Clustering-based Methods for Fast Epitome Generation

Abstract : This paper deals with epitome generation, mainly dedicated here to image coding applications. Existing approaches are known to be memory and time consuming due to exhaustive self-similarities search within the image for each non-overlapping block. We propose here a novel approach for epitome construction that first groups close patches together. In a second time the self-similarities search is performed for each group. By limiting the number of exhaustive searches we limit the memory occupation and the processing time. Results show that interesting complexity reduction can be achieved while keeping a good epitome quality (down to 18.08 % of the original memory occupation and 41.39 % of the original processing time).
Type de document :
Communication dans un congrès
European Signal Processing Conference (EUSIPCO 2014), Sep 2014, Lisbonne, Portugal. 2014
Liste complète des métadonnées

Littérature citée [12 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01008279
Contributeur : Martin Alain <>
Soumis le : mardi 17 juin 2014 - 11:16:56
Dernière modification le : jeudi 15 novembre 2018 - 11:57:53
Document(s) archivé(s) le : mercredi 17 septembre 2014 - 10:56:23

Fichier

Fast_epitome_ICIP_2014.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01008279, version 1

Citation

Martin Alain, Christine Guillemot, Dominique Thoreau, Philippe Guillotel. Clustering-based Methods for Fast Epitome Generation. European Signal Processing Conference (EUSIPCO 2014), Sep 2014, Lisbonne, Portugal. 2014. 〈hal-01008279〉

Partager

Métriques

Consultations de la notice

664

Téléchargements de fichiers

179