Accéder directement au contenu Accéder directement à la navigation
Article dans une revue

Evaluation for Uncertain Image Classification and Segmentation

Abstract : Each year, numerous segmentation and classification algorithms are invented or reused to solve problems where machine vision is needed. Generally, the efficiency of these algorithms is compared against the results given by one or many human experts. However, in many situations, the location of the real boundaries of the objects as well as their classes are not known with certainty by the human experts. Furthermore, only one aspect of the segmentation and classification problem is generally evaluated. In this paper we present a new evaluation method for classification and segmentation of image, where we take into account both the classification and segmentation results as well as the level of certainty given by the experts. As a concrete example of our method, we evaluate an automatic seabed characterization algorithm based on sonar images.
Liste complète des métadonnées

Littérature citée [24 références]  Voir  Masquer  Télécharger

https://hal.archives-ouvertes.fr/hal-00286593
Contributeur : Arnaud Martin <>
Soumis le : mercredi 11 juin 2008 - 03:45:30
Dernière modification le : mardi 8 septembre 2020 - 09:56:03
Archivage à long terme le : : vendredi 28 mai 2010 - 21:47:02

Fichiers

paper_eval2.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-00286593, version 1
  • ARXIV : 0806.1796

Citation

Arnaud Martin, Hicham Laanaya, Andreas Arnold-Bos. Evaluation for Uncertain Image Classification and Segmentation. Pattern Recognition, Elsevier, 2006, 39 (11), pp.1987-1995. ⟨hal-00286593⟩

Partager

Métriques

Consultations de la notice

320

Téléchargements de fichiers

733