Shape Matching by Segmentation Averaging

  • Hongzhi Wang
  • John Oliensis
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5302)


We use segmentations to match images by shape. To address the unreliability of segmentations, we give a closed form approximation to an average over all segmentations. Our technique has many extensions, yielding new algorithms for tracking, object detection, segmentation, and edge-preserving smoothing. For segmentation, instead of a maximum a posteriori approach, we compute the “central” segmentation minimizing the average distance to all segmentations of an image. Our methods for segmentation and object detection perform competitively, and we also show promising results in tracking and edge–preserving smoothing.


Image Segmentation Segmentation Algorithm Object Detection Spatial Pyramid Spatial Pyramid Match 
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.


  1. 1.
    Agarwal, S., Roth, D.: Learning a sparse representation for object detection. In: Tistarelli, M., Bigun, J., Jain, A.K. (eds.) ECCV 2002. LNCS, vol. 2359, pp. 113–127. Springer, Heidelberg (2002)Google Scholar
  2. 2.
    Ahuja, N., Todorovic, S.: Learning the taxonomy and models of categories present in arbitrary images. ICCV (2007)Google Scholar
  3. 3.
    Basri, R., Jacobs, D.: Recognition using region correspondences. In: IJCV (1997)Google Scholar
  4. 4.
    Belongie, S., Malik, J., Puzicha, J.: Shape matching and object recognition using shape contexts. IEEE Trans. PAMI 24(4), 509–522 (2002)CrossRefGoogle Scholar
  5. 5.
    Berg, A., Malik, J.: Geometric blur for template matching. In: CVPR (2001)Google Scholar
  6. 6.
    Bosch, A., Zisserman, A., Munoz, X.: Representing shape with a spatial pyramid kernel. In: CIRV (2007)Google Scholar
  7. 7.
    Comaniciu, D., Meer, P.: Mean shift: a robust approach towards feature space analysis. IEEE Trans. PAMI 24(5), 603–619 (2002)CrossRefGoogle Scholar
  8. 8.
    Danal, N., Triggs, B.: k Histograms of oriented gradients for human detection. In: CVPR (2005)Google Scholar
  9. 9.
    Felzenszwalb, P., Huttenlocher, D.: Efficient graph-based image segmentation. IJCV 59(2) (2004)Google Scholar
  10. 10.
    Ferrari, V., Jurie, F., Schmid, C.: Accurate object detection with deformable shape models learnt from images. In: CVPR (2007)Google Scholar
  11. 11.
    Gdalyahu, Y., Weinshall, D., Werman, M.: Self organization in vision: stochastic clustering for image segmentation, perceptual grouping, and image database. IEEE Trans. PAMI 23(10), 1053–1074 (2001)CrossRefGoogle Scholar
  12. 12.
    Lazebnik, S., Schmid, C., Ponce, J.: Beyond bags of features: spatial pyramid matching for recognizing natural scene catergories. In: CVPR (2006)Google Scholar
  13. 13.
    Leibe, B., Leonardis, A., Schiele, B.: Combined object catergorization and segmentation with an implicit shape model. In: ECCV workshop on SLCV (2004)Google Scholar
  14. 14.
    Lowe, D.: Distinctive image features from scale-invariant keypoints. IJCV (2004)Google Scholar
  15. 15.
    Malik, J., Belongie, S., Leung, T., Shi, J.: Contour and texture analysis for image segmentation. IJCV (2001)Google Scholar
  16. 16.
    Martin, D.R., Fowlkes, C.C., Tal, D., Malik, J.: A database of human segmented natural images and its applications to evaluating segmentation algorithms and measuring ecological statistics. In: ICCV (2001)Google Scholar
  17. 17.
    Meila, M.: Comparing clusterings by the variation of information. In: COLT (2003)Google Scholar
  18. 18.
    Opelt, A., Pinz, A., Zisserman, A.: A boundary-fragment-model for object detection. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. LNCS, vol. 3954, pp. 575–588. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  19. 19.
    Opelt, A., Pinz, A., Zisserman, A.: Fusing shape and appearance information for object catergory detection. In: BMVC (2006)Google Scholar
  20. 20.
    Ross, D., Lim, J., Lin, R.-S., Yang, M.-H.: Incremental learning for robust visual tracking. In: IJCV (2007)Google Scholar
  21. 21.
    Russell, B., Efros, A., Sivic, J., Freeman, W., Zisserman, A.: Using multiple segmentations to discover objects and their extent in image collections. In: CVPR (2006)Google Scholar
  22. 22.
    Sharon, E., Galun, M., Sharon, D., Basri, R., Brandt, A.: Hierarchy and adaptivity in segmenting visual scenes. Nature (2006)Google Scholar
  23. 23.
    Shi, J., Malik, J.: Normalized cuts and image segmentation. IEEE Trans. PAMI 22(8), 888–905 (2000), CrossRefGoogle Scholar
  24. 24.
    Shotton, J., Blake, A., Cipolla, R.: Multi-scale categorical object recognition using contour fragments. IEEE Transactions on PAMI (2008)Google Scholar
  25. 25.
    Stauffer, C., Grimson, E.: Similarity templates for detection and recognition. In: CVPR (2001)Google Scholar
  26. 26.
    Unnikrishnan, R., Pantofaru, C., Hebert, M.: Toward objective evaluation of image segmentation algorithms. IEEE Trans. PAMI 29(6), 929–944 (2007)CrossRefGoogle Scholar
  27. 27.
    Young, W.E., Trent, R.H.: Geometric mean approximation of individual security and portfolio performance. J. Finan. Quant. Anal. 4, 179–199 (1969)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  • Hongzhi Wang
    • 1
  • John Oliensis
    • 1
  1. 1.Stevens Institute of TechnologyUSA

Personalised recommendations