Hybrid Transform Based Denoising with Block Thresholding
A frequently used approach for denoising is the shrinkage of coefficients of the noisy signal representation in a transform domain. This paper proposes an algorithm based on hybrid transform (stationary wavelet transform proceeding by slantlet transform); The slantlet transform is applied to the app...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | Arabic |
| Published: |
College of Education for Women
2019-02-01
|
| Series: | مجلة كلية التربية للبنات |
| Online Access: | http://jcoeduw.uobaghdad.edu.iq/index.php/journal/article/view/922 |
| Summary: | A frequently used approach for denoising is the shrinkage of coefficients of the noisy signal representation in a transform domain. This paper proposes an algorithm based on hybrid transform (stationary wavelet transform proceeding by slantlet transform); The slantlet transform is applied to the approximation subband of the stationary wavelet transform. BlockShrink thresholding technique is applied to the hybrid transform coefficients. This technique can decide the optimal block size and thresholding for every wavelet subband by risk estimate (SURE). The proposed algorithm was executed by using MATLAB R2010aminimizing Stein’s unbiased with natural images contaminated by white Gaussian noise. Numerical results show that our algorithm competes favorably with SWT, and SLT based algorithms, and obtain up to 1.23 dB PSNR improvement. |
|---|---|
| ISSN: | 1680-8738 2663-547X |