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

Method for classifying bizygomatic colors of face on basis of support vector machine

A technology of support vector machine and color classification, applied in computer parts, instruments, character and pattern recognition, etc., can solve problems such as poor repeatability, and achieve the effect of simple judgment mechanism

Inactive Publication Date: 2013-10-16
SHANGHAI UNIV
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The purpose of the present invention is to address the deficiencies in the prior art, and propose a method for color classification of two cheekbones based on a support vector machine. As the feature vector, the computer simulation of Chinese medicine experts is used to identify the color of the two cheeks, and then overcome the shortcomings of the traditional two-zygomatic color recognition of strong subjectivity and poor repeatability

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
  • Method for classifying bizygomatic colors of face on basis of support vector machine
  • Method for classifying bizygomatic colors of face on basis of support vector machine
  • Method for classifying bizygomatic colors of face on basis of support vector machine

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] The following is attached figure 1 The embodiments of the present invention are further described in detail.

[0033] The present embodiment implements on the premise of the technical solution of the present invention:

[0034] Such as figure 1 As shown, the method for the color classification of the two cheekbones of the face based on the support vector machine of the present invention, its specific steps are as follows:

[0035] (1) Establish two zygomatic color training sample sets:

[0036] (11) Using the Graphcut segmentation algorithm to segment 36 face photos into two zygomatic images to obtain several two zygomatic images, identify the two zygomatic colors of all the two zygomatic images, and divide the two zygomatic colors of all the two zygomatic images that have been identified into : red cheeks and non-red cheeks;

[0037] (12) Use the image processing software photoshop to divide the 36 two-zygomatic images in the two-zygomatic image database into block...

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 a method for classifying bizygomatic colors of a face on the basis of a support vector machine, which comprises the following steps of: (1) establishing a bizygomatic color training sample set; (2) training the bizygomatic color training sample set by utilizing the support vector machine and constructing a bizygomatic color classifier; and (3) identifying by utilizing the bizygomatic color classifier and judging whether a bizygomatic image to be identified belongs to a red bizygomatic image or a non-red bizygomatic image or not. In the method, the support vector machine is used as the classifier, R, G and B values of pixels are used as feature vectors, a computer is utilized to simulate a Chinese medical specialist to identify the bizygomatic colors, and the method has repeatability; in the method, due to the adoption of a threshold value judging method in the identification phase, a bizygomatic color judging mechanism is simpler, more visual and more impartial; the Chinese medical specialist is simulated to identify the bizygomatic colors, so that the defects of strong subjectivity and poor repeatability which are generated when the Chinese medical specialist visually observes the bizygomatic colors are overcome; and the method is obtained by summarizing and inheriting the bizygomatic color identification experience of the Chinese medical specialist.

Description

technical field [0001] The invention relates to a method for classifying two cheekbones of a human face based on a support vector machine, and belongs to the fields of pattern recognition and image processing. Background technique [0002] There are four basic methods of Chinese medicine, namely: look, smell, ask, and cut. In inspection, the color of a person's cheeks can reflect his health status. Clinically, the color of cheeks is generally divided into: red and non-red Two categories. Zygomatic redness refers to the redness of the two cheekbones on the face. The redness is mainly caused by the red blood under the skin. Traditional Chinese medicine believes that the redness of the two cheekbones is mostly a sign of yin deficiency and internal heat. Generally, zygomatic color refers to the complexion of the cheekbones. If there are obvious red blood streaks on it, it will be judged as two zygomatic reds, otherwise it is two zygomatic non-red. The traditional method of jud...

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 Patents(China)
IPC IPC(8): G06K9/00G06K9/62
Inventor 李晓强汪晶晶范华付郑莉丽闫西平闵彦荣李福凤张煌赵洋洋
Owner SHANGHAI UNIV