Last update: July 8, 2000

BACK

Publications by Etienne Bertin et al. on shape symmetry elicitation :

• 2D and 3D Voronoi Diagrams, applications in image analysis, PhD, 1994.

BibTeX references.

The aim of this Ph.D. thesis is to show how computational geometry in the general case and the Voronoi diagram in the particular case contribute to image analysis. The purpose of image analysis is the description of the image content in order to interpret it and make a decision. Computational geometry is used to find optimal algorithms to solve geometric problems. We are interested here in the representation image problem. We will propose a solution based on the partitionning of the image content. Among the various solutions to partitionning, we will specifically develop the Voronoi model. The 3D shape codage by skeletons will then be developed as it relates to the generalized 3D Voronoi diagram. Image segmentation is an important problem in image analysis. We will present a new approach in a pyramidal environment, initialized by the Voronoi diagram and controled by Hopfiel neural networks. Finally, Markov random field will be used to determine an optimal partitionning in such a way which is still to be defined.

Keywords : Voronoi ; Delaunay ; analyse d'images ; segmentation ; pyramid ; Markov

BACK

Page created & maintained by Frederic Leymarie, 2000.
Comments, suggestions, etc., mail to: leymarie@lems.brown.edu