Advertisement

Fast Multi-view Graph Kernels for Object Classification

  • Luming Zhang
  • Mingli Song
  • Jiajun Bu
  • Chun Chen
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7106)

Abstract

Object classification is an important problem in multimedia information retrieval. In order to better objects classification, we often employ a set of multi-view images to describe an object for classification. However, two issues remain unsolved: 1) exploiting the spatial relations of local features in the multi-view images for classification, and 2) accelerating the classification process. To solve them, Fast Multi-view Graph Kernel (FMGK), is proposed. Given a set of multi-view images for an object, we segment each view image into several regions. And inter- and intra- view linkage graphs are constructed to describe the spatial relations of the regions between and within each multi-view image respectively. Then, the inter- and intra- view graphs are integrated into a so-called multi-view region graph. Finally, the kernel between objects is computed by accumulating all matchings’ of walk structures between corresponding multi-view region graphs. And a SVM [11] classifier is trained based on the computed kernels for object classification. The experimental results on different datasets validate the effectiveness of our FMGK.

Keywords

Support Vector Machine Spatial Relation Latent Dirichlet Allocation Scale Invariant Feature Transformation Product Graph 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Yuan, X.T., Zhu, H.W., Yang, S.T.: A Robust Framework For Eigenspace Image Reconstruction. In: IEEE Workshop on Motion and Video Computing, pp. 54–59 (2005)Google Scholar
  2. 2.
    Todorovic, S., Ahuja, N.: Region-based hierarchical image matching. In: IJCV (2007)Google Scholar
  3. 3.
    Fatih Demirci, M., Shokoufandeh, A., Keselman, Y., Bretzner, L., Dickinson, S.J.: Object recognition as many-to-many feature matching. In: IJCV (2006)Google Scholar
  4. 4.
    Felzenszwalb, P.F.: Pictorial structure for object recognition. In: IJCV (2005)Google Scholar
  5. 5.
    Hedau, V., Arora, H., Ahuja, N.: Matching images under unstable segmentations. In: Proc. of CVPR, pp. 1–8 (2008)Google Scholar
  6. 6.
    Keselman, Y., Dickinson, S.J.: Generic Model Abstraction from Examples. IEEE T-PAMI, 1141–1156 (2005)Google Scholar
  7. 7.
    Shervashidze, N., Vishwanathan, S.V.N., Petri, T., Mehlhorn, K., Borgwardt, K.M.: Efficient Graphlet Kernels for Large Graph Comparison. In: Proc. of ICAIS, pp. 488–495 (2009)Google Scholar
  8. 8.
    Lazebnik, S., Schmid, C., Ponce, J.: Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories. In: Proc. of CVPR, pp. 2169–2178 (2006)Google Scholar
  9. 9.
    Cao, L., Fei-Fei, L.: Spatially Coherent Latent Topic Model for Concurrent Segmentation and Classification of Objects and Scenes. In: Proc. of ICCV, pp. 1–8 (2007)Google Scholar
  10. 10.
    Porway, J., Wang, K., Yao, B., Zhu, S.C.: Scale-invariant shape features for recognition of object categories. In: Proc. of ICCV, pp. 90–96 (2004)Google Scholar
  11. 11.
    Duda, R.O., Hart, P.E., Stork, D.G.: Pattern Classification. Wiley-Interscience (2000)Google Scholar
  12. 12.
    Lazebnik, S., Schmid, C., Ponce, J.: Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories. In: Proc. of ICCV, pp. 2169–2178 (2006)Google Scholar
  13. 13.
    Cao, L., Fei-Fei, L.: Spatially Coherent Latent Topic Model for Concurrent Segmentation and Classification of Objects and Scenes. In: Proc. of ICCV, pp. 1–8 (2007)Google Scholar
  14. 14.
    Quelhas, P., Monay, F., Odobez, J.-M., Gatica-perez, D., Tuytelaars, T., Van Gool, L.: Modeling scenes with local descriptors and latent aspects. In: Proc. of ICCV, pp. 883–890 (2005)Google Scholar
  15. 15.
    Shi, J., Malik, J.: Normalized Cuts and Image Segmentation. IEEE T-PAMI (2000)Google Scholar
  16. 16.
    Everingham, M., Van Gool, L., Williams, C.K.I., Winn, J., Zisserman, A.: The PASCAL Visual Object Classes Challenge (VOC 2008) Results (2008), http://www.pascal-network.org/challenges/VOC/voc2008/workshop/index.html
  17. 17.
    Leibe, B., Schiele, B.: Analyzing Appearance and Contour Based Methods for Object Categorization. In: Proc. of CVPR, pp. 409–415 (2003)Google Scholar
  18. 18.
    Xia, T., Tao, D., Mei, T., Zhang, Y.: Multiview Spectral Embedding. IEEE T-SMCB, 1438–1446 (2010)Google Scholar
  19. 19.
    Xie, B., Mu, Y., Tao, D., Huang, K.: m-SNE: Multiview Stochastic Neighbor Embedding. IEEE T-SMCB, 338–346 (2010)Google Scholar
  20. 20.
    Harchaoui, Z., Bach, F.: Image Classification with Segmentation Graph Kernels. In: Proc. of CVPR (2007)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Luming Zhang
    • 1
  • Mingli Song
    • 1
  • Jiajun Bu
    • 1
  • Chun Chen
    • 1
  1. 1.College of Computer ScienceZhejiang UniversityChina

Personalised recommendations