HAL will be down for maintenance from Friday, June 10 at 4pm through Monday, June 13 at 9am. More information
Skip to Main content Skip to Navigation
Conference papers

Multi-Layer Local Graph Words for Object Recognition

Abstract : In this paper, we propose a new multi-layer structural approach for the task of object based image retrieval. In our work we tackle the problem of structural organization of local features. The structural features we propose are nested multi-layered local graphs built upon sets of SURF feature points with Delaunay triangulation. A Bag-of-Visual-Words (BoVW) framework is applied on these graphs, giving birth to a Bag-of-Graph-Words representation. The multi-layer nature of the descriptors consists in scaling from trivial Delaunay graphs - isolated feature points - by increasing the number of nodes layer by layer up to graphs with maximal number of nodes. For each layer of graphs its own visual dictionary is built. The experiments conducted on the SIVAL and Caltech-101 data sets reveal that the graph features at different layers exhibit complementary performances on the same content and perform better than baseline BoVW approach. The combination of all existing layers, yields significant improvement of the object recognition performance compared to single level approaches.
Document type :
Conference papers
Complete list of metadata

Cited literature [10 references]  Display  Hide  Download

Contributor : Svebor Karaman Connect in order to contact the contributor
Submitted on : Sunday, October 30, 2011 - 7:29:59 PM
Last modification on : Saturday, March 5, 2022 - 3:18:02 PM
Long-term archiving on: : Tuesday, January 31, 2012 - 2:22:02 AM


Publisher files allowed on an open archive


  • HAL Id : hal-00637120, version 1
  • ARXIV : 1110.6895


Svebor Karaman, Jenny Benois-Pineau, Rémi Mégret, Aurélie Bugeau. Multi-Layer Local Graph Words for Object Recognition. International Conference on MultiMedia Modeling, Jan 2012, Klagenfurt, Austria. pp.29-39. ⟨hal-00637120⟩



Record views


Files downloads