denoisingNetwork
获取图像去噪网络
说明
示例
获取预训练的图像去噪卷积神经网络 "DnCNN"。
net = denoisingNetwork("DnCNN")net =
dlnetwork with properties:
Layers: [58×1 nnet.cnn.layer.Layer]
Connections: [57×2 table]
Learnables: [76×3 table]
State: [36×3 table]
InputNames: {'InputLayer'}
OutputNames: {'Conv20'}
Initialized: 1
View summary with summary.
加载预训练去噪卷积神经网络 "DnCNN"。
net = denoisingNetwork("DnCNN");将一个灰度图像加载到工作区，然后创建图像的含噪版本。
I = imread("cameraman.tif"); noisyI = imnoise(I,"gaussian",0,0.01);
将这两个图像以蒙太奇方式显示。
montage({I,noisyI})
title("Original Image (Left) and Noisy Image (Right)")
从含噪图像中去除噪声，然后显示结果。
denoisedI = denoiseImage(noisyI,net);
imshow(denoisedI)
title("Denoised Image")
输入参数
输出参量
参考
[1] Zhang, K., W. Zuo, Y. Chen, D. Meng, and L. Zhang. "Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising." IEEE Transactions on Image Processing. Vol. 26, Number 7, Feb. 2017, pp. 3142-3155.
