Thürck, Daniel (2013)
A Well-Posed Parameter-Free Model for Nonlinear Diffusion and its Applications in Mobile Image Processing.
Technische Universität Darmstadt
Bachelorarbeit, Bibliographie
Kurzbeschreibung (Abstract)
Images and videos today represent our most important media. Recently, taking pictures and recording videos with mobile phones and uploading them to the internet has become common, especially in social networks. However, due to low-quality CCD sensors, those pictures often suffer from noise. A solution here would be to use quite well-known image processing algorithms, especially anisotropic diffusion. The most famous model, the Perona and Malik equation, unfortunately is ill-posed and thus is problematic. In this work, we present an alternative model for anisotropic diffusion that is constructed in a bottom-up fashion for denoising and well-posedness. The problem of setting the matching input parameters for denoising is tackled by the use of machine learning techniques. Ultimately, we present a prototypical implementation on embedded hardware that shows that the use of such sophisticated techniques is possible for mobile use.
| Typ des Eintrags: | Bachelorarbeit | ||||
|---|---|---|---|---|---|
| Erschienen: | 2013 | ||||
| Autor(en): | Thürck, Daniel | ||||
| Art des Eintrags: | Bibliographie | ||||
| Titel: | A Well-Posed Parameter-Free Model for Nonlinear Diffusion and its Applications in Mobile Image Processing | ||||
| Sprache: | Englisch | ||||
| Publikationsjahr: | 2013 | ||||
| Ort: | Darmstadt | ||||
| Kollation: | 65 p. | ||||
| Kurzbeschreibung (Abstract): | Images and videos today represent our most important media. Recently, taking pictures and recording videos with mobile phones and uploading them to the internet has become common, especially in social networks. However, due to low-quality CCD sensors, those pictures often suffer from noise. A solution here would be to use quite well-known image processing algorithms, especially anisotropic diffusion. The most famous model, the Perona and Malik equation, unfortunately is ill-posed and thus is problematic. In this work, we present an alternative model for anisotropic diffusion that is constructed in a bottom-up fashion for denoising and well-posedness. The problem of setting the matching input parameters for denoising is tackled by the use of machine learning techniques. Ultimately, we present a prototypical implementation on embedded hardware that shows that the use of such sophisticated techniques is possible for mobile use. |
||||
| Alternatives oder übersetztes Abstract: |
|
||||
| Freie Schlagworte: | Business Field: Digital society, Research Area: Generalized digital documents, Partial differential equations, Image processing, Machine learning, Mobile devices, Parallel algorithms | ||||
| Fachbereich(e)/-gebiet(e): | 20 Fachbereich Informatik 20 Fachbereich Informatik > Graphisch-Interaktive Systeme |
||||
| Hinterlegungsdatum: | 12 Nov 2018 11:16 | ||||
| Letzte Änderung: | 10 Dez 2021 07:23 | ||||
| PPN: | |||||
| Export: | |||||
| Suche nach Titel in: | TUfind oder in Google | ||||
 |
Frage zum Eintrag |
Optionen (nur für Redakteure)
 |
Redaktionelle Details anzeigen |
Drucken
Impressum