A Cascade of Unsupervised and Supervised Neural Networks for Natural Image Classification - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2006

A Cascade of Unsupervised and Supervised Neural Networks for Natural Image Classification

Julien Ros
  • Fonction : Auteur
Grégoire Lefebvre

Résumé

This paper presents an architecture well suited for natural image classification or visual object recognition applications. The image content is described by a distribution of local prototype features obtained by projecting local signatures on a self-organizing map. The local signatures describe singularities around interest points detected by a wavelet-based salient points detector. Finally, images are classified by using a multilayer perceptron receiving local prototypes distribution as input. This architecture obtains good results both in terms of global classification rates and computing times on different well known datasets.
Fichier principal
Vignette du fichier
CIVR2006-1.pdf (603.89 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01224262 , version 1 (04-11-2015)

Identifiants

Citer

Julien Ros, Christophe Laurent, Grégoire Lefebvre. A Cascade of Unsupervised and Supervised Neural Networks for Natural Image Classification. Image and Video Retrieval, 5th International Conference, CIVR 2006, Jul 2006, Tempe, United States. ⟨10.1007/11788034_10⟩. ⟨hal-01224262⟩
20 Consultations
75 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More