Image processing method, system and device and storage medium

Abstract

The invention provides an image processing method, system and device and a storage medium, which are used for image sparse reconstruction, image denoising, compressed sensing image reconstruction or image restoration. The image processing method comprises the following steps: establishing a general linear optimization inverse problem under the norm regular constraint of a sparse signal; on the basis of a standard or learned iterative soft threshold shrinkage algorithm, establishing a differentiable deep network model based on convex combination to solve the problem; introducing a deep neural network of any structure in the solving step to accelerate the solving step, and reducing the number of iterations required for convergence of the algorithm. According to the method, a traditional iterative optimization algorithm and a deep neural network of any structure are combined, the image reconstruction performance is improved, rapid convergence is ensured, and the current demand of image sparse reconstruction is met.

Description

technical field [0001] The present invention relates to the field of signal processing, in particular to an image processing method, system, device and storage medium. Background technique [0002] With the development of media technology, massive data is facing huge challenges in real-time transmission, analysis, and storage. For example, the development of a large number of applications of media images in various aspects puts forward higher requirements for image resolution and imaging speed. Image sparse reconstruction can solve the problems of partial loss of image signals and low image compression efficiency during the compression process due to the large amount of image information. , in order to reconstruct the image required by the application. [0003] In response to the above technical requirements, researchers have proposed solutions, such as Chinese patents CN201611029446.2 and CN106780636A, which propose a sparse reconstruction method and device for images. Acc...

AI Technical Summary

Problems solved by technology

However, the current differentiable neural network cannot take into account both model flexibility and theoretical convergence. Some of the methods with theoretical convergence have strict dimension and operation restrictions on the introduced network parameters, while the methods that allow the introduction of flexible network parameters cannot. Demonstrate the convergence of the method from the perspective of optimization

Therefore, it is difficult to meet the current needs of image sparse reconstruction

Images