Journal of Mathematical Imaging and Vision

, Volume 59, Issue 2, pp 187–210 | Cite as

A Transportation \(L^p\) Distance for Signal Analysis

  • Matthew Thorpe
  • Serim Park
  • Soheil Kolouri
  • Gustavo K. Rohde
  • Dejan Slepčev
Article
  • 252 Downloads

Abstract

Transport-based distances, such as the Wasserstein distance and earth mover’s distance, have been shown to be an effective tool in signal and image analysis. The success of transport-based distances is in part due to their Lagrangian nature which allows it to capture the important variations in many signal classes. However, these distances require the signal to be non-negative and normalised. Furthermore, the signals are considered as measures and compared by redistributing (transporting) them, which does not directly take into account the signal intensity. Here, we study a transport-based distance, called the \(TL^p\) distance, that combines Lagrangian and intensity modelling and is directly applicable to general, non-positive and multichannelled signals. The distance can be computed by existing numerical methods. We give an overview of the basic properties of this distance and applications to classification, with multichannelled non-positive one-dimensional signals and two-dimensional images, and colour transfer.

Keywords

Optimal transport Signal comparison Colour transfer Histogram specification Image Registration 

Notes

Acknowledgements

Authors gratefully acknowledge funding from the NSF (CCF 1421502) and the NIH (GM090033, CA188938) in contributing to a portion of this work. DS also acknowledges funding by NSF (DMS-1516677). The authors are grateful to the Center for Nonlinear Analysis at CMU for its support. In addition, the authors would like to thank the referees for their valuable comments that lead to significant improvements in the paper.

