Tutorial on image reconstruction based on weighted sum (WS) filter approach: from single image to multi-frame image
Files (Excerpt)
Publisher
item.page.dcterms.publisher
Issued Date
2009
Copyright Date
Genre
Series
Edition
Language
eng
File Type
application/pdf
No. of Pages/File Size
ISBN
ISSN
eISSN
DOI
item.page.dc.identifier
Access Rights
Access Status
Call number
Other identifier(s)
Copyright date
Physical location
Citation
AU Journal of Technology 13, 2 (October 2009), 75-86
Title
Tutorial on image reconstruction based on weighted sum (WS) filter approach: from single image to multi-frame image
Other title(s)
Author(s)
Editor(s)
Advisor(s)
item.page.ithesis.email.advisor
item.page.dc.contributor
Other Contributor(s)
Abstract
For large magnification factors, the prior classical smoothness leads to overly smooth results with very little high-frequency content. The classical image restorations are failing to reconstruct the desired image. Consequently, the Recognition-Based Restoration is desired for these purposes and one of the most effective techniques is of a weighted sum (WS) filter. This paper reviews the research framework of weighted sum (WS) filter approach for image reconstruction. This research framework first starts with the Hard-Partition-based Weighted Sum (HP-WS) filter proposed in 1999 and then consequently reviews the Subspace HP-WS (S-HPWS) using PCA (Principal Component Analysis) Filter proposed in 2005, The Soft-Partition-based Weighted Sum (SP-WS) proposed in 2006, and the fast Adaptive Wiener Filter proposed in 2007. The paper reviews each filter technique in terms of its computational concepts, demonstrates parameter optimization from the point of view of the mathematical analysis, and discusses advantages and disadvantages.
Table of contents
Description
In English ; only abstract in English.
item.page.dcterms.description
Links
Sponsorship
Spatial coverage
item.page.dc.relation.ispartof
Degree Name
Degree Level
Degree Department
Degree Discipline
Degree Grantor(s)
item.page.dc.subject.classification
item.page.dc.subject.lcc
Rights
This work is protected by copyright. Reproduction or distribution of the work in any format is prohibited without written permission of the copyright owner.