Abstract
Two local adaptative nonlinear filters for image denoising are described and compared to other methods. The first one is a median filter computed over a connected neighborhood that fits the local conformation of level lines. The second one deals with the size of grains in image. Both filters depend on a single parameter, the area A, are morphological and associated with smooth as well as unsmooth fixed points. They make the total variation decrease and are able more than other classic morphological filters to denoise while preserving image structures. They are particularly designed for automation.
| Original language | English |
|---|---|
| Title of host publication | Proceedings of the Sixth International Workshop on Digital Image Processing and Computer Graphics |
| Editors | Emanuel WENGER, Leonid I. DIMITROV |
| Publisher | SPIE |
| Pages | 84-95 |
| Number of pages | 12 |
| Volume | 3346 |
| DOIs | |
| Publication status | Published - 1 Feb 1998 |
| Externally published | Yes |
| Event | 6th International Workshop on Digital Image Processing and Computer Graphics - Vienna, Austria Duration: 20 Oct 1997 → 22 Oct 1997 |
Workshop
| Workshop | 6th International Workshop on Digital Image Processing and Computer Graphics |
|---|---|
| Abbreviated title | DIP-97 |
| Country/Territory | Austria |
| City | Vienna |
| Period | 20/10/97 → 22/10/97 |
Bibliographical note
Acknowledgments:The first author thanks Leonid Yaroslavsky for useful discussions.
Keywords
- Additive or impulse noise
- Automation
- Blind restoration
- Connectedness
- Local adaptative morphological filtering
- Smooth and unsmooth fixed point
Fingerprint
Dive into the research topics of 'Image restoration involving connectedness'. Together they form a unique fingerprint.Cite this
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver