Sectioned Optimization Methods for Image Restoration
Summary :
Sectioned optimization methods for image restoration is presented in order to restore the original image from the observation degraded by a point spread function and additive noise. This is a locally adaptive filter which minimizes the mean square errors of the estimate for each section of the image. The required information for this processing is derived from the observation as a proto-type and then it is modified to fit for processing in each section of the image by using an iterative algorithm. The simulation examples show that the restored image is always superior than that of the usual minimum mean square error-filter. This can not only be utilized for the usual degraded image but also for the image suffered from the band width compression in the image communication.
- Publication
- IEICE TRANSACTIONS on transactions Vol.E69-E No.12 pp.1342-1353
- Publication Date
- 1986/12/25
- Publicized
- Online ISSN
- DOI
- Type of Manuscript
- PAPER
- Category
- Pattern Recognition and Learning
Authors
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Hiroshi KONDO, "Sectioned Optimization Methods for Image Restoration" in IEICE TRANSACTIONS on transactions,
vol. E69-E, no. 12, pp. 1342-1353, December 1986, doi: .
Abstract: Sectioned optimization methods for image restoration is presented in order to restore the original image from the observation degraded by a point spread function and additive noise. This is a locally adaptive filter which minimizes the mean square errors of the estimate for each section of the image. The required information for this processing is derived from the observation as a proto-type and then it is modified to fit for processing in each section of the image by using an iterative algorithm. The simulation examples show that the restored image is always superior than that of the usual minimum mean square error-filter. This can not only be utilized for the usual degraded image but also for the image suffered from the band width compression in the image communication.
URL: https://global.ieice.org/en_transactions/transactions/10.1587/e69-e_12_1342/_p
Copy
@ARTICLE{e69-e_12_1342,
author={Hiroshi KONDO, },
journal={IEICE TRANSACTIONS on transactions},
title={Sectioned Optimization Methods for Image Restoration},
year={1986},
volume={E69-E},
number={12},
pages={1342-1353},
abstract={Sectioned optimization methods for image restoration is presented in order to restore the original image from the observation degraded by a point spread function and additive noise. This is a locally adaptive filter which minimizes the mean square errors of the estimate for each section of the image. The required information for this processing is derived from the observation as a proto-type and then it is modified to fit for processing in each section of the image by using an iterative algorithm. The simulation examples show that the restored image is always superior than that of the usual minimum mean square error-filter. This can not only be utilized for the usual degraded image but also for the image suffered from the band width compression in the image communication.},
keywords={},
doi={},
ISSN={},
month={December},}
Copy
TY - JOUR
TI - Sectioned Optimization Methods for Image Restoration
T2 - IEICE TRANSACTIONS on transactions
SP - 1342
EP - 1353
AU - Hiroshi KONDO
PY - 1986
DO -
JO - IEICE TRANSACTIONS on transactions
SN -
VL - E69-E
IS - 12
JA - IEICE TRANSACTIONS on transactions
Y1 - December 1986
AB - Sectioned optimization methods for image restoration is presented in order to restore the original image from the observation degraded by a point spread function and additive noise. This is a locally adaptive filter which minimizes the mean square errors of the estimate for each section of the image. The required information for this processing is derived from the observation as a proto-type and then it is modified to fit for processing in each section of the image by using an iterative algorithm. The simulation examples show that the restored image is always superior than that of the usual minimum mean square error-filter. This can not only be utilized for the usual degraded image but also for the image suffered from the band width compression in the image communication.
ER -
English
