Image tone adjustment method, apparatus thereof and computer storage medium

Patent metadata

Field	Value
Publication number	US-9736336-B2
Application number	US-201514802755-A
Country	US
Kind code	B2
Filing date	Jul 17, 2015
Priority date	Jan 22, 2013
Publication date	Aug 15, 2017
Grant date	Aug 15, 2017

Abstract

The disclosure relates to an image tone adjustment method, an apparatus thereof, and a computer-readable storage medium. The method includes: fitting overlapping areas to obtain a first correction parameter and a second correction parameter, performing interpolation on each pixel of the target image to obtain a corresponding correction parameter, correcting the target image according to the corresponding correction parameters; fitting an overlapping area between the corrected target image and the first image, and an overlapping area between the corrected target image and the second image to obtain a first RGB three-channel linear transformation parameter and a second RGB three-channel linear transformation parameter, performing linear interpolation on each pixel of the corrected target image to obtain a corresponding RGB three-channel linear transformation parameter, and transforming the corrected target image.

First claim

The invention claimed is:

1. An image tone adjustment method, performed by a computer having computer-readable instructions stored therein, such that the computer-readable instructions configure the computer to perform the method, comprising:
fitting, by an image tone adjustment apparatus, an overlapping area between a target image and a first image to obtain a first correction parameter, and fitting an overlapping area between the target image and a second image to obtain a second correction parameter, wherein a portion of the target image at a first side overlaps with the first image, and a portion of the target image at a second side overlaps with the second image;
performing interpolation, by the image tone adjustment apparatus, on each pixel of the target image according to the first correction parameter and the second correction parameter to obtain a corresponding correction parameter, and correcting the target image according to the corresponding correction parameters;
fitting, by the image tone adjustment apparatus, an overlapping area between the corrected target image and the first image to obtain a first RGB three-channel linear transformation parameter, and fitting an overlapping area between the corrected target image and the second image to obtain a second RGB three-channel linear transformation parameter, wherein for RGB, R is red, G is green, and B is blue; and
performing linear interpolation, by the image tone adjustment apparatus, on each pixel of the corrected target image according to the first RGB three-channel linear transformation parameter and the second RGB three-channel linear transformation parameter, to obtain a corresponding RGB three-channel linear transformation parameter, and transforming the corrected target image according to the corresponding RGB three-channel linear transformation parameters.

2. The image tone adjustment method according to claim 1 , further comprising: dividing the overlapping area between the target image and the first image into a plurality of segments, calculating, for each segment, an average luminance of the target image and an average luminance of the first image, forming a correspondence therebetween, and performing fitting according to the plurality of correspondences to obtain the first correction parameter; and
dividing the overlapping area between the target image and the second image into a plurality of segments, calculating, for each segment, an average luminance of the target image and an average luminance of the second image, forming a correspondence therebetween, and performing fitting according to the plurality of correspondences to obtain the second correction parameter.

3. The image tone adjustment method according to claim 1 , further comprising:
performing linear interpolation on each pixel of the target image according to a distance between the pixel and an edge of the target image at the first side of the target image, and a distance between the pixel and an edge of the target image at the second side of the target image, to obtain the corresponding correction parameter, and correcting the target image according to the corresponding correction parameters.

4. The image tone adjustment method according to claim 3 , further comprising: correcting the overlapping area between the target image and the first image according to the first correction parameter;
correcting the overlapping area between the target image and the second image according to the second correction parameter; and
using a weighted average value, which is obtained according to the first correction parameter, the second correction parameter, and the distance between the pixel and the edge at the first side and the distance between the pixel and the edge at the second side, as a correction parameter corresponding to the pixel, and correcting an area other than the overlapping areas of the target image according to the corresponding correction parameters.

5. The image tone adjustment method according to claim 1 , further comprising:
dividing the overlapping area between the corrected target image and the first image into a plurality of segments, calculating, for each segment, an average luminance of the target image and an average luminance of the first image, forming a correspondence therebetween, and performing fitting according to the plurality of correspondences to obtain the first RGB three-channel linear transformation parameter; and
dividing the overlapping area between the corrected target image and the second image into a plurality of segments, calculating for each segment, an average luminance of the target image and an average luminance of the second image, forming a correspondence therebetween, and performing fitting according to the plurality of correspondences to obtain the second RGB three-channel linear transformation parameter.

6. The image tone adjustment method according to claim 1 , further comprising:
performing the linear interpolation according to the distance between each pixel and the edge at the first side and the distance between the pixel and the edge at the second side, to obtain the corresponding RGB three-channel linear transformation parameter, and transforming the corrected target image according to the corresponding RGB three-channel linear transformation parameters.

7. The image tone adjustment method according to claim 6 , further comprising: transforming the overlapping area between the corrected target image and the first image according to the first RGB three-channel linear transformation parameter;
transforming the overlapping area between the corrected target image and the second image according to the second RGB three-channel linear transformation parameter; and
using a weighted average value, which is obtained according to the first RGB three-channel linear transformation parameter, the second RGB three-channel linear transformation parameter, and the distance between the pixel and the edge at the first side and the distance between the pixel and the edge at the second side, as a RGB three-channel linear transformation parameter corresponding to the pixel, and transforming an area other than the overlapping areas of the target image according to the corresponding RGB three-channel linear transformation parameters.

8. An image tone adjustment apparatus, comprising:
a processor and memory machine-readable instruction code stored therein, wherein the processor executes the code to comprise:
a correction parameter acquisition module that fits an overlapping area between a target image and a first image to obtain a first correction parameter, and that fits an overlapping area between the target image and a second image to obtain a second correction parameter, a portion of the target image at a first side overlaps with the first image, and a portion of the target image at a second side overlaps with the second image;
a correction module that performs interpolation on each pixel of the target image according to the first correction parameter and the second correction parameter to obtain a corresponding correction parameter, and that corrects the target image according to the corresponding correction parameters;
a transformation parameter acquisition module that fits an overlapping area between the corrected target image and the first image to obtain a first RGB three-channel linear transformation parameter, and that fits an overlapping area between the corrected target image and the second image to obtain a second RGB three-channel linear transformation parameter, wherein for RGB, R is red, G is green, and B is blue; and
a transformation module that performs linear interpolation on each pixel of the corrected target image according to the first RGB three-channel linear transforma

Assignees

• Tencent Tech Shenzhen Co Ltd

Inventors

• Hu Shimin
• Wang Jianyu
• Li Baoli
• Deng Haifeng
• Li Xianying

Classifications

• H04N1/6008 Primary

  with primary colour signals, e.g. RGB or CMY(K) · CPC title

• H04N1/407 Primary

  Control or modification of tonal gradation or of extreme levels, e.g. background level · CPC title

• G06T5/00

  Image enhancement or restoration · CPC title

• H04N1/6027

  Correction or control of colour gradation or colour contrast (H04N1/6058 takes precedence) · CPC title

• G06T2207/20208

  High dynamic range [HDR] image processing · CPC title