Bio-Inspired Bags-of-Features for Image Classification

Wafa Bel Haj Ali 1 Eric Debreuve 1 Pierre Kornprobst 2 Michel Barlaud 1
2 NEUROMATHCOMP
CRISAM - Inria Sophia Antipolis - Méditerranée , INRIA Rocquencourt, ENS Paris - École normale supérieure - Paris, UNS - Université Nice Sophia Antipolis, CNRS - Centre National de la Recherche Scientifique : UMR8548
Abstract : The challenge of image classification is based on two key elements: the image representation and the algorithm of classification. In this paper, we revisited the topic of image representation. Classical descriptors such as Bag-of-Features are usually based on SIFT. We propose here an alternative based on bio-inspired features. This approach is inspired by a model of the retina which acts as an image filter to detect local contrasts. We show the promising results that we obtained in natural scenes classification with the proposed bio-inspired image representation.
Document type :
Conference papers
Complete list of metadatas

https://hal.inria.fr/hal-00845745
Contributor : Pierre Kornprobst <>
Submitted on : Wednesday, July 17, 2013 - 4:13:31 PM
Last modification on : Wednesday, August 28, 2019 - 3:52:02 PM

Identifiers

  • HAL Id : hal-00845745, version 1

Citation

Wafa Bel Haj Ali, Eric Debreuve, Pierre Kornprobst, Michel Barlaud. Bio-Inspired Bags-of-Features for Image Classification. KDIR - International Conference on Knowledge Discovery and Information Retrieval - 2011, 2011, Paris, France. pp.277-281. ⟨hal-00845745⟩

Share

Metrics

Record views

2402