Image processing apparatus, image processing method, and computer-readable recording medium

An image processing method executed by an image processing apparatus for correcting blinking defect noise contained in image data generated by an image sensor, the image sensor comprising:

• a plurality of pixels arranged two-dimensionally and configured to receive light to generate a signal in accordance with an amount of the received light;
• and a plurality of reading circuits configured to read the signal as a pixel value, the method comprising:
• acquiring noise information that is defined by associating positional information of the plurality of reading circuits or positional information of each of the plurality of pixels with feature data related to the blinking defect noise caused by the plurality of reading circuits;
• estimating a random noise amount in a pixel of interest based on the feature data and a random noise model for estimating the random noise amount in the pixel of interest;
• and
• correcting a pixel value of the pixel of interest based on the random noise amount.

A non-transitory computer-readable recording medium with an executable program stored thereon to be executed by an image processing apparatus an image processing apparatus for correcting blinking defect noise contained in image data generated by an image sensor, the image sensor comprising:

• a plurality of pixels arranged two-dimensionally and configured to receive light to generate a signal in accordance with an amount of the received light;
• and a plurality of reading circuits configured to read the signal as a pixel value, the program causing the image processing apparatus to execute:
• acquiring noise information that is defined by associating positional information of the plurality of reading circuits or positional information of each of the plurality of pixels with feature data related to the blinking defect noise caused by the plurality of reading circuits;
• estimating a random noise amount in a pixel of interest based on the feature data and a random noise model for estimating the random noise amount in the pixel of interest;
• and
• correcting a pixel value of the pixel of interest based on the random noise amount.