Advertisement

Function-described graphs applied to 3D object representation

  • Francesc Serratosa
  • Alberto Sanfeliu
Session 8: Recognition
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1310)

Abstract

The aim of this work is the characterization of a new structure called Function-Described Graphs (FDG) which can be used to represent objects in computer vision. The FDGs are useful in synthesizing structural information from a set of objects described through their structure. The FDG nodes and arcs are characterized by the probability distribution of the attributes of the ARGs nodes and arcs from where they have been synthesized. The FDG incorporates information of the family of the synthesized ARG and of the antagonistic node and arcs. In this work we apply this new structure to 3D object labeling.

Keywords

Random Graph Relational Structure Edge Type Node Attribute Label 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.

References

  1. [1]
    J.T.LWANG, KZHANG, G-W. CHIRN, “The approximate Graph Matching Problem”, IEEE pp. 284–288, 1994.Google Scholar
  2. [2]
    A.K.CWONG, J.CONSTANT and M.L.YOU, “Random graphs”, (H. BUNKE and A. SANFELIU eds.). “Syntactic and structural pattern recognition: Theory and applications”, World Scientific Publishing Co. Pte. Ltd pp 179–195, 1990.Google Scholar
  3. [3]
    A.SANFELIU and K.FU,“ A Distance Measure Between Attributed Relational Graphs for Pattern Recognition”, IEEE Trans. on Sys. man and cybern. Vol. smc 13 No 3 May/June, 1983.Google Scholar
  4. [4]
    R.C.WILSON, A.N.EVANS and E.R.HANCOCK, “Relational matching by discrete relaxation”, Image and vision computing, Vol. 13, pp 411–421, 1995.Google Scholar
  5. [5]
    W.Y.KIM and A.C.KAK, “3D object recognition using bipartite matching embedded in discrete relaxation”, IEEE Trans. Pattern anal. mach. intell. 13 pp 224–251, 1991.Google Scholar
  6. [6]
    L.SHAPIRO and R.M.HARALICK, “Matching relational structures using discrete relaxation”, (H. BUNKE and A. SANFELIU eds.). “Syntactic and structural pattern recognition: Theory and applications”, World Scientific Publishing Co. Pte. Ltd pp 179–195, 1990.Google Scholar
  7. [7]
    A. SANFELIU, “Matching Methods”, 8th Scandinavian conference on image analysis, 1993.Google Scholar
  8. [8]
    E.R.HANCOCK and J.KITTLER, “Discrete relaxation”, Pattern recognition Vol. 23 pp.711–733, 1990.Google Scholar
  9. [9]
    W.J.CHRISTMAS, J.KITTLER and M.PETROU, “Structural matching in computer vision using probabilistic relaxation”, PAMI, Vol. 17, No 8 pp 749–764, 1995.Google Scholar
  10. [10]
    D.H.BALLARD and C.M.BROWN, “Computer Vision”, Prentice Hall 1982.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1997

Authors and Affiliations

  • Francesc Serratosa
    • 1
  • Alberto Sanfeliu
    • 2
  1. 1.Departament d'Enginyeria InformàticaUniversitat Rovira i VirgiliItaly
  2. 2.Institut de Robòtica i Informàtica IndustrialUniversitat Politècnica de CatalunyaItaly

Personalised recommendations