Advertisement

A Convex Image Segmentation: Extending Graph Cuts and Closed-Form Matting

  • Youngjin Park
  • Suk I. Yoo
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6494)

Abstract

Image matting and segmentation are two closely related topics that concern extracting the foreground and background of an image. While the methods based on global optimization are popular in both fields, the cost functions and the optimization methods have been developed independently due to the different interests of the fields: graph cuts optimize combinatorial functions yielding hard segments, and closed-form matting minimizes quadratic functions yielding soft matte.

In this paper, we note that these seemingly different costs can be represented in very similar convex forms, and suggest a generalized framework based on convex optimization, which reveals a new insight. For the optimization, a primal-dual interior point method is adopted. Under the new perspective, two novel formulations are presented showing how we can improve the state-of-the-art segmentation and matting methods. We believe that this will pave the way for more sophisticated formulations in the future.

Keywords

Cost Function Mean Square Error Convex Optimization Hard Segment Data Term 
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.
    Argyriou, A., Evgeniou, T., Pontil, M.: Multi-task feature learning. In: Advances in Neural Information Processing Systems, vol. 19 (2007)Google Scholar
  2. 2.
    Bhusnurmath, A., Taylor, C.J.: Graph cuts via l\(_{\mbox{1}}\) norm minimization. IEEE Trans. PAMI 30, 1866–1871 (2008)CrossRefGoogle Scholar
  3. 3.
    Boyd, S., Vandenberghe, L.: Convex Optimization. Cambridge University Press, New York (2004)CrossRefzbMATHGoogle Scholar
  4. 4.
    Buatois, L., Caumon, G., Levy, B.: Concurrent number cruncher: an efficient sparse linear solver on the GPU. In: High Performance Computation Conference (2007)Google Scholar
  5. 5.
    Boykov, Y., Veksler, O., Zabih, R.: Fast approximate energy minimization via graph cuts. IEEE Trans. PAMI 23, 2001 (1999)Google Scholar
  6. 6.
    Ford, L.R., Fulkerson, D.R.: Maximal flow through a network. Canad. J. Math. 8, 399–404 (1956)MathSciNetCrossRefzbMATHGoogle Scholar
  7. 7.
    Fu, H., Ng, M.K., Nikolova, M., Barlow, J.L.: Efficient minimization methods of mixed l2-l1 and l1-l1 norms for image restoration. SIAM J. Sci. Comput. 27 (2006)Google Scholar
  8. 8.
    Goldberg, A.V., Tarjan, R.E.: A new approach to the maximum flow problem. In: Eighteenth Annual ACM Symposium on Theory of Computing, pp. 136–146 (1986)Google Scholar
  9. 9.
    Grady, L.: Random walks for image segmentation. IEEE Trans. PAMI 28(11), 1768–1783 (2006)CrossRefGoogle Scholar
  10. 10.
    Greig, D.M., Porteous, B.T., Seheult, A.H.: Exact maximum a posteriori estimation for binary images. Journal of the Royal Statistical Society (1989)Google Scholar
  11. 11.
    Gulshan, V., Rother, C., Criminisi, A., Blake, A., Zisserman, A.: Geodesic star convexity for interactive image segmentation. In: CVPR (2010)Google Scholar
  12. 12.
    He, K., Sun, J., Tang, X.: Fast matting using large kernel matting laplacian matrices. In: CVPR (2010)Google Scholar
  13. 13.
    Kim, S., Koh, K., Lustig, M., Boyd, S., Gorinevsky, D.: An interior-point method for large-scale l1-regularized least squares. IEEE Journal of Selected Topics in Signal Processing 1, 606–617 (2007)CrossRefGoogle Scholar
  14. 14.
    Lempitsky, V., Kohli, P., Rother, C., Sharp, T.: Image segmentation with a bounding box prior. In: CVPR (2009)Google Scholar
  15. 15.
    Levin, A., Lischinski, D., Weiss, Y.: A closed-form solution to natural image matting. IEEE Trans. PAMI (2008)Google Scholar
  16. 16.
    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 (2001)Google Scholar
  17. 17.
    Rhemann, C., Rother, C., Gelautz, M.: Improving color modeling for alpha matting. In: BMVC (2008)Google Scholar
  18. 18.
    Rhemann, C., Rother, C., Rav-Acha, A., Sharp, T.: High resolution matting via interactive trimap segmentation. In: CVPR, pp. 1–8 (2008)Google Scholar
  19. 19.
    Rhemann, C., Rother, C., Wang, J., Gelautz, M., Kohli, P., Rott, P.: A perceptually motivated online benchmark for image matting. In: CVPR, pp. 1826–1833 (2009)Google Scholar
  20. 20.
    Rother, C.: Grabcut dataset, http://tinyurl.com/grabcut
  21. 21.
    Rother, C., Kolmogorov, V., Blake, A.: “GrabCut”: interactive foreground extraction using iterated graph cuts. ACM Trans. Graphics 23, 309–314 (2004)CrossRefGoogle Scholar
  22. 22.
    Singaraju, D., Rother, C., Rhemann, C.: New appearance models for natural image matting. In: CVPR, pp. 659–666 (2009)Google Scholar
  23. 23.
    Singaraju, D., Vidal, R.: Interactive image matting for multiple layers. In: CVPR (2008)Google Scholar
  24. 24.
    Sinop, A.K., Grady, L.: A seeded image segmentation framework unifying graph cuts and random walker which yields a new algorithm. In: ICCV, pp. 1–8 (2007)Google Scholar
  25. 25.
    Vicente, S., Kolmogorov, V., Rother, C.: Graph cut based image segmentation with connectivity priors. In: ICCV (2008)Google Scholar
  26. 26.
    Wang, J., Cohen, M.F.: Image and video matting: a survey. Foundations and Trends in Computer Graphics and Vision 3, 97–175 (2007)CrossRefGoogle Scholar
  27. 27.
    Wang, J., Cohen, M.F.: Optimized color sampling for robust matting. In: CVPR, pp. 1–8 (2007)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Youngjin Park
    • 1
  • Suk I. Yoo
    • 1
  1. 1.Seoul National UniversityKwanakKorea

Personalised recommendations