ASARI: a new adaptive oversegmentation method

Abstract : Using superpixels instead of pixels has become a popular pre-processing step in computer vision. However, there are few adaptive methods able to automatically find the best comprise between boundary adherence and superpixel number. Moreover, no algorithm producing color and texture homogeneous superpixels keeps competitive execution time. In this article we suggest a new graph-based region merging method, called Adaptive Superpixel Algorithm with Rich Information (ASARI) to solve these two difficulties. We will show that ASARI achieves results similar to the state-of-the-art methods on the existing benchmarks and outperforms these methods when dealing with big images.
Type de document :
Communication dans un congrès
Iberian Conference on Pattern Recognition and Image Analysis (IbPRIA 2017), Jun 2017, Faro, Portugal. Pattern Recognition and Image Analysis, pp. 194-202, 2017
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-01913673
Contributeur : Open Archive Toulouse Archive Ouverte (oatao) <>
Soumis le : mardi 6 novembre 2018 - 14:40:19
Dernière modification le : samedi 10 novembre 2018 - 01:17:18
Document(s) archivé(s) le : jeudi 7 février 2019 - 16:31:38

Fichier

mathieu_19095.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01913673, version 1
  • OATAO : 19095

Collections

Citation

Bérengère Mathieu, Alain Crouzil, Jean-Baptiste Puel. ASARI: a new adaptive oversegmentation method. Iberian Conference on Pattern Recognition and Image Analysis (IbPRIA 2017), Jun 2017, Faro, Portugal. Pattern Recognition and Image Analysis, pp. 194-202, 2017. 〈hal-01913673〉

Partager

Métriques

Consultations de la notice

11

Téléchargements de fichiers

13