Skip to Main content Skip to Navigation
Book sections

Fuzzy Edge Detection in Computed Tomography Through Genetic Algorithm Optimization

Abstract : The ill posedness of the image reconstruction problem requires approached solution as a regularization of a specific criterion, in general, a penalty is imposed on the solution. The challenge is to avoid the smoothing of edges which are very important attributes of the image when it is regularized. The x-ray Tomography is classified as sensing problems for which we do not know the equipment measurement transfer function so it is considered as an ill posed inverse problem. Many studies have been developed to solve this problem, among them the Bayesian inference which aims at smoothing artifact in image. The problem for Bayesian methods is the edge penalization. In this work, we first present a fuzzy inference model for the edge preservation. Under this condition, we show that it is possible to find the best global solution to the problem by introducing genetic algorithm optimization (GA).
Document type :
Book sections
Complete list of metadata
Contributor : Kathleen TORCK Connect in order to contact the contributor
Submitted on : Thursday, October 28, 2021 - 10:05:06 AM
Last modification on : Wednesday, November 3, 2021 - 3:59:38 AM




Mohamed Tahar Ali Gouicem, Mostepha Yahi, Abdelmalik Taleb-Ahmed. Fuzzy Edge Detection in Computed Tomography Through Genetic Algorithm Optimization. Metaheuristics for Medicine and Biology, 704, Springer Berlin Heidelberg, pp.37-47, 2017, Studies in Computational Intelligence, ⟨10.1007/978-3-662-54428-0_3⟩. ⟨hal-03406836⟩



Record views