Watersheds, extension maps, and the emergence paradigm

In this paper, we investigate the links between the flooding paradigm and the topological watershed. Guided by the analysis of a classical flooding algorithm, we introduce several notions that help us to understand the watershed: minima extension, extension map, and pass values. We investigate the possibility for a flooding to produce a topological watershed, and conclude that this is not feasible. This leads us to reverse the flooding paradigm, and to propose a notion of emergence. An emergence process is a transformation based on a topological criterion, in which points are processed in decreasing altitude order while preserving the number of connected components of lower cross-sections. Our main result states that any emergence watershed is a topological watershed, and more remarkably, that any topological watershed of a given image can be obtained as an emergence watershed of the image.

[1]  Pierre Soille,et al.  Order independent homotopic thinning for binary and grey tone anchored skeletons , 2002, Pattern Recognit. Lett..

[2]  Azriel Rosenfeld,et al.  On connectivity properties of grayscale pictures , 1981, Pattern Recognit..

[3]  Jos B. T. M. Roerdink,et al.  The Watershed Transform: Definitions, Algorithms and Parallelization Strategies , 2000, Fundam. Informaticae.

[4]  Laurent Najman,et al.  Watershed of a continuous function , 1994, Signal Process..

[5]  Michel Couprie,et al.  Watershed Algorithms and Contrast Preservation , 2003, DGCI.

[6]  Serge Beucher.  Segmentation d'images et morphologie mathématique , 1990 .

[7]  Fernand Meyer,et al.  Topographic distance and watershed lines , 1994, Signal Process..

[8]  Gilles Bertrand,et al.  Quasi-Linear Algorithms for the Topological Watershed , 2005, Journal of Mathematical Imaging and Vision.

[9]  Serge Beucher,et al.  Watershed, Hierarchical Segmentation and Waterfall Algorithm , 1994, ISMM.

[10]  Azriel Rosenfeld,et al.  Fuzzy Digital Topology , 1979, Inf. Control..

[11]  Gilles Bertrand,et al.  Topological operators for grayscale image processing , 2001, J. Electronic Imaging.

[12]  S. Beucher.  Use of watersheds in contour detection , 1979 .

[13]  Gilles Bertrand.  Some properties of topological grayscale watersheds , 2004, IS&T/SPIE Electronic Imaging.

[14]  Luc Vincent,et al.  Watersheds in Digital Spaces: An Efficient Algorithm Based on Immersion Simulations , 1991, IEEE Trans. Pattern Anal. Mach. Intell..

[15]  Laurent Najman.  Morphologie Mathématique: de la Segmentation d'Images à l'Analyse Multivoque. (Mathematical Morphology: from Image Segmentation to Set-Valued Analysis) , 1994 .

[16]  Luc Vincent,et al.  Determining watersheds in digital pictures via flooding simulations , 1990, Other Conferences.

[17]  Gilles Bertrand,et al.  Tesselations by Connection in Orders , 2000, DGCI.

[18]  Edward R. Dougherty,et al.  Hands-on Morphological Image Processing , 2003 .

[19]  Michel Couprie,et al.  Quasilinear algorithm for the component tree , 2004, IS&T/SPIE Electronic Imaging.

[20]  Kristel Michielsen,et al.  Morphological image analysis , 2000 .

[21]  P. Soille,et al.  Automated basin delineation from digital elevation models using mathematical morphology , 1990 .

[22]  Azriel Rosenfeld,et al.  The fuzzy geometry of image subsets , 1984, Pattern Recognit. Lett..

[23]  H. Heijmans.  Morphological image operators , 1994 .

[24]  Vartkes Goetcherian,et al.  From binary to grey tone image processing using fuzzy logic concepts , 1980, Pattern Recognit..

[25]  Gilles Bertrand,et al.  Image segmentation through operators based on topology , 1997, J. Electronic Imaging.

[26]  Alexandre X. Falcão,et al.  IFT-Watershed from gray-scale marker , 2002, Proceedings. XV Brazilian Symposium on Computer Graphics and Image Processing.

[27]  Laurent Najman,et al.  Geodesic Saliency of Watershed Contours and Hierarchical Segmentation , 1996, IEEE Trans. Pattern Anal. Mach. Intell..