Details
| Originalsprache | Deutsch |
|---|---|
| Qualifikation | Doktor der Ingenieurwissenschaften |
| Gradverleihende Hochschule | |
| Betreut von |
|
| Datum der Verleihung des Grades | 21 Feb. 2017 |
| Publikationsstatus | Veröffentlicht - 2018 |
Abstract
Schlagwörter
- Super Resolution, Manifold Learning, Inverse Problems, Computer Vision Image Processing, Machine Learning, Upscaling
Zitieren
- Standard
- Harvard
- Apa
- Vancouver
- BibTex
- RIS
2018. 114 S.
Publikation: Qualifikations-/Studienabschlussarbeit › Dissertation
}
TY - BOOK
T1 - Manifold Learning for Super Resolution
AU - Pérez Pellitero, Eduardo
N1 - Dissertation
PY - 2018
Y1 - 2018
N2 - The development pace of high-resolution displays has been so fast in the recent years that many images acquired with low-end capture devices are already outdated or will be shortly in time. Super Resolution is central to match the resolution of the already existing image content to that of current and future high resolution displays and applications. This dissertation is focused on learning how to upscale images from the statistics of natural images. We build on a sparsity model that uses learned coupled low- and high-resolution dictionaries in order to upscale images, and move towards a more efficient L2 regularization scheme. Instead of using a patch-todictionary decomposition, we propose a fully collaborative neighbor embedding approach. We study the positive impact of antipodally invariant metrics for linear regression frameworks, and extend them by also taking into consideration the dihedral group of transforms (i.e. rotations and reflections), as a group of symmetries within the
AB - The development pace of high-resolution displays has been so fast in the recent years that many images acquired with low-end capture devices are already outdated or will be shortly in time. Super Resolution is central to match the resolution of the already existing image content to that of current and future high resolution displays and applications. This dissertation is focused on learning how to upscale images from the statistics of natural images. We build on a sparsity model that uses learned coupled low- and high-resolution dictionaries in order to upscale images, and move towards a more efficient L2 regularization scheme. Instead of using a patch-todictionary decomposition, we propose a fully collaborative neighbor embedding approach. We study the positive impact of antipodally invariant metrics for linear regression frameworks, and extend them by also taking into consideration the dihedral group of transforms (i.e. rotations and reflections), as a group of symmetries within the
KW - Super Resolution
KW - Manifold Learning
KW - Inverse Problems
KW - Computer Vision Image Processing
KW - Machine Learning
KW - Upscaling
M3 - Dissertation
ER -