Improving FREAK Descriptor for Image Classification

Cristina Hilario Gomez 1 N. V. Kartheek Medathati 2 Pierre Kornprobst 2 Vittorio Murino 1 Diego Sona 1
2 NEUROMATHCOMP - Mathematical and Computational Neuroscience
CRISAM - Inria Sophia Antipolis - Méditerranée , JAD - Laboratoire Jean Alexandre Dieudonné : UMR6621
Abstract : In this paper we propose a new set of bio-inspired descrip- tors for image classification based on low-level processing performed by the retina. Taking as a starting point a descriptor called FREAK (Fast Retina Keypoint), we further extend it mimicking the center-surround organization of ganglion receptive fields.To test our approach we com- pared the performance of the original FREAK and our proposal on the 15 scene categories database. The results show that our approach out- performs the original FREAK for the scene classification task.
Type de document :
Communication dans un congrès
The 10th International Conference on Computer Vision Systems (ICVS 2015), Jul 2015, Nice, France. 2015, 〈http://icvs2015.aau.dk〉
Liste complète des métadonnées

Littérature citée [17 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01205376
Contributeur : Pierre Kornprobst <>
Soumis le : vendredi 25 septembre 2015 - 13:54:00
Dernière modification le : jeudi 3 mai 2018 - 13:32:58
Document(s) archivé(s) le : mardi 29 décembre 2015 - 10:02:31

Fichier

paper_ICVS_2015.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01205376, version 1

Collections

Citation

Cristina Hilario Gomez, N. V. Kartheek Medathati, Pierre Kornprobst, Vittorio Murino, Diego Sona. Improving FREAK Descriptor for Image Classification. The 10th International Conference on Computer Vision Systems (ICVS 2015), Jul 2015, Nice, France. 2015, 〈http://icvs2015.aau.dk〉. 〈hal-01205376〉

Partager

Métriques

Consultations de la notice

233

Téléchargements de fichiers

340