Local Histogram Based Segmentation Using the Wasserstein Distance

Abstract

We propose and analyze a nonparametric region-based active contour model for segmenting cluttered scenes. The proposed model is unsupervised and assumes pixel intensity is independently identically distributed. Our proposed energy functional consists of a geometric regularization term that penalizes the length of the partition boundaries and a region-based image term that uses histograms of pixel intensity to distinguish different regions. More specifically, the region data encourages segmentation so that local histograms within each region are approximately homogeneous. An advantage of using local histograms in the data term is that histogram differentiation is not required to solve the energy minimization problem. We use Wasserstein distance with exponent 1 to determine the dissimilarity between two histograms. The Wasserstein distance is a metric and is able to faithfully measure the distance between two histograms, compared to many pointwise distances. Moreover, it is insensitive to oscillations, and therefore our model is robust to noise. A fast global minimization method based on (Chan et al. in SIAM J. Appl. Math. 66(5):1632–1648, 2006; Bresson et al. in J. Math. Imaging Vis. 28(2):151–167, 2007) is employed to solve the proposed model. The advantages of using this method are two-fold. First, the computational time is less than that of the method by gradient descent of the associated Euler-Lagrange equation (Chan et al. in Proc. of SSVM, pp. 697–708, 2007). Second, it is able to find a global minimizer. Finally, we propose a variant of our model that is able to properly segment a cluttered scene with local illumination changes.

References

  1. Ambrosio, L., & Tortorelli, V. M. (1990). Approximation of functionals depending on jumps by elliptic functionals via Gamma convergence. Communications on Pure and Applied Mathematics, 43, 999–1036.

    MATH  Article  MathSciNet  Google Scholar 

  2. Aubert, G., Barlaud, M., Faugeras, O., & Jehan-Besson, S. (2005). Image segmentation using active contours: calculus of variations or shape gradients? SIAM Journal on Applied Mathematics, 1(2), 2128–2145.

    MathSciNet  Google Scholar 

  3. Aujol, J. F., Gilboa, G., Chan, T., & Osher, S. (2006). Structure-texture image decomposition—modeling, algorithms, and parameter selection. International Journal of Computer Vision, 67(1).

  4. Bresson, X., & Chan, T. (2007). Fast minimization of the vectorial total variation norm and applications to color image processing. UCLA CAM report 07-25.

  5. Bresson, X., Esedoglu, S., Vandergheynst, P., Thiran, J. P., & Osher, S. (2007). Fast global minimization of the active contour/snake model. Journal of Mathematical Imaging and Vision, 28(2), 151–167.

    Article  MathSciNet  Google Scholar 

  6. Caselles, V., Kimmel, R., & Sapiro, G. (1997). Geodesic active contours. International Journal of Computer Vision, 22(1), 61–79.

    MATH  Article  Google Scholar 

  7. Chambolle, A. (2004). An algorithm for total variation minimization and applications. Journal of Mathematical Imaging and Vision, 20(1–2), 89–97.

    MathSciNet  Google Scholar 

  8. Chan, T. F., & Vese, L. A. (2001). Active contours without edges. IEEE Transactions on Image Processing, 10(2), 266–277.

    MATH  Article  Google Scholar 

  9. Chan, T., Esedoglu, S., & Nikolova, M. (2006). Algorithms for finding global minimizers of image segmentation and denoising models. SIAM Journal on Applied Mathematics, 66(5), 1632–1648.

    MATH  Article  MathSciNet  Google Scholar 

  10. Chan, T., Esedoglu, S., & Ni, K. (2007). Histogram based segmentation using Wasserstein distances. In Proceedings of SSVM (pp. 697–708).

  11. Chartrand, R., Vixie, K., Wohlber, B., & Bollt, E. (2005). A gradient descent solution to the Monge-Kantorovich problem. Preprint: LA-UR-04-6305.

  12. Cohen, L. (1991). On active contour models and balloons. Computer Vision, Graphics, and Image Processing, 53, 211–218.

    MATH  Google Scholar 

  13. Georgiou, T., Michailovich, O., Rathi, Y., Malcolm, J., & Tannenbaum, A. (2007). Distribution metrics and image segmentation. Linear Algebra and its Applications, 405, 663–672.

    Article  MathSciNet  Google Scholar 

  14. Haker, S., Zhu, L., & Tannnenbaum, A. (2004). Optimal mass transport for registration and warping. International Journal of Computer Vision, 60(3), 225–240.

    Article  Google Scholar 

  15. Herbulot, A., Jehan-Besson, S., Barlaud, M., & Aubert, G. (2004). Shape gradient for image segmentation using information theory. In ICASSP (Vol. 3, pp. 21–24).

  16. Herbulot, A., Jehan-Besson, S., Duffner, S., Barlaud, M., & Aubert, G. (2006). Segmentation of vectorial image features using shape gradients and information measures. Journal of Mathematical Imaging and Vision, 25(3), 365–386.

