Convolutional neural network image denoising method based on multi-scale convolution groups and parallelism

Abstract

The invention discloses a convolutional neural network image denoising method based on multi-scale convolution groups and parallelism. The method specifically comprises the following steps of 1, preparing a training set, selecting an appropriate data set as an original image in the training set, preprocessing the original image, simulating the real noise by adopting the Gaussian white noise, and adding the real noise into the original image as a noise image corresponding to the original image; 2, constructing a network model, and constructing a network model in combination with a convolution network mode of the multi-scale convolution group and the parallelism; 3, setting the hyper-parameters, a loss function and an optimization algorithm of the network according to the network model constructed in the step 2; 4, performing network training, and using the constructed network model in the step 2 to train a single-noise training set and a multi-noise training set respectively to obtain aplurality of network models corresponding to the training sets; and 5, testing the network performance. According to the method, more image contours and texture details can be reserved while the noise is eliminated.

Description

technical field [0001] The invention belongs to the technical field of image processing methods, in particular to an image denoising method based on multi-scale convolution groups and parallel convolutional neural networks. Background technique [0002] With the advent of the digital information age, especially the continuous development of computer technology and the improvement of the popularization of image digitization equipment, a large part of the multimedia information that people receive is the visual information of images. However, in the process of image digital transmission, it is inevitable to receive noise pollution, which will deteriorate the image quality. The polluted image will not only affect people's visual recognition, but also bring great impact to computer recognition. Negative impact, affecting the readability of the image. The purpose of image denoising is to reduce or eliminate the influence of noise on the image, so as to obtain high-quality images...

AI Technical Summary

Problems solved by technology

The main idea of ​​these two types of methods is to use the correlation of adjacent pixels in the image. They are effective in dealing with simple noises, but they have serious defects: the method of using the neighborhood mean will definitely smooth the edges, details, etc. of the image. important features

Although the above methods can deal with the problem of image denoising and can achieve good results, they generally have the following two shortcomings. The original image can be recovered efficiently under the circumstances; the second is that these methods all need artificial adjustment parameters, which have great uncertainty and artificiality, which makes it difficult to obtain good denoising results.

Images