CN110495888B - Standard color card based on tongue and face images of traditional Chinese medicine and application thereof - Google Patents

Standard color card based on tongue and face images of traditional Chinese medicine and application thereof Download PDF

Info

Publication number
CN110495888B
CN110495888B CN201910798364.1A CN201910798364A CN110495888B CN 110495888 B CN110495888 B CN 110495888B CN 201910798364 A CN201910798364 A CN 201910798364A CN 110495888 B CN110495888 B CN 110495888B
Authority
CN
China
Prior art keywords
value
color
tongue
person
detected
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN201910798364.1A
Other languages
Chinese (zh)
Other versions
CN110495888A (en
Inventor
李福凤
袁善敏
钱鹏
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shanghai University of Traditional Chinese Medicine
Original Assignee
Shanghai Taiyi Health Technology Co ltd
Shanghai University of Traditional Chinese Medicine
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Shanghai Taiyi Health Technology Co ltd, Shanghai University of Traditional Chinese Medicine filed Critical Shanghai Taiyi Health Technology Co ltd
Priority to CN201910798364.1A priority Critical patent/CN110495888B/en
Publication of CN110495888A publication Critical patent/CN110495888A/en
Application granted granted Critical
Publication of CN110495888B publication Critical patent/CN110495888B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • AHUMAN NECESSITIES
    • A61MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61BDIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00Measuring for diagnostic purposes; Identification of persons
    • A61B5/103Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
    • A61B5/1032Determining colour for diagnostic purposes
    • A61B5/1034Determining colour for diagnostic purposes by means of colour cards
    • AHUMAN NECESSITIES
    • A61MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61BDIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00Measuring for diagnostic purposes; Identification of persons
    • A61B5/48Other medical applications
    • A61B5/4854Diagnosis based on concepts of traditional oriental medicine

Landscapes

  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Engineering & Computer Science (AREA)
  • Medical Informatics (AREA)
  • Molecular Biology (AREA)
  • General Health & Medical Sciences (AREA)
  • Biophysics (AREA)
  • Pathology (AREA)
  • Biomedical Technology (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Veterinary Medicine (AREA)
  • Surgery (AREA)
  • Animal Behavior & Ethology (AREA)
  • Physics & Mathematics (AREA)
  • Public Health (AREA)
  • Alternative & Traditional Medicine (AREA)
  • Dentistry (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • Image Analysis (AREA)
  • Image Processing (AREA)
  • Measuring And Recording Apparatus For Diagnosis (AREA)

Abstract

The invention discloses a standard color card based on tongue and face images of traditional Chinese medicine and application thereof. The system applying the standard color card comprises a central processing unit, an image acquisition device and a data memory, wherein the image acquisition device and the data memory are respectively connected with the central processing unit; the image acquisition device is used for acquiring a tongue surface image of a person to be detected and transmitting the information to the central processing unit; the central processing unit is used for carrying out color correction on the acquired tongue surface image of the person to be detected, calling a standard color card in the data storage device and comparing the acquired tongue surface image of the person to be detected after the color correction, and obtaining the color classification of the tongue surface of the person to be detected; the data memory is used for storing the standard color card. The standard color card well makes up the defect that the prior traditional Chinese medicine tongue surface diagnosis field lacks relevant standards, and provides an objective and accurate evaluation standard for the traditional Chinese medicine tongue surface diagnosis; the system has high automation degree, good auxiliary effect on doctors and great application prospect.