References

  1. 1.
    Åström, F., Petra, S., Schmitzer, B., Schnörr, C.: Image labeling by assignment. arXiv:1603.05285 (2016)
  2. 2.
    Aswolinskiy, W., Reinhart, R.F., Steil, J.: Artificial Neural Networks in Pattern Recognition: 7th IAPR TC3 Workshop, ANNPR 2016, Ulm, Germany, September 28–30, 2016, Proceedings, chapter Time Series Classification in Reservoir- and Model-Space: A Comparison, pp. 197–208. Springer International Publishing (2016)Google Scholar
  3. 3.
    Basu, S., Kolouri, S., Rohde, G.K.: Detecting and visualizing cell phenotype differences from microscopy images using transport-based morphometry. Proc. Natl. Acad. Sci. 111(9), 3448–3453 (2014)CrossRefGoogle Scholar
  4. 4.
    Benamou, J.-D., Brenier, Y.: A computational fluid mechanics solution to the Monge–Kantorovich mass transfer problem. Numer. Math. 84(3), 375–393 (2000)MathSciNetMATHCrossRefGoogle Scholar
  5. 5.
    Benamou, J.-D., Carlier, G., Cuturi, M., Nenna, L., Peyré, G.: Iterative bregman projections for regularized transportation problems. SIAM J. Sci. Comput. 37(2), A1111–A1138 (2015)MathSciNetMATHCrossRefGoogle Scholar
  6. 6.
    Birkhoff, G.: Three observations on linear algebra. Univ. Nac. Tacum án Rev. Ser. A 5, 147–151 (1946)MathSciNetMATHGoogle Scholar
  7. 7.
    Bonneel, N., Rabin, J., Peyré, G., Pfister, H.: Sliced and Radon Wasserstein barycenters of measures. J. Math. Imaging Vis. 51(1), 22–45 (2015)MathSciNetMATHCrossRefGoogle Scholar
  8. 8.
    Bonneel, N., Van De Panne, M., Paris, S., Heidrich, W.: Displacement interpolation using Lagrangian mass transport. In: ACM Transactions on Graphics (TOG)-Proceedings of ACM SIGGRAPH Asia 2011, vol. 30 (2011)Google Scholar
  9. 9.
    Brenier, Y., Frisch, U., Hénon, M., Loeper, G., Matarrese, S., Mohayaee, R., Sobolevski, A.: Reconstruction of the early universe as a convex optimization problem. Mon. Not. R. Astron. Soc. 346(2), 501–524 (2003)CrossRefGoogle Scholar
  10. 10.
    Chen, J., Paris, S., Durand, F.: Real-time edge-aware image processing with the bilateral grid. In: ACM SIGGRAPH 2007 Papers, SIGGRAPH ’07. ACM (2007)Google Scholar
  11. 11.
    Chen, Y., Georgiou, T.T., Tannenbaum, A.: Matrix optimal mass transport: a quantum mechanical approach. arXiv:1610.03041 (2016)
  12. 12.
    Chen, Y., Georgiou, T.T., Tannenbaum, A.: Interpolation of matrices and matrix-valued measures: the unbalanced case. arXiv:1612.05914 (2017)
  13. 13.
    Chizat, L., Peyré, G., Schmitzer, B., Vialard, F.-X.: An interpolating distance between optimal transport and Fisher–Rao metrics. Found. Comput. Math. doi: 10.1007/s10208-016-9331-y
  14. 14.
    Chizat, L., Peyré, G., Schmitzer, B., Vialard, F.-X.: Scaling algorithms for unbalanced optimal transport problems. arXiv:1607.05816 (2016)
  15. 15.
    Courty, N., Flamary, R., Tuia, D.: Machine Learning and Knowledge Discovery in Databases: European Conference, ECML PKDD 2014, Nancy, France, September 15–19, 2014. In: Proceedings, Part I, chapter Domain Adaptation with Regularized Optimal Transport, pp. 274–289. Springer, Berlin (2014)Google Scholar
  16. 16.
    Cuturi, M.: Sinkhorn distances: lightspeed computation of optimal transport. In: Proceeding NIPS’13 Proceedings of the 26th International Conference on Neural Information Processing Systems, pp. 2292–2300 (2013)Google Scholar
  17. 17.
    Ferradans, S., Papadakis, N., Rabin, J., Peyré, G., Aujol, J.-F.: Scale Space and Variational Methods in Computer Vision: 4th International Conference, SSVM 2013, Schloss Seggau, Leibnitz, Austria, June 2–6, 2013. In: Proceedings, chapter Regularized Discrete Optimal Transport, pp. 428–439. Springer, Berlin (2013)Google Scholar
