Convex Multi-Region Segmentation on Manifolds - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2009

Convex Multi-Region Segmentation on Manifolds


In this paper, we address the problem of segmenting data defined on a manifold into a set of regions with uniform properties. In particular, we propose a numerical method when the manifold is represented by a triangular mesh. Based on recent image segmentation models, our method minimizes a convex energy and then enjoys significant favorable properties: it is robust to initialization and avoid the problem of the existence of local minima present in many variational models. The contributions of this paper are threefold: firstly we adapt the convex image labelling model to manifolds; in particular the total variation formulation. Secondly we show how to implement the proposed method on triangular meshes, and finally we show how to use and combine the method in other computer vision problems, such as 3D reconstruction. We demonstrate the efficiency of our method by testing it on various data.
Fichier principal
Vignette du fichier
Delaunoy-etal-iccv2009.pdf (2.43 Mo) Télécharger le fichier
Vignette du fichier
Delaunoy-etal-iccv09.jpg (794.2 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Format : Figure, Image

Dates and versions

inria-00435133 , version 1 (23-11-2009)



Amael Delaunoy, Ketut Fundana, Emmanuel Prados, Anders Heyden. Convex Multi-Region Segmentation on Manifolds. ICCV 2009 - 12th IEEE International Conference on Computer Vision, Sep 2009, Kyoto, Japan. pp.662-669, ⟨10.1109/ICCV.2009.5459174⟩. ⟨inria-00435133⟩
298 View
701 Download



Gmail Facebook X LinkedIn More