Description

Standard color card based on tongue and face images of traditional Chinese medicine and application thereof
Technical Field
The invention belongs to the technical field of traditional Chinese medicine, and particularly relates to a standard color chart based on tongue and face images of traditional Chinese medicine and application thereof.
Background
Inspection is an important content of diagnosis in traditional Chinese medicine, and the inspection mainly comprises: observe the spirit, color, shape, state, tongue manifestation, collaterals, complexion, skin, five sense organs, nine orifices and other conditions of human body and the shape, color, quality and the like of excreta, secretion and secretion, wherein although tongue diagnosis and facial color diagnosis belong to the head and face five sense organs, the tongue manifestation and complexion reflect visceral lesions more accurately, and the practical value is higher. The tongue and face picture contains many important clinical information, and can be seen before the onset of disease, which can objectively reflect the abundance or insufficiency of qi and blood, the nature of the disease, the depth of the disease, and the outcome of the disease, and reflect the physiological and pathological changes of the body. Inspection of color is to examine the color change of the skin collaterals, and because of the abundance of the capillaries in the face, inspection of Chinese medicine is mainly to examine the complexion. Su Wen & Wu zang Sheng say: the five-color micro diagnosis can be visually observed. The Chinese medicine inspection color diagnosis theory guides the clinical diagnosis and treatment activities of the Chinese medicine. However, the five colors of the tongue and surface diagnosis of the traditional Chinese medicine are mainly judged by doctors through experience, which has extremely high requirements on the clinical experience of the doctors, the existing western medicine skin color cards are completely different from the judgment of the five colors in the field of the traditional Chinese medicine, the guidance on the five color judgment of the tongue and surface diagnosis of the traditional Chinese medicine is difficult, the tongue and surface diagnosis of the traditional Chinese medicine lacks a constant objective judgment standard, the judgment accuracy is influenced, and the application and the development of the tongue and surface diagnosis of the traditional Chinese medicine are seriously hindered. Therefore, it is very urgent to standardize, quantify and objectify the tongue and facial diagnosis.
With the rapid development of computer information processing technology, human biological feature recognition technology (Biometrics) such as image processing and pattern recognition has been more and more emphasized by the scientific research world and is widely applied to traditional Chinese medicine. The human body biological characteristic identification technology can provide objective and quantitative indexes for the traditional Chinese medicine diagnosis by automatically analyzing and identifying the pathological representation of holographic elements such as tongue, face, pulse, iris and the like in the human body biological characteristics, and promotes the traditional Chinese medicine diagnosis to enter a new computerized and automatic high-speed development stage. Since the 80 s in the 20 th century, the research on tongue and facial diagnosis has made a certain progress with the development of color optical theory, the updating of color measuring instrument and the wide application of objective research on tongue and facial diagnosis. In order to overcome the defects of the traditional tongue diagnosis method, some scholars input tongue and facial images into a computer for quantitative detection and analysis to realize the objectification and digitalization of tongue and facial diagnosis to a certain extent, but for the tongue and facial diagnosis in traditional Chinese medicine, whether the color of the image can truly reproduce objective and real color information becomes an important foundation for objectification of the tongue and facial images through tongue and facial image acquisition. The tongue and the surface of the human body are irradiated by the illuminating light source, collected and processed by the imaging device, and finally displayed by the display, and color distortion inevitably occurs. For image analysis, color distortion first causes incorrect judgment for a doctor who directly observes an image; in addition, the color distortion also affects the accuracy and robustness of the automatic analysis of tongue and facial image characteristics, and particularly affects the automatic analysis of tongue color, fur color, facial color and luster characteristics which play an important role in the traditional Chinese medicine dialectics. Therefore, for tongue and face image analysis in traditional Chinese medicine, color correction is a key step of image processing, and aims to reduce or eliminate the influence of various factors such as illumination environment and imaging equipment on image color in the imaging process.
The difficulty of tongue and face image analysis of traditional Chinese medicine is overcome in multiple aspects by a plurality of documents, such as 'new research on the color degree quantification characteristic of the blue-violet tongue color', 'application and research on a posterior feature extraction and auxiliary traditional Chinese medicine tongue image diagnosis system' and 'research and design on a mobile terminal-based traditional Chinese medicine tongue image data mining system', but a standard capable of guiding the analysis of the tongue and face images of traditional Chinese medicine and a method for guiding actual diagnosis according to the standard are still not obtained in the traditional Chinese medicine field at present.
