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

Area-based complexion dividing method

A skin color segmentation and area technology, applied in the direction of instruments, character and pattern recognition, computer components, etc., can solve the problems of misjudgment of non-skin color pixels as skin color pixels, and can not consider the correlation between pixels and pixels, so as to improve the effect Effect

Inactive Publication Date: 2011-08-24
INST OF AUTOMATION CHINESE ACAD OF SCI
View PDF3 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] This type of method cannot consider the correlation between pixels, so it is easy to misjudge non-skin color pixels as skin color pixels

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
  • Area-based complexion dividing method
  • Area-based complexion dividing method
  • Area-based complexion dividing method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0029] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be described in further detail below in conjunction with specific embodiments and with reference to the accompanying drawings.

[0030] Overall frame of the present invention sees figure 1 , the execution environment of the present invention is formed by a computer realizing the following three module groups:

[0031] 1. Color space conversion module. The main function of this module is to convert the original image from the red-green-blue RGB color space to the brightness-red chroma-blue chroma YCrCb color space. Skin tones can be better modeled in the YCrCb color space and the effects of lighting changes can be reduced.

[0032] 2. Feature extraction module. The main function of this module is to extract the regional texture features and regional color features of each small area on the image, and generate the final regional feature vectors for ...

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 area-based complexion dividing method. The method comprises the following steps of: converting an image from a red-green-blue color space into a luminance-red chroma-blue chroma color space; dividing the image into small areas, and extracting the covariance descriptor-based area textural feature of each small area in the image; calculating a mean value and a standard offset value in each small area on a red chroma color channel and a blue chroma color channel respectively, and generating area color features; combining the area textural features with the area color features to generate area feature vectors; and training a classifier model by using the area feature vectors and dividing complexion. A human body complexion area in the image can be quickly and efficiently divided by the method.

Description

technical field [0001] The invention relates to the field of computer application technology, in particular to a method for segmenting skin color based on regions. Background technique [0002] Skin color segmentation is the process of selecting regions corresponding to human skin in an image. As an underlying feature, human skin color is widely used in various machine vision systems related to people. Typical applications include: pornographic image recognition, face detection and recognition, facial expression recognition, gesture recognition, human-computer interaction, video surveillance, and healthcare. [0003] Existing solutions often judge whether a single pixel is skin-colored or non-skin-colored. For example, in the red-green-blue RGB color space, it is judged whether the color range of a certain pixel is within a certain area, thereby judging whether it belongs to human skin color. A pixel is judged as a skin color pixel if it satisfies the following conditions ...

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 & Authority Applications(China)
IPC IPC(8): G06K9/00G06K9/46
Inventor 胡卫明左海强吴偶
Owner INST OF AUTOMATION CHINESE ACAD OF SCI
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com