    Article  MathSciNet  Google Scholar 

  17. Kantorovich, L. V. (1942). On the translocation of masses. Doklady Akademii Nauk SSSR, 37, 199–201.

    Google Scholar 

  18. Kass, M., Witkin, A., & Terzopoulos, D. (1991). Snakes: active contours model. International Journal of Computer Vision, 1, 1167–1186.

    Google Scholar 

  19. Kichenesamy, S., Kumar, A., Olver, P., Tannenbaum, A., & Yezzi, A. (1996). Conformal curvature flows: from phase transitions to active vision. Archive for Rational Mechanics and Analysis, 134, 275–301.

    Article  MathSciNet  Google Scholar 

  20. Kim, J., Fisher, J. W., Yezzi, A., Cetin, M., & Willsky, A. S. (2005). A nonparametric statistical method for image segmentation using information theory and curve evolution. IEEE Transactions on Image Processing, 14, 1486–1502.

    Article  MathSciNet  Google Scholar 

  21. Michailovich, O., Rathi, Y., & Tannenbaum, A. (2007). Image segmentation using active contours driven by the Bhattacharya gradient flow. IEEE Transactions on Image Processing, 16(11), 2787–2801.

    Article  MathSciNet  Google Scholar 

  22. Mory, B., & Ardon, R. (2007). Fuzzy region competition: a convex two-phase segmentation framework. In Proceedings of SSVM (pp. 214–226).

  23. Mumford, D., & Shah, J. (1989). Optimal approximation by piecewise smooth functions and associated variational problems. Communications on Pure and Applied Mathematics, 42, 577–685.

    MATH  Article  MathSciNet  Google Scholar 

  24. Osher, S., & Fedkiw, R. (2002). Applied mathematical sciences: Vol. 153. Level set methods and dynamic implicit surfaces. New York: Springer.

    Google Scholar 

  25. Osher, S., & Sethian, J. A. (1988). Fronts propagating with curvature-dependent speed: algorithms based on Hamilton-Jacobi formulation. Journal of Computational Physics, 79, 12–49.

    MATH  Article  MathSciNet  Google Scholar 

  26. Paragios, N., & Deriche, R. (2002). Geodesic active regions: a new paradigm to deal with frame partition problems in computer vision. Journal of Visual Communication and Image Representation, 13(1–2), 249–268.

    Article  Google Scholar 

  27. Parzen, E. (1962). On estimation of a probability density function and mode. Annals of Mathematical Statistics, 33, 1065–1076.

    MATH  Article  MathSciNet  Google Scholar 

  28. Rachev, S., & Rüschendorf, L. (1998). Mass transportation problems. Vol. I: Theory, Vol. II: Applications. Probability and its applications. New York: Springer.

    Google Scholar 

  29. Rubner, Y., Tomasi, C., & Guibas, L. J. (1998). A metric for distributions with applications to image databases. In: IEEE international conference on computer vision (pp. 59–66).

  30. Sapiro, G., & Caselles, V. (1997). Histogram modification via differential equations. Journal of Differential Equations, 135(2), 238–268.

    MATH  Article  MathSciNet  Google Scholar 

  31. Tu, Z., & Zhu, S. (2002). Image segmentation by data-driven Markov chain Monte Carlo. IEEE Transactions on Pattern Analysis and Machine Intelligence, 24(5).

  32. Vese, L. A., & Chan, T. F. (2002). A multiphase level set framework for image segmentation using the Mumford and Shah model. International Journal of Computer Vision, 50(3), 271–293.

    MATH  Article  Google Scholar 

  33. Villani, C. (2003). Graduate studies in mathematics: Vol. 58. Topics in optimal transportation. Providence: American Mathematical Society.

    Google Scholar 

  34. Yezzi, A. Jr., Tsai, A., & Willsky, A. (1999). A statistical approach to snakes for bimodal and trimodal imagery. In International conference on computer vision (pp. 898–903).

  35. Zhu, S. C., & Yuille, A. (1996). Region competition: unifying snakes, region growing, and Bayes/MDL for multiband image segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 18(9), 884–900.

    Article  Google Scholar 

  36. Zhu, W., Jiang, T., & Li, X. (2005). Local region based medical image segmentation using J-divergence measures. In Proceedings of EMBC.

Download references

Author information

Affiliations

Authors

Corresponding author

Correspondence to Kangyu Ni.

Additional information

This research is supported by ONR grant N00014-09-1-0105 and NSF grant DMS-0610079.

Rights and permissions

Open Access This is an open access article distributed under the terms of the Creative Commons Attribution Noncommercial License (https://creativecommons.org/licenses/by-nc/2.0), which permits any noncommercial use, distribution, and reproduction in any medium, provided the original author(s) and source are credited.

Reprints and Permissions

About this article

Cite this article

Ni, K., Bresson, X., Chan, T. et al. Local Histogram Based Segmentation Using the Wasserstein Distance. Int J Comput Vis 84, 97–111 (2009). https://doi.org/10.1007/s11263-009-0234-0

Download citation

Keywords

  • Image segmentation
  • Unsupervised
  • Wasserstein distance
  • Image processing
  • Computer vision
  • Nonparametric