  18. 18.
    Frisch, U., Matarrese, S., Mohayaee, R., Sobolevski, A.: A reconstruction of the initial conditions of the universe by optimal mass transportation. Nature 417(6886), 260–262 (2002)CrossRefGoogle Scholar
  19. 19.
    Frisch, U., Sobolevskii, A.: Application of optimal transportation theory to the reconstruction of the early universe. J. Math. Sci. (New York) 133(1), 303–309 (2004)MathSciNetGoogle Scholar
  20. 20.
    Frogner, C., Zhang, C., Mobahi, H., Araya-Polo, M., Poggio, T.A.: Learning with a Wasserstein loss. In: Proceeding NIPS’15 Proceedings of the 28th International Conference on Neural Information Processing Systems, pp. 2053–2061 (2015)Google Scholar
  21. 21.
    García Trillos, N., Slepčev, D.: Continuum limit of Total Variation on point clouds. Arch. Rational Mech. Anal. 220(1), 193–241 (2016)Google Scholar
  22. 22.
    Górecki, T., Łuczak, M.: Multivariate time series classification with parametric derivative dynamic time warping. Expert Syst. Appl. 42(5), 2305–2312 (2015)CrossRefGoogle Scholar
  23. 23.
    Grenander, U., Miller, M.I.: Computational anatomy: an emerging discipline. Q. Appl. Math. LVI(4), 617–694 (1998)MathSciNetMATHCrossRefGoogle Scholar
  24. 24.
    Haber, E., Rehman, T., Tannenbaum, A.: An efficient numerical method for the solution of the \(L_2\) optimal mass transfer problem. SIAM J. Sci. Comput. 32(1), 197–211 (2010)MathSciNetMATHCrossRefGoogle Scholar
  25. 25.
    Haker, S., Tannenbaum, A.: On the Monge–Kantorovich problem and image warping. IMA Vol. Math. Appl. 133, 65–86 (2003)MathSciNetMATHCrossRefGoogle Scholar
  26. 26.
    Haker, S., Tannenbaum, A., Kikinis, R.: Medical Image Computing and Computer-Assisted Intervention—MICCAI 2001: 4th International Conference Utrecht, The Netherlands, October 14–17, 2001 Proceedings, chapter Mass Preserving Mappings and Image Registration, pp. 120–127. Springer, Berlin (2001)Google Scholar
  27. 27.
    Haker, S., Zhu, L., Tannenbaum, A., Angenent, S.: Optimal mass transport for registration and warping. Int. J. Comput. Vis. 60(3), 225–240 (2004)CrossRefGoogle Scholar
  28. 28.
    Hug, R., Maitre, E., Papadakis, N.: Multi-physics optimal transportation and image interpolation. ESAIM. Math. Model. Numer. Anal. 49(6), 1671–1692 (2015)MathSciNetMATHCrossRefGoogle Scholar
  29. 29.
    Joshi, S.C., Miller, M.I.: Landmark matching via large deformation diffeomorphisms. IEEE Trans. Image Process. 9(8), 1357–1370 (2000)MathSciNetMATHCrossRefGoogle Scholar
  30. 30.
    Kadous, M.W.: Temporal classification: extending the classification paradigm to multivariate time series. PhD thesis, The University of New South Wales (2002)Google Scholar
  31. 31.
    Kantorovich, L.V.: On the translocation of masses. Dokl. Akad. Nauk SSSR 37, 199–201 (1942)MathSciNetMATHGoogle Scholar
  32. 32.
    Kantorovich, L.V.: A problem of Monge. Uspekhi Mat. Nauk. 3(24), 225–226 (1948)Google Scholar
  33. 33.
    Khan, A.M., Rajpoot, N., Treanor, D., Magee, D.: A nonlinear mapping approach to stain normalization in digital histopathology images using image-specific color deconvolution. IEEE Trans. Biomed. Eng. 61(6), 1729–1738 (2014)CrossRefGoogle Scholar
  34. 34.
    Kolouri, S., Park, S., Rohde, G.K.: The Radon cumulative distribution transform and its application to image classification. IEEE Trans. Image Process. 25(2), 920–934 (2016)MathSciNetCrossRefGoogle Scholar
  35. 35.
    Kolouri, S., Park, S., Thorpe, M., Slepčev, D., Rohde, G.K.: Transport-based analysis, modeling, and learning from signal and data distributions. arXiv:1609.04767 (2016)
  36. 36.
