Abstract
We introduce a new complexity regularization method for image denoising and explore the use of sophisticated complexity penalties. We have found improvements of the order of 2 dB in reconstructed image mean-squared error over existing complexity-regularized estimators.
Original language | English (US) |
---|---|
Pages | 370-373 |
Number of pages | 4 |
State | Published - Dec 1 1997 |
Event | Proceedings of the 1997 International Conference on Image Processing. Part 2 (of 3) - Santa Barbara, CA, USA Duration: Oct 26 1997 → Oct 29 1997 |
Other
Other | Proceedings of the 1997 International Conference on Image Processing. Part 2 (of 3) |
---|---|
City | Santa Barbara, CA, USA |
Period | 10/26/97 → 10/29/97 |
Fingerprint
ASJC Scopus subject areas
- Hardware and Architecture
- Computer Vision and Pattern Recognition
- Electrical and Electronic Engineering
Cite this
Complexity-regularized image denoising. / Liu, Juan; Moulin, Pierre.
1997. 370-373 Paper presented at Proceedings of the 1997 International Conference on Image Processing. Part 2 (of 3), Santa Barbara, CA, USA, .Research output: Contribution to conference › Paper
}
TY - CONF
T1 - Complexity-regularized image denoising
AU - Liu, Juan
AU - Moulin, Pierre
PY - 1997/12/1
Y1 - 1997/12/1
N2 - We introduce a new complexity regularization method for image denoising and explore the use of sophisticated complexity penalties. We have found improvements of the order of 2 dB in reconstructed image mean-squared error over existing complexity-regularized estimators.
AB - We introduce a new complexity regularization method for image denoising and explore the use of sophisticated complexity penalties. We have found improvements of the order of 2 dB in reconstructed image mean-squared error over existing complexity-regularized estimators.
UR - http://www.scopus.com/inward/record.url?scp=0031359281&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=0031359281&partnerID=8YFLogxK
M3 - Paper
AN - SCOPUS:0031359281
SP - 370
EP - 373
ER -