 |
My ICIP 2006 Schedule
Note: Your custom schedule will not be saved unless you create a new account or login to an existing account.
Paper Detail
| Paper: | MP-P6.8 |
| Session: | Color and Multispectral Processing |
| Time: | Monday, October 9, 14:20 - 17:00 |
| Presentation: |
Poster |
| Topic: |
Color and Multispectral Processing: Color processing |
| Title: |
BLUR ROBUST AND COLOR CONSTANT IMAGE DESCRIPTION |
| Authors: |
Joost van de Weijer; INRIA Rhône-Alpes | | | | | Cordelia Schmid; INRIA Rhône-Alpes | | |
| Abstract: |
An important class of color constant image descriptors is based on image derivatives. These derivative-based image descriptors have a major drawback: they are very sensitive to changes of image blur. Image blur has various causes such as being out-of-focus, relative motion between the camera and the object, and inaccurate acquisition settings. Since image blur is a frequently occurring image degradation, it is desirable for object description to be robust to its variations. In this article we propose a set of color descriptors which are both robust with respect to blurring effects, and invariant to illuminant color changes. Experiments on retrieval tasks show that the newly proposed object descriptors outperform existing descriptors in the presence of blurring effects. |
|
