Minimizing hallucination in Histogram of Oriented Gradients

Abstract : Histogram of Oriented Gradients is one of the most extensively used image descriptors in computer vision. It has successfully been applied to various vision tasks such as localization, classification and recognition. As it mainly captures gradient strengths in an image, it is sensitive to local variations in illumination and contrast. In the result, a normalization of this descriptor turns out to be essential for good performance [3, 4]. Although different normal-ization schemes have been investigated, all of them usually employ L1 or L2-norm. In this paper we show that an in-cautious application of L-like norms to the HOG descrip-tor might produce a hallucination effect. To overcome this issue, we propose a new normalization scheme that effectively minimizes hallucinations. This scheme is built upon a detailed analysis of the gradient distribution resulting in adding an extra bin with a specific value that increases HOG distinctiveness. We validated our approach on person re-identification and action recognition, demonstrating significant boost in the performance.
Type de document :
Communication dans un congrès
The 12th IEEE International Conference on Advanced Video and Signal-based, Aug 2015, Karlsruhe, Germany. 2015, 〈http://avss2015.org/〉
Liste complète des métadonnées

Littérature citée [18 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01199386
Contributeur : Michal Koperski <>
Soumis le : mardi 15 septembre 2015 - 12:25:10
Dernière modification le : jeudi 11 janvier 2018 - 16:48:01
Document(s) archivé(s) le : mardi 29 décembre 2015 - 07:11:25

Fichier

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

Identifiants

  • HAL Id : hal-01199386, version 1

Collections

Citation

Javier Ortiz, Slawomir Bak, Michał Koperski, François Brémond. Minimizing hallucination in Histogram of Oriented Gradients. The 12th IEEE International Conference on Advanced Video and Signal-based, Aug 2015, Karlsruhe, Germany. 2015, 〈http://avss2015.org/〉. 〈hal-01199386〉

Partager

Métriques

Consultations de la notice

223

Téléchargements de fichiers

114