Phase Based 3D Texture Features

  • Janis Fehr
  • Hans Burkhardt
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4174)


In this paper, we present a novel method for the voxel-wise extraction of rotation and gray-scale invariant features. These features are used for simultaneous segmentation and classification of anisotropic textured objects in 3D volume data. The proposed new class of phase based voxel-wise features achieves two major properties which can not be achieved by the previously known Haar-Integral based gray-scale features [1]: invariance towards non-linear gray-scale changes and a easy to handle data driven feature selection. In addition, the phase based features are specialized to encode 3D textures, while texture and shape information interfere in the Haar-Integral approach. Analog to the Haar-Integral features, the phase based approach uses convolution methods in the spherical harmonic domain in order to achieve a fast feature extraction.

The proposed features were evaluated and compared to existing methods on a database of volumetric data sets containing cell nuclei recorded in tissue by use of a 3D laser scanning microscope.


Simultaneous Segmentation Rotational Invariant Feature Harmonic Band Harmonic Domain Spherical Harmonic Domain 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Ronneberger, O., Fehr, J., Burkhardt, H.: Voxel-Wise Gray Scale Invariants for Simultaneous Segmentation and Classification. In: Kropatsch, W.G., Sablatnig, R., Hanbury, A. (eds.) DAGM 2005. LNCS, vol. 3663, pp. 85–92. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  2. 2.
    Wählby, C., et al.: Compining intensity, edge, and shape information for 2d and 3d segmentation of cell nuclei in tissue sections. Journal of Microscopy 215(1), 67–76 (2004)CrossRefMathSciNetGoogle Scholar
  3. 3.
    Fehr, J., Ronneberger, O., Kurz, H., Burkhardt, H.: Self-learning Segmentation and Classification of Cell-Nuclei in 3D Volumetric Data Using Voxel-Wise Gray Scale Invariants. In: Kropatsch, W.G., Sablatnig, R., Hanbury, A. (eds.) DAGM 2005. LNCS, vol. 3663, pp. 377–384. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  4. 4.
    Ronneberger, O.: Libsvmtl - a support vector machine template library (2004), Download at:
  5. 5.
    Vapnik, V.N.: The nature of statistical learning theory. Springer, Heidelberg (1995)zbMATHGoogle Scholar
  6. 6.
    Ronneberger, O., Fehr, J., Burkhardt, H.: Voxel-wise gray scale invariants for simultaneous segmentation and classification – theory and application to cell-nuclei in 3d volumetric data. Internal report 2/05, IIF-LMB, University Freiburg (2005)Google Scholar
  7. 7.
    Groemer, H.: Geometric Applications of Fourier Series and Spherical Harmonics. Cambridge University Press, Cambridge (1996)zbMATHCrossRefGoogle Scholar
  8. 8.
    Kazhdan, M., Funkhonser, T., Rusinkiewicz, S.: Rotation invariant spherical harmonic representation of 3D shape descriptors. In: Symposium on Geometry Processing (2003)Google Scholar
  9. 9.
    Vasconecelos, N.: Feature selection by maximum marginal diversity: optimality and implications for visual recognition. In: Proceedings of IEEE Conf. on Computer Vision and Pattern Recogniton, Madison, USA (2003)Google Scholar
  10. 10.
    Kurz, H., Papoutsi, M., Wilting, J., Christ, B.: Pericytes in experimental mda-mb231 tumor angiogenesis. Histochem. Cell Biol. 117, 527–534 (2002)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Janis Fehr
    • 1
  • Hans Burkhardt
    • 1
  1. 1.Institut für Informatik, Lehrstuhl für Mustererkennung und BildverarbeitungAlbert-Ludwigs-Universität FreiburgFreiburgDeutschland

Personalised recommendations