Therefore, the development of the standard color card based on the tongue and face images of the traditional Chinese medicine and the application thereof, which can guide the tongue and face image analysis of the traditional Chinese medicine, have practical significance.
Disclosure of Invention
The invention aims to overcome the defects that the prior art does not have a standard which can play a guiding role in the analysis of tongue and face images of the traditional Chinese medicine and a method for guiding the actual diagnosis according to the standard, and provides a standard color chart based on the tongue and face images of the traditional Chinese medicine and an application thereof.
In order to achieve the purpose, the invention provides the following technical scheme:
a standard color card based on tongue and face images of traditional Chinese medicine comprises the following color blocks:
the value of L of color block one is 61, the value of a is 14, and the value of b is 18;
the value of L of color block two is 65, the value of a is 15, and the value of b is 18;
the value of L of color block three is 69, the value of a is 15, and the value of b is 18;
the value of L of color block four is 56, the value of a is 17, and the value of b is 20;
the value of L of color block five is 67, the value of a is 19, and the value of b is 20;
the value of L of color block six is 62, the value of a is 18, and the value of b is 21;
the value of L of color block seven is 38, the value of a is 18, and the value of b is 19;
the value of L of color block eight is 45, the value of a is 19, and the value of b is 22;
the value of L of color block nine is 51, the value of a is 18, and the value of b is 23;
the value of L of color block ten is 66, the value of a is 21, and the value of b is 19;
the L value of color block eleven is 52, the a value is 20, and the b value is 19;
the value of L of color block twelve is 60, the value of a is 20, and the value of b is 18;
the value of L of color block thirteen is 51, the value of a is 14, and the value of b is 24;
the value of L of fourteen color blocks is 63, the value of a is 16, and the value of b is 23;
the value of L of color block fifteen is 57, the value of a is 16, and the value of b is 23;
the value of L of sixteen color blocks is 60, the value of a is 11, and the value of b is 27;
the L value of color block seventeen is 54, the a value is 11, and the b value is 26;
the color patch eighteen has an L value of 67, an a value of 9, and a b value of 25.
The color blocks in the standard color card of the present invention adopt a Lab color model, which is independent of the device and directly based on the physiological characteristics, compared with two color modes of RGB and CMYK, where L is the luminance, and a and b are two color channels, where a includes colors from dark green (low luminance value) to gray (medium luminance value) to bright pink red (high luminance value), and b includes colors from bright blue (low luminance value) to gray (medium luminance value) to yellow (high luminance value), and the colors of a and b will produce a color with bright effect after being mixed. The color blocks of the standard color card are selected according to five colors of the traditional Chinese medicine, and the determination process of the specific value of each color block Lab is as follows: widely collecting tongue and face images → experts classify tongue and face images → extract color features → cluster analysis → obtain color blocks. The standard color card well makes up the defect that the prior traditional Chinese medicine tongue surface diagnosis field lacks relevant standards, and provides an objective, accurate and well-inherited evaluation standard for the traditional Chinese medicine tongue surface diagnosis.
As a preferred technical scheme:
the standard color card based on the tongue and face images in the traditional Chinese medicine further comprises the following color blocks:
nineteen color patches with an L value of 96, a value of 0, b value of 0;
the value of L of color block twenty is 81, the value of a is 0, and the value of b is 0;
the value of L of twenty one color blocks is 66, the value of a is 0, and the value of b is 0;
the value of L of twenty-two color blocks is 51, the value of a is 0, and the value of b is 1;
the value of L of twenty-three color blocks is 36, the value of a is 0, and the value of b is 0;
the twenty-four color blocks have an L value of 22, an a value of 0, and a b value of 0.
The color blocks nineteen to twenty-four belong to gray color blocks, the gray scale is the chromatic aberration formed by black and white transition, the color blocks one to eighteen can be contrasted and referred, and the correction precision can be improved during correction.
As for the standard color card based on the tongue and face images in the traditional Chinese medicine, one to three color blocks belong to white; the color blocks four to six belong to the normal color class; seven to nine color blocks belong to black; the color blocks ten to twelve belong to red; thirteen to fifteen color blocks belong to the yellow category; sixteen to eighteen color blocks belong to cyan; nineteen to twenty-four color patches belong to the gray class.
The invention also provides a system applying the standard color card based on the tongue and face images in the traditional Chinese medicine, which comprises a central processing unit, an image acquisition device and a data memory, wherein the image acquisition device and the data memory are respectively connected with the central processing unit;
the image acquisition device is used for acquiring a tongue surface image of a person to be detected and transmitting the information to the central processing unit;
the central processing unit is used for carrying out color correction on the acquired tongue surface image of the person to be detected, calling a standard color card in the data storage device and comparing the acquired tongue surface image of the person to be detected after the color correction, and obtaining the color classification of the tongue surface of the person to be detected;
