Abstract
We apply complexity regularization to statistical ill-posed inverse problems in imaging. We formulate a natural distortion measure in image space and develop nonasymptotic bounds on estimation performance in terms of an index of resolvability that characterizes the compressibility of the true image. These bounds extend previous results that were obtained under simpler observational models.
| Original language | English (US) |
|---|---|
| Pages (from-to) | 54 |
| Number of pages | 1 |
| Journal | IEEE International Symposium on Information Theory - Proceedings |
| State | Published - 2000 |
| Event | 2000 IEEE International Symposium on Information Theory - Serrento, Italy Duration: Jun 25 2000 → Jun 30 2000 |
ASJC Scopus subject areas
- Theoretical Computer Science
- Information Systems
- Modeling and Simulation
- Applied Mathematics