Phase Based 3D Texture Features
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 : 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.
KeywordsSimultaneous Segmentation Rotational Invariant Feature Harmonic Band Harmonic Domain Spherical Harmonic Domain
Unable to display preview. Download preview PDF.
- 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.Ronneberger, O.: Libsvmtl - a support vector machine template library (2004), Download at: http://lmb.informatik.uni-freiburg.de/lmbsoft/libsvmtl/
- 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
- 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.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