Image processing apparatus, method for processing image and computer-readable recording medium

Patent metadata

Field	Value
Publication number	US-11006108-B2
Application number	US-201816130253-A
Country	US
Kind code	B2
Filing date	Sep 13, 2018
Priority date	Sep 14, 2017
Publication date	May 11, 2021
Grant date	May 11, 2021

Abstract

An image processing apparatus is provided. The image processing apparatus includes a processor configured to, in response to an image including a plurality of frames being input, change a predetermined parameter to a parameter corresponding to a compression rate of each of the plurality of frames for each frame, and process the input image by using the parameter changed for each frame, and an output interface configured to output the processed image.

First claim

What is claimed is:

1. An image processing apparatus, comprising:
a processor configured to:
in response to an image including a plurality of frames being input, acquire a feature value of the plurality of frames by inputting the image to a layer to acquire a structural feature of an image,
acquire a parameter of the plurality of frames by normalizing the acquired feature value using an image quality figure, the image quality figure corresponding to a compression rate of each of the plurality of frames, and
process the input image by using the parameter; and

an output interface configured to output the processed image,
wherein the processor is further configured to: normalize the acquired feature value by using a first parameter, and acquire the feature value of the plurality of frames by using a second parameter, and
wherein the second parameter has a same value even if a compression rate of a frame is changed.

2. The image processing apparatus as claimed in claim 1 , further comprising:
a memory configured to store a predetermined parameter corresponding to a plurality of predetermined compression rates,
wherein the processor is further configured to:
in a case that a compression rate of a frame is one of the plurality of predetermined compression rates, perform an image process using a parameter corresponding to the compression rate from among the stored parameter, and
in a case that a compression rate of a frame is different from the plurality of predetermined compression rates, perform an image process by calculating a new parameter and store the new parameter in the memory.

3. The image processing apparatus as claimed in claim 2 , wherein the processor is further configured to:
analyze linearity between a compression rate and a parameter by using the plurality of predetermined compression rates and the predetermined parameter; and
calculate a new parameter corresponding to a new compression rate based on the analyzed linearity.

4. The image processing apparatus as claimed in claim 2 , wherein the predetermined parameter is calculated as a result of machine learning of a plurality of frames having a same compression rate.

5. The image processing apparatus as claimed in claim 1 ,
wherein an image process is at least one of decoding and image quality improvement process for the plurality of frames, and
wherein the parameter is a parameter for the decoding and the image quality improvement process.

6. The image processing apparatus as claimed in claim 1 , wherein the processor is further configured to acquire a compression rate of the plurality of frames by using a metadata of the plurality of frames.

7. The image processing apparatus as claimed in claim 1 , wherein the output interface includes a communication interface for transmitting the processed image to an external apparatus.

8. The image processing apparatus as claimed in claim 1 , wherein the output interface includes a display for displaying the processed image.

9. A method for processing an image, the method comprising:
receiving input of an image including a plurality of frames;
acquiring a feature value of the plurality of frames by inputting the image to a layer to acquire a structural feature of an image;
acquiring a parameter of the plurality of frames by normalizing the acquired feature value using an image quality figure, the image quality figure corresponding to a compression rate of each of the plurality of frames;
processing the input image by using the parameter; and
outputting the processed image,
wherein acquiring the parameter of the plurality of frames comprises normalizing the acquired feature value by using a first parameter,
wherein the acquire the feature value comprises acquiring the feature value of the plurality of frames by using a second parameter, and
wherein the second parameter has a same value even if a compression rate of a frame is changed.

10. The method as claimed in claim 9 , further comprising:
storing a predetermined parameter corresponding to a plurality of predetermined compression rates,
wherein the processing the image comprises:
in a case that a compression rate of a frame is one of the plurality of predetermined compression rates, performing an image process using a parameter corresponding to the compression rate from among the stored parameter, and
in a case that a compression rate of a frame is different from the plurality of predetermined compression rates, performing an image process by calculating a new parameter and storing the new parameter in a memory.

11. The method as claimed in claim 10 , wherein the processing the image comprises:
analyzing linearity between a compression rate and a parameter by using the plurality of predetermined compression rates and the predetermined parameter; and
calculating a new parameter corresponding to a new compression rate based on the analyzed linearity.

12. The method as claimed in claim 10 , wherein the predetermined parameter is calculated as a result of machine learning of a plurality of frames having a same compression rate.

13. The method as claimed in claim 9 ,
wherein the processing of the image is at least one of decoding and image quality improvement process for the plurality of frames, and,
wherein the parameter is a parameter for the decoding and the image quality improvement process.

14. The method as claimed in claim 9 , further comprising:
acquiring a compression rate of the plurality of frames by using a metadata of the plurality of frames.

15. The method as claimed in claim 9 , wherein the outputting comprises displaying the processed image or transmitting the processed image to an external apparatus.

16. A non-transitory computer-readable recording medium comprising a program for executing a method for processing an image, wherein the method for processing the image comprises:
receiving input of an image including a plurality of frames;
acquiring a feature value of the plurality of frames by inputting the image to a layer to acquire a structural feature of an image;
acquiring a parameter of the plurality of frames by normalizing the acquired feature value using an image quality figure, the image quality figure corresponding to a compression rate of each of the plurality of frames; and
processing the input image by using the acquired parameter,
wherein acquiring the parameter of the plurality of frames comprises normalizing the acquired feature value by using a first parameter,
wherein the acquire the feature value comprises acquiring the feature value of the plurality of frames by using a second parameter, and
wherein the second parameter has a same value even if a compression rate of a frame is changed.

Assignees

• Samsung Electronics Co Ltd

Inventors

• Cho Ki-Heum
• Park Yong-Sup
• Park Jae-Yeon
• Kim Chang-Han
• Ahn Il-Jun
• Oh Hee-Seok
• Lee Tammy
• Cheon Min-Su

Classifications

• H04N19/136 Primary

  Incoming video signal characteristics or properties · CPC title

• H04N19/115 Primary

  Selection of the code volume for a coding unit prior to coding · CPC title

• G06T3/4053

  based on super-resolution, i.e. the output image resolution being higher than the sensor resolution · CPC title

• H04N19/172

  the region being a picture, frame or field · CPC title

• G06T2207/20081

  Training; Learning · CPC title