Image denoising method and system based on deep learning

Abstract

The invention discloses an image denoising method and system based on deep learning. The image denoising method based on deep learning includes the steps: constructing a main neural network structureand an auxiliary neural network structure, respectively assigning the trainable parameter initial value of the first convolutional layer and the trainable parameter initial value of the fifth convolutional layer in the auxiliary neural network structure to the trainable parameter initial value of the first convolutional layer and the trainable parameter initial value of the 15th convolutional layer in the main neural network structure; adding a training set noise adding image into the main neural network structure after assignment, and obtaining a noise characteristic image by performing imagecharacteristic extraction, training and learning on the input training set noise adding image through a forward propagation algorithm; according to the noise characteristic image, determining a training model; inputting a verification set noise adding image into the training model, and outputting a final training denoising model; and adding a test set noise adding image into the final training denoising model to test, and obtaining a denoised image, thus greatly improving the denoising efficiency and the denoising effect.

Description

technical field [0001] The present invention relates to the technical field of image denoising, in particular to an image denoising method and system based on deep learning. Background technique [0002] With the rapid development of information science and technology, people are doing more and more research on target detection, object recognition, image retrieval, etc. However, many applications such as target detection, object recognition, and image retrieval require the input of digital images that are as clear as possible, and Digital images will be polluted by noise due to various reasons in the process of acquisition and storage, so image denoising is a very important topic. [0003] At present, the existing denoising methods include: using the K-SVD dictionary training algorithm for denoising, using the TNRD nonlinear reaction diffusion algorithm for denoising, using median filtering for denoising, using wavelet transform for denoising, and using BM3D block matching s...

AI Technical Summary

Problems solved by technology

However, the ReLU function is very fragile during neural network training, and it is easy to die. For example, a very large gradient flows through a ReLU neuron. After updating the parameters, this neuron will no longer activate any data. up

If this happens, the gradient of this neuron will always be 0. In actual operation, if the learning rate is set relatively large, then 40% of the neurons in the neural network will die, causing all negative axis information to be lost. Relatively speaking, the available information will be less, the more susceptible to noise interference, and the worse the denoising effect will be

Images