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

Patent metadata

Field	Value
Publication number	US-11257186-B2
Application number	US-201716345616-A
Country	US
Kind code	B2
Filing date	Oct 26, 2017
Priority date	Oct 26, 2016
Publication date	Feb 22, 2022
Grant date	Feb 22, 2022

Abstract

An image processing apparatus is disclosed. The present image processing apparatus includes an input unit to which an image is input; and a processor which extracts visual characteristics by reducing an input image and obtains a high-definition image by reflecting extracted visual characteristics on the input image. The disclosure relates to an artificial intelligence (AI) system and application thereof that simulate functions such as cognition and decision-making of a human brain using a machine learning algorithm such as deep learning.

First claim

What is claimed is:

1. An image processing apparatus comprising:
a memory configured to store a plurality of scale factors for determining an extent of reduction of an input image;
an input unit to which the image is input; and
a processor configured to:
receive an input image through the input unit,
perform pre-processing to improve an image quality of the input image,
determine a degree of degradation of the input image based on an image quality improvement rate of the pre-processed image which is measured by comparing the pre-processed image with the input image,
obtain a plurality of reduced images by reducing the pre-processed image based on a scale factor corresponding to the determined degree of degradation from among the plurality of scale factors stored in the memory,
obtain a texture feature corresponding to the pre-processed image, and a plurality of texture features corresponding to the plurality of reduced images,
identify, among the plurality of texture features corresponding to the plurality of reduced images, a texture feature having a minimum difference from the texture feature corresponding to the pre-processed image, and
obtain an output image by applying the identified texture feature to a plurality of first areas of the pre-processed image, the plurality of first areas being a portion of the pre-processed image in which a frequency of an image signal corresponding to the pre-processed image is greater than or equal to a preset frequency, wherein a size of the plurality of first areas corresponds to a size of the plurality of reduced images.

2. The image processing apparatus of claim 1 , wherein the plurality of scale factors are different from each other.

3. The image processing apparatus of claim 1 , wherein the processor is further configured to arrange the plurality of reduced images to correspond to a size of the input image and obtain a first texture feature from the plurality of arranged images.

4. The image processing apparatus of claim 1 , further comprising:
a display unit configured to display the obtained output image.

5. The image processing apparatus of claim 1 , further comprising:
a communicator configured to transmit the obtained output image to a display device.

6. An image processing method comprising:
receiving an input image;
performing pre-processing to improve an image quality of the input image,
determining a degree of degradation of the input image based on an image quality improvement rate of the pre-processed image which is measured by comparing the pre-processed image with the input image,
obtaining a plurality of reduced images by reducing the pre-processed image based on a scale factor corresponding to the determined degree of degradation from among a plurality of scale factors for determining an extent of reduction of the pre-processed image;
obtaining a texture feature corresponding to the pre-processed image and a plurality of texture features corresponding to the plurality of reduced images;
identifying, among the plurality of texture features corresponding to the plurality of reduced images, a texture feature having a minimum difference from the texture feature corresponding to the pre-processed image, and
obtaining an output image by applying the identified texture feature to a plurality of first areas of the pre-processed image, the plurality of first areas being a portion of the pre-processed image in which a frequency of an image signal corresponding to the pre-processed image is greater than or equal to a preset frequency, wherein a size of the plurality of first areas corresponds to a size of the plurality of reduced images.

7. The method of claim 6 , wherein the plurality of scale factors are different from each other.

8. The method of claim 6 , further comprising:
storing the plurality of scale factors corresponding to a plurality of degrees of degradation of an image.

9. The method of claim 6 , wherein the obtaining comprises arranging the plurality of reduced images to correspond to a size of the input image and obtaining a first texture feature from the plurality of arranged images.

Assignees

• Samsung Electronics Co Ltd

Inventors

• Ahn Il-Jun
• Nam Woo-Hyun
• Cho Ki-Heum
• Park Yong-Sup
• Lee Tammy
• Cheon Min-Su

Classifications

• G06T3/4053 Primary

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

• G06T3/4069 Primary

  by subpixel displacements · CPC title

• G06T5/50

  using two or more images, e.g. averaging or subtraction · CPC title

• G06T3/4007 Primary

  based on interpolation, e.g. bilinear interpolation (image demosaicing G06T3/4015; edge-driven or edge-based scaling G06T3/403) · CPC title

• G06T2207/20221

  Image fusion; Image merging · CPC title