Version franšaise

Using 2D Topological Map Information in a Markovian Image Segmentation

Using 2D Topological Map Information in a Markovian Image Segmentation

Damiand G., Alata O., Bihoreau C.
Procedings of 11th Discrete Geometry for Computer Imagery, Volume 2886, pages 288-297 - November 2003
Download the publication:  ps 
Topological map is a mathematical model of labeled image representation which contains both topological and geometrical information. In this work, we use this model to improve a Markovian segmentation algorithm. Image segmentation methods based on Markovian assumption consist in optimizing a Gibbs energy function. This energy function can be given by a sum of potentials which could be based on the shape or the size of a region, the number of adjacencies,... and can be computed by using topological map. In this work we propose the integration of a new potential: the global linearity of the boundaries, and show how this potential can be extracted from the topological map. Moreover, to decrease the complexity of our algorithm, we propose a local modification of the topological map in order to avoid the reconstruction of the entire structure.

BibTex references

@InProceedings{DAB2003_1642,
author = {Damiand, G. and Alata, O. and Bihoreau, C.},
title = {Using 2D Topological Map Information in a Markovian Image Segmentation.},
booktitle = {Procedings of 11th Discrete Geometry for Computer Imagery},
series = {LNCS},
volume = {2886},
pages = {288-297},
month = {November},
year = {2003},
address = {Naples, Italy},
url = {http://springerlink.metapress.com/link.asp?id=9lgpgl9lbl3yg43n},
}