Visual object retrieval by graph features - Archive ouverte HAL Access content directly
Reports Year :

Visual object retrieval by graph features

Abstract

Our approach addresses the well-known problem of adding spatial information to the standard bag-of-visual-words (BoVW) approach. To that end, a set of graphs descriptors are constructed for the entire image or for local image regions. These descriptors are then incorporated into a bag-of-visual-words approach, leading to a method called bag-of-bag-of-visual-words (BBoVW).
Fichier principal
Vignette du fichier
gretsi_resumefr.pdf (221.38 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-00977125 , version 1 (14-04-2014)

Identifiers

  • HAL Id : hal-00977125 , version 1

Cite

Yi Ren, Aurélie Bugeau, Jenny Benois-Pineau. Visual object retrieval by graph features. 2013. ⟨hal-00977125⟩

Collections

CNRS LARA
154 View
160 Download

Share

Gmail Facebook Twitter LinkedIn More