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

Method for segmenting traditional Chinese medicine tongue images under open environment

An image segmentation and image technology, applied in the field of medical image processing, can solve problems such as subsequent analysis difficulties

Active Publication Date: 2017-09-22
XIAMEN UNIV
View PDF5 Cites 24 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0010] The purpose of the present invention is to address the many deficiencies in the existing process of collecting tongue images in an open environment, such as: the influence of many uncertain factors such as the color temperature of the light source, the intensity of the light, the shooting angle, and the difference in equipment, so that the final obtained Compared with the image in a fixed environment, the collected tongue images often have large differences, which bring difficulties to subsequent analysis and other problems. Provides a quick and accurate segmentation of tongue images for subsequent analysis, so as to facilitate subsequent tongue images Analysis of a TCM tongue image segmentation method in an open environment

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 segmenting traditional Chinese medicine tongue images under open environment
  • Method for segmenting traditional Chinese medicine tongue images under open environment
  • Method for segmenting traditional Chinese medicine tongue images under open environment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0136] The present invention will be described in further detail below in conjunction with the accompanying drawings and embodiments.

[0137] Embodiments of the present invention include the following steps:

[0138] 1) Input the image A collected in an open environment, such as figure 1 shown;

[0139] 2) Perform color correction on the collected image A to obtain the corrected image B;

[0140] In step 2), the specific method for color correction of the collected image A is as follows:

[0141] (1) Collect the tongue image S1 under the standard lighting environment, and calculate the mean values ​​of the RGB three color channels of the tongue image S1 and the overall mean value K of the tongue image S1 respectively. S Ratio α r 、α g 、α b :

[0142]

[0143]

[0144] Among them, the overall mean K of the tongue image S1 S =(R avgs +G avgs +B avgs ) / 3; R avgs , G avgs , B avgs are respectively the mean values ​​of the RGB three color channels of the tongue...

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 method for segmenting traditional Chinese medicine tongue images under open environment, relates to medical image processing, and aims at rapidly ad correctly segmenting tongue images for subsequent analysis so as to facilitate subsequent tongue image analysis. The method comprises the following steps of: 1) inputting an image A acquired under the open environment; 2) carrying out color correction on the acquired image A to obtain a corrected image B; 3) carrying out preliminary image segmentation on the corrected image B obtained in the step 2); 4) carrying out feature extraction on each connected domain in an image C obtained in the step 3); 5) for features of each convex hum extracted in the step 4), calculating a tongue body position by using a random forest classifier; and 6) carrying out traditional Chinese medicine tongue image segmentation on the image B by taking a tongue body area D obtained in the step 5) as basis.

Description

technical field [0001] The invention relates to medical image processing, in particular to a method for segmenting TCM tongue image images in an open environment. Background technique [0002] The traditional TCM tongue diagnosis mainly relies on the doctor's naked eye observation for analysis and judgment. The diagnosis result is often related to the doctor's knowledge level and experience accumulation. In recent years, the development of information technology has promoted the process of objectification, digitization and automation of TCM tongue analysis. . Scholars at home and abroad have carried out many beneficial explorations on this, and developed some tongue image analysis systems, which have achieved good results (Yu Xinglong, Zhu Zimin, Jin Guopan, etc. Automatic recognition system for tongue diagnosis in traditional Chinese medicine[J]. Chinese Journal of Integrated Traditional Chinese and Western Medicine, 2000, 20(2): 145-147; Cai Y.A novel imaging system for t...

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): G06T7/11G06T7/136G06T7/187G06T7/12G06T7/149G06T7/45G06T7/90G06T5/00G06K9/62
CPCG06T7/11G06T7/12G06T7/136G06T7/149G06T7/187G06T7/45G06T7/90G06T2207/30004G06T2207/20192G06T2207/20116G06T2207/20076G06T2207/20081G06F18/24323G06T5/00
Inventor 黄晓阳王彦晖郑丰
Owner XIAMEN UNIV
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