Asymmetric Cuts: Joint Image Labeling and Partitioning

  • Thorben Kroeger
  • Jörg H. Kappes
  • Thorsten Beier
  • Ullrich Koethe
  • Fred A. Hamprecht
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8753)

Abstract

For image segmentation, recent advances in optimization make it possible to combine noisy region appearance terms with pairwise terms which can not only discourage, but also encourage label transitions, depending on boundary evidence. These models have the potential to overcome problems such as the shrinking bias. However, with the ability to encourage label transitions comes a different problem: strong boundary evidence can overrule weak region appearance terms to create new regions out of nowhere. While some label classes exhibit strong internal boundaries, such as the background class which is the pool of objects. Other label classes, meanwhile, should be modeled as a single region, even if some internal boundaries are visible.

We therefore propose in this work to treat label classes asymmetrically: for some classes, we allow a further partitioning into their constituent objects as supported by boundary evidence; for other classes, further partitioning is forbidden. In our experiments, we show where such a model can be useful for both 2D and 3D segmentation.

References

  1. 1.
    Alush, A., Goldberger, J.: Break and conquer: efficient correlation clustering for image segmentation. In: 2nd International Workshop on Similarity-Based Pattern Analysis and Recognition (2013)Google Scholar
  2. 2.
    Andres, B., Beier, T., Kappes, J.H.: OpenGM: A C++ library for discrete graphical models, ArXiv e-prints (2012). http://hci.iwr.uni-heidelberg.de/opengm2
  3. 3.
    Andres, B., Kappes, J.H., Beier, T., Kothe, U., Hamprecht, F.A.: Probabilistic image segmentation with closedness constraints. In: ICCV, pp. 2611–2618. IEEE(2011)Google Scholar
  4. 4.
    Andres, B., Kroeger, T., Briggman, K.L., Denk, W., Korogod, N., Knott, G., Koethe, U., Hamprecht, F.A.: Globally optimal closed-surface segmentation for connectomics. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part III. LNCS, vol. 7574, pp. 778–791. Springer, Heidelberg (2012)CrossRefGoogle Scholar
  5. 5.
    Arbelaez, P.: Boundary extraction in natural images using ultrametric contour maps. In: Conference on Computer Vision and Pattern Recognition Workshop, CVPRW’06, pp. 182–182. IEEE (2006)Google Scholar
  6. 6.
    Bagon, S., Galun, M.: Large scale correlation clustering optimization. CoRR abs/1112.2903 (2011)Google Scholar
  7. 7.
    Bansal, N., Blum, A., Chawla, S.: Correlation clustering. Mach. Learn. 56(1–3), 89–113 (2004)CrossRefMATHGoogle Scholar
  8. 8.
    Becker, C., Ali, K., Knott, G., Fua, P.: Learning context cues for synapse segmentation in EM volumes. In: Ayache, N., Delingette, H., Golland, P., Mori, K. (eds.) MICCAI 2012, Part I. LNCS, vol. 7510, pp. 585–592. Springer, Heidelberg (2012)CrossRefGoogle Scholar
  9. 9.
    Beier, T., Kroeger, T., Kappes, J.H., Koethe, U., Hamprecht, F.: Cut, glue & cut: A fast, approximate solver for multicut partitioning. In: CVPR (2014)Google Scholar
  10. 10.
    Borenstein, E., Ullman, S.: Class-specific, top-down segmentation. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002, Part II. LNCS, vol. 2351, pp. 109–122. Springer, Heidelberg (2002)CrossRefGoogle Scholar
  11. 11.
    Boykov, Y., Kolmogorov, V.: An experimental comparison of min-cut/max-flow algorithms for energy minimization in vision. Pattern Anal. Mach. Intell. 26(9), 1124–1137 (2004)CrossRefGoogle Scholar
  12. 12.
    Boykov, Y., Veksler, O., Zabih, R.: Fast approximate energy minimization via graph cuts. Pattern Anal. Mach. Intell. 23(11), 1222–1239 (2001)CrossRefGoogle Scholar
  13. 13.
    Chopra, S., Rao, M.: The partition problem. Math. Program. 59(1–3), 87–115 (1993). http://dx.doi.org/10.1007/BF01581239 MathSciNetCrossRefMATHGoogle Scholar
  14. 14.
    Everingham, M., Van Gool, L., Williams, C.K.I., Winn, J., Zisserman, A.: The PASCAL Visual Object Classes Challenge 2012 (VOC2012) Results. http://www.pascal-network.org/challenges/VOC/voc2012/workshop/index.html
  15. 15.
    Jain, V., Bollmann, B., Richardson, M., Berger, D.R., Helmstaedter, M.N., Briggman, K.L., Denk, W., Bowden, J.B., Mendenhall, J.M., Abraham, W.C., et al.: Boundary learning by optimization with topological constraints. In: CVPR. IEEE (2010)Google Scholar
  16. 16.
    Jurrus, E., Watanabe, S., Giuly, R.J., Paiva, A.R., Ellisman, M.H., Jorgensen, E.M., Tasdizen, T.: Semi-automated neuron boundary detection and nonbranching process segmentation in electron microscopy images. Neuroinformatics 11(1), 5–29 (2013)CrossRefGoogle Scholar
  17. 17.
