Skip to Main content Skip to Navigation
New interface
Conference papers

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.
Document type :
Conference papers
Complete list of metadata

Cited literature [17 references]  Display  Hide  Download
Contributor : Pierre Kornprobst Connect in order to contact the contributor
Submitted on : Friday, September 25, 2015 - 1:54:00 PM
Last modification on : Thursday, August 4, 2022 - 4:58:17 PM
Long-term archiving on: : Tuesday, December 29, 2015 - 10:02:31 AM


Files produced by the author(s)


  • HAL Id : hal-01205376, version 1


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⟩



Record views


Files downloads