Skip to Main content Skip to Navigation
Theses

Adaptive control, regularization techniques and their applications in image

Abstract : An adaptive control and regularization techniques are studied for some linear and nonlinear ill-posed problems in image processing and computer vision. These methods are based on variational approach which constitutes the minimization of a suitable energy functional made up of two parts data term obtained from constancy of grey value assumption and regularization term which cope with ill-posed problem by its filling in effect property. We have provided a novel adaptive approach for optic flow and stero vision problems. Which is based on adaptive finite element method using unstructutred grid as the domain of computation, which allow the automatic choice of local optimal regularization parameters. Various linear and nonlinear variational models have been considered in this thesis for scientific computations of optic flow and stereo vision problems and an efficient adaptive control is obtained. This novel regularization strategy is controlled by the regularization parameter [alpha] which depends on space and a posteriori error estimator called residual error indicator. This local adptive behavior has encouraged us to experiment with other problems in image analysis such as denoising, we add a preliminary chapter on hte model of Perona-Malik. This work falls in to the category novel and advanced numerical strategies for scientific computations specifically for image motion problems
Document type :
Theses
Complete list of metadata

Cited literature [90 references]  Display  Hide  Download

https://hal.univ-lorraine.fr/tel-01749033
Contributor : Thèses Ul <>
Submitted on : Thursday, March 29, 2018 - 11:59:19 AM
Last modification on : Friday, July 9, 2021 - 11:30:45 AM
Long-term archiving on: : Friday, September 14, 2018 - 9:39:24 AM

File

Amur.Khua_Bux.SMZ1111.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : tel-01749033, version 1

Collections

Citation

Khua Bux Amur. Adaptive control, regularization techniques and their applications in image. General Mathematics [math.GM]. Université Paul Verlaine - Metz, 2011. English. ⟨NNT : 2011METZ011S⟩. ⟨tel-01749033⟩

Share

Metrics

Record views

57

Files downloads

46