information and communication theory (94A08)
Abstract: The main purpose of this paper is providing a systematic study and classification of non-scalar kernels for Reproducing Kernel Hilbert Spaces (RKHS), to be used in the analysis of deformation in shape spaces endowed with metrics induced by the action of groups of diffeomorphisms. After providing an introduction to matrix-valued kernels and their relevant differential properties, we explore extensively those, that we call TRI kernels, that induce a metric on the corresponding Hilbert spaces of vector fields that is both translation- and rotation-invariant. These are analyzed in an effective manner in the Fourier domain, where the characterization of RKHS of curl-free and divergence-free vector fields is particularly natural. A simple technique for constructing generic matrix-valued kernels from scalar kernels is also developed. We accompany the exposition of the theory with several examples, and provide numerical results that show the dynamics induced by different choices of TRI kernels on the manifold of labeled landmark points.
Recommendations
- Kernels on Riemannian manifolds
- A kernel class allowing for fast computations in shape spaces induced by diffeomorphisms
- Metamorphosis of images in reproducing kernel Hilbert spaces
- Piecewise rigid motion in diffeomorphism groups with strong right-invariant metrics
- scientific article; zbMATH DE number 5957433
Cited in
(23)- A kernel class allowing for fast computations in shape spaces induced by diffeomorphisms
- Metrics, quantization and registration in varifold spaces
- Weight metamorphosis of varifolds and the LDDMM-Fisher-Rao metric
- Interpreting the dual Riccati equation through the LQ reproducing kernel
- Diffeomorphic Surface Registration with Atrophy Constraints
- Sub-Riemannian methods in shape analysis
- Indirect image registration with large diffeomorphic deformations
- Linearly constrained linear quadratic regulator from the viewpoint of kernel methods
- Matrix-valued positive definite kernels given by expansions: strict positive definiteness
- The Determination of Distances between Images by de Rham Currents Method
- Matrix valued positive definite kernels related to the generalized Aitken's integral for Gaussians
- Operator-valued positive definite kernels and differentiable universality
- Weak dual pairs and jetlet methods for ideal incompressible fluid models in \(n \geq 2\) dimensions
- Diffeomorphic learning
- A geodesic landmark shooting algorithm for template matching and its applications
- Kernel metrics on normal cycles and application to curve matching
- Interpolation with uncoupled separable matrix-valued kernels
- Comparison of different parallel transport methods for the study of deformations in 3D cardiac data
- Large deviations for perturbed Gaussian processes and logarithmic asymptotic estimates for some exit probabilities
- Controlling moments with kernel Stein discrepancies
- Approximation of optimization problems with constraints through kernel Sum-of-Squares
- Error estimates for vector field interpolation based on generalized matrix-valued kernels
- Explainable binary classification of separable shape ensembles
This page was built for publication: Matrix-valued kernels for shape deformation analysis
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2018097)
