Shape priors using Manifold Learning Techniques

DMCA

Shape priors using Manifold Learning Techniques (2007)

Cached

Download Links

[certis.enpc.fr]
[www.enpc.fr]
[imagine.enpc.fr]

Other Repositories/Bibliography

DBLP

by Patrick Etyngier , Florent Ségonne , Renaud Keriven

Venue:	in "11th IEEE International Conference on Computer Vision, Rio de Janeiro
Citations:	38 - 2 self

BibTeX

@INPROCEEDINGS{Etyngier07shapepriors,
    author = {Patrick Etyngier and Florent Ségonne and Renaud Keriven},
    title = {Shape priors using Manifold Learning Techniques},
    booktitle = {in "11th IEEE International Conference on Computer Vision, Rio de Janeiro},
    year = {2007}
}

OpenURL

Abstract

We introduce a non-linear shape prior for the deformable model framework that we learn from a set of shape samples using recent manifold learning techniques. We model a category of shapes as a finite dimensional manifold which we approximate using Diffusion maps, that we call the shape prior manifold. Our method computes a Delaunay triangulation of the reduced space, considered as Euclidean, and uses the resulting space partition to identify the closest neighbors of any given shape based on its Nyström extension. Our contribution lies in three aspects. First, we propose a solution to the pre-image problem and define the projection of a shape onto the manifold. Based on closest neighbors for the Diffusion distance, we then describe a variational framework for manifold denoising. Finally, we introduce a shape prior term for the deformable framework through a non-linear energy term designed to attract a shape towards the manifold at given constant embedding. Results on shapes of cars and ventricule nuclei are presented and demonstrate the potentials of our method.

Keyphrases

shape prior manifold learning technique recent manifold constant embedding diffusion map finite dimensional manifold non-linear shape diffusion distance deformable model framework deformable framework non-linear energy term pre-image problem reduced space shape sample delaunay triangulation ventricule nucleus nystr extension shape prior term variational framework manifold denoising space partition

DMCA