    Kolouri, S., Rohde, G.K.: Transport-based single frame super resolution of very low resolution face images. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4876–4884 (2015)Google Scholar
  37. 37.
    Kolouri, S., Tosun, A.B., Ozolek, J.A., Rohde, G.K.: A continuous linear optimal transport approach for pattern analysis in image datasets. Pattern Recognit. 51, 453–462 (2016)CrossRefGoogle Scholar
  38. 38.
    Kondratyev, S., Monsaingeon, L., Vorotnikov, D.: A new optimal transport distance on the space of finite radon measures. Adv. Differ. Equ. 21(11–12), 1117–1164 (2016)MathSciNetMATHGoogle Scholar
  39. 39.
    Kruskal, J.B.: Nonmetric multidimensional scaling: a numerical method. Psychometrika 29(2), 115–129 (1964)MathSciNetMATHCrossRefGoogle Scholar
  40. 40.
    Lellmann, J., Lorenz, D.A., Schönlieb, C., Valkonen, T.: Imaging with Kantorovich–Rubinstein discrepancy. SIAM J. Imaging Sci. 7(4), 2833–2859 (2014)MathSciNetMATHCrossRefGoogle Scholar
  41. 41.
    Lichman, M.: UCI machine learning repository (2013)Google Scholar
  42. 42.
    Liero, M., Mielke, A., Savaré, G.: Optimal transport in competition with reaction: the hellinger–kantorovich distance and geodesic curves. arXiv:1509.00068 (2015)
  43. 43.
    Liero, M., Mielke, A., Savaré, G.: Optimal entropy-transport problems and a new Hellinger–Kantorovich distance between positive measures. arXiv:1508.07941 (2016)
  44. 44.
    Lipman, Y., Daubechies, I.: Conformal Wasserstein distances: comparing surfaces in polynomial time. Adv. Math. 227(3), 1047–1077 (2011)MathSciNetMATHCrossRefGoogle Scholar
  45. 45.
    Magee, D., Treanor, D., Crellin, D., Shires, M., Smith, K., Mohee, K., Quirke, P.: Colour normalisation in digital histopathology images. In: Proceedings of Optical Tissue Image analysis in Microscopy, Histopathology and Endoscopy (MICCAI Workshop), vol. 100 (2009)Google Scholar
  46. 46.
    Mérigot, Q.: A multiscale approach to optimal transport. Comput. Graph. Forum 30(5), 1583–1592 (2011)CrossRefGoogle Scholar
  47. 47.
    Monge, G.: Mémoire sur la théorie des déblais et des remblais. Histoire de l’Académie Royale des Sciences, 666–704 (1781)Google Scholar
  48. 48.
    Montavon, G., Müller, K.-R., Cuturi, M.: Wasserstein training of Boltzmann machines. arXiv:1507.01972 (2015)
  49. 49.
    Morovic, J., Sun, P.-L.: Accurate 3d image colour histogram transformation. Pattern Recognit. Lett. 24(11), 1725–1735 (2003)CrossRefGoogle Scholar
  50. 50.
    Museyko, O., Stiglmayr, M., Klamroth, K., Leugering, G.: On the application of the Monge–Kantorovich problem to image registration. SIAM J. Imaging Sci. 2(4), 1068–1097 (2009)MathSciNetMATHCrossRefGoogle Scholar
  51. 51.
    Nikolova, M., Wen, Y.-W., Chan, R.: Exact histogram specification for digital images using a variational approach. J. Math. Imaging Vis. 46(3), 309–325 (2013)MathSciNetMATHCrossRefGoogle Scholar
  52. 52.
    Ning, L., Georgiou, T.T., Tannenbaum, A.: Matrix-valued monge–kantorovich optimal mass transport. In: 52nd IEEE Conference on Decision and Control, pp. 3906–3911 (2013)Google Scholar
  53. 53.
    Oberman, A.M., Ruan, Y.: An efficient linear programming method for optimal transportation. arXiv:1509.03668 (2015)
  54. 54.
    Oudre, L., Jakubowicz, J., Bianchi, P., Simon, C.: Classification of periodic activities using the Wasserstein distance. IEEE Trans. Biomed. Eng. 59(6), 1610–1619 (2012)CrossRefGoogle Scholar
  55. 55.
    Ozolek, J.A., Tosun, A.B., Wang, W., Chen, C., Kolouri, S., Basu, S., Huang, H., Rohde, G.K.: Accurate diagnosis of thyroid follicular lesions from nuclear morphology using supervised learning. Med. Image Anal. 18(5), 772–780 (2014)CrossRefGoogle Scholar
