Optimizing color information processing inside an SVM network

Jérôme Pasquet 1 Gérard Subsol 1 Mustapha Derras 2 Marc Chaumont 1
1 ICAR - Image & Interaction
LIRMM - Laboratoire d'Informatique de Robotique et de Microélectronique de Montpellier
Abstract : Today, with the higher computing power of CPUs and GPUs, many different neural network architectures have been proposed for object detection in images. However, these networks are often not optimized to process color information. In this paper, we propose a new method based on an SVM network, that efficiently extracts this color information. We describe different network archi-tectures and compare them with several color models (CIELAB, HSV, RGB...). The results obtained on real data show that our network is more efficient and robust than a single SVM network, with an average precision gain ranging from 1.5% to 6% with respect to the complexity of the test image database. We have optimized the network architecture in order to gain information from color data, thus increasing the average precision by up to 10%.
Type de document :
Communication dans un congrès
Electronic Imaging, Feb 2016, San Francisco, California, United States. IS&T International Symposium on Electronic Imaging, 2016, Visual Information Processing and Communication VII
Liste complète des métadonnées

Littérature citée [19 références]  Voir  Masquer  Télécharger

https://hal.archives-ouvertes.fr/hal-01374090
Contributeur : Marc Chaumont <>
Soumis le : jeudi 29 septembre 2016 - 16:54:05
Dernière modification le : jeudi 24 mai 2018 - 15:59:23
Document(s) archivé(s) le : vendredi 30 décembre 2016 - 14:45:36

Fichier

IST_ELECTRONIC_IMAGING_Visual_...
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01374090, version 1

Collections

Citation

Jérôme Pasquet, Gérard Subsol, Mustapha Derras, Marc Chaumont. Optimizing color information processing inside an SVM network. Electronic Imaging, Feb 2016, San Francisco, California, United States. IS&T International Symposium on Electronic Imaging, 2016, Visual Information Processing and Communication VII. 〈hal-01374090〉

Partager

Métriques

Consultations de la notice

127

Téléchargements de fichiers

49