the data memory is used for storing the standard color card based on the tongue and face images of the traditional Chinese medicine.
The invention also provides a system for judging the tongue and face color classification of the person to be detected based on the standard color chart of the tongue and face images in the traditional Chinese medicine, the system has a simple structure, a simple processing process and high automation degree, and compared with the traditional means of manual observation, the system has good objectivity, can be widely applied to various hospitals, and can assist doctors to quickly obtain the tongue and face color classification results.
As a preferred technical scheme:
the system also comprises a display device and/or a communication device which are connected with the central processing unit;
the display device is used for displaying the tongue and face color classification of the person to be tested, which is obtained by the processing of the central processing unit;
the communication device is used for signal and data transmission with the outside. The specific structure of the system of the present invention is not limited thereto, and those skilled in the art can add/subtract devices according to actual needs.
According to the system, the acquired tongue image of the person to be detected simultaneously comprises the tongue image information of the person to be detected and the image information of the standard color card, namely when the tongue image of the person to be detected is acquired, the person to be detected holds the standard color card to pick up a camera, and the image comprises the tongue image information of the person to be detected and the image information of the handheld standard color card.
In the system, the color correction of the acquired tongue image of the person to be detected refers to performing color correction on the acquired tongue image of the person to be detected based on image information of a standard color chart in the tongue image of the person to be detected and actual image information of the standard color chart, and adjusting relevant parameters of the acquired tongue image of the person to be detected with reference to the image information of the standard color chart held by the person to be detected in the image until the adjusted image information of the standard color chart of the tongue image of the person to be detected is substantially matched with the actual image information of the standard color chart.
The invention also provides a control method of the system, which comprises the following steps:
(1) the image acquisition device acquires tongue surface images of the persons to be detected, and the acquired tongue surface image of any person to be detected simultaneously comprises tongue surface image information of the person to be detected and image information of the standard color card;
(2) the central processing unit carries out color correction on the acquired tongue surface image of the person to be detected;
(3) and the central processing unit compares the image after color correction with the actual image information of the standard color card to finally obtain the color classification of the tongue and the face of the person to be detected.
According to the method, the requirement of subsequent color correction is considered when the tongue surface image of the person to be detected is collected, the person to be detected holds the standard color card to take a picture, the collected tongue surface image of the person to be detected is subjected to color correction subsequently based on the image information of the standard color card in the tongue surface image of the person to be detected and the actual image information of the standard color card, the influence of an image collection environment on the collected image is overcome to a certain extent, the accuracy of color correction is good, and then the color classification of the tongue surface and the tongue surface of the person to be detected can be obtained by comparing the image after the color correction with the actual image information of the standard color card. The method has the advantages of small data processing amount, accurate obtained result, lower configuration of required hardware, low cost and wide application prospect.
As a preferred technical scheme:
in the above control method, the specific step of performing color correction on the collected tongue surface image of the person to be measured includes:
(2.1) taking i as the iteration number, and enabling the current iteration number i to be 1;
(2.2) adjusting the L value, the a value and the b value of the acquired tongue surface image of the person to be detected by using a color correction model, wherein the color correction model comprises a polynomial regression algorithm model, a backward propagation network model (BP network) or a support vector regression model (SVM algorithm), the color correction model is not limited to the above, other color correction models can be applied to the invention, and the invention only lists three types of models which are more commonly used as examples;
(2.3) calculating the absolute value | L of the difference between the average L value, the average a value and the average b value of the image information of the Chinese medicine standard color chart in the adjusted acquired tongue surface image of the person to be detected and the actual image information of the Chinese medicine standard color chart1-L2|、|a1-a2I and | b1-b2L whereinL1、a1And b1Respectively the average L value, the average a value and the average b value of the image information of the Chinese medicine standard color chart in the tongue surface image of the person to be measured after adjustment, and L2、a2And b2Respectively an average L value, an average a value and an average b value of actual image information of the traditional Chinese medicine standard color card;
