Skin roughness adaptive skin exfoliating method and system and client

A skin rough and self-adaptive technology, applied in the field of image processing, can solve problems such as unovercome image edge effects, high microdermabrasion coefficient, and image processing result impact, and achieve the effect of avoiding excessive microdermabrasion from losing image details and improving experience

Active Publication Date: 2017-01-04
FUJIAN TQ DIGITAL
View PDF4 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, the above-mentioned technical solution does not overcome the influence of the image edge. If the image edge, such as rough areas such as around the eyes and

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 roughness adaptive skin exfoliating method and system and client
  • Skin roughness adaptive skin exfoliating method and system and client
  • Skin roughness adaptive skin exfoliating method and system and client

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0098] Please refer to figure 1 , Embodiment 1 of the present invention is:

[0099] Skin roughness adaptive microdermabrasion methods, including:

[0100] S11. Acquire the image to be processed, preset one or more average eigenvectors, and a skin smoothing coefficient corresponding to the preset average eigenvectors;

[0101] S12. Extract the feature vector of the image to be processed; the feature vector of the image to be processed is extracted by a feature extraction method;

[0102] S13. Compare the feature vector of the image to be processed with the preset average feature vector one by one, and obtain the corresponding similarity coefficients one by one; through the feature vector H of the image to be processed and the preset average feature of the kth sample image group Vector MH k Calculate the corresponding similarity coefficient sc k (If MH k Trained by support vector machine, then sc k for H and MH k point distance), the specific calculation formula is as fo...

Embodiment 2

[0107] Please refer to Figure 2 to Figure 4 , the second embodiment of the present invention is:

[0108] Feature extraction methods, specifically:

[0109] S21. Obtain an image to be processed;

[0110] S22. Generate a skin template of the image to be processed; generate a skin template of the image to be processed by using skin detection;

[0111] S23. Extract the strong edge of the image to be processed to obtain the variance template; calculate the variance of each pixel of the image to be processed to obtain the variance image, and calculate the variance average, and generate the variance template by the variance image and the variance average, the specific variance template Calculated as follows:

[0112] v ( i , j ) = 0 if g ( i , ...

Embodiment 3

[0128] Please refer to Figure 5 , Embodiment three of the present invention is:

[0129] The preset average eigenvector and the method for obtaining the skin mop coefficient corresponding to the preset average eigenvector are specifically:

[0130] S31. Obtain more than two sample images; collect a large number of face photos as sample images;

[0131] S32. Divide the sample image into one or more sample image groups according to the roughness of the skin in the sample image; divide the sample image into k sample image groups according to the roughness of the skin in the sample image, and each type of sample image Group denoted as S k , preferably, k=5;

[0132] S33. Extracting a feature vector of each sample image; using a feature extraction method to extract a feature vector from each sample image of each type of sample image group;

[0133] S34. Obtain the average eigenvector of each type of sample image group according to the eigenvector, and respectively set the skin...

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 provides a skin roughness adaptive skin exfoliating method and system and a client. The skin roughness adaptive skin exfoliating method comprises steps of obtaining an image to be processed, presetting one or more than one average characteristic vectors and an exfoliating coefficient corresponding to the preset average characteristic vector, extracting a characteristic vector of the image to be processed, successively comparing the characteristic vectors of the image to be processed with the preset average characteristic vector, obtaining corresponding similarity coefficients one by one, and obtaining an exfoliating coefficient of the image to be processed. Through extracting the characteristic vector of the image to be processed, the skin roughness adaptive skin exfoliating method and system and the client compare the characteristic vector of the image to be processed with the preset average characteristic vector to obtain a corresponding similarity coefficient, combine with the preset exfoliating coefficient to obtain the exfoliating coefficient of the image to be processed, dynamically regulate the exfoliating coefficient according to the skin quality of the processed image, can avoid detail loss of the image because of excessive exfoliating and perform accuracy exfoliating.

Description

technical field [0001] The present invention relates to the field of image processing, in particular to a method, system and client for skin roughness self-adaptive microdermabrasion. Background technique [0002] Facial beautification is widely popular, and microdermabrasion is essential as a key core technology, and the intensity control of microdermabrasion determines the quality of the final effect. The current image processing software, such as photoshop, Meitu Xiuxiu, etc., are all controlled by fixed default parameters, which affect the user experience with manual adjustment. [0003] The patent document with application number 201310653333.X discloses a method and device for image processing. The image processing method includes: receiving an image to be processed; obtaining the first gray value of each pixel from the image; The first grayscale value of each pixel point is converted into a grayscale image in the face skin area in the image to be processed; according...

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): G06T5/00
Inventor 洪初阳张垚关胤吴拥民陈宏展刘德建
Owner FUJIAN TQ DIGITAL
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap