Unlock instant, AI-driven research and patent intelligence for your innovation.

Image processing method for automatic face buffing

An image processing and automatic technology, applied in the field of image processing, can solve problems such as difficulty in obtaining average skin color, inaccurate facial contour curve, etc.

Pending Publication Date: 2019-09-10
安徽变脸智能技术有限公司
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] There are currently many algorithms and software for face microdermabrasion, but the thin-plate spline interpolation algorithm is not used, and the facial contour curve is inaccurate; a method of adaptively estimating similar areas of skin color is not used, and the parameters are adjusted accurately. Therefore, it is difficult to obtain an accurate average skin tone

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
  • Image processing method for automatic face buffing
  • Image processing method for automatic face buffing
  • Image processing method for automatic face buffing

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0044] An image processing method for face automatic dermabrasion, comprising the following steps:

[0045] (1) Perform face recognition on the image to obtain facial feature points;

[0046] (2) Obtain the face area by fitting the feature points obtained in step (1);

[0047] (3) Carry out mean value calculation to the people's face area that step (2) obtains, obtain average skin color;

[0048] (4) Calculate the skin color similarity map according to the average skin color, and utilize the smooth contour obtained in the skin color similarity map fusion step (3) after normalization;

[0049] (5) Perform global smoothing filtering on the image to obtain the smoothed picture.

[0050] The method for obtaining facial feature points described in step (1) is to locate the position of the feature points by means of a convolutional neural network, and obtain the positions of the feature points surrounding the facial features.

[0051] The method for obtaining the human face area ...

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 invention discloses an image processing method for automatic face buffing, and the method comprises the following steps: (1) carrying out the face recognition of an image, and obtaining face feature points; (2) fitting the feature points to obtain a face region; (3) carrying out mean value calculation on the face region to obtain an average skin color; (4) calculating a skin color similarity graph according to the average skin color, and fusing the skin color similarity graph obtained in the step (3) with the normalized skin color similarity graph; and (5) carrying out global smoothing filtering on the image to obtain a smoothed picture. According to the method, the convolutional neural network method is adopted to obtain the positions of feature points surrounding five sense organs, and the feature points are connected into a closed face contour curve by using a thin plate spline curve interpolation algorithm, so that the face contour curve can be accurately obtained. A skin colorelliptic model method for adaptively estimating a skin color similar region is used, and parameter adjustment is carried out through a parameter adjustment method combining chroma channel statisticalinformation and elliptic clustering information, so that the average skin color can be accurately obtained.

Description

technical field [0001] The present invention mainly relates to the technical field of image processing, and in particular to an image processing method for automatic face dermabrasion. Background technique [0002] There are currently many algorithms and software for face microdermabrasion, but the thin-plate spline interpolation algorithm is not used, and the facial contour curve is inaccurate; a method of adaptively estimating similar areas of skin color is not used, and the parameters are adjusted accurately. Therefore, it is difficult to obtain an accurate average skin color. Contents of the invention [0003] The object of the present invention is to provide an image processing method for automatic face dermabrasion in order to make up for the defects of the prior art. [0004] The present invention is achieved through the following technical solutions: [0005] A kind of image processing method of human face automatic dermabrasion, is characterized in that, compris...

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
IPC IPC(8): G06T5/00G06K9/00G06T7/90
CPCG06T7/90G06T2207/10024G06T2207/30201G06T2207/20221G06V40/168G06T5/77G06T5/70
Inventor 张智森温泉黄章进李明
Owner 安徽变脸智能技术有限公司