Skin identification method based on skin color model

A skin color model and skin recognition technology, applied in the field of skin recognition based on skin color model, to achieve the effect of high recognition accuracy and improved operating efficiency

Active Publication Date: 2013-12-18
厦门美图宜肤科技有限公司
View PDF4 Cites 27 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, the technical solution of the above invention is mainly to build

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 identification method based on skin color model
  • Skin identification method based on skin color model
  • Skin identification method based on skin color model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0045] The present invention will be further described in detail below in conjunction with the examples.

[0046] The invention provides a skin recognition method based on a skin color model, the steps are as follows:

[0047] 1) Perform face recognition on the image to obtain the face area; when the face area recognition fails, define the entire image as the face area;

[0048] 2) Calculate the mean value of the face area obtained in step 1) to obtain the average skin color;

[0049] 3) Calculate the skin color probability mapping table of the current image according to the average skin color obtained in step 2);

[0050] 4) Perform skin color recognition on the current image according to the skin color probability mapping table obtained in step 3), and obtain the result map of the skin color probability of the current image.

[0051] The face recognition involved in step 1) does not involve the main content of the present invention, so it will not be described in detail. ...

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 relates to a skin identification method based on a skin color model. The skin identification method comprises the steps of (1) carrying out face identification on an image, and obtaining a face area, (2) carrying out mean value computing on the obtained face area obtained in the step (1), and obtaining a mean skin color, (3) computing a skin color probability mapping table of the current image according to the mean skin color obtained in the step (2), and (4) carrying out skin color identification on the current image according to the skin color probability mapping table obtained in the step (3), and obtaining a result graph of the skin color probability of the current image. According to the skin identification method, the skin color mean value after face detection is used for building the skin color model, the skin identification method can adapt to images shot under various conditions, and wide covering of the application range is achieved. In addition, according to the skin identification method, training data are not required to be accumulated, implementation can be easily achieved, comparison with huge training data is not required, and the operation efficiency is improved. Identification is carried out through the skin color model, the identification accuracy is high, and the defect that under excessively bright or excessively dark conditions, skin identification is not accurate is overcome.

Description

technical field [0001] The invention relates to an image recognition method, more specifically, to a skin recognition method based on a skin color model. Background technique [0002] The goal of skin recognition is to automatically identify the skin area of ​​the human body from the image, and perform cosmetic beautification operations based on the identified skin area. However, in the prior art, the skin recognition of the human body in the image has the disadvantages of high misrecognition rate, long time and cumbersome steps to build the database, complex implementation, and low program operation efficiency. [0003] Chinese invention patent application 201110185739.0 discloses an illumination-adaptive human skin color detection method in the field of pattern recognition and image processing technology. By collecting a training database, the training database is used to train the basic skin color model and the lighting model, and the basic skin color model is used Scree...

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): G06K9/00
Inventor 张伟傅松林张长定
Owner 厦门美图宜肤科技有限公司
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