Adaptation of Tensor Voting to Image Structure Estimation

  • Rodrigo Moreno
  • Luis Pizarro
  • Bernhard Burgeth
  • Joachim Weickert
  • Miguel Angel Garcia
  • Domenec Puig
Conference paper
Part of the Mathematics and Visualization book series (MATHVISUAL)


Tensor voting is a well-known robust technique for extracting perceptual information from clouds of points. This chapter proposes a general methodology to adapt tensor voting to different types of images in the specific context of image structure estimation. This methodology is based on the structural relationships between tensor voting and the so-called structure tensor, which is the most popular technique for image structure estimation. The problematic Gaussian convolution used by the structure tensor is replaced by tensor voting. Afterwards, the results are appropriately rescaled. This methodology is adapted to gray-valued, color, vector- and tensor-valued images. Results show that tensor voting can estimate image structure more appropriately than the structure tensor and also more robustly.


Noisy Image Structure Tensor Flat Region Structure Estimation Vote Process 
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.



This research has been partially supported by the Spanish Ministry of Science and Technology under project DPI2007-66556-C03-03, by the Commissioner for Universities and Research of the Department of Innovation, Universities and Companies of the Catalonian Government and by the European Social Fund.


  1. 1.
    Arseneau, S., Cooperstock, J.R.: An improved representation of junctions through asymmetric tensor diffusion. In: Bebis, G. et al. (eds.) Proc. Int. Symp. Vis. Comp. (ISVC). Lake Tahoe, NV, USA, Lecture Notes in Computer Science, vol. 4291, pp. I:363–372. Springer, Berlin/Heidelberg (2006)Google Scholar
  2. 2.
    Bigün, J., Granlund, G., Wiklund, J.: Multidimensional orientation estimation with applications to texture analysis and optical flow. IEEE Trans. Pattern Anal. Mach. Intell. 13(8), 775–790 (1991)Google Scholar
  3. 3.
    Bigün, J., Bigun, T., Nilsson, K.: Recognition by symmetry derivatives and the generalized structure tensor. IEEE Trans. Pattern Anal. Mach. Intell. 26(12), 1590–1605 (2004)Google Scholar
  4. 4.
    Brox, T., Weickert, J., Burgeth, B., Mrázek, P.: Nonlinear structure tensors. Image Vis. Comput. 24(1), 41–55 (2006)Google Scholar
  5. 5.
    Bruce, V., Green, P.R., Georgeson, M.A.: Visual Perception: Physiology, Psychology and Ecology, 4th edn. Psychology Press, London, UK (2003)Google Scholar
  6. 6.
    Burgeth, B., Didas, S., Weickert, J.: A general structure tensor concept and coherence-enhancing diffusion filtering for matrix fields. In: Laidlaw, D., Weikert, J. (eds.) Visualization and Processing of Tensor Fields: Advances and Perspectives, pp. 305–323. Springer, Berlin/Heidelberg (2009)Google Scholar
  7. 7.
    Di Zenzo, S.: A note on the gradient of a multi-image. Comput. Vis. Graph. Image Process. 33(1), 116–125 (1986)Google Scholar
  8. 8.
    Farnebäck, G., Rydell, J., Ebbers, T., Andersson, M., Knutsson, H.: Efficient computation of the inverse gradient on irregular domains. In: Int. Conf. Comput. Vis. (ICCV), Rio de Janeiro, pp. 1–8. IEEE Computer Society Press, Los Alamitos (2007)Google Scholar
  9. 9.
    Felsberg, M., Jonsson, E.: Energy tensors: quadratic, phase invariant image operators. In: Kropatsch, W., Sablatnig, R., Hanbury, A. (eds.) Proc. Symp. Ger. Assoc. Pattern Recognit. (DAGM), Vienna. Lecture Notes in Computer Science, vol. 3663, pp. 493–500. Springer, Berlin/New York (2005)Google Scholar
  10. 10.
    Förstner, W.: A feature based correspondence algorithm for image matching. In: Int. Arch. Photogramm. Remote Sens., Rovaniemi, vol. 26, pp. 150–166. ISPRS, Enschede (1986)Google Scholar
  11. 11.
    Förstner, W.: A framework for low-level feature extraction. In: Eklundh, J-O. (ed.) Proc. Eur. Conf. Comput. Vis. (ECCV), Stockholm. Lecture Notes in Computer Science, vol. 801, pp. 383–394. Springer, Berlin/New York (1994)Google Scholar
  12. 12.
    Granlund, G., Knutsson, H.: Signal Processing for Computer Vision. Kluwer, Dordrecht (1995)Google Scholar
  13. 13.
    Hahn, J., Lee, C.O.: A nonlinear structure tensor with the diffusivity matrix composed of the image gradient. J. Math. Imaging Vis. 34, 137–151 (2009)Google Scholar
  14. 14.
    Hwang, C., Zhuang, S., Lai, S.H.: Efficient intra mode selection using image structure tensor for H.264/AVC. In: Proc. Int. Conf. Image Process. (ICIP), San Antonio, pp. V:289–292. IEEE, Piscataway (2007)Google Scholar
  15. 15.
    Jia, J., Tang, C.K.: Inference of segmented color and texture description by tensor voting. IEEE Trans. Pattern Anal. Mach. Intell. 26(6), 771–786 (2004)Google Scholar
  16. 16.
    Kenney, C., Zuliani, M., Manjunath, B.: An axiomatic approach to corner detection. In: Proc. Comput. Vis. Pattern Recognit. (CVPR), San Diego, pp. I:191–197. IEEE Computer Society Press, Los Alamitos (2005)Google Scholar
  17. 17.
    Kim, H.S., Choi, H.K., Lee, K.H.: Feature detection of triangular meshes based on tensor voting theory. Comput.-Aided Des. 41(1), 47–58 (2009)Google Scholar
  18. 18.
    Kindlmann, G., Ennis, D.B., Whitaker, R., Westin, C.F.: Diffusion tensor analysis with invariant gradients and rotation tangents. IEEE Trans. Med. Imaging 26(11), 1483–1499 (2007)Google Scholar
  19. 19.
    Knutsson, H.: A tensor representation of 3-D structures. In: Proc. Workshop Multidimens. Signal Process. (1987)Google Scholar
  20. 20.
    Köthe, U.: Edge and junction detection with an improved structure tesnsor. In: Michaelis, B., Krell, G. (eds.) Proc. Symp. Ger. Assoc. Pattern Recognit. (DAGM), Magdeburg. Lecture Notes in Computer Science, vol. 2781, pp. 25–32. Springer, Berlin/New York (2003)Google Scholar
  21. 21.
    Köthe, U., Felsberg, M.: Riesz-transforms versus derivatives: on the relationship between the boundary tensor and the energy tensor. In: Kimmel, R., Sochen, N., Weickert, J. (eds.) Scale Space and PDE Methods in Computer Vision. Lecture Notes in Computer Science, vol. 3459, pp. 179–191. Hofgeismar, Germany (2005)Google Scholar
  22. 22.
    Lim, J., Park, J., Medioni, G.: Text segmentation in color images using tensor voting. Image Vis. Comput. 25(5), 671–685 (2007)Google Scholar
  23. 23.
    Loss, L.A., Bebis, G., Parvin, B.: Iterative tensor voting for perceptual grouping of ill-defined curvilinear structures: application to adherens junctions. IEEE Trans. Med. Imaging 30(8), 1503–1513 (2011)Google Scholar
  24. 24.
    Lucas, B.D., Kanade, T.: An iterative image registration technique with an application to stereo vision. In: Proc. Imagning Underst. Workshop, pp. 121–130 (1981)Google Scholar
