Server and operating method thereof, and image processing device and operating method thereof

Patent metadata

Field	Value
Publication number	US-2025117911-A1
Application number	US-202418906775-A
Country	US
Kind code	A1
Filing date	Oct 4, 2024
Priority date	Oct 5, 2023
Publication date	Apr 10, 2025
Grant date	—

Abstract

A server may include: a communication interface; memory storing one or more instructions; and at least one processor operatively connected to the memory and the communication interface, and configured to execute the one or more instructions to: obtain a first image by compressing an original image; obtain quality information of the first image by analyzing image quality of the first image; obtain, based on the quality information, meta model information of a meta model used for performing image quality processing on the first image; and control the communication interface to transmit the meta model information and the first image to an image processing device configured to display a second image based on the meta model information and the first image.

First claim

What is claimed is:

1 . A server comprising:
a communication interface; memory storing one or more instructions; and at least one processor operatively connected to the memory and the communication interface, and configured to execute the one or more instructions to:
obtain a first image by compressing an original image;
obtain quality information of the first image by analyzing image quality of the first image;
obtain, based on the quality information, meta model information of a meta model used for performing image quality processing on the first image; and
control the communication interface to transmit the meta model information and the first image to an image processing device configured to display a second image based on the meta model information and the first image.

2 . The server of claim 1 ,
wherein the first image comprises a plurality of frame images of video content, and wherein the at least one processor is further configured to execute the one or more instructions to obtain quality information of a first frame image at a first time point from among the plurality of frame images based on overall quality information of the plurality of frame images.

3 . The server of claim 2 , wherein the at least one processor is further configured to execute the one or more instructions to:
set a quality upper bound value and a quality lower bound value based on a quality average value and standard deviation of the plurality of frame images; and determine a quality value of the first frame image based on the quality upper bound value and the quality lower bound value.

4 . The server of claim 1 , wherein the at least one processor is further configured to execute the one or more instructions to control the communication interface to transmit the quality information to the image processing device.

5 . The server of claim 1 ,
wherein the meta model is obtained based on at least one reference model, wherein the meta model information comprises information about the at least one reference model and information about a weight applied to the at least one reference model, and wherein the at least one processor is further configured to execute the one or more instructions to determine the at least one reference model and the weight applied to the at least one reference model based on the quality information.

6 . The server of claim 5 , wherein the at least one processor is further configured to execute the one or more instructions to determine the weight based on a difference between quality information corresponding to the at least one reference model and the quality information of the first image.

7 . The server of claim 5 , wherein the at least one reference model comprises a first reference model pre-stored in the server or a second reference model pre-stored in the image processing device.

8 . The server of claim 7 , wherein the at least one processor is further configured to execute the one or more instructions to generate the first reference model corresponding to the first image based on the first image.

9 . The server of claim 7 , wherein the at least one processor is further configured to execute the one or more instructions to:
select the first reference model or the second reference model based on the quality information; based on the first reference model being selected, control the communication interface to transmit information about the first reference model to the image processing device; and based on the second reference model being selected, control the communication interface to transmit identification information of the second reference model to the image processing device.

10 . An image processing device comprising:
a communication interface; a display; memory storing one or more instructions; and at least one processor operatively connected to the memory, the display, and the communication interface, and configured to execute the one or more instructions to:
control the communication interface to receive a first image and meta model information from a server;
generate a meta model based on the meta model information;
train the meta model by using a learning data set corresponding to the first image, to obtain a trained meta model;
obtain, based on the trained meta model, a second image obtained by performing image quality processing on the first image; and
control the display to display the second image.

11 . The image processing device of claim 10 , wherein the at least one processor is further configured to execute the one or more instructions to generate the meta model based on reference model information in the meta model information and weight information applied to the reference model information.

12 . The image processing device of claim 11 , wherein the at least one processor is further configured to execute the one or more instructions to:
obtain quality information of the first image; and generate the learning data set by degrading images classified into a same category as the first image based on the quality information of the first image.

13 . An operating method of a server, the operating method comprising:
obtaining a first image by compressing an original image; obtaining quality information of the first image by analyzing image quality of the first image; obtaining, based on the quality information, meta model information of a meta model used for performing image quality processing on the first image; and transmitting the meta model information and the first image to an image processing device configured to display a second image based on the meta model information and the first image.

14 . The operating method of claim 13 ,
wherein the first image comprises a plurality of frame images of video content, and wherein the obtaining the quality information of the first image comprises obtaining quality information of a first frame image at a first time point from among the plurality of frame images based on overall quality information of the plurality of frame images.

15 . The operating method of claim 14 , wherein the obtaining the quality information of the first image comprises:
setting a quality upper bound value and a quality lower bound value based on a quality average value and standard deviation of the plurality of frame images; and determining a quality value of the first frame image based on the quality upper bound value and the quality lower bound value.

16 . The operating method of claim 13 , further comprising transmitting the quality information to the image processing device.

17 . The operating method of claim 13 ,
wherein the meta model is obtained based on at least one reference model, wherein the meta model information comprises information about the at least one reference model and information about a weight applied to the at least one reference model, and wherein the obtaining the meta model information comprises determining the at least one reference model and the weight applied to the at least one reference model based on the quality information.

18 . The operating method of claim 17 , wherein the determining of the weight applied to the at least one reference model comprises determining the weight based on a difference between quality information corresponding to the at least one reference model and the quality information of the first image.

19 . The operating method of claim 17 ,
wherein the at least one reference model comprises a first reference model pre-stored in the server or a second

Assignees

• Samsung Electronics Co Ltd

Inventors

• Kim Donghyun
• Lee Hyunseung
• Moon Youngsu
• Jeong Younghoon
• Choi Kyuha

Classifications

• G06T2207/10016

  Video; Image sequence · CPC title

• G06T2207/20084

  Artificial neural networks [ANN] · CPC title

• G06T2207/20081

  Training; Learning · CPC title

• G06T2207/30168

  Image quality inspection · CPC title

• G06T7/0002 Primary

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