PhotoMole: retrieval from a database of natural images - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2005

PhotoMole: retrieval from a database of natural images

Matthijs Douze
  • Fonction : Auteur
  • PersonId : 843109
Michaël Sdika
Cordelia Schmid
  • Fonction : Auteur
  • PersonId : 831154

Résumé

This demonstration extracts images from a set, based on their similarity to a query image. The scenes handled are of various types: indoor or outdoor, natural (trees) or structured (furniture). The constraints on the shooting are weak, allowing viewpoint changes, partial occlusion and illumination changes. Different sensors can be used to capture the database images and the query image: we tested it on digital cameras, webcams and low-resolution mobile phones. The retrieval is fast (< 1/3 second) and images can be added dynamically to the database.
Fichier non déposé

Dates et versions

hal-01902510 , version 1 (23-10-2018)

Identifiants

  • HAL Id : hal-01902510 , version 1

Citer

Matthijs Douze, Michaël Sdika, Cordelia Schmid. PhotoMole: retrieval from a database of natural images. CVPR'05 - IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Jun 2005, San Diego, United States. pp.1-4. ⟨hal-01902510⟩
109 Consultations
0 Téléchargements

Partager

Gmail Facebook X LinkedIn More