Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Application of improved maximum between-class variance method in tongue crack recognition

A technology with the largest variance and cracks between classes, applied in the computer field, can solve problems such as increasing the recognition range, and achieve the effect of accurate recognition and convenient tongue image teaching

Inactive Publication Date: 2011-09-21
TIANJIN TELLYES SCI INC
View PDF0 Cites 19 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The example of the present invention provides a method for identifying cracks in tongue images to solve the problem of automatic identification of cracks in existing tongue diagnosis, and based on the maximum between-class variance filtering algorithm (OSTU), the image is automatically threshold filtered to remove Noise, increase the recognition range for processing

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
  • Application of improved maximum between-class variance method in tongue crack recognition
  • Application of improved maximum between-class variance method in tongue crack recognition
  • Application of improved maximum between-class variance method in tongue crack recognition

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0014] Examples of the present invention provide a crack feature recognition and denoising method of tongue image, such as figure 1 shown, including the following steps:

[0015] Step 1: Get a standard tongue map, such as figure 2 ;

[0016] Step 2: Copy the tongue map to get two identical images image1 and image2, and partition the two images, such as image 3 ;

[0017] Step 3: Use the OSTU method to filter each small area of ​​the two images separately;

[0018] Step 4: merge images, merge;

[0019] Step 5: Denoise, reduce interference, and obtain the tongue map after crack identification, such as Figure 4 ;

[0020] Step 6: Extract crack features, including the number of cracks, crack length, such as Figure 5 .

[0021] The above steps will be described in detail below.

[0022] In the example of the present invention, it is assumed that the current tongue map is already a standard tongue map that has undergone tongue contour checking and tongue body extraction...

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 embodiment of the invention provides a method for tongue crack recognition, wherein the method provided by the invention is used for solving the problem of automatic crack recognition in the prior tongue diagnosis, and comprises the following step: performing the automatic threshold filtration on an image on the basis of the maximum between-class variance method (OSTU) so as to remove the noise and enlarge the recognition range. The invention provides an image feature recognizing and denoising method which comprises the following steps: after obtaining a standard tongue image, converting the standard tongue image into a gray image; copying the image, dividing two images into small regions according to the size of the image, wherein any small region of two images cannot overlap with the small region of an original image; independently filtering each small region of two images by using the OTSU filter method; combining the two images in accordance with a certain rule according to the filter results of the two images; and denoising the filtered image so as to eliminate the interference.

Description

technical field [0001] The invention relates to the field of computer technology, in particular to an image automatic threshold filtering method. Background technique [0002] Tongue diagnosis is an important part of the four clinical examinations of TCM. The results of tongue diagnosis can reflect the information of many patients, and it is an important part of TCM diagnosis. In today's TCM tongue diagnosis, doctors only conduct directional analysis on the characteristics of the patient's tongue, and simply describe the characteristics of the tongue, which is quite subjective. Today, with the rapid advancement of science and technology, how to introduce advanced technology and strict standards into TCM tongue diagnosis, so that the results of tongue diagnosis can be described qualitatively and quantitatively has become a research topic for many relevant scholars. This kind of research is bound to promote the objectivity, standardization and standardization of tongue diagno...

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): G06K9/62G06T5/00
Inventor 赵亮
Owner TIANJIN TELLYES SCI INC
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com