Multi-layer local graph words for object recognition

Authors:
Svebor Karaman;Jenny Benois-Pineau;Rémi Mégret;Aurélie Bugeau
Affiliations:
LaBRI - University of Bordeaux, Talence Cedex, France;LaBRI - University of Bordeaux, Talence Cedex, France;IMS - University of Bordeaux, Talence Cedex, France;LaBRI - University of Bordeaux, Talence Cedex, France
Venue:
MMM'12 Proceedings of the 18th international conference on Advances in Multimedia Modeling
Year:
2012

Citing 7
Cited 1

Video Google: A Text Retrieval Approach to Object Matching in Videos

ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Distinctive Image Features from Scale-Invariant Keypoints

International Journal of Computer Vision
One-Shot Learning of Object Categories

IEEE Transactions on Pattern Analysis and Machine Intelligence
Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories

CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2
Combining visual dictionary, kernel-based similarity and learning strategy for image category retrieval

Computer Vision and Image Understanding
Speeded-Up Robust Features (SURF)

Computer Vision and Image Understanding
Robust matching and recognition using context-dependent kernels

Proceedings of the 25th international conference on Machine learning

Visual word spatial arrangement for image retrieval and classification

Pattern Recognition

Quantified Score

Hi-index	0.00

Visualization

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. The combination of all layers, yields significant improvement of the object recognition performance.