From Linear Representations to Object Parts

  • Gabriella Sanniti di Baja
  • L. Serino
  • Carlo Arcelli
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7329)


The use of the skeleton for object decomposition in the framework of the structural approach to shape description is discussed. Object decomposition is obtained starting from a suitable partition of the skeleton. The elements of the skeleton partition are then used as seeds from which to recover the various regions into which the object is decomposed. A merging process is also accomplished so as to have a final decomposition in accordance with human perception and stable when the object is available in different poses or sizes.


Basic Region Object Part Simple Curve Polygonal Approximation Identity Label 
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.
    Hoffman, D.D., Richards, W.A.: Parts of recognition. Cognition 18, 65–96 (1984)CrossRefGoogle Scholar
  2. 2.
    Biederman, I.: Recognition-by-components: a theory of human image understanding. Psycological Review 94(2), 115–147 (1987)CrossRefGoogle Scholar
  3. 3.
    Singh, M., Seyranian, G.D., Hoffman, D.D.: Parsing silhouettes: the short-cut rule. Perception & Psychophysics 61(4), 636–660 (1999)CrossRefGoogle Scholar
  4. 4.
    Shamir, A.: A survey on mesh segmentation techniques. Computer Graphics Forum 27(6), 1539–1556 (2008)zbMATHCrossRefGoogle Scholar
  5. 5.
    Sanniti di Baja, G., Thiel, E.: (3,4)-weighted skeleton decomposition for pattern representation and description. Pattern Recognition 27, 1039–1049 (1994)CrossRefGoogle Scholar
  6. 6.
    Cheng, Z.-Q., Li, B., Dang, G., Jin, S.-Y.: Meaningful Mesh Segmentation Guided by the 3D Short-Cut Rule. In: Chen, F., Jüttler, B. (eds.) GMP 2008. LNCS, vol. 4975, pp. 244–257. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  7. 7.
    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
  8. 8.
    Blum, H.: Biological shape and visual science. J. Theor. Biol. 38, 205–287 (1973)CrossRefGoogle Scholar
  9. 9.
    Borgefors, G.: On digital distance transform in three dimensions. CVIU 64(3), 368–376 (1996)Google Scholar
  10. 10.
    Arcelli, C., Sanniti di Baja, G., Serino, L.: Distance driven skeletonization in voxel images. IEEE Trans. PAMI 33(4), 709–720 (2011)CrossRefGoogle Scholar
  11. 11.
    Borgefors, G.: Digital distance transforms in 2D, 3D, and 4D. In: Chen, C.H., Wang, P.P.S. (eds.) Handbook of Pattern Recognition and Computer Vision, pp. 157–176. World Scientific, Singapore (2005)CrossRefGoogle Scholar
  12. 12.
    Svensson, S., Sanniti di Baja, G.: Using distance transforms to decompose 3D discrete objects. IMAVIS 20, 529–540 (2002)Google Scholar
  13. 13.
    Ramer, U.: An iterative procedure for the polygonal approximation of plane curves. CGIP 1, 244–256 (1972)Google Scholar
  14. 14.
    Borgefors, G., Sanniti di Baja, G.: Analyzing non-convex 2D and 3D patterns. CVIU 63(1), 145–157 (1996)Google Scholar
  15. 15.
    AIM@SHAPE Shape Repository,
  16. 16.
    Shilane, P., Min, P., Kazhdan, M., Funkhouser, T.: The Princeton Shape Benchmark, Shape Modeling International, Genova, Italy (2004)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Gabriella Sanniti di Baja
    • 1
  • L. Serino
    • 1
  • Carlo Arcelli
    • 1
  1. 1.Institute of Cybernetics “E.Caianiello”, CNRPozzuoliItaly

Personalised recommendations