Exploiting Low-Level Image Segmentation for Object Recognition

  • Volker Roth
  • Björn Ommer
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4174)


A method for exploiting the information in low-level image segmentations for the purpose of object recognition is presented. The key idea is to use a whole ensemble of segmentations per image, computed on different random samples of image sites. Along the boundaries of those segmentations that are stable under the sampling process we extract strings of vectors that contain local image descriptors like shape, texture and intensities. Pairs of such strings are aligned, and based on the alignment scores a mixture model is trained which divides the segments in an image into fore- and background. Given such candidate foreground segments, we show that it is possible to build a state-of-the-art object recognition system that exhibits excellent performance on a standard benchmark database. This result shows that despite the inherent problems of low-level image segmentation in poor data conditions, segmentation can indeed be a valuable tool for object recognition in real-world images.


Object Recognition Gaussian Mixture Model Training Image Category Label Segment Boundary 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Agarwal, S., Awan, A., Roth, D.: Learning to detect objects in images via a sparse, part-based representation. IEEE Trans. Pattern Anal. Machine Intell. 26(11) (2004)Google Scholar
  2. 2.
    Leibe, B., Schiele, B.: Scale-invariant object categorization using a scale-adaptive mean-shift search. In: Rasmussen, C.E., Bülthoff, H.H., Schölkopf, B., Giese, M.A. (eds.) DAGM 2004. LNCS, vol. 3175, pp. 145–153. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  3. 3.
    Ommer, B., Buhmann, J.M.: Object Categorization by Compositional Graphical Models. In: Rangarajan, A., Vemuri, B.C., Yuille, A.L. (eds.) EMMCVPR 2005. LNCS, vol. 3757, pp. 235–250. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  4. 4.
    Ommer, B., Buhmann, J.M.: Learning Compositional Categorization Models. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. LNCS, vol. 3953, pp. 316–329. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  5. 5.
    Berg, A.C., Berg, T.L., Malik, J.: Shape matching and object recognition using low distortion correspondence. In: CVPR 2005, pp. 26–33 (2005)Google Scholar
  6. 6.
    Yu, S.X., Gross, R., Shi, J.: Concurrent object recognition and segmentation by graph partitioning. In: NIPS, pp. 1383–1390. MIT Press, Cambridge (2002)Google Scholar
  7. 7.
    Geman, S., Potter, D.F., Chi, Z.: Composition Systems. Technical report, Division of Applied Mathematics, Brown University, Providence, RI (1998)Google Scholar
  8. 8.
    Fei-Fei, L., Fergus, R., Perona, P.: Learning generative visual models from few training examples: An incremental bayesian approach tested on 101 object categories. In: CVPR Workshop GMBV (2004)Google Scholar
  9. 9.
    Roth, V., Lange, T.: Adaptive Feature Selection in Image Segmentation. In: Rasmussen, C.E., Bülthoff, H.H., Schölkopf, B., Giese, M.A. (eds.) DAGM 2004. LNCS, vol. 3175, pp. 9–17. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  10. 10.
    Lange, T., Roth, V., Braun, M.L., Buhmann, J.M.: Stability-based validation of clustering solutions. Neural Computation 16(6), 1299–1323 (2004)MATHCrossRefGoogle Scholar
  11. 11.
    Belongie, S., Malik, J., Puzicha, J.: Matching shapes. In: ICCV 2001, pp. 454–463 (2001)Google Scholar
  12. 12.
    Smith, T.F., Waterman, M.S.: Identification of common molecular subsequences. Journal of Molecular Biology 147, 195–197 (1981)CrossRefGoogle Scholar
  13. 13.
    Roth, V., Steinhage, V.: Nonlinear discriminant analysis using kernel functions. In: Solla, S., Leen, T., Müller, K.R. (eds.) NIPS 12, pp. 568–574. MIT Press, Cambridge (1999)Google Scholar
  14. 14.
    Schölkopf, B., Smola, A., Müller, K.R.: Nonlinear component analysis as a kernel eigenvalue problem. Neural Computation 10(5), 1299–1319 (1998)CrossRefGoogle Scholar
  15. 15.
    Roth, V., Tsuda, K.: Pairwise coupling for machine recognition of hand-printed japanese characters. In: CVPR, pp. 1120–1125 (2001)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Volker Roth
    • 1
  • Björn Ommer
    • 1
  1. 1.ETH Zurich, Institute of Computational ScienceZurich

Personalised recommendations