Information processing apparatus, information processing method, and storage medium

Patent metadata

Field	Value
Publication number	US-2025200714-A1
Application number	US-202418984078-A
Country	US
Kind code	A1
Filing date	Dec 17, 2024
Priority date	Dec 18, 2023
Publication date	Jun 19, 2025
Grant date	—

Abstract

An information processing apparatus divides an input image into a plurality of divided images and selects an appropriate image generator for each divided image from among a plurality of image generators based on the divided images of the input image. The information processing apparatus generates a plurality of generated images from the input image or the divided images of the input image using the plurality of selected image generators and combines two or more of the generated images.

First claim

What is claimed is:

1 . An information processing apparatus comprising:
a division unit configured to divide an input image into a plurality of divided images; a selection unit configured to select an appropriate image generator for each of the divided images from among a plurality of image generators based on the divided images of the input image; an image generation unit configured to generate a plurality of generated images from or the divided images of the input image using the plurality of image generators selected by the selection unit; and a combining unit configured to combine two or more of the generated images.

2 . The information processing apparatus according to claim 1 ,
wherein the image generation unit generates the generated images from the divided images using the image generators selected for the divided images by the selection unit, and wherein the combining unit combines the plurality of generated images generated for the divided images by arranging the generated images at positions corresponding to the divided images of the input image.

3 . The information processing apparatus according to claim 1 ,
wherein the image generation unit generates the plurality of generated images from the input image using the plurality of image generators selected for the divided images and wherein the combining unit extracts area images generated by the appropriate image generator selected for each of the divided images from among the plurality of generated images generated from the input image, and combines the area images by arranging the area images at positions corresponding to the divided images of the input image.

4 . The information processing apparatus according to claim 1 , wherein the selection unit selects the appropriate image generator for each of the divided images of the input image based on a result of a user's subjective evaluation performed on a plurality of generated images preliminarily generated by the plurality of image generators from a plurality of images.

5 . The information processing apparatus according to claim 1 , wherein the selection unit selects the appropriate image generator for each of the divided images of the input image based on a result of an evaluation correlated with a user's subjective evaluation on a plurality of generated images preliminarily generated by the plurality of image generators from a plurality of images.

6 . The information processing apparatus according to claim 5 , further comprising an evaluation unit configured to calculate a result of an evaluation correlated with the user's subjective evaluation based on an image obtained after a plurality of image processes to which a weight correlated with the user's subjective evaluation is applied is performed on the plurality of images and the plurality of generated images generated by the plurality of image generators from the plurality of images.

7 . The information processing apparatus according to claim 4 , wherein the selection unit searches divided images of the plurality of images for a divided image similar to a divided image of interest in the input image, and selects an image generator corresponding to the similar divided image as an appropriate image generator for the divided image of interest.

8 . The information processing apparatus according to claim 7 , wherein the selection unit determines a degree of similarity between the divided image of interest and the plurality of generated images generated by the plurality of image generators from the plurality of images using at least one feature amount of a spatial frequency characteristic, an average luminance value, and a contrast value of an image, and performs the search based on the degree of similarity.

9 . The information processing apparatus according to claim 8 , wherein the selection unit obtains the degree of similarity by converting the feature amount into a feature vector.

10 . The information processing apparatus according to claim 1 , wherein the combining unit combines the generated images corresponding to adjacent divided images, such that the generated images overlap each other with a predetermined width.

11 . The information processing apparatus according to claim 1 , wherein the combining unit combines the generated images by adjusting an average luminance value such that the generated images corresponding to the adjacent divided images have the same average luminance value.

12 . The information processing apparatus according to claim 1 , wherein the division unit linearly divides the input image or linearly divides the input image for each object in the input image.

13 . The information processing apparatus according to claim 1 , wherein the plurality of image generators generates the generated images using at lease one of a learning model for noise removal processing, a learning model for super-resolution processing, a learning model for style conversion processing, and image filter processing.

14 . An information processing method comprising:
dividing an input image into a plurality of divided images; selecting an appropriate image generator for each of the divided images from among a plurality of image generators based on the divided images of the input image; generating a plurality of generated images from the divided images of the input image using the plurality of selected image generators; and combining two or more of the generated images.

15 . A non-transitory computer-readable storage medium storing a computer-executable program for causing a computer to perform the method according to claim 14 .

Assignees

• Canon Kk

Inventors

• Yamamoto Masashi

Classifications

• G06T2207/30168

  Image quality inspection · CPC title

• G06T7/10

  Segmentation; Edge detection (motion-based segmentation G06T7/215) · CPC title

• G06T7/0002 Primary

  Inspection of images, e.g. flaw detection · CPC title

• G06T2207/20081

  Training; Learning · CPC title

• G06T2207/20021

  Dividing image into blocks, subimages or windows · CPC title