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

Patent metadata

Field	Value
Publication number	US-10922798-B2
Application number	US-201816121057-A
Country	US
Kind code	B2
Filing date	Sep 4, 2018
Priority date	Sep 1, 2017
Publication date	Feb 16, 2021
Grant date	Feb 16, 2021

Abstract

An image processing apparatus is provided. The image processing apparatus according to an exemplary embodiment includes a communicator configured to receive an image, and a processor configured to generate a first image obtained by performing image processing on the received image by using a parameter for image processing, generate a second image obtained by reducing the first image at a predetermined ratio, and extract respective visual features from the first image and the second image, wherein the processor is further configured to adjust the parameter to allow a difference between the visual feature of the first image and the visual feature of the second image to be within a predetermined range.

First claim

What is claimed is:

1. An image processing apparatus, comprising:
a communicator configured to receive a low-quality image of lower quality than an original image and the original image; and
a processor configured to:
generate a first image of higher quality than the low-quality image obtained by performing image processing on the received low-quality image by using a parameter for image processing,
generate a plurality of reduced images to reduce the first image at a plurality of different ratios,
extract respective visual features from the original image and the plurality of reduced images, and
select a second image which is a reduced image having a visual feature most similar to a visual feature extracted from the original image among the plurality of reduced images,

wherein the processor is further configured to adjust the parameter to allow a difference between the visual feature of the first image and the visual feature of the second image to be within a first predetermined range.

2. The image processing apparatus as claimed in claim 1 , wherein the processor is configured to adjust the parameter by using a machine learning method.

3. The image processing apparatus as claimed in claim 1 , wherein the processor is further configured to repeatedly perform the generation of the first image, the generation of the second image, the extraction of the visual features of the original image and the second image, and the adjustment of the parameter to allow the difference between the visual feature of the first image and the visual feature of the second image to be within the first predetermined range.

4. The image processing apparatus as claimed in claim 1 , wherein the processor is further configured to adjust the parameter to allow the visual feature of the second image to be within the first predetermined range of the visual feature of the first image.

5. The image processing apparatus as claimed in claim 1 ,
wherein the processor is further configured to:
extract respective structural features of the first image and the original image, and
adjust the parameter by using a machine learning method to allow a difference between the structural feature of the first image and the structural feature of the original image to be within a second predetermined range.

6. The image processing apparatus as claimed in claim 1 ,
wherein the processor is further configured to:
extract respective structural features of the first image and the original image, and
adjust the parameter by using a machine learning method to allow a sum of a difference between the visual feature of the first image and the visual feature of the second image and a difference between the structural feature of the first image and the structural feature of the original image to be within a third predetermined range.

7. The image processing apparatus as claimed in claim 1 , wherein the processor is further configured to perform image processing on a received image by using the adjusted parameter.

8. The image processing apparatus as claimed in claim 7 , further comprising:
a display configured to display the image processed image.

9. The image processing apparatus as claimed in claim 7 , wherein the processor is further configured to control the communicator to transmit the image processed image to an external apparatus.

10. A method for image processing, the method comprising:
receiving a low-quality image of lower quality than an original image and the original image; and
adjusting a parameter for performing image processing on the received image,
wherein the adjusting comprises:
generating a first image of higher quality than the low-quality image obtained by performing image processing on the received low-quality image by using a predetermined parameter,
generating a plurality of reduced images to reduce the first image at a plurality of different ratios,
extracting respective visual features from the original image and the plurality of reduced images,
selecting a second image which is a reduced image having a visual feature most similar to a visual feature extracted from the original image among the plurality of reduced images, and
modifying the parameter to allow a difference between the visual feature of the first image and the visual feature of the second image to be within a first predetermined range.

11. The method as claimed in claim 10 , wherein the adjusting comprises repeatedly adjusting the parameter by using a machine learning method.

12. The method as claimed in claim 10 , wherein the modifying comprises modifying the parameter to allow the visual feature of the second image to be within the first predetermined range of the visual feature of the first image.

13. The method as claimed in claim 10 ,
wherein the adjusting comprises:
extracting respective structural features of the first image and the original image, and
modifying the parameter to allow a difference between the structural feature of the first image and the structural feature of the original image to be within a second predetermined range.

14. The method as claimed in claim 10 ,
wherein the adjusting comprises:
extracting respective structural features of the first image and the original image, and
modifying the parameter to allow a sum of a difference between the visual feature of the first image and the visual feature of the second image and a difference between the visual feature of the first image and the structural feature of the original image to be within a third predetermined range.

15. The method as claimed in claim 10 , further comprising:
performing image processing on the received image by using the adjusted parameter.

16. The method as claimed in claim 15 , further comprising:
displaying the image processed image.

17. The method as claimed in claim 15 , further comprising:
transmitting the image processed image to an external apparatus.

18. A computer readable recording medium having a program for executing an image processing method, the image processing method comprising:
receiving a low-quality image of lower quality than an original image and the original image; and
adjusting a parameter for performing image processing on the received image,
wherein the adjusting comprises:
generating a first image of higher quality than the low-quality image obtained by performing image processing on the received low-quality image by using a predetermined parameter,
generating a plurality of reduced images to reduce the first image at a plurality of different ratios,
extracting respective visual features from the original image and the plurality of reduced images,
selecting a second image which is a reduced image having a visual feature most similar to a visual feature extracted from the original image among the plurality of reduced images, and
modifying the parameter to allow a difference between the visual feature of the first image and the visual feature of the second image to be within a first predetermined range.

Assignees

• Samsung Electronics Co Ltd

Inventors

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

Classifications

• G06T5/92

  based on global image properties · CPC title

• G06T3/40 Primary

  Scaling of whole images or parts thereof, e.g. expanding or contracting · CPC title

• G06V40/169

  Holistic features and representations, i.e. based on the facial image taken as a whole · CPC title

• G06T3/4053 Primary

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

• G06T2207/20081

  Training; Learning · CPC title