Advertisement

Segmentation via NCuts and Lossy Minimum Description Length: A Unified Approach

  • Mingyang Jiang
  • Chunxiao Li
  • Jufu Feng
  • Liwei Wang
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6494)

Abstract

We investigate a fundamental problem in computer vision: unsupervised image segmentation. During the last decade, the Normalized Cuts has become very popular for image segmentation. NCuts guarantees a globally optimal solution in the continuous solution space, however, how to automatically select the number of segments for a given image is left as an open problem. Recently, the lossy minimum description length (LMDL) criterion has been proposed for segmentation of images. This criterion can adaptively determine the number of segments, however, as the optimization is combinatorial, only a suboptimal solution can be achieved by a greedy algorithm. The complementarity of both criteria motivates us to combine NCuts and LMDL into a unified fashion, to achieve a better segmentation: given the NCuts segmentations under different numbers of segments, we choose the optimal segmentation to be the one that minimizes the overall coding length, subject to a given distortion. We then develop a new way to use the coding length decrement as the similarity measure for NCuts, so that our algorithm is able to seek both the optimal NCuts solution under fixed number of segments, and the optimal LMDL solution among different numbers of segments. Extensive experiments demonstrate the effectiveness of our algorithm.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Duda, R., Hart, P., Stork, D.: Pattern Classification. John Wiley and Sons, Chichester (2001) 0-471-05669-3zbMATHGoogle Scholar
  2. 2.
    Comaniciu, D., Meer, P.: Mean shift: A robust approach toward feature space analysis. PAMI 24, 603–619 (2002)CrossRefGoogle Scholar
  3. 3.
    Felzenszwalb, P.F., Huttenlocher, D.P.: Efficient graph-based image segmentation. IJCV 59, 167–181 (2004)CrossRefGoogle Scholar
  4. 4.
    Ren, X., Fowlkes, C., Malik, J.: Learning probabilistic models for contour completion in natural images. IJCV 77, 47–63 (2008)CrossRefGoogle Scholar
  5. 5.
    Malik, J., Belongie, S., Leung, T.K., Shi, J.: Contour and texture analysis for image segmentation. IJCV 43, 7–27 (2001)CrossRefzbMATHGoogle Scholar
  6. 6.
    Zhu, S.C., Tu, Z.W.: Image segmentation by data-driven markov chain monte carlo. PAMI II, 131–138 (2002)Google Scholar
  7. 7.
    Chung, F.R.K.: Spectral graph theory. Regional Conference Series in Mathematics, vol. 92, pp. 1–212. American Mathematical Society, Providence (1997)CrossRefGoogle Scholar
  8. 8.
    Shi, J., Malik, J.: Normalized cuts and image segmentation. PAMI 22, 888–905 (2000)CrossRefGoogle Scholar
  9. 9.
    Yu, S.X., Shi, J.B.: Multiclass spectral clustering. In: ICCV, pp. 313–319 (2003)Google Scholar
  10. 10.
    Cour, T., Benezit, F., Shi, J.B.: Spectral segmentation with multiscale graph decomposition. In: CVPR, vol. II, pp. 1124–1131 (2005)Google Scholar
  11. 11.
    Kim, T.H., Lee, K.M., Lee, S.U.: Learning full pairwise affinities for spectral segmentation. In: CVPR (2010)Google Scholar
  12. 12.
    Ma, Y., Derksen, H., Hong, W., Wright, J.: Segmentation of multivariate mixed data via lossy data coding and compression. PAMI 29, 1546–1562 (2007)CrossRefGoogle Scholar
  13. 13.
    Yang, A.Y., Wright, J., Ma, Y., Sastry, S.S.: Unsupervised segmentation of natural images via lossy data compression. CVIU 110, 212–225 (2008)Google Scholar
  14. 14.
    Rao, S.R., Mobahi, H., Yang, A.Y., Sastry, S.S., Ma, Y.: Natural image segmentation with adaptive texture and boundary encoding. In: Zha, H., Taniguchi, R.-i., Maybank, S. (eds.) ACCV 2009. LNCS, vol. 5994, pp. 135–146. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  15. 15.
    Mobahi, H., Rao, S.R., Yang, A.Y., Sastry, S.S., Ma, Y.: Segmentation of natural images by texture and boundary compression. In: arXiv:1006.3679v1 (2010)Google Scholar
  16. 16.
    Bagon, S., Boiman, O., Irani, M.: What is a good image segment? A unified approach to segment extraction. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part IV. LNCS, vol. 5305, pp. 30–44. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  17. 17.
    Arbelaez, P., Maire, M., Fowlkes, C., Malik, J.: From contours to regions: An empirical evaluation. In: CVPR, pp. 2294–2301 (2009)Google Scholar
  18. 18.
    Ren, X.F., Malik, J.: Learning a classification model for segmentation. In: ICCV, pp. 10–17 (2003)Google Scholar
  19. 19.
    Ren, X.F., Fowlkes, C.C., Malik, J.: Scale-invariant contour completion using conditional random fields. In: ICCV, vol. II, pp. 1214–1221 (2005)Google Scholar
  20. 20.
    Mori, G.: Guiding model search using segmentation. In: ICCV (2005)Google Scholar
  21. 21.
    Martin, D., Fowlkes, C., Tal, D., Malik, J.: A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics. In: ICCV, vol. 2, pp. 416–423 (2001)Google Scholar
  22. 22.
    Shotton, J., Winn, J., Rother, C., Criminisi, A.: Textonboost: Joint appearance, shape and context modeling for multi-class object recognition and segmentation. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. LNCS, vol. 3951, pp. 1–15. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  23. 23.
    Rand, W.M.: Objective criteria for the evaluation of clustering methods. American Statistical Association Journal 66, 846–850 (1971)CrossRefGoogle Scholar
  24. 24.
    Meila, M.: Comparing clusterings: An axiomatic view. In: ICML (2005)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Mingyang Jiang
    • 1
    • 2
  • Chunxiao Li
    • 1
    • 2
  • Jufu Feng
    • 1
    • 2
  • Liwei Wang
    • 1
    • 2
  1. 1.Key Laboratory of Machine PerceptionPeking UniversityBeijingP.R. China
  2. 2.MOE, Department of Machine Intelligence, School of Electronics Engineering and Computer SciencePeking UniversityBeijingP.R. China

Personalised recommendations