Proceedings 2000 International Conference on Image Processing (Cat. No.00CH37101)
DOI: 10.1109/icip.2000.899579
|View full text |Cite
|
Sign up to set email alerts
|

Satellite image deconvolution using complex wavelet packets

Abstract: ABSTRACT

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
59
0

Publication Types

Select...
4
2
2

Relationship

1
7

Authors

Journals

citations
Cited by 56 publications
(59 citation statements)
references
References 4 publications
0
59
0
Order By: Relevance
“…The 2-band multidimensionnal dual-tree complex wavelet transform has already been proved to be useful in denoising problems, in particular for video processing [32] or satellite imaging [33]. In this part, we show that M -band dual-tree wavelet transforms also demonstrate good performances in image denoising and outperform existing methods such as those relying on classical M -band wavelet transforms (M ≥ 2) or even 2-band dual-tree wavelet transforms.…”
Section: Application To Denoisingmentioning
confidence: 70%
“…The 2-band multidimensionnal dual-tree complex wavelet transform has already been proved to be useful in denoising problems, in particular for video processing [32] or satellite imaging [33]. In this part, we show that M -band dual-tree wavelet transforms also demonstrate good performances in image denoising and outperform existing methods such as those relying on classical M -band wavelet transforms (M ≥ 2) or even 2-band dual-tree wavelet transforms.…”
Section: Application To Denoisingmentioning
confidence: 70%
“…[55] develops a algorithm by iterating between calculations of the state coefficients in a 2-state GMM model and the MAP estimate of the coefficients. Complex wavelet packets have also been used [56]. This is based on using complex wavelets with a packet decomposition to denoise the result of applying the inverse filter, // '.…”
Section: Image Restorationmentioning
confidence: 99%
“…The proposed algorithm has been compared to other algorithms: Wiener filter, which gives poor results (noisy image and blurred edges); RHEA method [6], which gives sharp edges (but still noisy homogeneous areas); COWPATH 2 [5], which does not work properly because of the non invertible blurring function; and EM-DEC 0, which is a simplified version of the proposed method, where the denoising step is a simple soft thresholding (with an optimal threshold). The results and the related SNRs are shown in Fig.…”
Section: Resultsmentioning
confidence: 99%
“…To estimate the adaptive parameters, we use a hybrid approach derived from the algorithm COWPATH 2 [5]. It consists of performing the estimation from a good approximation of the original image, within a complete data framework, which enables us to get a simple and robust estimate.…”
Section: Adaptive Parameter Estimation and Denoisingmentioning
confidence: 99%
See 1 more Smart Citation