A Segmentation Methodology for Real 3D Images
Segmentation is the process of dividing an image into segments that have similar attributes. There are a variety of traditional segmentation technique in the literature, mainly for 2D image processing applications. 3D segmentation is a much more complex problem. This is even harder for real 3D data sets where the images are degraded by blur and noise, the background is nonuniform and objects do not possess clear cut boundaries. These traditional techniques are usually unsuitable for segmentation of real 3D images. In this paper we present a novel and effective data driven segmentation framework based on a combination of nonlinear restoration and watershedding. The framework is presented and discussed as are experimental results showing its effectiveness in accurately segmenting real 3D images.
Unable to display preview. Download preview PDF.
- Pawley, J.B., “Handbook of Biological Confocal Microscopy”, Plenum Press. (1995)Google Scholar
- Razaz M and Lee R. A. “Restoration of 3D Real Images Using Projection onto Convex Sets”, Image Processing: Math. Methods & Applic., Oxford Univ. Press, pp. 127–144, 1997.Google Scholar
- Groetsch, C. W. “The theory of Tikhonov regularisation for Fredholm equations of the first kind”, Pitman, London, 1984.Google Scholar
- D.M.P. Hagyard and Razaz M “Analysis of Watershed Algorithms for Greyscale Images”, Proc. IEEE I.C Image Processing, Vol. I, 1996, pp. 41–44.Google Scholar
- Razaz M et al Three dimensional segmentation of optical microscope images, Proc. IEEE NSIP, 1997.Google Scholar
- Russ J.C. The image processing handbook, CRC Press, 1995.Google Scholar
- Dougherty, E.R., Mathematical Morphology in Image Processing New York: Marcel Dekker, Chapter 12, 1993.Google Scholar
- Beucher S. “Watershed of functions”, Proc. IEEE ICASSP, 1982.Google Scholar