Improving FREAK Descriptor for Image Classification - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2015

Improving FREAK Descriptor for Image Classification

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.
Fichier principal
Vignette du fichier
paper_ICVS_2015.pdf (483.55 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01205376 , version 1 (25-09-2015)

Identifiers

  • HAL Id : hal-01205376 , version 1

Cite

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. ⟨hal-01205376⟩
216 View
557 Download

Share

Gmail Facebook X LinkedIn More