Image processing method, and image processor

摘要

Included are (a) performing processes on second training data items stored in a training database to generate third training data items each obtained through a corresponding one of the processes, (b) selecting, from among the third training data items generated in step (a), a selection data item having a highest similarity to a feature data item of the input image, (c) generating a high-frequency data item by: determining (i) the second training data item used in generating the selection data item and (ii) a first process performed on the second training data item to generate the selection data item; and performing the first process on the first training data item that is paired with the determined second training data item; and (d) generating an output image by adding an image indicated by the high-frequency data item to the input image.

主权项

1. An image processing method for performing image processing using a training database in which pairs of training data items are stored, to generate, from an input image, an output image having a higher resolution than a resolution of the input image, the pairs of training data items each including (i) a first training data item obtained from a high-frequency component of a training image and (ii) a second training data item obtained from at least a low-frequency component of the training image, the method comprising:
(a) performing different processes on each of the second training data items stored in the training database, to generate third training data items each of which is obtained through a corresponding one of the processes; (b) selecting, from among the third training data items generated from the second training data items in step (a), a selection data item having a highest similarity to a feature data item indicating a feature of the input image; (c) generating a high-frequency data item by: determining (i) the second training data item used in generating the selection data item and (ii) a first process that is one of the processes performed on the second training data item to generate the selection data item; and performing the first process on the first training data item that is paired with the determined second training data item; and (d) generating the output image by adding an image indicated by the high-frequency data item to the input image.