Optimizing color information processing inside an SVM network - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2016

Optimizing color information processing inside an SVM network

Jérôme Pasquet
Gérard Subsol
Mustapha Derras
  • Fonction : Auteur
  • PersonId : 972011
Marc Chaumont

Résumé

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%.
Fichier principal
Vignette du fichier
IST_ELECTRONIC_IMAGING_Visual_Information_Processing_Communication_2016_PASQUET_SUBSOL_DERRAS_CHAUMONT.pdf (765.72 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01374090 , version 1 (29-09-2016)

Identifiants

  • HAL Id : hal-01374090 , version 1

Citer

Jérôme Pasquet, Gérard Subsol, Mustapha Derras, Marc Chaumont. Optimizing color information processing inside an SVM network. EI: Electronic Imaging, Feb 2016, San Francisco, CA, United States. ⟨hal-01374090⟩
151 Consultations
95 Téléchargements

Partager

Gmail Facebook X LinkedIn More