Climbing: A Unified Approach for Global Constraints on Hierarchical Segmentation - HAL Accéder directement au contenu
Communication dans un congrès Année : 2012

Climbing: A Unified Approach for Global Constraints on Hierarchical Segmentation

Résumé

The paper deals with global constraints for hierarchical segmentations. The proposed framework associates, with an input image, a hierarchy of segmentations and an energy, and the subsequent optimization problem. It is the first paper that compiles the different global constraints and unifies them as Climbing energies. The transition from global optimization to local optimization is attained by the h-increasingness property, which allows to compare parent and child partition energies in hierarchies. The laws of composition of such energies are established and examples are given over the Berkeley Dataset for colour and texture segmentation.
Fichier principal
Vignette du fichier
KSC-ECCV2012.pdf ( 1.46 Mo ) Télécharger
Origine : Fichiers éditeurs autorisés sur une archive ouverte
Loading...

Dates et versions

hal-00789392, version 1 (18-02-2013)

Identifiants

  • HAL Id : hal-00789392 , version 1

Citer

Bangalore Ravi Kiran, Jean Serra, Jean Cousty. Climbing: A Unified Approach for Global Constraints on Hierarchical Segmentation. Computer Vision - ECCV 2012. Workshops and Demonstrations, Oct 2012, Italy. pp.324-334. ⟨hal-00789392⟩
183 Consultations
251 Téléchargements
Dernière date de mise à jour le 26/06/2024
comment ces indicateurs sont-ils produits

Partager

Gmail Facebook Twitter LinkedIn Plus