System and method for image correction

A system, comprising:

• at least one storage device including a set of instructions for image correction;
• at least one processor in communication with the at least one storage device, wherein when executing the set of instructions, the at least one processor is configured to cause the system to:
• receive an original image including a metal artifact;
• pre-correct the original image by removing or correcting the metal artifact in the original image;
• determine an error image based on the original image and a pre-corrected image;
• for each of a plurality of target pixels in the error image, determine a weighting coefficient corresponding to the target pixel by:
• determining a first neighborhood matrix of a first pixel in the pre-corrected image based on a second neighborhood matrix of a second pixel in the original image and a target neighborhood matrix of the target pixel in the error image, the first pixel corresponding to the second pixel in the original image and the target pixel in the error image, wherein a size of the second neighborhood matrix or a size of the target neighborhood matrix is determined based on a feature of the error image;
• determining information entropy of the first pixel in the pre-corrected image based on the first neighborhood matrix;
• and
• determining the weighting coefficient corresponding to the target pixel in the error image based on the information entropy of the first pixel in the pre-corrected image;
• weight the original image and the error image based on a plurality of weighting coefficients corresponding to the plurality of target pixels;
• and
• generate a corrected image based on the weighting.

A non-transitory computer readable medium comprising executable instructions that, when executed by at least one processor, cause the at least one processor to effectuate a method for image correction implemented on a computing device, the method comprising:

• receiving an original image including a metal artifact;
• pre-correcting the original image by removing or correcting the metal artifact in the original image;
• determining an error image based on the original image and a pre-corrected image;
• for each of a plurality of target pixels in the error image, determining a weighting coefficient corresponding to the target pixel by:
• determining a first neighborhood matrix of a first pixel in the pre-corrected image based on a second neighborhood matrix of a second pixel in the original image and a target neighborhood matrix of the target pixel in the error image, the first pixel corresponding to the second pixel in the original image and the target pixel in the error image, wherein a size of the second neighborhood matrix or a size of the target neighborhood matrix is determined based on a feature of the error image;
• determining information entropy of the first pixel in the pre-corrected image based on the first neighborhood matrix;
• and
• determining the weighting coefficient corresponding to the target pixel in the error image based on the information entropy of the first pixel in the pre-corrected image;
• weighting the original image and the error image based on a plurality of weighting coefficients corresponding to the plurality of target pixels;
• and
• generating a corrected image based on the weighting.