We describe an image fusion algorithm for data exhibiting heavy tails with no convergent second- or higher-order moments. Our developments rely on recent results showing that wavelet decomposition coefficients of images are best modeled by alpha-stable distributions, a family of heavy-tailed densities. Thus, in the multiscale wavelet domain we develop a novel fusion rule based on fractional lower order moments (FLOM's). Simulation results show that our method achieves better performance in comparison with previously proposed pixel-level fusion approaches.
|Translated title of the contribution
|Complex wavelet domain image fusion based on fractional lower order moments
|Title of host publication
|IEEE 8th International Conference on Information Fusion, Philadelphia, USA
|Institute of Electrical and Electronics Engineers (IEEE)
|515 - 521
|Number of pages
|Published - Jul 2005
|8th International Conference on Information Fusion - Philadelphia, PA, United States
Duration: 1 Jul 2005 → …
|8th International Conference on Information Fusion
|1/07/05 → …
Bibliographical noteConference Proceedings/Title of Journal: IEEE 8th International Conference on Information Fusion
Rose publication type: Conference contribution
This material is posted here with permission of the IEEE. Such permission of the IEEE does not in any way imply IEEE endorsement of any of the University of Bristol's products or services. Internal or personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution must be obtained from the IEEE by writing to email@example.com.
By choosing to view this document, you agree to all provisions of the copyright laws protecting it.
- image fusion
- wavelet decomposition
- alpha-stable distributions
- parameter estimation
- fractional lower order moments
- symmetric covariation