基于快速非局部均值和超分辨率重建的图像降噪算法

An Image Deniosing Algorithm Based on Fast Non-local Mean and Super-resolution Reconstruction

针对实际图像噪声强度变化范围宽,目前已有的图像降噪算法多数只能用于处理强度范围有限的噪声情况,结合快速非局部均值和基于深度残差卷积网的超分辨率重建,提出一种适用于不同噪声强度的图像降噪算法。利用改进的非局部均值算法和Boxfilter滤波器对图像进行初步降噪,再通过深度残差卷积网络对初步降噪的图像实现端到端的低分辨率图像超分辨重建。仿真实验结果表明:当噪声强度分别为15、25、40、50、60时,相比于其他经典降噪算法,新算法能获得更高的峰值信噪比和结构相似性,且随着噪声强度的升高,优势越来越明显;新算法适用于已知噪声水平的降噪,也适用于盲噪声降噪,且盲降噪性能优于其他经典降噪算法;此外,该算法还可以更好地恢复图像细节,产生较好的视觉效果。

Most of the existing image denoising algorithms can only deal with the noise intensity varying in a limited range.For the actual image noise intensity varying in a wide range,an image denoising algorithm is proposed based on the fast non-local means algorithm and the deep residual convolutional network-based super-resolution reconstruction algorithm.The improved non-local means algorithm and Box filter are used to denoise the image initially,and then the initial denoised image is reconstructed with end-to-end super-resolution of low-resolution images by the deep residual convolutional network.The simulated results show that the proposed algorithm can be used to obtain higher peak signal-to-noise ratio(PSNR)and structural similarity(SSIM)compared with other classical denoising algorithms when the noise intensities are 15,25,40,50 and 60.And with the increase in noise intensity,its advantage is more and more obvious.The proposed algorithm is suitable for denoising of known noise and blind noise.And the proposed algorithm is superior to the classical noise reduction algorithms in blind noise reduction.In addition,the proposed algorithm can restore the image details better and generate a better visual effect.