Thèse soutenue

FR
Auteur / Autrice : Mehmet Türkan
Direction : Christine Guillemot
Type : Thèse de doctorat
Discipline(s) : Informatique
Date : Soutenance en 2011
Etablissement(s) : Rennes 1
Partenaire(s) de recherche : autre partenaire : Université européenne de Bretagne (2007-2016)

Mots clés

FR

Résumé

FR  |  
EN

This thesis presents novel exemplar-based texture synthesis methods for image prediction (i. E. , predictive coding) and image inpainting problems. The main contributions of this study can also be seen as extensions to simple template matching, however the texture synthesis problem here is well-formulated in an optimization framework with different constraints. The image prediction problem has first been put into sparse representations framework by approximating the template with a sparsity constraint. The proposed sparse prediction method with locally and adaptive dictionaries has been shown to give better performance when compared to static waveform (such as DCT) dictionaries, and also to the template matching method. The image prediction problem has later been placed into an online dictionary learning framework by adapting conventional dictionary learning approaches for image prediction. The experimental observations show a better performance when compared to H. 264/AVC intra and sparse prediction. Finally a neighbor embedding framework has been proposed for image prediction using two data dimensionality reductions methods: non-negative matrix factorization (NMF) and locally linear embedding (LLE). This framework has then been extended to the image inpainting problem. The experimental evaluations demonstrate the effectiveness of the underlying ideas in both image prediction and inpainting applications.