    Kappes, J.H., Andres, B., Hamprecht, F.A., Schnörr, C., Nowozin, S., Batra, D., Kim, S., Kausler, B.X., Lellmann, J., Komodakis, N., Rother, C.: A comparative study of modern inference techniques for discrete energy minimization problems. In: CVPR (2013)Google Scholar
  18. 18.
    Kappes, J.H., Speth, M., Andres, B., Reinelt, G., Schn, C.: Globally optimal image partitioning by multicuts. In: Boykov, Y., Kahl, F., Lempitsky, V., Schmidt, F.R. (eds.) EMMCVPR 2011. LNCS, vol. 6819, pp. 31–44. Springer, Heidelberg (2011)Google Scholar
  19. 19.
    Kappes, J.H., Speth, M., Reinelt, G., Schnörr, C.: Higher-order segmentation via multicuts. CoRR abs/1305.6387 (2013)Google Scholar
  20. 20.
    Kim, S., Nowozin, S., Kohli, P., Yoo, C.: Task-specific image partitioning. Transactions on Image Processing (2012)Google Scholar
  21. 21.
    Kohli, P., Shekhovtsov, A., Rother, C., Kolmogorov, V., Torr, P.: On partial optimality in multi-label MRFs. In: ICML, pp. 480–487. ACM (2008)Google Scholar
  22. 22.
    Kolmogorov, V.: Convergent tree-reweighted message passing for energy minimization. IEEE Trans. Pattern Anal. Mach. Intell. 28(10), 1568–1583 (2006)CrossRefGoogle Scholar
  23. 23.
    Kolmogorov, V., Zabin, R.: What energy functions can be minimized via graph cuts? Pattern Anal. Mach. Intell. 26(2), 147–159 (2004)CrossRefGoogle Scholar
  24. 24.
    Komodakis, N., Paragios, N., Tziritas, G.: MRF energy minimization and beyond via dual decomposition. IEEE Trans. Pattern Anal. Mach. Intell. 33(3), 531–552 (2011)CrossRefGoogle Scholar
  25. 25.
    Komodakis, N., Tziritas, G.: Approximate labeling via graph cuts based on linear programming. IEEE Trans. Pattern Anal. Mach. Intell. 29(8), 1436–1453 (2007)CrossRefGoogle Scholar
  26. 26.
    Kreshuk, A., Straehle, C.N., Sommer, C., Koethe, U., Cantoni, M., Knott, G., Hamprecht, F.A.: Automated detection and segmentation of synaptic contacts in nearly isotropic serial electron microscopy images. PloS One 6(10), e24899 (2011)CrossRefGoogle Scholar
  27. 27.
    Kroeger, T., Mikula, S., Denk, W., Koethe, U., Hamprecht, F.A.: Learning to segment neurons with non-local quality measures. In: Mori, K., Sakuma, I., Sato, Y., Barillot, C., Navab, N. (eds.) MICCAI 2013, Part II. LNCS, vol. 8150, pp. 419–427. Springer, Heidelberg (2013)CrossRefGoogle Scholar
  28. 28.
    Lucchi, A., Smith, K., Achanta, R., Knott, G., Fua, P.: Supervoxel-based segmentation of mitochondria in EM image stacks with learned shape features. Trans. Med. Imaging 31(2), 474–486 (2012)CrossRefGoogle Scholar
  29. 29.
    Maire, M., Arbeláez, P., Fowlkes, C., Malik, J.: Using contours to detect and localize junctions in natural images. In: CVPR, pp. 1–8. IEEE (2008)Google Scholar
  30. 30.
    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. IEEE (2001)Google Scholar
  31. 31.
    Opelt, A., Pinz, A., Fussenegger, M., Auer, P.: Generic object recognition with boosting. Pattern Anal. Mach. Intell. 28(3), 416–431 (2006)CrossRefGoogle Scholar
  32. 32.
    Perazzi, F., Krähenbühl, P., Pritch, Y., Hornung, A.: Saliency filters: Contrast based filtering for salient region detection. In: CVPR, pp. 733–740. IEEE (2012)Google Scholar
  33. 33.
    Rother, C., Kolmogorov, V., Blake, A.: Grabcut: Interactive foreground extraction using iterated graph cuts. ACM Trans. Graph. 23, 309–314 (2004)CrossRefGoogle Scholar
  34. 34.
    Sommer, C., Straehle, C., Kothe, U., Hamprecht, F.A.: Ilastik: Interactive learning and segmentation toolkit. In: Symposium on Biomedical Imaging: From Nano to Macro, pp. 230–233. IEEE (2011)Google Scholar
  35. 35.
    Szeliski, R., Zabih, R., Scharstein, D., Veksler, O., Kolmogorov, V., Agarwala, A., Tappen, M., Rother, C.: A comparative study of energy minimization methods for Markov random fields. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. LNCS, vol. 3952, pp. 16–29. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  36. 36.
    Vicente, S., Kolmogorov, V., Rother, C.: Graph cut based image segmentation with connectivity priors. In: CVPR, pp. 1–8. IEEE (2008)Google Scholar
  37. 37.
    Yarkony, J., Ihler, A., Fowlkes, C.C.: Fast planar correlation clustering for image segmentation. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part VI. LNCS, vol. 7577, pp. 568–581. Springer, Heidelberg (2012)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Thorben Kroeger
    • 1
  • Jörg H. Kappes
    • 2
  • Thorsten Beier
    • 1
  • Ullrich Koethe
    • 1
  • Fred A. Hamprecht
    • 1
    • 2
  1. 1.Multidimensional Image Processing GroupHeidelberg UniversityHeidelbergGermany
  2. 2.Heidelberg Collaboratory for Image ProcessingHeidelberg UniversityHeidelbergGermany

Personalised recommendations