Systems and methods for image processing

A system comprising:

• at least one storage device storing a set of instructions;
• and
• at least one processor in communication with the at least one storage device, when executing the stored set of instructions, the at least one processor causes the system to perform operations including:
• obtaining an image including at least one of a first type of artifact or a second type of artifact;
• and
• generating a target image by processing, based on a trained machine learning mode, the image, wherein the trained machine learning mode includes a first trained model and a second trained model, the first trained model being configured to correct the first type of artifact in the image, the second trained model being configured to correct the second type of artifact in the image, and the first trained model is obtained according to a process including:
• obtaining a plurality of training samples, wherein the plurality of training samples include a plurality of sample input images and a plurality of corresponding sample expected images, and each of the plurality of corresponding sample expected images is determined by performing an artifact correction operation on a sample input image;
• and
• determining the first trained model by inputting the plurality of sample input images and a plurality of first residual images into a first preliminary model, wherein each of the plurality of first residual images is determined by performing a subtraction operation between a sample input image and a corresponding sample expected image.

A method for image processing implemented on a computing device having one or more processors and one or more storage devices, the method comprising:

• obtaining an image including at least one of a first type of artifact or a second type of artifact;
• determining, based on a trained machine learning model, at least one of first information associated with the first type of artifact or second information associated with the second type of artifact in the image, wherein the trained machine learning model includes a first trained model and a second trained model, the first trained model being configured to determine the first information, and the second trained model being configured to determine the second information, and the first trained model is obtained according to a process including:
• obtaining a plurality of training samples, wherein the plurality of training samples include a plurality of sample input images and a plurality of corresponding sample expected images, and each of the plurality of corresponding sample expected images is determined by performing an artifact correction operation on a sample input image;
• and
• determining the first trained model by inputting the plurality of sample input images and a plurality of first residual images into a first preliminary model, wherein each of the plurality of first residual images is determined by performing a subtraction operation between a sample input image and a corresponding sample expected image;
• and
• generating a target image based on at least part of the first information and the second information.