Skip to Main content Skip to Navigation

Analyse d'images par des méthodes variationnelles et géométriques

Abstract : In this work, we study both theoretical and numerical aspects of an anisotropic Mumford-Shah problem for image restoration and segmentation. The Mumford-Shah functional allows to both reconstruct a degraded image and extract the contours of the region of interest. Numerically, we use the Amborsio-Tortorelli approximation to approach a minimizer of the Mumford-Shah functional. It Gamma-converges to the Mumford-Shah functional and allows also to extract the contours. However, the minimization of the Ambrosio-Tortorelli functional using standard discretization schemes such as finite differences or finite elements leads to difficulties. We thus present two new discrete formulations of the Ambrosio-Tortorelli functional using the framework of discrete calculus. We use these approaches for image restoration and for the reconstruction of normal vector field and feature extraction on digital data. We finally study another similar shape optimization problem with Robin boundary conditions. We first prove existence and partial regularity of solutions and then construct and demonstrate the Gamma-convergence of two approximations. Numerical analysis shows once again the difficulties dealing with Gamma-convergent approximations.
Document type :
Complete list of metadatas

Cited literature [118 references]  Display  Hide  Download
Contributor : Abes Star :  Contact
Submitted on : Friday, January 12, 2018 - 4:26:19 PM
Last modification on : Tuesday, May 19, 2020 - 8:08:33 AM
Long-term archiving on: : Monday, May 7, 2018 - 12:18:46 PM


Version validated by the jury (STAR)


  • HAL Id : tel-01682981, version 1



Marion Foare. Analyse d'images par des méthodes variationnelles et géométriques. Mathématiques générales [math.GM]. Université Grenoble Alpes, 2017. Français. ⟨NNT : 2017GREAM043⟩. ⟨tel-01682981⟩



Record views


Files downloads