Advertisement

Object Recognition with Hierarchical Stel Models

  • Alessandro Perina
  • Nebojsa Jojic
  • Umberto Castellani
  • Marco Cristani
  • Vittorio Murino
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6316)

Abstract

We propose a new generative model, and a new image similarity kernel based on a linked hierarchy of probabilistic segmentations. The model is used to efficiently segment multiple images into a consistent set of image regions. The segmentations are provided at several levels of granularity and links among them are automatically provided. Model training and inference in it is faster than most local feature extraction algorithms, and yet the provided image segmentation, and the segment matching among images provide a rich backdrop for image recognition, segmentation and registration tasks.

Keywords

Object Recognition Spatial Pyramid Histogram Intersection Spatial Pyramid Match Pyramid Match Kernel 
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.

Supplementary material

978-3-642-15567-3_2_MOESM1_ESM.wmv (982 kb)
Electronic Supplementary Material (983 KB)

References

  1. 1.
    Fei-Fei, L., Perona, P.: A bayesian hierarchical model for learning natural scene categories. In: CVPR 2005 (2005)Google Scholar
  2. 2.
    Sivic, J., Russell, B.C., Efros, A.A., Zisserman, A., Freeman, W.T.: Discovering objects and their location in images. In: ICCV 2005 (2005)Google Scholar
  3. 3.
    Russell, B.C., Efros, A., Sivic, S., Freeman, W.T., Zisserman, A.: Segmenting Scenes by Matching Image Composites. In: NIPS 2009 (2009)Google Scholar
  4. 4.
    Leibe, B., et al.: An implicit shape model for combined object categorization and segmentation. In: Ponce, J., Hebert, M., Schmid, C., Zisserman, A. (eds.) Toward Category-Level Object Recognition. LNCS, vol. 4170, pp. 508–524. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  5. 5.
    Ferrari, V., Zissermann, A.: Learning Visual Attributes. In: NIPS 2007 (2007)Google Scholar
  6. 6.
    Weber, M., Welling, M., Perona, P.: Unsupervised learning of models for recognition. In: Vernon, D. (ed.) ECCV 2000. LNCS, vol. 1842, pp. 18–32. Springer, Heidelberg (2000)CrossRefGoogle Scholar
  7. 7.
    Lazebnik, S., Schmid, C., Ponce, J.: Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories. In: CVPR 2006 (2006)Google Scholar
  8. 8.
    Grauman, K., Darrell, T.: The pyramid match kernel: Discriminative classification with sets of image features. In: ICCV 2005 (2005)Google Scholar
  9. 9.
    Jojic, N., Perina, A., Cristani, M., Murino, V., Frey, B.J.: Stel component analysis: Modeling spatial correlations in image class structure. In: CVPR 2009 (2009)Google Scholar
  10. 10.
    Jojic, N., Caspi, Y.: Capturing image structure with probabilistic index maps. In: CVPR 2004 (2004)Google Scholar
  11. 11.
    Russell, B., et al.: Using Multiple Segmentations to Discover Objects and their Extent in Image Collections. In: CVPR 2006 (2006)Google Scholar
  12. 12.
    Munder, S., Gavrila, D.: An experimental study on pedestrian classification. IEEE Transactions on Pattern Analysis and Machine Intelligence 28, 1863–1868 (2006)CrossRefGoogle Scholar
  13. 13.
    Papageorgiou, C., Poggio, T.: A trainable system for object detection. Int. J. Comput. Vision 38, 15–33 (2000)zbMATHCrossRefGoogle Scholar
  14. 14.
    Maji, S., Berg, A.C., Malik, J.: Classification using intersection kernel support vector machines is efficient. In: CVPR 2008 (2008)Google Scholar
  15. 15.
    Perina, A., et al.: A Hybrid Generative/discriminative Classification Framework Based on Free-energy Terms. In: ICCV 2009 (2009)Google Scholar
  16. 16.
    Dalal, N., Triggs, B.: Histograms of Oriented Gradients for Human Detection. In: ICCV 2005 (2005)Google Scholar
  17. 17.
    Cao, L., Fei-Fei, L.: Spatially Coherent Latent Topic Model for Concurrent Segmentation and Classification of Objects and Scenes. In: ICCV 2007 (2007)Google Scholar
  18. 18.
    Winn, J., Jojic, N.: LOCUS: Learning Object Classes with Unsupervised Segmentation. In: ICCV 2005 (2005)Google Scholar
  19. 19.
    Jojic, N., Winn, J., Zitnick, L.: Escaping local minima through hierarchical model selection: Automatic object discovery, segmentation, and tracking in video. In: CVPR 2006 (2006)Google Scholar
  20. 20.
    Boiman, O., Shechtman, E.: In Defense of Nearest-Neighbor Based Image Classification. In: CVPR 2008 (2008)Google Scholar
  21. 21.
    Yang, J., Yuz, K., Gongz, Y., Huang, T.: Linear Spatial Pyramid Matching Using Sparse Coding for Image Classification. In: CVPR 2009 (2009)Google Scholar
  22. 22.
    Kapoor, A., Grauman, K., Urtasun, R., Darrell, T.: Active Learning with Gaussian Processes for Object Categorization. In: ICCV 2007 (2007)Google Scholar
  23. 23.
    Sun, M., Su, H., Savarese, S., Fei-Fei, L.: A multi-view probabilistic model for 3d object classes. In: CVPR 2009 (2009)Google Scholar
  24. 24.
    Stauffer, C., Miller, E., Tieu, K.: Transform-invariant image decomposition with similarity templates. In: NIPS 2002 (2002)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Alessandro Perina
    • 1
    • 2
  • Nebojsa Jojic
    • 2
  • Umberto Castellani
    • 1
  • Marco Cristani
    • 1
    • 3
  • Vittorio Murino
    • 1
    • 3
  1. 1.University of Verona 
  2. 2.Microsoft Research 
  3. 3.Italian Institute of Technology 

Personalised recommendations