Image processing apparatus and image processing method

Patent metadata

Field	Value
Publication number	US-11195261-B2
Application number	US-201716348584-A
Country	US
Kind code	B2
Filing date	Nov 8, 2017
Priority date	Nov 9, 2016
Publication date	Dec 7, 2021
Grant date	Dec 7, 2021

Abstract

Disclosed is an image processing apparatus. The present image processing apparatus comprises: an input unit for inputting an image; and a processor for shrinking the inputted image to a predetermined ratio, extracting a visual feature from the shrunken image, performing an image quality enhancement process reflecting the extracted visual feature in the inputted image, repeatedly performing, for a predetermined number of times, the shrinking, the extracting, and the image quality enhancement process on the image that has undergone the image quality enhancement process. The present disclosure relates to an artificial intelligence (AI) system and an application thereof that simulate the functions of a human brain, such as recognition, judgment, etc., by using a machine learning algorithm such as deep learning, etc.

First claim

The invention claimed is:

1. An image processing apparatus comprising:
an input unit configured to receive an image; and
a processor configured to determine a degradation state of the received image, determine a predetermined ratio based on the determined degradation state, reduce the received image to the predetermined ratio, extract a visual feature from the reduced image, perform an image quality enhancement process in which the extracted visual feature is reflected in the received image, and repeatedly perform, for a predetermined number of times, the reducing, the extracting, and the image quality enhancement process on the image subjected to the image quality enhancement process,
wherein the processor performs the image quality enhancement process by partitioning the received image into a plurality of regions each of which has a size corresponding to a size of the reduced image, reflecting the extracted visual feature in each of the plurality of partitioned regions, and overlapping the plurality of regions, in which the extracted visual feature is reflected, with each other.

2. The image processing apparatus as claimed in claim 1 , wherein the processor reduces the received image based on each of a plurality of reference points in the received image and extracts a visual feature from each of a plurality of reduced images.

3. The image processing apparatus as claimed in claim 2 , wherein the plurality of reference points correspond to the plurality of regions, respectively, and
the processor reflects visual features in the plurality of partitioned regions, respectively, the visual features being extracted from the images reduced based on the reference points corresponding to the plurality of regions.

4. The image processing apparatus as claimed in claim 1 , wherein the extracted visual feature is at least one of a brightness, a color, a darkness, a saturation, a contrast, shapes and density of edges, or a color arrangement.

5. The image processing apparatus as claimed in claim 1 , wherein the predetermined ratio is a value in a range from 0.9 to 0.99.

6. The image processing apparatus as claimed in claim 1 , wherein the processor determines the predetermined number of times for which the reducing, the extracting, and the image quality enhancement process are repeatedly performed, depending on the determined degradation state.

7. The image processing apparatus as claimed in claim 1 , wherein the processor performs a pre-processing for enhancing an image quality of the received image, and performs the image quality enhancement process by reflecting a visual feature extracted from a reduced image in which the pre-processed image is reduced by the predetermined ratio, on the pre-processed image.

8. The image processing apparatus as claimed in claim 1 , wherein the processor determines whether or not a pattern region having a predetermined frequency range is included in the received image, repeatedly performs the reducing, the extracting, and the image quality enhancement process on the pattern region in a case in which the pattern region is included in the received image, and performs the reducing, the extracting, and the image quality enhancement process on a region other than the pattern region only once.

9. The image processing apparatus as claimed in claim 1 , further comprising: a display configured to display the image repeatedly subjected to the image quality enhancement process for the predetermined number of times.

10. The image processing apparatus as claimed in claim 1 , further comprising: a communicator configured to transmit, to a display device, the image repeatedly subjected to the image quality enhancement process for the predetermined number of times.

11. An image processing method comprising:
receiving an image;
determining a degradation state of the received image;
determining a predetermined ratio based on the determined degradation state;
reducing the received image to the predetermined ratio;
extracting a visual feature from the reduced image;
performing an image quality enhancement process in which the extracted visual feature is reflected in the received image; and
repeatedly performing, for a predetermined number of times, the reducing, the extracting, and the image quality enhancement process on the image subjected to the image quality enhancement process,
wherein the performing of the image quality enhancement process comprises:
partitioning the received image into a plurality of regions each of which has a size corresponding to a size of the reduced image;
reflecting the extracted visual feature in each of the plurality of partitioned regions; and
overlapping the plurality of regions, in which the extracted visual feature is reflected, with each other.

12. The image processing method as claimed in claim 11 , wherein in the reducing, the received image is reduced based on each of a plurality of reference points in the received image, and
in the extracting, a visual feature is extracted from each of a plurality of reduced images.

13. The image processing method as claimed in claim 12 , wherein the plurality of reference points correspond to the plurality of regions, respectively, and
in the reflecting, visual features are reflected in the plurality of partitioned regions, respectively, the visual features being extracted from the images reduced based on the reference points corresponding to the plurality of regions.

Assignees

• Samsung Electronics Co Ltd

Inventors

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

Classifications

• G06T3/4007 Primary

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

• G06T5/50 Primary

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

• G06T2207/20221

  Image fusion; Image merging · CPC title

• G06T3/4053 Primary

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

• G06T7/33

  using feature-based methods · CPC title