Journal of Mathematical Imaging and Vision

, Volume 61, Issue 1, pp 160–171 | Cite as

Discrepancy: Local/Global Shape Characterization with a Roundness Bias

  • Asli Genctav
  • Sibel TariEmail author


Disk shape frequently appears as a reference in shape characterization applications. We propose a local measure of deviation from a disk as the local difference between numerical solution of a PDE on the shape and an analytical expression in the form of modified Bessel function. The deviation defined at each shape point defines a field over the shape. This field has useful properties, which we demonstrate via illustrative applications ranging from shape decomposition to shape characterization. Furthermore, we show that a global measure extracted from the field is capable of characterizing the body roundness and periphery thickness uniformity.


Global shape measures Shape entropy Roundness Signed distance Modified Bessel Screened Poisson 



The work is funded by Turkish National Science Foundation TUBITAK under Grant 112E208.


  1. 1.
    Aktas, M.A., Zunic, J.: A family of shape ellipticity measures for galaxy classification. SIAM J. Imaging Sci. 6(2), 765–781 (2013)MathSciNetCrossRefzbMATHGoogle Scholar
  2. 2.
    Baseski, E., Erdem, A., Tari, S.: Dissimilarity between two skeletal trees in a context. Pattern Recognit. 42(3), 370–385 (2009)CrossRefzbMATHGoogle Scholar
  3. 3.
    Genctav, M., Genctav, A., Tari, S.: Nonlocal via local-nonlinear via linear: a new part-coding distance field via screened poisson equation. J. Math. Imaging Vis. 55(2), 242–252 (2016)MathSciNetCrossRefzbMATHGoogle Scholar
  4. 4.
    Herrera-Navarro, A.M., Jimenez-Hernandez, H., Terol-Villalobos, I.R.: A probabilistic measure of circularity. In: Combinatorial Image Analysis, pp. 75–89. Springer (2012)Google Scholar
  5. 5.
    Latecki, L., Lakamper, R., Eckhardt, T.: Shape descriptors for non-rigid shapes with a single closed contour. CVPR 1, 424–429 (2000)Google Scholar
  6. 6.
    Maurer, C.R., Qi, R., Raghavan, V.: A linear time algorithm for computing exact euclidean distance transforms of binary images in arbitrary dimensions. IEEE Trans. Pattern Anal. Mach. Intell. 25(2), 265–270 (2003)CrossRefGoogle Scholar
  7. 7.
    Misztal, K., Tabor, J.: Ellipticity and circularity measuring via Kullback–Leibler divergence. J. Math. Imaging Vis. 55(1), 136–150 (2016)MathSciNetCrossRefzbMATHGoogle Scholar
  8. 8.
    Montero, R.S., Bribiesca, E.: State of the art of compactness and circularity measures. Int. Math. Forum 4(27), 1305–1335 (2009)MathSciNetzbMATHGoogle Scholar
  9. 9.
    Rosin, P.L.: Measuring shape: ellipticity, rectangularity, and triangularity. Mach. Vis. Appl. 14(3), 172–184 (2003)CrossRefGoogle Scholar
  10. 10.
    Tari, S.: Hierarchical shape decomposition via level sets. In: ISMM, pp. 215–225. Springer (2009)Google Scholar
  11. 11.
    Tari, S., Genctav, M.: From a non-local Ambrosio–Tortorelli phase field to a randomized part hierarchy tree. J. Math. Imaging Vis. 49(1), 69–86 (2014)CrossRefGoogle Scholar
  12. 12.
    van der Maaten, L., Hinton, G.: Visualizing high-dimensional data using t-SNE. J. Mach. Learn. Res. 9, 2579–2605 (2008)zbMATHGoogle Scholar
  13. 13.
    Zunic, J., Hirota, K., Rosin, P.L.: A Hu moment invariant as a shape circularity measure. Pattern Recognit. 43(1), 47–57 (2010)CrossRefzbMATHGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2018

Authors and Affiliations

  1. 1.Middle East Technical UniversityAnkaraTurkey

Personalised recommendations