  25. 25.
    Massad, A., Babós, M., Mertsching, B.: Application of the tensor voting technique for perceptual grouping to grey-level images. In: Van Gool, L. (ed.) Proc. Symp. Ger. Assoc. Pattern Recognit. (DAGM), Zürich. Lecture Notes in Computer Science, vol. 2449, pp. 306–313. Springer, Berlin/New York (2002)Google Scholar
  26. 26.
    Medioni, G., Lee, M.S., Tang, C.K.: A Computational Framework for Feature Extraction and Segmentation. Elsevier Science, Amsterdam/New York (2000)Google Scholar
  27. 27.
    Min, C., Medioni, G.: Inferring segmented dense motion layers using 5D tensor voting. IEEE Trans. Pattern Anal. Mach. Intell. 30(9), 1589–1602 (2008)Google Scholar
  28. 28.
    Mordohai, P., Medioni, G.: Dimensionality estimation, manifold learning and function approximation using tensor voting. J. Mach. Learn. 11, 411–450 (2010)Google Scholar
  29. 29.
    Moreno, R., Garcia, M.A., Puig, D.: Graph-based perceptual segmentation of stereo vision 3D images at multiple abstraction levels. In: Escolano, F., Vento, M. (eds.) Proc. Workshop Graph-Based Represent. Pattern Recognit. (GbRPR), Alicante. Lecture Notes in Computer Science, vol. 4538, pp. 148–157. Springer, Berlin/New York (2007)Google Scholar
  30. 30.
    Moreno, R., Garcia, M.A., Puig, D., Julià, C.: On adapting the tensor voting framework to robust color image denoising. In: Jiang, X., Petkov, N. (eds.) Proc. Comput. Anal. Images Patterns (CAIP), Münster. Lecture Notes in Computer Science, vol. 5702, pp. 492–500. Springer, Berlin/New York (2009)Google Scholar
  31. 31.
    Moreno, R., Garcia, M.A., Puig, D., Julià, C.: Robust color edge detection through tensor voting. In: Proceedings of International Conference on Image Processing (ICIP), Cairo, pp. 2153–2156. IEEE, Piscataway (2009)Google Scholar
  32. 32.
    Moreno, R., Garcia, M.A., Puig, D.: Robust color image segmentation through tensor voting. In: Proc. Int. Conf. Pattern Recognit (ICPR), Istanbul, Turkey, pp. 3372–3375 (2010)Google Scholar
  33. 33.
    Moreno, R., Garcia, M.A., Puig, D., Pizarro, L., Burgeth, B., Weickert, J.: On improving the efficiency of tensor voting. IEEE Trans. Pattern Anal. Mach. Intell. 33(11), 2215–2228 (2011)Google Scholar
  34. 34.
    Nagel, H.H., Gehrke, A.: Spatiotemporally adaptive estimation and segmentation of OF-fields. In: Burkhardt, H., Neumann, B. (eds.) Proc. Eur. Conf. Comput. Vis. (ECCV), Freiburg. Lecture Notes in Computer Science, vol. 1407, pp. 86–102. Springer, Berlin/New York (1998)Google Scholar
  35. 35.
    Nath, S., Palaniappan, K.: Adaptive robust structure tensors for orientation estimation and image segmentation. In: Boyle, R., Koracin, D., Parvin, B. (eds.) Proc. Int. Symp. Vis. Comp. (ISVC), Lake Tahoe. Lecture Notes in Computer Science, vol. 3804, pp. 445–453. Springer, Berlin/New York (2005)Google Scholar
  36. 36.
    Nicolescu, M., Medioni, G.: A voting-based computational framework for visual motion analysis and interpretation. IEEE Trans. Pattern Anal. Mach. Intell. 27(5), 739–752 (2005)Google Scholar
  37. 37.
    Pajevic, S., Aldroubi, A., Basser, P.J.: A continuous tensor field approximation of discrete DT-MRI data for extracting microstructural and architectural features of tissue. J. Magn. Reson. 154, 85–100 (2002)Google Scholar
  38. 38.
