A Method of Image Denoising Based on Dilated Convolution

Abstract

The present invention relates to an image denoising method based on dilated convolution, specifically comprising the following steps: step 1, preparation of training data; step 2, establishment of a model; step 3, compiling the image obtained in step 2 to obtain a compiled model Step 4, adding additive Gaussian white noise to the block image obtained in step 1 to obtain a batch of images with noise; Step 5, training the batch of images with noise obtained in step 4 to obtain a trained model; Step 6, preparation of test data; Step 7, import the obtained test image into the predict prediction function of the step 5 model to obtain the denoised figure; the denoising method of the present invention can not only restore sharp edges and fine details, but also It can also produce pleasing visual effects in smooth areas, and the network structure of this method consists of 14 layers, which can reduce the required time and improve efficiency.

Description

technical field [0001] The invention belongs to the technical field of image denoising, and in particular relates to an image denoising method based on dilated convolution. Background technique [0002] Image denoising refers to the process of reducing noise in digital images. In reality, digital images are often affected by imaging equipment and external environmental noise interference during digitization and transmission, which are called noisy images or noisy images. [0003] DnCNN uses residual learning to remove the clean image in the hidden layer to obtain a noisy image, and then subtracts the noisy image from the noisy input image to obtain a clear image. DnCNN uses a 17-layer network, of which the first layer is expansion convolution + nonlinear activation function (Relu), the 2nd-16th layer is expansion convolution + batch normalization + nonlinear activation function (Relu), and the 17th layer is Expansion convolution, the number of layers of this type of network...

AI Technical Summary

Problems solved by technology

DnCNN uses a 17-layer network, of which the first layer is expansion convolution + nonlinear activation function (Relu), the 2nd-16th layer is expansion convolution + batch normalization + nonlinear activation function (Relu), and the 17th layer is Expansion convolution, the number of layers of this type of network is too deep, it takes a long time, so it will reduce the efficiency

Images