基于小波域变分滤波器的超声图像去噪算法

Despeckling Algorithm for Ultrasound Images Based on Variational Filter in Wavelet Domain

针对超声图像的斑点噪声干扰问题,提出了一种基于小波域的变分滤波算法.该算法利用小波变换的时频特性,对低频域的小波系数使用基于贝叶斯最大后验估计的变分滤波器进行去噪;对高频域的小波系数选择自适应的小波阈值函数,然后使用基于拉普拉斯分布模型的小波收缩算法进行收缩处理.实验结果表明,与小波软阈值滤波器和变分滤波器相比,该算法在去噪能力和边缘信息的保留上均有较好的表现.

To effectively remove the speckle noise of ultrasound images,a despeckling algorithm based on the variational filter in wavelet domain has been proposed.The wavelet transform with time-frequency characteristic is used to decompose the ultrasound image firstly,and the variational filter based on Bayesian maximum a posteriori estimation is applied to filter the coefficients of the low frequency part in wavelet domain.The speckle noise in wavelet is modeled as Laplace distribution,then the coefficients of high frequency part is shrank by a new adaptive wavelet threshold function.Compared with the wavelet softthreshold filter and variational filter,results show that the proposed filter performs better despeckling ability while preserving the edge information.