  56. 56.
    Papadakis, N., Bugeau, A., Caselles, V.: Image editing with spatiograms transfer. IEEE Trans. Image Process. 21(5), 2513–2522 (2012)MathSciNetCrossRefMATHGoogle Scholar
  57. 57.
    Paris, S., Durand, F.: A fast approximation of the bilateral filter using a signal processing approach. Int. J. Comput. Vis. 81(1), 24–52 (2009)CrossRefGoogle Scholar
  58. 58.
    Park, S., Kolouri, S., Kundu, S., Rohde, G.: The cumulative distribution transform and linear pattern classification. arXiv:1507.05936 (2015)
  59. 59.
    Pele, O., Werman, M.: A linear time histogram metric for improved sift matching. In: European conference on computer vision, pp. 495–508 (2008)Google Scholar
  60. 60.
    Pele, O., Werman, M.: Fast and robust Earth Mover’s Distances. In: IEEE 12th International Conference on Computer Vision, pp. 460–467 (2009)Google Scholar
  61. 61.
    Pitié, F., Kokaram, A.: The linear Monge–Kantorovitch linear colour mapping for example-based colour transfer. In: 4th European Conference on Visual Media Production, pp. 1–9 (2007)Google Scholar
  62. 62.
    Rabin, J., Ferradans, S., Papadakis, N.: Adaptive color transfer with relaxed optimal transport. In: IEEE International Conference on Image Processing (ICIP), pp. 4852–4856 (2014)Google Scholar
  63. 63.
    Rabin, J., Papadakis, N.: Geometric Science of Information: Second International Conference, GSI 2015, Palaiseau, France, October 28–30, 2015, Proceedings, chapter Non-convex Relaxation of Optimal Transport for Color Transfer Between Images, pp. 87–95. Springer International Publishing (2015)Google Scholar
  64. 64.
    Rabin, J., Peyré, G.: Wasserstein regularization of imaging problem. In: 18th IEEE International Conference on Image Processing (ICIP), pp. 1521–1544 (2011)Google Scholar
  65. 65.
    Rabin, J., Peyré, G., Cohen, L.D.: Computer Vision—ECCV 2010: 11th European Conference on Computer Vision, Heraklion, Crete, Greece, September 5-11, 2010, Proceedings, Part V, chapter Geodesic Shape Retrieval via Optimal Mass Transport, pp. 771–784. Springer, Berlin (2010)Google Scholar
  66. 66.
    Reinhard, E., Adhikhmin, M., Gooch, B., Shirley, P.: Color transfer between images. IEEE Comput. Graph. Appl. 21(5), 34–41 (2001)CrossRefGoogle Scholar
  67. 67.
    Rockafellar, R.T.: Convex Analysis. Princeton University Press, princeton (1970)MATHCrossRefGoogle Scholar
  68. 68.
    Rubner, Y., Tomasi, C., Guibas, L.J.: The Earth Mover’s Distance as a metric for image retrieval. Int. J. Comput. Vis. 40(2), 99–121 (2000)MATHCrossRefGoogle Scholar
  69. 69.
    Russell, E.J.: Letters to the editor-extension of Dantzig’s algorithm to finding an initial near-optimal basis for the transportation problem. Oper. Res. 17(1), 187–191 (1969)MATHCrossRefGoogle Scholar
  70. 70.
    Samaria, F.S., Harter, A.C.: Parameterisation of a stochastic model for human face identification. In: Proceedings of 1994 IEEE Workshop on Applications of Computer Vision, pp. 138–142 (1994)Google Scholar
  71. 71.
    Schmitzer, B.: Scale Space and Variational Methods in Computer Vision: 5th International Conference, SSVM 2015, Lège-Cap Ferret, France, May 31–June 4, 2015, Proceedings, chapter A sparse algorithm for dense optimal transport, pp. 629–641. Springer International Publishing (2015)Google Scholar
  72. 72.
    Schmitzer, B.: Stabilized sparse scaling algorithms for entropy regularized transport problems. arXiv:1610.06519 (2016)
  73. 73.
    Shinohara, R.T., Sweeney, E.M., Goldsmith, J., Shiee, N., Mateen, F.J., Calabresi, P.A., Jarso, S., Pham, D.L., Reich, D.S., Crainiceanu, C.M.: Statistical normalization techniques for magnetic resonance imaging. NeuroImage Clin. 6, 9–19 (2014)CrossRefGoogle Scholar
