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).
Liste complète des métadonnées

Cited literature [8 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-00977125
Contributor : Yi Ren <>
Submitted on : Monday, April 14, 2014 - 10:55:30 AM
Last modification on : Thursday, January 11, 2018 - 6:20:17 AM
Document(s) archivé(s) le : Monday, July 14, 2014 - 10:47:54 AM

File

gretsi_resumefr.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00977125, version 1

Collections

Citation

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

Share

Metrics

Record views

264

Files downloads

280