An image denoising method based on relu convolutional neural network

Abstract

The invention discloses an image denoising method based on ReLU convolutional neural network, which includes the following steps: building a ReLU convolutional neural network model. The ReLU convolutional neural network model includes multiple convolutional layers and each of the convolutional neural network models. The activation layer after stacking, the activation layer is a ReLU function; select a training set, and set the training parameters of the ReLU convolutional neural network model; according to the ReLU convolutional neural network model and its training parameters, to minimize The loss function trains the ReLU convolutional neural network model for the target to form an image denoising neural network model; input the image to be processed into the image denoising neural network model and output the denoised image. The image denoising method based on ReLU convolutional neural network disclosed by the present invention greatly enhances the learning ability of the neural network, establishes an accurate mapping of noisy images to clean images, and can achieve real-time denoising.

Description

technical field [0001] The invention relates to the fields of computer vision and digital image processing, in particular to an image denoising method based on a ReLU convolutional neural network. Background technique [0002] Image denoising is a classic and fundamental problem in computer vision and image processing. It is a necessary preprocessing process to solve many related problems. Its purpose is to restore a potential clean image x from a noisy image y. The process can be expressed as: y=x+n, where n is usually considered as Additive White Gaussian (AWG), which is a typical ill-conditioned linear inverse problem. In order to solve this problem, many early methods are solved by local filtering, such as Gaussian filtering, median filtering, bilateral filtering, etc. These local filtering methods neither filter in the global scope nor consider the relationship between natural image blocks and The connection between blocks, so the obtained denoising effect is not satis...

AI Technical Summary

Problems solved by technology

However, this mixed model and low-rank estimation are not so accurate, so the denoising effect is not very good; and the time complexity and space complexity are high, which brings great inconvenience to practical applications

Images