Abstract
A unified variational model which has a spatially-varying weight function on smoothness constraints for early vision is discussed. The validity of the smoothness constraint in early vision is based on the assumption that the coherence of matter give rise to smoothly varying characteristics in a visual scene. The smoothing is controlled in the direction along the image features to avoid the damages. The spatially-varying weight function is used for elastic model so that the smoothness constraints are small on large variation area.
| Original language | English |
|---|---|
| Pages | 461-464 |
| Number of pages | 4 |
| State | Published - 1998 |
| Event | 4th International Conference on Computer Science and Informatics, JCIS 1998, 1st International Workshop on High Performance, 1st International Workshop on Computer Vision, Pattern Recognition and Image Processing Volume 4 - Research Triangle Park, NC, United States Duration: Oct 23 1998 → Oct 28 1998 |
Conference
| Conference | 4th International Conference on Computer Science and Informatics, JCIS 1998, 1st International Workshop on High Performance, 1st International Workshop on Computer Vision, Pattern Recognition and Image Processing Volume 4 |
|---|---|
| Country/Territory | United States |
| City | Research Triangle Park, NC |
| Period | 10/23/98 → 10/28/98 |