Abstract
We are interested in incrementally discovering the set of object classes present in a scalable database of images. This paper describes a graph-based framework for learning the set of object classes in a weakly supervisedly manner. Rather than making use of the ”Bag-of-Features (BoF)” approach widely used in current work on object recognition, we represent each image by a graph using a group of selected local invariant features. Using local feature matching and iterative Procrustes alignment, we perform graph matching and compute a similarity measure. Borrowing the idea of query expansion, we develop a similarity propagation based graph clustering (SPGC) method. Using this method class specific clusters of the graphs can be obtained. Such a cluster can be generally represented by using a higher level graph model whose vertices are the clustered graphs, and the edge weights are determined by the pairwise similarity measure. Experiments are performed on a dataset, in which the number of images increases from 1 to 50K and the number of objects increases from 1 to over 500. Some objects have been discovered with total recall and a precision 1 in a single cluster.
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
Hofmann, T.: Unsupervised learning by probabilistic latent semantic analysis. Machine Learning 43, 17–196 (2001)
Blei, D., Ng, A., Jordan, M.: Latent dirichlet allocation. In: NIPS (2002)
Fei-Fei, L., Perona, P.: A bayesian hierarchical model for learning natural scene categories. In: CVPR (2005)
Sivic, J., Russell, B.C., Efros, A.A., Zisserman, A., Freeman, W.: Discovering object categories in image collections. In: ICCV (2005)
Russell, B.C., Efros, A.A., Sivic, J., Freeman, W.T., Zisserman, A.: Using multiple segmentations to discover objects and their extent in image collections. In: CVPR (2006)
Csurka, G., Bray, C., Dance, C., Fan, L.: Visual categorization with bags of keypoints. In: Workshop on Statistical Learning in Computer Vision, ECCV, pp. 1–22 (2004)
Sivic, J., Zisserman, A.: Video google: A text retrieval approach to object matching in videos. In: ICCV, pp. 1470–1477 (2003)
Li, Y., Wang, W., Gao, W.: A robust approach for object recognition. In: Zhuang, Y.-t., Yang, S.-Q., Rui, Y., He, Q. (eds.) PCM 2006. LNCS, vol. 4261, pp. 262–269. Springer, Heidelberg (2006)
Philbin, J., Sivic, J., Zisserman, A.: Geometric lda: A generative model for particular object discovery. In: BMVC (2008)
Lowe, D.: Distinctive image features from scale-invariant key points. IJCV 60(2), 91–110 (2004)
Chum, O., Philbin, J., Sivic, J., Isard, M., Zisserman, A.: Total recall: Automatic query expansion with a generative feature model for object retrieval. In: ICCV (2007)
Nister, D., Stewenius, H.: Scalable recognition with a vocabulary tree. In: CVPR (2006)
Philbin, J., Chum, O., Isard, M., Sivic, J., Zissermans, A.: Object retrieval with large vocabularies and fast spatial matching. In: CVPR (2007)
Xia, S.P., Ren, P., Hancock, E.R.: Ranking the local invariant features for the robust visual saliencies. In: ICPR 2008 (2008)
Chung, F.: Spectral graph theory. American Mathematical Society (1997)
Rothganger, F., Lazebnik, S., Schmid, C., Ponce, J.: 3d object modeling and recognition using local affine-invariant image descriptors and multi-view spatial constraints. IJCV 66(3), 231–259 (2006)
Xia, S., Hancock, E.: 3D object recognition using hyper-graphs and ranked local invariant features. In: da Vitoria Lobo, N., Kasparis, T., Roli, F., Kwok, J.T., Georgiopoulos, M., Anagnostopoulos, G.C., Loog, M. (eds.) S+SSPR 2008. LNCS, vol. 5342, pp. 117–126. Springer, Heidelberg (2008)
Jegou, H., Harzallah, H., Schmid, C.: A contextual dissimilarity measure for accurate and efficient image search. In: CVPR (2007)
Xia, S.P., Liu, J.J., Yuan, Z.T., Yu, H., Zhang, L.F., Yu, W.X.: Cluster-computer based incremental and distributed rsom data-clustering. ACTA Electronica sinica 35(3), 385–391 (2007)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2010 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Xia, S., Hancock, E.R. (2010). Incrementally Discovering Object Classes Using Similarity Propagation and Graph Clustering. In: Zha, H., Taniguchi, Ri., Maybank, S. (eds) Computer Vision – ACCV 2009. ACCV 2009. Lecture Notes in Computer Science, vol 5996. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-12297-2_36
Download citation
DOI: https://doi.org/10.1007/978-3-642-12297-2_36
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-12296-5
Online ISBN: 978-3-642-12297-2
eBook Packages: Computer ScienceComputer Science (R0)