Image Denoising Method and System Based on Enhanced Deep Dilated Convolutional Neural Network

In order to improve the performance of image denoising, in the case of can not only reduce the computational cost at the same time to ensure the superiority of denoising, we made a change on the basis of the original network, through the way of increasing network breadth rather than depth for more features, and to improve the running speed, by means of expansion convolution to extract more information used for denoising task. A large number of experimental results show that this kind of network can not only reduce the gradient explosion, but also effectively reduce the noise intensity of the image.