联合均值滤波与泊松核双边滤波降噪算法研究

Image Denoising Research of Combining Mean Filtering with Poisson Kernel Improved Bilateral Filtering

针对均值滤波算法降噪精度低、降噪后图像信息丢失严重以及双边滤波在参数选择时不具有自适应性、噪声点检测不精确,容易将噪声放大等问题,同时为了能够抑制图像噪声并保持其边缘信息和细节信息,提出了一种结合均值滤波与基于泊松核改进的双边滤波图像降噪算法。首先利用均值滤波对噪声图像进行预处理,然后再由利用泊松核改进的双边滤波对预处理图像进行最终降噪,得出两种算法结合既可以有效地抑制噪声,同时又可以保护图像中的边缘细节。实验结果表明,与传统均值滤波以及均值滤波联合传统双边滤波算法相比,改进算法在降噪的同时,又能够保留细节信息,并能够提升图像预处理的显示效果,具有较高的实用价值。

Aiming at the low denoising accuracy and the serious loss of image information of the mean filtering,a method of combining mean filtering with Poisson kernel improved bilateral filtering is put forward to reduce noise and retain the detailed information of images.The bilateral filtering is not adaptive in parameter selection and its detection of noise points is inaccurate.Firstly,the noise of the image was pre-processed by mean filtering,and then the preprocessed image was finally denoised by the bilateral filtering improved with Poisson kernel.The combination of the two algorithms can achieve the improvement of denoising and protecting the edge details.The experiment results show that the proposed algorithm can effectively protect the detailed information and reduce the noise while improving the image quality,compared with the traditional mean filtering and the mean filtering combined with the traditional bilat⁃eral filtering.Therefore,the algorithm of this paper has high practical value.