Dark circle detection and evaluation method and apparatus

Patent metadata

Field	Value
Publication number	US-11779264-B2
Application number	US-201917297684-A
Country	US
Kind code	B2
Filing date	Nov 15, 2019
Priority date	Nov 29, 2018
Publication date	Oct 10, 2023
Grant date	Oct 10, 2023

Abstract

A dark circle detection and evaluation method includes: obtaining a to-be-processed image; extracting a dark circle region of interest from the to-be-processed image; performing color clustering on the dark circle region of interest to obtain n types of colors in the dark circle region of interest, where n is a positive integer; recognizing a dark circle region in the dark circle region of interest based on the n types of colors; and obtaining a dark circle evaluation result based on the dark circle region.

First claim

What is claimed is:

1. A dark circle detection and evaluation method, comprising:
obtaining, by a processor, a to-be-processed image;
extracting, by the processor, a dark circle region of interest from the to-be-processed image;
performing, by the processor, color clustering on the dark circle region of interest to obtain n types of colors in the dark circle region of interest, wherein n is a positive integer;
determining, by the processor, a first color in the n types of colors as a dark circle color in the dark circle region of interest;
determining, by the processor, a second color in the n types of colors as a reference skin color in the dark circle region of interest;
determining, by the processor, a dark circle region in the dark circle region of interest based on the dark circle color and the reference skin color; and
obtaining, by the processor, a dark circle evaluation result based on the dark circle region.

2. The method of claim 1 , wherein the first color is a darkest color obtained after noise is removed from the n types of colors, and the second color is a lightest color obtained after bright light is removed from the n types of colors.

3. The method of claim 1 , further comprising:
wherein a first pixel in the dark circle region of interest satisfies:

C
-

C
⁢
D

CS
-
C

<

T
⁢
1

,

wherein the first pixel belongs to the dark circle region, wherein C is the first pixel, CD is the dark circle color, CS is the reference skin color, and T1 is a contrast of the first pixel with respect to the dark circle color and the reference skin color.

4. The method of claim 3 , wherein the first pixel satisfies:
CS−C>=T 2,
wherein C is the first pixel, CS is the reference skin color, and T2 is a minimum contrast between two colors between which human eyes can distinguish.

5. The method of claim 1 , wherein the reference skin color satisfies at least one of:
CS<T 3,
or
CS−CS i-1 <=T 4,
wherein CS is the reference skin color, CS is an i th type of colors in the n types of colors, and CS i-1 is an (i−1) th type of colors in the n types of colors;
wherein i is a positive integer greater than or equal to 1 and less than or equal to n;
wherein T3 is a minimum value of a color of a bright light region; and
wherein T4 is a difference between the i th type of color and (i−1) th types of color.

6. The method of claim 1 , further comprising:
removing an eyelash region from the to-be-processed image; and
extracting the dark circle region of interest from the to-be-processed image after the eyelash region is removed from the to-be-processed image.

7. The method of claim 1 , further comprising:
extracting a feature of the dark circle region, wherein the feature comprises at least one of a contrast of the dark circle region, an area of the dark circle region, or a variance of the dark circle region; and
evaluating, based on the feature, a severity of dark circles by using a pattern recognition method.

8. The method of claim 1 , wherein the dark circle region comprises j regions, the j regions one-to-one correspond to j types of colors in the n types of colors, and j is an integer greater than or equal to 1 and less than n; and the method further comprises:
for each type of color in the j types of colors, extracting a Y value, a CR value, and a CB value of the type of color, wherein the Y value represents brightness of the type of color, the CR value represents a difference between a red component of the type of color and the brightness of the type of color, and the CB value represents a difference between a blue component of the type of color and the brightness of the type of color; and
determining, based on the Y value, the CR value, and the CB value of each type of color, that a type of dark circles comprised in a region corresponding to each type of color is pigmented dark circles or vascular dark circles, wherein the vascular dark circles comprise red eye circles, dark-cyan dark circles, light-cyan dark circles, light-red dark circles, or blue eye circles.

9. The method of claim 8 , wherein:
a color of a middle region in the dark circle region of interest is darker than the dark circle color,
the color of the middle region is darker than a color of a region surrounding the middle region, and
the middle region is a non-discrete region, wherein the dark circle region comprises structural dark circles.

10. The method of claim 9 ,
wherein the dark circle region comprises at least two types of dark circles in the vascular dark circles, the pigmented dark circles, or the structural dark circles, and
wherein dark circles in the dark circle region are mixed dark circles.

11. An electronic device, comprising:
a non-transitory memory comprising instructions; and
a processor coupled to the non-transitory memory, wherein the instructions being executed by the processor cause the electronic device to:
obtain a to-be-processed image;
extract a dark circle region of interest from the to-be-processed image;
perform color clustering on the dark circle region of interest to obtain n types of colors in the dark circle region of interest, wherein n is a positive integer;
determine a first color in the n types of colors as a dark circle color in the dark circle region of interest;
determine a second color in the n types of colors as a reference skin color in the dark circle region of interest;
determine a dark circle region in the dark circle region of interest based on the dark circle color and the reference skin color; and
obtain a dark circle evaluation result based on the dark circle region.

12. The electronic device of claim 11 , wherein the first color is a darkest color obtained after noise is removed from the n types of colors, and the second color is a lightest color obtained after bright light is removed from the n types of colors.

13. The electronic device of claim 11 , wherein a first pixel in the dark circle region of interest satisfies:

C
-

C
⁢
D

CS
-
C

<

T
⁢
1

,

wherein the first pixel belongs to the dark circle region, wherein C is the first pixel, CD is the dark circle color, CS is the reference skin color, and T1 is a contrast of the first pixel with respect to the dark circle color and the reference skin color.

14. The electronic device of claim 13 , wherein the first pixel satisfies:
CS−C>=T 2,
wherein C is the first pixel, CS is the reference skin color, and T2 is a minimum contrast between

Assignees

• Honor Device Co Ltd

Inventors

• Yao Ye
• Dong Chen
• Ding Xin
• Hu Hongwei
• Gao Wenmei

Classifications

• A61B5/441 Primary

  Skin evaluation, e.g. for skin disorder diagnosis · CPC title

• A61B5/1032

  Determining colour of tissue for diagnostic purposes · CPC title

• A61B5/444

  Evaluating skin marks, e.g. mole, nevi, tumour, scar · CPC title

• G06V10/25

  Determination of region of interest [ROI] or a volume of interest [VOI] · CPC title

• G06V30/18105

  related to colour · CPC title