Abstract:
An image processing apparatus includes a camera configured to generate first image data, a pre-processor configured to generate second image data based on performing a pre-processing operation on the first image data, a neural network processor configured to generate third image data based on performing an image processing operation on the second image data based on using a neural network model trained to perform one or more particular image processing operations, and a main processor configured to generate corrected image data based on performing a post-processing operation on the third image data.
Abstract:
A lens shading correction method includes providing lens shading correction profile data; calculating an intensity values of light passing through each of one or more visible light pass filters and each of one or more infrared light pass filters; calculating an average of the intensity values of the light passing through the one or more visible light pass filters; calculating an average of the intensity values of the light passing through the one or more infrared light pass filters; calculating a normalized intensity value of the light passing through the one or more infrared light pass filters, based on the calculated averages; adjusting one or more lens shading correction coefficients included in the lens shading correction profile data and each having a value varying depending on a frequency element of light, based on the calculated normalized intensity value; and correcting lens shading by using the adjusted lens shading correction coefficient.