Passer à la navigation principale Passer à la recherche Passer au contenu principal

A multilevel banded graph cuts method for fast image segmentation

  • Siemens

Résultats de recherche: Chapitre dans un livre, rapport, actes de conférence › Participation à un ouvrage collectif lié à un colloque ou une conférence › Revue par des pairs

206 Citations (Scopus)

Résumé

In the short time since publication of Boykov and Jolly's seminal paper [3], graph cuts have become well established as a leading method in 2D and 3D semi-automated image segmentation. Although this approach is computationally feasible for many tasks, the memory overhead and supralinear time complexity of leading algorithms results in an excessive computational burden for high-resolution data. In this paper, we introduce a multilevel banded heuristic for computation of graph cuts that is motivated by the well-known narrow band algorithm in level set computation. We perform a number of numerical experiments to show that this heuristic drastically reduces both the running time and the memory consumption of graph cuts while producing nearly the same segmentation result as the conventional graph cuts. Additionally, we are able to characterize the type of segmentation target for which our multilevel banded heuristic will yield different results from the conventional graph cuts. The proposed method has been applied to both 2D and 3D images with promising results.

Langue originaleAnglais
titreProceedings - 10th IEEE International Conference on Computer Vision, ICCV 2005
Pages259-265
Nombre de pages7
Les DOIs
ÉtatPublié - 2005
Modification externeOui
EvénementProceedings - 10th IEEE International Conference on Computer Vision, ICCV 2005 - Beijing, Chine
Durée: 17 oct. 2005 → 20 oct. 2005

Série de publications

NomProceedings of the IEEE International Conference on Computer Vision
VolumeI

Conférence

ConférenceProceedings - 10th IEEE International Conference on Computer Vision, ICCV 2005
Pays/TerritoireChine
La villeBeijing
Période17/10/05 → 20/10/05

Classification disciplinaire ASJC Scopus

  • Logiciel
  • Vision par ordinateur et reconnaissance de formes

Empreinte digitale

Voici les principaux termes ou expressions associés à « A multilevel banded graph cuts method for fast image segmentation ». Ces libellés thématiques sont générés à partir du titre et du résumé de la publication. Ensemble, ils forment une empreinte digitale unique.

Citer cette ressource