A gray level image noise reduction method based on hole convolution and an automatic coding and decoding neural network

Abstract

The invention discloses a gray level image noise reduction method based on hole convolution and an automatic coding and decoding neural network, which comprises the following steps of taking a clear image and a noise image corresponding to the clear image as a training sample to construct a training set; constructing an image noise reduction model, wherein the image noise reduction model comprisesan image feature coding unit for performing feature coding on a noise image, the image feature decoding unit is used for decoding the coded feature map output by the image feature coding unit, the image feature coding unit comprises a feature extraction module and 10 coding modules, and the image decoding unit comprises 10 decoding modules and an image restoration module; utilizing the training set to train the constructed image noise reduction model to obtain a trained image noise reduction model; during application, inputting a noise image into the trained image noise reduction model, and outputting a noise reduction image through calculation. The grayscale image noise reduction method can quickly remove the noise of the image and improve the visual effect of the image.

Description

technical field [0001] The invention belongs to the field of image signal processing, and in particular relates to a grayscale image noise reduction method based on atrous convolution and automatic codec neural network. Background technique [0002] Images are an extremely important source of information for people. In today's information age, with the popularization of digital devices, digital images have become an important means for people to obtain information, penetrate into all aspects of production and life, and have achieved huge social and economic benefits. In recent years, the combination of image processing technology and research fields such as machine learning and machine vision has produced unprecedented new developments and breakthroughs. However, in the process of image acquisition, processing, compression, transmission, storage and reproduction, noise will inevitably be introduced, thereby reducing image quality. The main goal of image denoising is to fil...

AI Technical Summary

Problems solved by technology

Although deep neural network methods can achieve better results, such methods still need to occupy a large amount of memory and huge computing resources, and it is difficult to use them in the actual production process.

Images