The Riemannian Geometry of the Space of Positive-Definite Matrices and Its Application to the Regularization of Positive-Definite Matrix-Valued Data.
Maher MoakherMourad ZéraïPublished in: J. Math. Imaging Vis. (2011)
Keyphrases
- positive definite
- valued data
- geometric structure
- riemannian metric
- fisher information
- reproducing kernel hilbert space
- covariance matrix
- tensor field
- structure tensor
- covariance matrices
- matrix valued
- lie group
- riemannian manifolds
- symmetric positive definite
- kernel function
- diffusion tensor
- kernel machines
- euclidean space
- kernel matrix
- kernel methods
- loss function
- semi parametric
- input space
- visual data
- data dependent
- image denoising
- mixture model