Learning device, image processing device, parameter generation device, learning method, and image processing method

Abstract

In a learning device, a first learning unit performs first machine learning using first training data including a first evaluation result for an evaluation target image to generate a first learned model outputting a second evaluation result for an input image, an evaluation unit uses the first learned model to acquire a plurality of the second evaluation results for a plurality of the input images, a generation unit selects a second image quality parameter from a plurality of first image quality parameters having different values, based on the plurality of the second evaluation results and generates second training data including the selected second image quality parameter, and a second learning unit performs second machine learning using the second training data to generate a second learned model outputting a third image quality parameter used for processing a processing target image.