Detection of Elongated Structures with Hierarchical Active Partitions and CEC-Based Image Representation

  • Arkadiusz Tomczyk
  • Przemysław Spurek
  • Michał Podgórski
  • Krzysztof Misztal
  • Jacek Tabor
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 403)


In this paper, a method of elongated structure detection is presented. In general, this is not a trivial task since standard image segmentation techniques require usually quite complex procedures to incorporate the information about the expected shape of the segments. The presented approach may be an interesting alternative for them. In its first phase, it changes the representation of the image. Instead of a set of pixels, the image is described by a set of ellipses representing fragments of the regions of similar color. This representation is obtained using cross-entropy clustering (CEC) method. The second phase analyses geometrical and spatial relationships between ellipses to select those of them that form an elongated structure within an acceptable range of its width. Both phases are elements of hierarchical active partition framework which iteratively collects semantic information about image content.


CEC Hierarchical active partition Structural description 



This project has been funded with support from the National Science Centre, Republic of Poland, decision number DEC-2012/05/D/ST6/03091.

\(-\) The work of Przemysław Spurek was supported by the National Centre of Science (Poland) [grant no. 2013/09/N/ST6/01178].

\(-\) The work of Krzysztof Misztal was supported by the National Centre of Science (Poland) [grant no. 2012/07/N/ST6/02192].

\(-\) The work of Jacek Tabor was supported by the National Centre of Science (Poland) [grant no. 2014/13/B/ST6/01792].


  1. 1.
    Cootes, T., Taylor, C., Cooper, D., Graham, J.: Active shape models - their training and application. CVGIP Image Underst. 61(1), 38–59 (1994)CrossRefGoogle Scholar
  2. 2.
    Davies, E.R.: Machine Vision: Theory, Algorithms, Practicalities. Morgan Kaufmann, San Francisco (2004)Google Scholar
  3. 3.
    Frisby, J., Stone, J.: Seeing: The Computational Approach to Biological Vision. The MIT Press, Cambridge (2010)Google Scholar
  4. 4.
    Gonzalez, R.C., Woods, R.E.: Digital Image Processing. Prentice Hall, Upper Saddle River (2002)Google Scholar
  5. 5.
    Iranpour-Boroujeni, T., Watanabe, A., Bashtar, R., Yoshioka, H., Duryea, J.: Quantification of cartilage loss in local regions of knee joints using semi-automated segmentation software: analysis of longitudinal data from the osteoarthritis initiative (OAI). Osteoarthr. Cartil. 19(3), 309–314 (2011)CrossRefGoogle Scholar
  6. 6.
    Kamieniecki, K., Spurek, P.: CEC: cross-entropy clustering., (2014), R package version 0.9.2
  7. 7.
    Kass, M., Witkin, A., Terzopoulos, D.: Snakes: active contour models. Int. J. Comput. Vis. 1, 321–331 (1988)CrossRefzbMATHGoogle Scholar
  8. 8.
    Laberge, M., Baum, T., Virayavanich, W., Nardo, L., Nevitt, M., Lynch, J., McCulloch, C., Link, T.: Obesity increases the prevalence and severity of focal knee abnormalities diagnosed using 3T MRI in middle-aged subjects - data from the osteoarthritis initiative. Skelet. Radiol. 41(6), 633–641 (2012)Google Scholar
  9. 9.
    Marr, D., Poggio, T., Ullman, S.: Vision: A Computational Investigation into the Human Representation and Processing of Visual Information. The MIT Press, Cambridge (2010)CrossRefGoogle Scholar
  10. 10.
    Schneider, E., Nevitt, M., McCulloch, C., Cicuttini, F., Duryea, J., Eckstein, F., Tamez-Pena, J.: Equivalence and precision of knee cartilage morphometry between different segmentation teams, cartilage regions, and MR acquisitions. Osteoarthr. Cartil. 20(8), 869–879 (2012)CrossRefGoogle Scholar
  11. 11.
    Śmieja, M., Tabor, J.: Image segmentation with use of cross-entropy clustering. In: Proceedings of the 8th International Conference on Computer Recognition Systems CORES 2013, pp. 403–409. Springer International Publishing (2013)Google Scholar
  12. 12.
    Sonka, M., Hlavac, V., Boyle, R.: Image Processing, Analysis, and Machine Vision. Cengage Learning, New York (2014)Google Scholar
  13. 13.
    Stehling, C., Liebl, H., Krug, R., Lane, N., Nevitt, M., Lynch, J., McCulloch, C., Link, T.: Patellar cartilage: T2 values and morphologic abnormalities at 3.0-T MR imaging in relation to physical activity in asymptomatic subjects from the osteoarthritis initiative. Radiology 254(2), 509–520 (2010)CrossRefGoogle Scholar
  14. 14.
    Tabor, J., Misztal, K.: Detection of elliptical shapes via cross-entropy clustering. In: Sanches, J.M., Micó, L., Cardoso, J.S. (eds.) Pattern Recognition and Image Analysis, pp. 656–663. Springer, Berlin (2013)CrossRefGoogle Scholar
  15. 15.
    Tabor, J., Spurek, P.: Cross-entropy clustering. Pattern Recognit. 47(9), 3046–3059 (2014)CrossRefGoogle Scholar
  16. 16.
    Tomczyk, A., Szczepaniak, P.S., Pryczek, M.: Cognitive hierarchical active partitions in distributed analysis of medical images. J. Ambient Intell. Hum. Comput. 4(3), 357–367 (2013)CrossRefGoogle Scholar
  17. 17.
    Urish, K., Williams, A., Durkin, J., Chu, C.: Registration of magnetic resonance image series for knee articular cartilage analysis: data from the osteoarthritis initiative. Cartilage 4(1), 20–27 (2013)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2016

Authors and Affiliations

  • Arkadiusz Tomczyk
    • 1
  • Przemysław Spurek
    • 2
  • Michał Podgórski
    • 3
  • Krzysztof Misztal
    • 2
  • Jacek Tabor
    • 2
  1. 1.Institute of Information TechnologyLodz University of TechnologyŁódźPoland
  2. 2.Faculty of Mathematics and Computer ScienceJagiellonian UniversityKrakówPoland
  3. 3.Department of Radiology and Diagnostic ImagingMedical University of LodzŁódźPoland

Personalised recommendations