混合波原子和双边滤波的纹理图像滤波方法

Textural image filtering method by hybridizing wave atoms shrinkage with bilateral filtering

为了更好地去除纹理图像中的噪声,提出了一种新的混合波原子阈值的振荡纹理图像扩散模型;利用扩散方程和图像滤波方法的理论联系,给出了联合双边滤波的图像去噪算法;最后,利用峰值信噪比(PSNR)和结构相似度(SSIM)两个客观图像质量评价指标,与目前流行的图像去噪方法(包括波原子阈值、双边滤波、高斯尺度混合(GSM),以及非局部滤波(NLM))进行比较。实验结果验证了新方法的有效性。

This paper proposed a novel diffusion scheme by hybridizing wave atoms thresholding for textural images. Also de- signed a denoising algorithm based on the relationship between solution of nonlinear diffusion equation and bilateral filtering method. Numerical experiments illustrate the good performance in comparison to the state-of-the-art denoising algorithms, such as wave atoms shrinkage method, and the bilateral filtering method, scale mixtures of Gaussians （GSM） method, non-local mean （NLM） method, by using two objective measures： peak signal-to-noise ratio （PSNR） and structural similarity （SSIM）.