Image processing method, system and device and storage medium

Abstract

The invention provides an image processing method, system and device and a storage medium, and the method comprises the steps: obtaining a reversible image conversion model which is used for converting an image between a first format and a second format; acquiring a first image in a second format, and acquiring the first image in the first format based on the reversible image conversion model; processing the first image in the first format by adopting a reverse algorithm of a preset image processing algorithm to obtain a second image in the first format, and obtaining the second image in the second format based on the reversible image conversion model; training the image processing model based on the second image in the second format and the first image in the second format; and inputting the to-be-processed image in the second format into the trained image processing model to obtain a processed image in the second format. According to the invention, the second image and the first image in the second format for training the image processing model can be obtained, and the processing effect of the image processing model is improved.

Description

technical field [0001] The present invention relates to the technical field of data processing, in particular to an image processing method, system, device and storage medium. Background technique [0002] In many image processing algorithms, such as image white balance, image denoising and other fields, raw images without any processing are the most important data input part in image processing algorithms. However, the original Raw image collected by the CMOS (Complementary Metal Oxide Semiconductor, Complementary Metal Oxide Conductor) sensor is generally relatively large in size and takes up a large storage space. The time cost of manual collection of Raw images is often huge, which limits the usage scenarios of image processing algorithms. [0003] In addition, in the field of image processing algorithms based on deep learning, supervised learning methods generally have stronger generalization ability than unsupervised learning methods or semi-supervised learning method...

AI Technical Summary

Problems solved by technology

For some specific tasks, such as the image white balance algorithm, the target image is difficult to obtain. Due to the placement of the lens and the depth of field, the collected image has pixel deviation and often has a certain degree of depth for occluded objects. Error, unable to collect matching images with color cast and corresponding images at normal color temperature

In general, the above problems can be solved by image alignment, but after using this method, there are still slight errors between the target image and the source image, resulting in blurred images after white balance

In addition, color shift images can be synthesized by adding color temperature changes to the source RGB image, and then the source RGB image is used as the target image to form an image pair to realize the training of the image white balance model, but the color shift image synthesized by this method is different from the real There are large differences in the color cast images of the world, resulting in poor generalization ability of the model

Images