| Paper: | TA-L4.4 |
| Session: | Image and Video Restoration and Enhancement I |
| Time: | Tuesday, September 18, 10:50 - 11:10 |
| Presentation: |
Lecture
|
| Title: |
IMAGE DENOISING BASED ON ADAPTED DICTIONARY COMPUTATION |
| Authors: |
Noura Azzabou; Laboratoire MAS/ Ecole Centrale - DxOLabs | | |
| | Nikos Paragios; Laboratoire MAS/ Ecole Centrale | | |
| | Frédéric Guichard; DxOLabs | | |
| Abstract: |
This paper introduces a new denoising technique that consists in a convolution of the image with a kernel adapted to the image content. The definition of such a kernel relies on the computation of similarity between pixels of a given neighborhood. Our contribution consists in the definition of a new similarity criterion which is more robust to noise. This measure is computed from a new dictionary more adapted to image content. The projections of the image content to this subspace are used then to define a metric between a pixel and the neighborhood ones. Very promising experimental results show the potential of our approach. |