  74. 74.
    Solomon, J., de Goes, F., Peyré, G., Cuturi, M., Butscher, A., Nguyen, A., Du, T., Guibas, L.: Convolutional Wasserstein distances: efficient optimal transportation on geometric domains. ACM Trans. Graph. 34(4), 66:1–66:11 (2015)MATHCrossRefGoogle Scholar
  75. 75.
    Solomon, J., Rustamov, R., Guibas, L., Butscher, A.: Earth mover’s distances on discrete surfaces. ACM Trans. Graph. (TOG) 33(4), 67 (2014)CrossRefGoogle Scholar
  76. 76.
    Solomon, J., Rustamov, R., Leonidas, G., Butscher, A.: Wasserstein propagation for semi-supervised learning. In: Jebara, T., Xing, E.P. (eds. ) Proceedings of the 31st International Conference on Machine Learning (ICML-14), pp. 306–214. JMLR Workshop and Conference Proceedings (2014)Google Scholar
  77. 77.
    Su, Z., Zeng, W., Wang, Y., Lu, Z.-L., Gu, X.: Shape classification using Wasserstein distance for brain morphometry analysis. Inf. Process. Med. Imaging 24, 411–423 (2015)Google Scholar
  78. 78.
    Tannenbaum, E., Georgiou, T., Tannenbaum, A.: Signals and control aspects of optimal mass transport and the Boltzmann entropy. In: 49th IEEE Conference on Decision and Control (CDC), pp. 1885–1890 (2010)Google Scholar
  79. 79.
    Thorpe, M., Slepčev, D.: Transportation \(L^p\) distances: properties and extensions. In Preparation (2016)Google Scholar
  80. 80.
    Tosun, A.B., Yergiyev, O., Kolouri, S., Silverman, J.F., Rohde, G.K.: Novel computer-aided diagnosis of mesothelioma using nuclear structure of mesothelial cells in effusion cytology specimens. In: Proceedings of SPIE, vol. 9041, pp. 90410Z–90410Z–6 (2014)Google Scholar
  81. 81.
    Tosun, A.B., Yergiyev, O., Kolouri, S., Silverman, J.F., Rohde, G.K.: Detection of malignant mesothelioma using nuclear structure of mesothelial cells in effusion cytology specimens. Cytom. Part A 87(4), 326–333 (2015)CrossRefGoogle Scholar
  82. 82.
    ur Rehman, T., Haber, E., Pryor, G., Melonakos, J., Tannenbaum, A.: 3D nonrigid registration via optimal mass transport on the GPU. Med. Image Anal. 13(6), 931–940 (2009)CrossRefGoogle Scholar
  83. 83.
    Villani, C.: Topics in Optimal Transportation. Graduate Studies in Mathematics. American Mathematical Society, Providence (2003)Google Scholar
  84. 84.
    Villani, C.: Optimal Transport: Old and New. Springer, Berlin (2008)MATHGoogle Scholar
  85. 85.
    Wang, W., Slepčev, D., Basu, S., Ozolek, J.A., Rohde, G.K.: A linear optimal transportation framework for quantifying and visualizing variations in sets of images. Int. J. Comput. Vis. 101(2), 254–269 (2012)MathSciNetMATHCrossRefGoogle Scholar
  86. 86.
    Wang, Z., Bovik, A.C., Sheikh, H.R., Simoncelli, E.P.: Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13(4), 600–612 (2003)CrossRefGoogle Scholar
  87. 87.
    Weinberger, K.Q., Chapelle, O.: Large margin taxonomy embedding for document categorization. In: Advances in Neural Information Processing Systems, pp. 1737–1744 (2009)Google Scholar
  88. 88.
    Zhu, L., Haker, S., Tannenbaum, A.: Flattening maps for the visualization of multibranched vessels. IEEE Trans. Med. Imaging 24(2), 191–198 (2005)CrossRefGoogle Scholar
  89. 89.
    Zhu, L., Yang, Y., Haker, S., Tannenbaum, A.: An image morphing technique based on optimal mass preserving mapping. IEEE Trans. Image Process. 16(6), 1481–1495 (2007)MathSciNetCrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media New York 2017

Authors and Affiliations

  1. 1.Carnegie Mellon UniversityPittsburghUSA
  2. 2.University of VirginiaCharlottesvilleUSA
  3. 3.HRL LaboratoriesMalibuUSA

Personalised recommendations