The present disclosure relates to image learning method, apparatus, program, and recording medium using a generative adversarial network.
The present disclosure allows to learn various images as well as medical radiographic images to maintain structural information on the basis of a generative adversarial network. The present disclosure prevents the structural information of the generated image with respect to an original image from being lost, and improves image qualities, such as resolution, noise degree, contrast, etc. to the level of a target reference dataset. When the present disclosure is used for image standardization, medical radiographic images imaged by different institutions and any number of image datasets having various qualities can be standardized universally.