Tongue color automatic recognition method

An automatic identification and color technology, applied in the field of image processing, can solve the problems of great differences in diagnosis results and lack of storage methods for diagnosis experience, and achieve high practical value and reliable recognition process

Inactive Publication Date: 2006-07-19
SHANGHAI JIAO TONG UNIV
View PDF1 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, a significant disadvantage of traditional tongue diagnosis is that the diagnostic process relies on the subjective experience and personal ability of doctors, and the diagnostic results of different doctors may vary greatly. At the same time, these diagnostic experiences lack effective means of preservation.

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
  • Tongue color automatic recognition method
  • Tongue color automatic recognition method
  • Tongue color automatic recognition method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0019] The technical solution of the present invention will be further described in detail below in conjunction with the examples.

[0020] 1. Determine the tongue coating and tongue color reference sample set: For each type of coating color sample, experienced Chinese medicine practitioners manually select sample blocks from the tongue image, and then determine the final coating color reference sample by removing outlier samples set. For example, according to clinical experience, the tongue color is divided into 5 types: light red, light white, red, dark red, and purple; and the tongue coating color is divided into 4 types: white, light yellow, yellow, and gray. For each color type, 10 samples were manually selected from tongue images by experienced TCM practitioners. For each sample image, select its R-G, R-B, and G-B color histograms, divide each color component into 20 equal parts, and stack the data in each color histogram into a 1×400 vector, so that the three color his...

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 self-identification method of tongue-image color, which comprises the following steps: (1) establishing the color reference sample set of tongue fur and tongue quality; selecting the sample block from tongue-image for each kind of fur quality color sample; removing the leaving sample to affirm the final fur quality color reference sample set; (2) dividing the same quality region of tongue body to make each region possess similar color and veined character; (3) setting the mould according to the distribution regulation of tongue quality and fur; setting the ballot prior strategy to match the color sample; (4) judging whether the region belongs to the tongue fur color or tongue quality color; matching the sample of tongue fur color or tongue quality color; adapting k nearby method to affirm the color of the same quality region according to the matching result. The invention coincidences the inspection custom of traditional Chinese, which provides reliable identification result.

Description

technical field [0001] The present invention relates to a method in the technical field of image processing, in particular to a method for automatic tongue image color recognition. Background technique [0002] In TCM diagnostics, tongue diagnosis is one of the important ways to obtain patient health information. Tongue diagnosis is mainly by observing the tongue quality and tongue coating. The characteristics of the tongue quality can be described by color, luster, etc.; the characteristics of the tongue coating can be described by color and texture. However, a significant disadvantage of traditional tongue diagnosis is that the diagnostic process relies on the subjective experience and personal ability of doctors, and the diagnostic results of different doctors may vary greatly. At the same time, these diagnostic experiences lack effective means of preservation. This will inevitably affect the overall development of Chinese medicine, and the objectification of Chinese med...

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): A61B5/00A61B10/00G06K9/00G06F19/00G06T1/00
Inventor 杨杰周越郁生阳王永刚张艳
Owner SHANGHAI JIAO TONG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap