Abstract
In this paper, we propose a new shape/object retrieval algorithm, co-transduction. The performance of a retrieval system is critically decided by the accuracy of adopted similarity measures (distances or metrics). Different types of measures may focus on different aspects of the objects: e.g. measures computed based on contours and skeletons are often complementary to each other. Our goal is to develop an algorithm to fuse different similarity measures for robust shape retrieval through a semi-supervised learning framework. We name our method co-transduction which is inspired by the co-training algorithm [1]. Given two similarity measures and a query shape, the algorithm iteratively retrieves the most similar shapes using one measure and assigns them to a pool for the other measure to do a re-ranking, and vice-versa. Using co-transduction, we achieved a significantly improved result of 97.72% on the MPEG-7 dataset [2] over the state-of-the-art performances (91% in [3], 93.4% in [4]). Our algorithm is general and it works directly on any given similarity measures/metrics; it is not limited to object shape retrieval and can be applied to other tasks for ranking/retrieval.
Chapter PDF
References
Blum, A., Mitchell, T.: Combining labeled and unlabeled data with co-training. In: Proc. of COLT, pp. 92–100 (1998)
Latecki, L., Lakámper, R., Eckhardt, U.: Shape descriptors for non-rigid shapes with a single closed contour. In: Proc. of CVPR, pp. 424–429 (2000)
Yang, X., Bai, X., Latecki, L., Tu, Z.: Improving shape retrieval by learning graph transduction. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part IV. LNCS, vol. 5305, pp. 788–801. Springer, Heidelberg (2008)
Kontschieder, P., Donoser, M., Bischof, H.: Beyond pairwise shape similarity analysis. In: Zha, H., Taniguchi, R.-i., Maybank, S. (eds.) Computer Vision – ACCV 2009. LNCS, vol. 5996. Springer, Heidelberg (2010)
Belongie, S., Malik, J., Puzicha, J.: Shape matching and object recognition using shape contexts. IEEE Trans. PAMI 24, 522–705 (2002)
Ling, H., Jacobs, D.: Shape classification using the inner-distance. IEEE Trans. PAMI 29, 286–299 (2007)
Sebastian, T.B., Klein, P.N., Kimia, B.B.: Recognition of shapes by editing their shock graphs. IEEE Trans. PAMI 25, 116–125 (2004)
Zhu, X.: Semi-supervised learning with graphs. In: Doctoral Dissertation, Carnegie Mellon University, CMU–LTI–05–192 (2005)
Yang, X., Koknar-Tezel, S., Latecki, L.: Locally constrained diffusion process on locally densified distance spaces with applications to shape retrieval. In: Proc. of CVPR (2009)
Zhou, Z.H., Li, M.: Semi-supervised regression with co-training. In: Proc. of IJCAI (2004)
Belkin, M., Niyogi, P., Sindhwani, V.: Manifold regularization: A geometric framework for learning from labeled and unlabeled examples. J. of Machine Learning Research 7, 2399–2434 (2006)
Wang, W., Zhou, Z.H.: Analyzing co-training style algorithms. In: Kok, J.N., et al. (eds.) ECML 2007. LNCS (LNAI), vol. 4701, pp. 454–465. Springer, Heidelberg (2007)
Coifman, R., Lafon, S.: Diffusion maps. Applied and Comp. Harmonic Ana. (2006)
Aslan, C., Erdem, A., Erdem, E., Tari, S.: Disconnected skeleton: Shape at its absolute scale. IEEE Trans. PAMI 30, 2188–2201 (2008)
Wei, C.H., Li, Y., Chau, W.Y., Li, C.T.: Trademark image retrieval using synthetic features for describing global shape and interior structure. Pattern Recognition 42, 386–394 (2009)
Tu, Z., Yuille, A.L.: Shape matching and recognition - using generative models and informative features. In: Pajdla, T., Matas, J(G.) (eds.) ECCV 2004. LNCS, vol. 3023, pp. 195–209. Springer, Heidelberg (2004)
Schmidt, F.R., Toeppe, E., Cremers, D.: Efficient planar graph cuts with applications in computer vision. In: Proc. of CVPR (2009)
Felzenszwalb, P.F., Schwartz, J.: Hierarchical matching of deformable shapes. In: CVPR (2007)
Xu, C., Liu, J., Tang, X.: 2d shape matching by contour flexibility. IEEE Trans. PAMI 31, 180–186 (2009)
Egozi, A., Keller, Y., Guterman, H.: Improving shape retrieval by spectral matching and meta similarity. IEEE Trans. Image Processing 19, 1319–1327 (2010)
Gonzalez, R., Woods, R., Eddins, S.: Digital image processing using matlab. Prentice-Hall, EnglewoodCliffs (2004)
Kim, Y.S., Kim, W.Y.: Content-based trademark retrieval system using a visually salient feature. Image and Vision Computing 16, 931–939 (1998)
Nistér, D., Stewénius, H.: Scalable recognition with a vocabulary tree. In: Proc. CVPR, pp. 2161–2168 (2006)
Sivic, J., Zisserman, A.: Video google: A text retrieval approach to object matching in videos. In: Proc. ICCV, pp. 1470–1477 (2003)
Jegou, H., Schmid, C., Harzallah, H., Verbeek, J.: Accurate image search using the contextual dissimilarity measure. IEEE Trans. PAMI 32, 2–11 (2010)
Stewénius, H., Nistér, D.: Object recognition benchmark, http://vis.uky.edu/%7Estewe/ukbench/
Mikolajczyk, K., Schmid, C.: Scale and affine invariant interest point detectors. IJCV 60, 63–86 (2004)
Lowe, D.: Distinctive image features from scale-invariant key points. IJCV 60, 91–110 (2004)
Bai, X., Yang, X., Latecki, L., Liu, W., Tu, Z.: Learning context sensitive shape similarity by graph transduction. IEEE Trans. PAMI 32, 861–874 (2010)
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
Bai, X., Wang, B., Wang, X., Liu, W., Tu, Z. (2010). Co-transduction for Shape Retrieval. In: Daniilidis, K., Maragos, P., Paragios, N. (eds) Computer Vision – ECCV 2010. ECCV 2010. Lecture Notes in Computer Science, vol 6313. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-15558-1_24
Download citation
DOI: https://doi.org/10.1007/978-3-642-15558-1_24
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-15557-4
Online ISBN: 978-3-642-15558-1
eBook Packages: Computer ScienceComputer Science (R0)