Display apparatus and operating method of the same

Patent metadata

Field	Value
Publication number	US-2025182253-A1
Application number	US-202418980121-A
Country	US
Kind code	A1
Filing date	Dec 13, 2024
Priority date	Dec 5, 2023
Publication date	Jun 5, 2025
Grant date	—

Abstract

Provided are a display apparatus and an operating method of the same. The display apparatus includes: at least one memory storing one or more instructions; and at least one processor configured to execute the one or more instructions, wherein the one or more instructions, when executed by the at least one processor, cause the display apparatus to: obtain an input image, obtain a contour prediction result including information related to a prediction of whether a contour would be generated in an image output by the display apparatus based on the input image by inputting the input image to the contour prediction model, and based on the contour prediction result, perform at least one of a first blurring process or a second blurring process on the input image, wherein the first blurring process is different from the second blurring process.

First claim

What is claimed is:

1 . A display apparatus comprising:
at least one memory storing one or more instructions; and at least one processor configured to execute the one or more instructions, wherein the one or more instructions, when executed by the at least one processor, cause the display apparatus to:
obtain an input image,
obtain a contour prediction result comprising information related to a prediction of whether a contour would be generated in an image output by the display apparatus based on the input image by inputting the input image into the contour prediction model, and
based on the contour prediction result, perform at least one of a first blurring process or a second blurring process on the input image, wherein the first blurring process is different from the second blurring process.

2 . The display apparatus of claim 1 ,
wherein the contour prediction result comprises a contour generation probability, the contour generation probability comprising a probability that a contour would be generated in an image output by the display apparatus based on the input image, and wherein the one or more instructions, when executed by the at least one processor, cause the display apparatus to:
based on the contour generation probability being less than a threshold, perform the first blurring process on the input image, and
based on the contour generation probability being equal to or greater than the threshold, perform the second blurring process on the input image.

3 . The display apparatus of claim 1 , wherein the one or more instructions, when executed by the at least one processor, cause the display apparatus to:
obtain the contour prediction result by converting the input image into a vector representation to generate image embedding and inputting the image embedding into the contour prediction model.

4 . The display apparatus of claim 1 ,
wherein the first blurring process comprises downscaling, blurring, and upscaling the input image, and the second blurring process comprises downscaling, blurring, and upscaling the input image to generate a blurred image, and lowering a color gray scale of the blurred image through dimming.

5 . The display apparatus of claim 1 ,
wherein the second blurring process comprises contour interpolation of a blurred image generated by blurring the input image, wherein the contour interpolation comprises detecting a boundary region where a gray scale difference between a first pixel and a second pixel included in the input image is equal to or greater than a preset value, and interpolating an intermediate gray scale between a gray scale of the first pixel and a gray scale of the second pixel in the boundary region.

6 . The display apparatus of claim 1 ,
wherein the second blurring process comprises downscaling, blurring, and upscaling the input image, and wherein a second blurring intensity used in the second blurring process is lower than a first blurring intensity used in the first blurring process.

7 . The display apparatus of claim 6 , wherein a second scaling factor used in the second blurring process is smaller than a first scaling factor used in the first blurring process.

8 . The display apparatus of claim 6 , wherein a size of a second blur filter used in the second blurring process is smaller than a size of a first blur filter used in the first blurring process.

9 . The display apparatus of claim 1 , wherein a blurred image generated by performing the second blurring process on the input image includes fewer contours than a blurred image generated by performing the first blurring process on the input image.

10 . The display apparatus of claim 1 , wherein the one or more instructions, when executed by the at least one processor, cause the display apparatus to:
generate a blurred image by performing a blurring process on a training image, obtain feedback on a contour generation result of the blurred image, generate image embedding by converting the training image into a vector representation, and provide the image embedding and a label corresponding to the feedback to the contour prediction model as training data.

11 . The display apparatus of claim 10 , wherein the one or more instructions, when executed by the at least one processor, cause the display apparatus to:
obtain at least one of an user feedback through a user interface including an inquiry about whether a contour is generated in the blurred image, or the feedback corresponding to a contour generation result of the blurred image, obtained through a contour detection algorithm.

12 . The display apparatus of claim 1 , wherein the input image comprises a video image on which an image process has been performed in a YUV color space or a graphic image on which an image process has been performed in an RGB or an RGBA color space.

13 . An operating method of a display apparatus, the operating method comprising:
obtaining an input image; obtaining a contour prediction result comprising information related to a prediction of whether a contour would be generated in an image output by the display apparatus based on the input image by inputting the input image to the contour prediction model; and based on the contour prediction result, performing at least one of a first blurring process or a second blurring process on the input image, wherein the first blurring process is different from the second blurring process.

14 . The operating method of claim 13 ,
wherein the contour prediction result comprises a contour generation probability, the contour generation probability comprising a probability that a contour would be generated in an image output by the display apparatus based on the input image, and wherein the operating method further comprises:
based on the contour generation probability being less than a preset probability, performing the first blurring process on the input image; and
based on the contour generation probability being equal to or greater than the preset probability, performing the second blurring process on the input image.

15 . The operating method of claim 13 , wherein the obtaining the contour prediction result comprises:
obtaining the contour prediction result by converting the input image into a vector representation to generate image embedding and inputting the image embedding into the contour prediction model.

16 . The operating method of claim 13 ,
wherein the first blurring process comprises downscaling, blurring, and upscaling the input image, and wherein the second blurring process comprises downscaling, blurring, and upscaling the input image to generate a blurred image, and lowering a color gray scale of the blurred image through dimming.

17 . The operating method of claim 13 ,
wherein the second blurring process comprises contour interpolation of a blurred image generated by blurring the input image, wherein the contour interpolation comprises detecting a boundary region where a gray scale difference between a first pixel and a second pixel included in the input image is equal to or greater than a preset value, and interpolating an intermediate gray scale between a gray scale of the first pixel and a gray scale of the second pixel in the boundary region.

18 . The operating method of claim 13 ,
wherein the second blurring process comprises downscaling, blurring, and upscaling the input image, and wherein a second blurring intensity used in the second blurring process is lower than a first blurring intensity used in the first blurring process.

Assignees

• Samsung Electronics Co Ltd

Inventors

• Jung Minhyo
• Kim Taehwan

Classifications

• G06T2207/20192

  Edge enhancement; Edge preservation · CPC title

• G06T2207/20084

  Artificial neural networks [ANN] · CPC title

• G06T5/70 Primary

  Denoising; Smoothing · CPC title

• G06T5/73

  Deblurring; Sharpening · CPC title

• G06T5/60

  using machine learning, e.g. neural networks · CPC title