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

An automatic analysis method of tongue textures

An automatic analysis and texture technology, applied in the field of analysis, can solve problems such as low accuracy rate, large randomness and uncertainty, tongue image texture stay, etc.

Inactive Publication Date: 2009-03-04
HARBIN INST OF TECH
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the current analysis and discrimination of tongue image texture is still at the level of manual processing based on experience.
This not only limits the application of tongue image texture, a useful human physiological feature, in judging human diseases and other fields, but also the accuracy rate of current manual analysis and judgment is low, with great randomness and uncertainty

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
  • An automatic analysis method of tongue textures
  • An automatic analysis method of tongue textures
  • An automatic analysis method of tongue textures

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0020] Principle of the present invention and analysis process are further analyzed below in conjunction with accompanying drawing:

[0021] The invention selects sub-images from the original image, preprocesses different sub-images respectively, extracts feature parameters after pre-processing, sends the extracted feature vectors to a classifier for classification, and outputs classification results after classification. Among them, preprocessing includes image gray level compression and normalization of gray level co-occurrence matrix; feature parameter extraction methods include Gabor filter, gray level co-occurrence matrix and fractal model method; classification method includes linear discriminant analysis method; The processing object is de-reflected before; the features used to analyze the gray-scale co-occurrence matrix include energy, contrast, entropy, deficit and the number of non-zero points in the gray-scale co-occurrence matrix; the fractal model method includes t...

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 present invention provides one kind of automatic tongue picture grain analysis method. The automatic tongue picture grain analysis method includes selecting sub-pictures from original pictures, pre-treating the sub-pictures separately, extracting characteristic parameters, classifying the extracted characteristic vectors in a classifier and outputting the classification results. The present invention adopts Gabor filtering, grey scale co-occurrence matrix, fractal model, etc in analyzing and recognizing different tongue picture grain characteristics; and classifies thick tongue coating and thin tongue coating, red stabs, tongue picture grains and red stars. The method has high accuracy and wide application value.

Description

(1) Technical field [0001] The invention relates to an analysis method, in particular to an automatic tongue image texture analysis method which adopts multiple methods such as Gabor filter, gray level co-occurrence matrix and fractal model to analyze and identify different tongue image texture features. (2) Background technology [0002] The characteristics of tongue image have high application value in the process of diagnosing diseases in TCM, especially the texture of tongue image is more important information in TCM tongue diagnosis. However, the analysis and discrimination of tongue image texture are still at the level of manual processing based on experience. This not only limits the application of tongue image texture, a useful human physiological feature, in judging human diseases and other fields, but also the accuracy of current manual analysis and judgment is low, with great randomness and uncertainty. (3) Contents of the invention [0003] The purpose of the ...

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): A61B5/00A61B19/00G06Q50/00G06F17/00G06T1/00G06T5/00
Inventor 张大鹏李乃民王宽全黄勃张宏志
Owner HARBIN INST OF TECH