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.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Lowe, D.G.: Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision 60(2), 91–110 (2004)
Sivic, J., Zisserman, A.: Video google: a text retrieval approach to object matching in videos. In: ICCV 2003, vol. 2, pp. 1470–1477 (2003)
Bay, H., Ess, A., Tuytelaars, T., Gool, L.V.: Surf:Speeded up robust features. Computer Vision and Image Understanding 110, 346–359 (2008)
Lazebnik, S., Schmid, C., Ponce, J.: Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories. In: Proc. CVPR (2006)
Albatal, R., Mulhem, P., Chiaramella, Y.: Visual Phrases for automatic images annotation. In: CBMI 2010, Grenoble, France (2010)
Mahboubi, A., Benois-Pineau, J., Barba, D.: Joint tracking of polygonal and triangulated meshes of objects in moving sequences with time varying content. In: IEEE International Conference on Image Processing, vol. 2, pp. 403–406 (2001)
Sahbi, H., Audibert, J.-Y., Rabarisoa, J., Keriven, R.: Robust matching and recognition using context-dependent kernels. In: Proceedings of the 25th International Conference on Machine Learning, pp. 856–863 (2008)
Gosselin, P.H., Cord, M., Philipp-Foliguet, S.: Combining visual dictionary, kernel-based similarity and learning strategy for image category retrieval. Computer Vision and Image Understanding 100(3) (June 2008)
SIVAL Data set, http://accio.cse.wustl.edu/sg-accio/SIVAL.html
Fei-Fei, L., Fergus, R., Perona, P.: One-Shot learning of object categories. IEEE Trans. Pattern Recognition and Machine Intelligence
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Karaman, S., Benois-Pineau, J., Mégret, R., Bugeau, A. (2012). Multi-layer Local Graph Words for Object Recognition. In: Schoeffmann, K., Merialdo, B., Hauptmann, A.G., Ngo, CW., Andreopoulos, Y., Breiteneder, C. (eds) Advances in Multimedia Modeling. MMM 2012. Lecture Notes in Computer Science, vol 7131. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-27355-1_6
Download citation
DOI: https://doi.org/10.1007/978-3-642-27355-1_6
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-27354-4
Online ISBN: 978-3-642-27355-1
eBook Packages: Computer ScienceComputer Science (R0)