• Corpus ID: 1618

Riemannian level-set methods for tensor-valued data

  title={Riemannian level-set methods for tensor-valued data},
  author={Mourad Z{\'e}ra{\"i} and Maher Moakher},
We present a novel approach for the derivation of PDEs modeling curvaturedriven flows for matrix-valued data. This approach is based on the Riemannian geometry of the manifold of Symmetric Positive Definite MatricesP(n). The differential geometric attributes ofP(n) such as the bi-invariant metric, the covariant derivative and the Christoffel symbols allow us to extend scalar-valued mean curvature and snakes methods to the tensor data setting. Since the data live onP(n), these methods have the… 

Figures from this paper

A Riemannian Bayesian Framework for Estimating Diffusion Tensor Images
This paper presents a Bayesian approach for simultaneous reconstruction and regularization of DT-MR images that allows to resolve the disadvantages of previous approaches and derives a maximum a posteriori estimator of the tensor image that considers both the statistical characteristics of the Rician noise occurring in MR images as well as the nonlinear structure of tensor valued images.


Curvature-Driven PDE Methods for Matrix-Valued Images
Experiments on three-dimensional DT-MRI data and an indefinite tensor field from fluid dynamics show that the proposed methods inherit the essential properties of their scalar-valued counterparts.
Statistics on the Manifold of Multivariate Normal Distributions: Theory and Application to Diffusion Tensor MRI Processing
The derivation of accurate and efficient numerical schemes to estimate statistical parameters of the space of multivariate normal distributions with zero mean vector are extensively addressed.
Fast and Simple Calculus on Tensors in the Log-Euclidean Framework
New metrics called Log-Euclidean are proposed, which have excellent theoretical properties and yield similar results in practice, but with much simpler and faster computations.
Vector-valued active contours
  • G. Sapiro
  • Mathematics, Computer Science
    Proceedings CVPR IEEE Computer Society Conference on Computer Vision and Pattern Recognition
  • 1996
An extension of the color active contours is presented which leads to a possible image flow for vector-valued image segmentation and also shows the relation of thecolor geodesic active contour with a number of partial-differential-equations based image processing algorithms as anisotropic diffusion and shock filters.
Color Snakes
  • G. Sapiro
  • Computer Science
    Comput. Vis. Image Underst.
  • 1997
An extension of these vector active contours is presented, proposing a possible image flow for vector-valued image segmentation, and shows the relation between active contour and a number of partial-differential-equations-based image processing algorithms as anisotropic diffusion and shock filters.
Variational Approaches to the Estimation, Regularizatinn and Segmentation of Diffusion Tensor Images
A set of new techniques for the robust estimation and regularization of diffusion tensor images (DTI) as well as a novel statistical framework for the segmentation of cerebral white matter structures from this type of dataset are presented.
Images as Embedded Maps and Minimal Surfaces: Movies, Color, Texture, and Volumetric Medical Images
The geometric framework and the general Beltrami flow are applied to feature-preserving denoising of images in various spaces to propose enhancement techniques that selectively smooth images while preserving either the multi-channel edges or the orientation-dependent texture features in them.
A general framework for low level vision
A new geometrical framework based on which natural flows for image scale space and enhancement are presented, which unifies many classical schemes and algorithms via a simple scaling of the intensity contrast, and results in new and efficient schemes.
Riemannian geometry and geometric analysis
* Established textbook * Continues to lead its readers to some of the hottest topics of contemporary mathematical research This established reference work continues to lead its readers to some of
Nonlinear total variation based noise removal algorithms
A constrained optimization type of numerical algorithm for removing noise from images is presented. The total variation of the image is minimized subject to constraints involving the statistics of