    Rao, A.R., Schunck, B.G.: Computing oriented texture fields. CVGIP: Graph. Models Image Process. 53, 157–185 (1991)Google Scholar
  39. 39.
    Rohr, K.: Localization properties of direct corner detectors. J. Math. Imaging Vis. 4, 139–150 (1994)Google Scholar
  40. 40.
    Rousson, M., Brox, T., Deriche, R.: Active unsupervised texture segmentation on a diffusion based feature space. In: Proc. Comput. Vis. Pattern Recognit. (CVPR), Madison, pp. II-699–704. IEEE, Los Alamitos (2003)Google Scholar
  41. 41.
    Schultz, T., Seidel, H.P.: Estimating crossing fibers: a tensor decomposition approach. IEEE Trans. Vis. Comput. Graph. 14(6), 1635–1642 (2008)Google Scholar
  42. 42.
    Tai, Y.W., Tong, W.S., Tang, C.K.: Perceptually-inspired and edge-directed color image super-resolution. In: Proc. Comput. Vis. Pattern Recognit. (CVPR), New York, NY, USA, pp. II:1948–1955. IEEE, Los Alamitos (2006)Google Scholar
  43. 43.
    Tang, C.K., Medioni, G., Lee, M.S.: N-Dimensional tensor voting and application to epipolar geometry estimation. IEEE Trans. Pattern Anal. Mach. Intell. 23(8), 829–844 (2001)Google Scholar
  44. 44.
    van de Weijer, J., van den Boomgaard, R.: Least squares and robust estimation of local image structure. Int. J. Comput. Vis. 64(2/3), 143–155 (2005)Google Scholar
  45. 45.
    Weickert, J.: Coherence-enhancing diffusion filtering. Int. J. Comput. Vis. 31(2–3), 111–127 (1999)Google Scholar
  46. 46.
    Weickert, J.: Coherence-enhancing diffusion of colour images. Image Vis. Comput. 17, 199–212 (1999)Google Scholar
  47. 47.
    Weickert, J., Brox, T.: Diffusion and regularization of vector- and matrix-valued images. In: Nashed, M.Z., Scherzer, O. (eds.) Inverse Problems, Image Analysis, and Medical Imaging, pp. 251–268. AMS, Providence (2002)Google Scholar
  48. 48.
    Westin, C.F., Knutsson, H.: Tensor field regularization using normalized convolution. In: Moreno Diaz, R., Pichler, F. (eds.) Proc. Int. Conf. Comput. Aided Syst. Theory (EUROCAST), Las Palmas de Gran Canaria. Lecture Notes in Computer Science, vol. 2809, pp. 564–572. Springer, Berlin/Heidelberg (2003)Google Scholar
  49. 49.
    Wu, T.P., Yeung, S.K., Jia, J., Tang, C.K.: Quasi-dense 3D reconstruction using tensor-based multiview stereo. In: Proc. Comput. Vis. Pattern Recognit. (CVPR), San Francisco, pp. 1482–1489. IEEE Computer Society Press, Los Alamitos (2010)Google Scholar

Copyright information

© Springer Berlin Heidelberg 2012

Authors and Affiliations

  • Rodrigo Moreno
    • 1
  • Luis Pizarro
    • 2
  • Bernhard Burgeth
    • 3
  • Joachim Weickert
    • 4
  • Miguel Angel Garcia
    • 5
  • Domenec Puig
    • 6
  1. 1.Department of Medical and Health Sciences (IMH)Linköping University, Center for Medical Image Science and Visualization (CMIV)LinköpingSweden
  2. 2.Department of ComputingImperial College LondonLondonUK
  3. 3.Faculty of Mathematics and Computer ScienceSaarland UniversitySaarbrückenGermany
  4. 4.Faculty of Mathematics and Computer ScienceSaarland University, Mathematical Image Analysis Group (MIA)SaarbrückenGermany
  5. 5.Department of Electronic and Communications TechnologyAutonomous University of MadridMadridSpain
  6. 6.Department of Computer Science and Mathematics, Intelligent Robotics and Computer Vision Group (IRCV)Rovira i Virgili UniversityTarragonaSpain

Personalised recommendations