Skin color correction algorithm based on face key points

A face key point and correction algorithm technology, applied in computing, image data processing, instruments, etc., can solve the problems of lack of position information, blurred lips transition, poor skin color correction effect, etc., to achieve good effect, natural effect, and accurate correction The effect of skin tone

Active Publication Date: 2017-12-01
CHENDU PINGUO TECH
View PDF8 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Existing methods mostly use color to distinguish skin and non-skin. No matter how accurate the skin color detection is, it will cause the lack of some important constraints such as location information, resulting in poor skin color correction; especially the area around the facial features; the most obvious is the lips. , the skin color of many people's lips is very close to that of the human face, which directly leads to the blurring of the lips when using the skin color map to guide skin smoothing

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Skin color correction algorithm based on face key points

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0043] In order to make the purpose, technical solution and advantages of the present invention clearer, the present invention will be further elaborated below in conjunction with the accompanying drawings.

[0044] In this example, see figure 1 As shown, the present invention proposes a skin color correction algorithm based on face key points,

[0045] A skin color correction algorithm based on human face key points, including steps S100-S700.

[0046] S100 acquires the original image ORI_IMAGE.

[0047] S200 performs skin color detection on the original image ORI_IMAGE to obtain a skin color probability map M.

[0048] Skin color probability map M, M(i,j) represents the pixel located in the jth row and i column of M, and its value range is [0, 255], M has the same resolution as ORI_IMAGE; the conventional skin color detection algorithm can be used .

[0049] S300 obtains the eyebrow area, eye area, lip area and nose area of ​​the original image, and obtains the key poin...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The present invention discloses a skin color correction algorithm based on face key points. The algorithm comprises: obtaining an original image; performing skin color detection of the original image, and obtaining a skin color probability graph; obtaining the eyebrow area, the eye area, the lip area and nose area of the original image, and obtaining key points of each area; performing line segment filling of the eyebrow area, correcting a skin color probability graph, and obtaining a correction skin color graph I; performing quadrangle filling for the eye area, correcting the correction skin color graph I, and obtaining a correction skin color graph II; performing quadrangle filling for the lip area, correcting the correction skin color graph II, and obtaining a correction skin color graph III; and performing skin color value correction for the nose area, correcting the correction skin color graph III, and obtaining a final correction skin color graph. The skin color correction is higher in precision and better in effect; the face skin color information can be completely obtained to more accurately correct the skin color so as to make a firm basis for the anaphase buffing process and allow the anaphase buffing effect to be more natural.

Description

technical field [0001] The invention belongs to the technical field of image processing, in particular to a skin color correction algorithm based on human face key points. Background technique [0002] In recent years, with the advancement of technology, mobile devices such as smartphones and tablets have become indispensable digital entertainment tools for people. With the rise of smart devices, the demand for beauty selfies is also increasing, especially the skin smoothing function is an important function favored by many women. [0003] The microdermabrasion function is generally realized by the edge-preserving noise reduction algorithm or the high-contrast preservation method. In order not to affect the facial features, hair and background, a mask map is usually required to guide the degree of noise reduction. A fast skin color detection algorithm is commonly used. accomplish. [0004] Existing methods mostly use color to distinguish skin and non-skin. No matter how ac...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & AuthorityApplications(China)
IPC IPC(8): G06T3/00G06T5/00
CPCG06T3/04G06T5/94
Inventor黄亮
OwnerCHENDU PINGUO TECH