From the Zones of Influence of Skeleton Branch Points to Meaningful Object Parts

  • L. Serino
  • C. Arcelli
  • G. Sanniti di Baja
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7749)


A 3D object decomposition method is presented, which is based on the decomposition of the linear skeleton guided by the zones of influence. These are the connected components of voxels obtained by applying the reverse distance transformation to the branch points of the skeleton. Their role is to group sufficiently close branch points and to detect perceptually meaningful skeleton branches that are in a one-to-one relation with the object parts.


Branch Point Overlap Region Object Part Input Object Tubular Shape 
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.


  1. 1.
    Palmer, S.E.: Hierarchical structure in perceptual representation. Cognitive Psychology 9, 441–474 (1977)MathSciNetCrossRefGoogle Scholar
  2. 2.
    Marr, D., Nishihara, H.K.: Representation and recognition of three-dimensional shapes. Proc. Royal Society of London: Series B 200, 269–294 (1978)CrossRefGoogle Scholar
  3. 3.
    Hoffman, D.D., Richards, W.A.: Parts of recognition. Cognition 18, 65–96 (1984)CrossRefGoogle Scholar
  4. 4.
    Biederman, I.: Recognition-by-components: A theory of human image understanding. Psychological Review 94, 115–147 (1987)CrossRefGoogle Scholar
  5. 5.
    Sanniti di Baja, G., Thiel, E.: The path-based distance skeleton: a flexible tool to analyse silhouette shape. In: Proc. 12th ICPR, vol. II, pp. 570–572 (1994)Google Scholar
  6. 6.
    Sanniti di Baja, G., Thiel, E.: (3,4)-weighted skeleton decomposition for pattern representation and description. Pattern Recognition 27, 1039–1049 (1994)Google Scholar
  7. 7.
    Cornea, N.D., Silver, D., Yuan, X., Balasubramanian, R.: Computing hierarchical curve-skeletons of 3D objects. The Visual Computer 21(11), 945–955 (2005)CrossRefGoogle Scholar
  8. 8.
    Lien, J.-M., Geyser, J., Amato, N.M.: Simultaneous shape decomposition and skeletonization. In: Proc. 2006 ACM Symposium on Solid and Physical Modeling, pp. 219–228 (2006)Google Scholar
  9. 9.
    Reniers, D., Telea, A.: Skeleton-based hierarchical shape segmentation. In: Proc. IEEE Int. Conf. on Shape Modeling and Applications, pp. 179–188 (2007)Google Scholar
  10. 10.
    Serino, L., Sanniti di Baja, G., Arcelli, C.: Object decomposition via curvilinear skeleton partition. In: Proc. 20th ICPR, pp. 4081–4084 (2010)Google Scholar
  11. 11.
    Serino, L., Sanniti di Baja, G., Arcelli, C.: Using the Skeleton for 3D Object Decomposition. In: Heyden, A., Kahl, F. (eds.) SCIA 2011. LNCS, vol. 6688, pp. 447–456. Springer, Heidelberg (2011)CrossRefGoogle Scholar
  12. 12.
    Chiang, P.-Y., Jay Kuo, C.-C.: Voxel-based shape decomposition for feature-preserving 3D thumbnail creation. J. Vis. Commun. Image R. 23, 1–11 (2012)CrossRefGoogle Scholar
  13. 13.
    Borgefors, G.: On digital distance transform in three dimensions. CVIU 64(3), 368–376 (1996)Google Scholar
  14. 14.
    Blum, H.: Biological shape and visual science. J. Theor. Biol. 38, 205–287 (1973)CrossRefGoogle Scholar
  15. 15.
    Nyström, I., Borgefors, G.: Synthesising Objects and Scenes Using the Reverse Distance Transformation in 2D and 3D. In: Braccini, C., Vernazza, G., DeFloriani, L. (eds.) ICIAP 1995. LNCS, vol. 974, pp. 441–446. Springer, Heidelberg (1995)CrossRefGoogle Scholar
  16. 16.
    Svensson, S., Sanniti di Baja, G.: Using distance transforms to decompose 3D discrete objects. Image and Vision Computing 20, 529–540 (2002)CrossRefGoogle Scholar
  17. 17.
    Arcelli, C., Sanniti di Baja, G., Serino, L.: Distance driven skeletonization in voxel images. IEEE Trans. PAMI 33(4), 709–720 (2011)CrossRefGoogle Scholar
  18. 18.
    Shilane, P., Min, P., Kazhdan, M., Funkhouser, T.: The Princeton Shape Benchmark, Shape Modeling International, Genova, Italy (June 2004)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • L. Serino
    • 1
  • C. Arcelli
    • 1
  • G. Sanniti di Baja
    • 1
  1. 1.Institute of Cybernetics “E. Caianiello”, CNRNaplesItaly

Personalised recommendations