Image enhancement method, device, and computer program

Patent metadata

Field	Value
Publication number	US-12567230-B2
Application number	US-202418412379-A
Country	US
Kind code	B2
Filing date	Jan 12, 2024
Priority date	Jul 13, 2021
Publication date	Mar 3, 2026
Grant date	Mar 3, 2026

Abstract

Disclosed is an image enhancement method, including: obtaining an image adjustment parameter; converting first image data to be processed into second image data; adjusting the luminance data to obtain adjusted luminance data, updating the luminance adjustment parameter when that the adjusted luminance data does not meet a preset luminance enhancement condition, and based on an updated luminance adjustment parameter, continuing to adjust the adjusted luminance data until final adjusted luminance data meets the luminance enhancement condition; adjusting the chroma data to obtain adjusted chroma data, updating the chroma adjustment parameter when that the adjusted chroma data does not meet a preset chroma enhancement condition, and based on an updated chroma adjustment parameter, continuing to adjust the adjusted chroma data until final adjusted chroma data meets the chroma enhancement condition; and performing image color dimension conversion on the luminance data and the chroma data to obtain third image data.

First claim

What is claimed is:

1 . An image enhancement method, executed by a computer equipment, wherein the method comprises:
obtaining an image adjustment parameter, wherein the image adjustment parameter comprises a luminance adjustment parameter and a chroma adjustment parameter; converting first image data to be processed into second image data, wherein the first image data and the second image data belong to different color dimensions, and the second image data comprises luminance data and chroma data; adjusting the luminance data based on the luminance adjustment parameter to obtain adjusted luminance data, determining whether the adjusted luminance data meets a preset luminance enhancement condition, updating the luminance adjustment parameter in response to that the adjusted luminance data does not meet the preset luminance enhancement condition, and based on an updated luminance adjustment parameter, continuing to adjust the adjusted luminance data until final adjusted luminance data meets the luminance enhancement condition; adjusting the chroma data based on the chroma adjustment parameter to obtain adjusted chroma data, determining whether the adjusted chroma data meets a preset chroma enhancement condition, updating the chroma adjustment parameter in response to that the adjusted chroma data does not meet the preset chroma enhancement condition, and based on an updated chroma adjustment parameter, continuing to adjust the adjusted chroma data until final adjusted chroma data meets the chroma enhancement condition; and performing image color dimension conversion on the luminance data that meets the luminance enhancement condition and the chroma data that meets the chroma enhancement condition, to obtain third image data belonging to a same color dimension as the first image data, thereby generating the third image data after image-enhanced from the first image data, wherein the adjusting the luminance data based on the luminance adjustment parameter to obtain the adjusted luminance data comprises: making statistics on luminance data before adjustment based on the luminance adjustment parameter, and determining a scaling coefficient based on a statistical result and maximum required luminance of the luminance adjustment parameter, wherein the statistical result comprises a minimum luminance value, a maximum luminance value and an initial average luminance value of the luminance data before adjustment; performing luminance linear scaling processing on the luminance data of the second image data to obtain luminance data after luminance linear scaling processing according to the scaling coefficient, and determining a scaling average luminance value based on the luminance data after luminance linear scaling processing; determining at least one target interval to be performed luminance adjustment of the second image data according to the scaling average luminance value; determining an adaptive luminance adjustment manner matching the second image data; and adjusting the luminance data in the at least one target interval to obtain the adjusted luminance data based on a matched adaptive luminance adjustment manner.

2 . The method according to claim 1 , wherein the determining at least one target interval to be performed luminance adjustment of the second image data according to the scaling average luminance value comprises:
dividing the luminance data after luminance linear scaling processing into a first luminance data set and a second luminance data set based on the scaling average luminance value; filtering out a first target luminance value with a highest occurrence frequency from the first luminance data set, and filtering out a second target luminance value with a highest occurrence frequency from the second luminance data set; and determining a target interval corresponding to luminance data to be performed luminance adjustment according to frequency values respectively corresponding to the first target luminance value and the second target luminance value.

3 . The method according to claim 2 , wherein the determining the target interval corresponding to the luminance data to be performed luminance adjustment according to the frequency values respectively corresponding to the first target luminance value and the second target luminance value comprises:
determining a first luminance frequency of the first target luminance value in the first luminance data set; determining a second luminance frequency of the second target luminance value in the second luminance data set; obtaining a first luminance data adjustment interval based on the first luminance frequency, wherein the first target luminance value is within the first luminance data adjustment interval; obtaining a second luminance data adjustment interval based on the second luminance frequency, wherein the second target luminance value is within the second luminance data adjustment interval; and using the first luminance data adjustment interval and the second luminance data adjustment interval as target intervals to be performed luminance adjustment of the second image data.

4 . The method according to claim 3 , wherein the obtaining the first luminance data adjustment interval based on the first luminance frequency comprises:
determining a luminance value corresponding to a middle frequency of a left side of a dark area and a luminance value corresponding to a middle frequency of a right side of the dark area according to the first luminance frequency, wherein the middle frequency of the dark area is half of the first luminance frequency; and determining a first luminance data adjustment area from the first luminance data set according to the luminance value corresponding to the middle frequency of the left side of the dark area and the luminance value corresponding to the middle frequency of the right side of the dark area.

5 . The method according to claim 3 , wherein the obtaining the second luminance data adjustment interval based on the second luminance frequency comprises:
determining a luminance value corresponding to a middle frequency of a left side of a bright area and a luminance value corresponding to a middle frequency of a right side of the bright area according to the second luminance frequency, wherein the middle frequency of the bright area is half of the second luminance frequency; and determining a second luminance data adjustment area from the second luminance data set according to the luminance value corresponding to the middle frequency of the left side of the bright area and the luminance value corresponding to the middle frequency of the right side of the bright area.

6 . The method according to claim 2 , wherein the luminance adjustment parameter comprises the maximum required luminance, and determining the adaptive luminance adjustment manner matching the second image data comprises:
multiplying the maximum required luminance by a first weight to obtain a first luminance threshold, and multiplying the maximum required luminance by a second weight to obtain a second luminance threshold, wherein the first weight is smaller than the second weight; and determining the adaptive luminance adjustment manner matching the second image data from a preset luminance adjustment manner according to the scaling average luminance value, the first target luminance value, the second target luminance value, the first luminance threshold and the second luminance threshold.

7 . The method according to claim 6 , wherein the adaptive luminance adjustment manner comprises a gamma adjustment formula corresponding to the luminance data, and the method further comprises:
calculating a normalized gamma value corresponding to each grayscale level based on a grayscale level of the first

Assignees

• Unilumin Group Co Ltd

Inventors

• Huang Bin
• Li Yongjie
• Shen Lingxiang

Classifications

• H04N1/60

  Colour correction or control {(H04N1/54 takes precedence)} · CPC title

• G06T11/60

  Creating or editing images; Combining images with text · CPC title

• G06T3/4007

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

• G06T5/92 Primary

  based on global image properties · CPC title

• G06V10/56

  relating to colour · CPC title