摘要
在WienerChop算法的基础上，提出了一种改进的小波域维纳滤波器，在小波域采用基于贝叶斯估计的小波阈值去噪技术估计期望信号，提高估计的精度，并以此设计经验维纳滤波器；进一步适当选择多小波基，使每个基函数通过小波变换能够比其他小波基更好地捕捉信号的某些特定特征，从而实现WienerChop算法的迭代．仿真实验表明提出的迭代WienerChop算法有效地改善了去噪后图像的均方误差和信噪比，与BayesShrink算法和非迭代的WienerChop算法相比，迭代WienerChop方法去噪后图像的峰值信噪比增益分别达到0．78～1．00dB和0．36～0．49dB．
On the basis of WienerChop algorithm, an improved Wiener filter in wavelet domain is proposed. Bayesian based wavelet thresholding denoising technique is adopted to estimate the expected signals accurately and design an empirical Wiener filter. Multiple wavelet bases were selected properly to uniquely capture some signal characteristics, which exist in the sparsity of the signal representation by wavelet transform, and the iteration was carried out. Simulation results show that the proposed method has effectively improved the quality of denoised image in terms of MSE and PSNR. Compared with BayesShrink, our iterative method has PSNR improvement betwen 0.78 and 1.00 dB. The increase PSNR by iterative method over noniterative WienerChop is betwwen 0.36 and 0.49 dB.
出处
《华中科技大学学报（自然科学版）》
EI
CAS
CSCD
北大核心
2006年第4期24-26,共3页
Journal of Huazhong University of Science and Technology(Natural Science Edition)
基金
国家高技术研究发展计划重点资助项目(2002AA133010).
