Image blind denoising method and system based on enhanced Transform

Abstract

The invention discloses an enhanced Transform-based image blind denoising method and system, and the method comprises the steps: combining a dynamic convolution layer with an enhanced Transform module, and carrying out the feature fusion of a plurality of modules in a weighting manner in a self-adaptive manner; a dynamic convolutional layer is introduced, parameters are adaptively adjusted under the condition that extra network depth and width are not increased, and the expression ability of the model is greatly improved; residual learning operation is added into the Transform module, so that the problem that the Transform module is difficult to train is solved, global features and semantic information are extracted more effectively, and the denoising effect is improved; a residual learning operation is adopted, hierarchical features obtained by a convolutional layer, a dynamic convolutional layer and an enhanced Transform module are fused respectively, and the memory ability of each layer of the network is transmitted; the features of the enhanced convolutional layer, the dynamic convolutional layer and the enhanced Transform module are fused through connection operation, then the weight is obtained through Softmax, secondary extraction of the features is achieved in an attention mode, and the saliency features are further obtained. According to the method, a good effect is obtained on an image blind denoising task.

Description

technical field [0001] The invention belongs to the technical fields of image processing, deep learning and computer vision, and in particular relates to a blind image denoising method and system based on an enhanced Transformer. Background technique [0002] In recent years, with the rapid development of mobile devices, digital images are more and more easily obtained due to their portability, the number of digital images in the physical world has increased dramatically, and the application of image processing has become more and more extensive. [0003] However, due to its small size, mobile devices abandon large photosensitive elements, which is a key factor limiting clear imaging. And due to the portability of mobile devices, people rarely carry professional photographic aids, such as tripods, stabilizers, etc., when taking pictures. These reasons will cause the captured image to contain a certain amount of noise. Through mathematical modeling, the noisy image can be r...

AI Technical Summary

Problems solved by technology

[0004] (1) Some methods have poor generalization performance, can only adapt to one or several types of noise, and can only be used in a certain scene

[0005] (2) Some methods have good performance, but due to their high complexity, their application scenarios are limited

[0007] (1) The methods involved in the above are to improve performance by deepening the number of network layers, but infinitely increasing the number of layers of the network cannot obtain the optimal model

Due to the limited ability of convolution operation to extract features, these methods cannot be well applied to blind denoising problems;

[0008] (2) The methods involved above cannot use one model to deal with tasks such as real noise and blind noise

Images