Titelaufnahme

Titel
Artifact-free decompression and zooming of JPEG compressed images with total generalized variation
VerfasserBredies, Kristian ; Holler, Martin
Erschienen in
Computer Vision, Imaging and Computer Graphics. Theory and Application / Gabriela Csurka ..., Berlin [u.a.], 2013, S. 242-258
SpracheEnglisch
DokumenttypAufsatz in einem Sammelwerk
Schlagwörter (EN)Artifact-free JPEG decompression / Total generalized Variation / Image reconstruction / Image zooming
Schlagwörter (GND)Bildverarbeitung / Online-Publikation
URNurn:nbn:at:at-ubg:3-1199 Persistent Identifier (URN)
DOIdoi:10.1007/978-3-642-11840-1 
Zugriffsbeschränkung
 Das Werk ist frei verfügbar
Dateien
Artifact-free decompression and zooming of JPEG compressed images with total generalized variation [2.86 mb]
Links
Nachweis
Klassifikation
Zusammenfassung (Englisch)

We propose a new model for the improved reconstruction and zooming of JPEG (Joint Photographic Experts Group) images. In the reconstruction process, given a JPEG compressed image, our method first determines the set of possible source images and then specifically chooses one of these source images satisfying additional regularity properties. This is realized by employing the recently introduced Total Generalized Variation (TGV) as regularization term and solving a constrained minimization problem. Data fidelity is modeled by the composition of a color-subsampling and a discrete cosine transformation operator. Furthermore, extending the notion of data set by allowing unconstrained intervals, the method facilitates optional magnification of the original image. In order to obtain an optimal solution numerically, we propose a primal-dual algorithm. We have developed a parallel implementation of this algorithm for the CPU and the GPU, using OpenMP and Nvidias Cuda, respectively. Finally, experiments have been performed, confirming a good visual reconstruction quality as well as the suitability for real-time application.

Notiz