基于二维变分模态分解和自适应中值滤波的图像去噪方法*

图像在采集、获取和传输过程中往往夹杂着噪声,针对几种常用方法去噪效果不理想,提出了一种新的图像去噪方法。此方法通过二维变分模态分解将图像分解为一系列不同中心频率的子模态。保留其低频模态,并对其进行自适应中值滤波处理,从而得到其去噪后的图像。实验结果表明,与其他几种常用的去噪方法相比,本文方法在滤除噪声的同时,又能较好地保留图像的边缘细节,图像也获得较好的视觉效果,此外客观评价参数也得到比较明显的改善,随着噪声强度加大去噪效果愈明显。

Image denoising method based on bi-dimensional variationalmode decomposition and adaptive median filtering

In the process of collection, access and transmission, images are often mixed with noise, but the effect of several traditional denoising methods is unsatisfactory. This paper proposes a new method for image denoising. A noised image was decomposed into a series of sub-frequency modes by bi-dimensional variational mode decomposition. After retaining its low frequency modes and processing them by adaptive median filtering, the denoising image was obtained. Comparied with the other common denoising methods, the experimental results show that the proposed approach can not only remove the noise effectively, but also preserve the details well. Moreover, it also can obtain better visual quality and improve objective measurements. The denoising effect is more obvious with the increase of the noise intense.