Automatic Detection of Features (Markers) on a Three-Dimensional Model of a Human Face

  • Witold Stankiewicz
  • Michał Rychlik
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8513)


The post-processing and correlation analysis (like Proper Orthogonal Decomposition) requires the same topology for all objects in the database. Thus, in the case of 3D scanned data, registration is required. One of possible choices is elastic registration based on the known positions of certain markers (features) on the surface of each scanned object.

The present paper targets the method of automatic detection of such markers on the scanned human faces and the elastic deformation resulting in the same topology of the triangular meshes after the registration. Resulting data might be analyzed using methods like POD.


data registration 3D scanning POD PCA 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Lumley, J.L.: The structure of inhomogeneous turbulent flows. Atmospheric Turbulence and Radio Wave Propagation, 166–178 (1967)Google Scholar
  2. 2.
    Rychlik, M., Stankiewicz, W., Morzynski, M.: Application of modal analysis for extraction of geometrical features of biological objects set. In: BIODEVICES 2008: Proc. 1st Int. Conf. Biomed. Electronics and Devices, vol. 2, pp. 227–232 (2008)Google Scholar
  3. 3.
    Hoffmann, H.: Kernel PCA for Novelty Detection. Pattern Recognition 40, 863–874 (2007)CrossRefzbMATHGoogle Scholar
  4. 4.
    Lu, H., Plataniotis, K.N., Venetsanopoulos, A.N.: MPCA: Multilinear principal component analysis of tensor objects. IEEE Trans. Neural Netw. 19(1), 18–39 (2008)CrossRefGoogle Scholar
  5. 5.
    Stankiewicz, W., Roszak, R., Morzynski, M., Noack, B.R., Tadmor, G.: Continuous Mode Interpolation between Multiple Operating and Boundary Conditions for Reduced Order Modelling of the Flow. AIP Conference Proceedings 1389(1), 94–97 (2011)CrossRefGoogle Scholar
  6. 6.
    Shepard, D.: A two-dimensional interpolation function for irregularly-spaced data. In: Proceedings of the 1968 ACM National Conference, pp. 517–524 (1968)Google Scholar
  7. 7.
    Dhondt, G.: The Finite Element Method for Three-Dimensional Thermomechanical Applications. Wiley (2004)Google Scholar
  8. 8.
    Geuzaine, C., Remacle, J.F.: Gmsh: A 3D finite element mesh generator with built in pre and post processing facilities. International Journal for Numerical Methods in Engineering 79(11), 1309–1331 (2009)CrossRefzbMATHMathSciNetGoogle Scholar
  9. 9.
    Kennel, M.B.: KDTREE 2: Fortran 95 and C++ software to efficiently search for near neighbors in a multi-dimensional Euclidean space. arXiv preprint physics/0408067 (2004)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Witold Stankiewicz
    • 1
  • Michał Rychlik
    • 1
  1. 1.Division of Virtual EngineeringPoznan University of TechnologyPoland

Personalised recommendations