(2.4)|L1-L2|、|a1-a2i or I b1-b2If | > 3, making i ═ i +1, and returning to the step (2.1); and otherwise, completing the color correction, wherein the adjusted collected tongue surface image of the person to be detected is the tongue surface image of the person to be detected obtained through the color correction.
In the above control method, the specific step of comparing the image after color correction with the actual image information of the standard color chart is as follows:
(3.1) dividing the tongue surface image of the person to be detected obtained by the color correction to respectively obtain a surface image and a tongue image;
(3.2) extracting the average L value, the average a value and the average b value of the facial skin area in the facial image and the tongue body area in the tongue image;
(3.3) sequentially selecting all color blocks in the standard color card, and comparing the L value, the a value and the b value of the color blocks with the average L value, the average a value and the average b value of the facial skin area or the tongue body area extracted in the step (3.2);
(3.4) if the average L value, the average a value and the average b value of the facial skin area or the tongue body area are completely the same as the L value, the a value and the b value of a color block, classifying the color of the tongue and the face of the person to be detected as the color block, and if not, the average L value, the average a value and the average b value of the facial skin area or the tongue body area are positioned between the L value, the a value and the b value of the color block I and the color block II, and carrying out the next step;
(3.5) extracting the L value, the a value and the b value of the central position of the facial skin area or the tongue body area;
(3.6) calculating absolute values of differences among the L value, the a value and the b value of the color block I and the color block II and the central position of the facial skin area or the tongue body area extracted in the step (3.5) respectively;
and (3.7) if the absolute values of the differences between the color block I and the central positions of the facial skin region or the tongue body region extracted in the step (3.5) and the L value, the a value and the b value are smaller than the absolute values of the differences between the color block II and the central positions of the facial skin region or the tongue body region extracted in the step (3.5), classifying the colors of the tongue and the face of the person to be detected as the color block I, and otherwise, classifying the colors of the tongue and the face of the person to be detected as the color block I and the color block II.
Has the advantages that:
(1) the standard color chart based on the tongue and face images of the traditional Chinese medicine well makes up the defect that the existing field of tongue and face diagnosis of the traditional Chinese medicine lacks relevant standards, and provides an objective, accurate and well-inherited evaluation standard for the tongue and face diagnosis of the traditional Chinese medicine;
(2) the system applying the standard color card based on the tongue and face images of the traditional Chinese medicine has the advantages of simple structure, low configuration, low cost and high automation degree, can well assist doctors in tongue and face diagnosis of the traditional Chinese medicine, and has wide application prospect;
(3) the control method disclosed by the invention is simple, accurate in correction result and high in comparison accuracy.
Drawings
FIG. 1 is a schematic diagram of a standard color chart based on tongue and face images of traditional Chinese medicine;
FIG. 2 is a schematic connection diagram of the components of the system of the present invention using a standard color chart based on tongue and face images of traditional Chinese medicine;
FIG. 3 is a flow chart of the operation of the system of the present invention using the standard color chart based on tongue and face images of TCM.
Detailed Description
The following further describes the embodiments of the present invention with reference to the attached drawings.
Example 1
A standard color card based on tongue and face images of traditional Chinese medicine is shown in figure 1 and comprises the following color blocks:
the value of L of color block one is 61, the value of a is 14, and the value of b is 18;
the value of L of color block two is 65, the value of a is 15, and the value of b is 18;
the value of L of color block three is 69, the value of a is 15, and the value of b is 18;
the value of L of color block four is 56, the value of a is 17, and the value of b is 20;
the value of L of color block five is 67, the value of a is 19, and the value of b is 20;
the value of L of color block six is 62, the value of a is 18, and the value of b is 21;
the value of L of color block seven is 38, the value of a is 18, and the value of b is 19;
the value of L of color block eight is 45, the value of a is 19, and the value of b is 22;
the value of L of color block nine is 51, the value of a is 18, and the value of b is 23;
the value of L of color block ten is 66, the value of a is 21, and the value of b is 19;
the L value of color block eleven is 52, the a value is 20, and the b value is 19;
the value of L of color block twelve is 60, the value of a is 20, and the value of b is 18;
the value of L of color block thirteen is 51, the value of a is 14, and the value of b is 24;
the value of L of fourteen color blocks is 63, the value of a is 16, and the value of b is 23;
the value of L of color block fifteen is 57, the value of a is 16, and the value of b is 23;
the value of L of sixteen color blocks is 60, the value of a is 11, and the value of b is 27;
the L value of color block seventeen is 54, the a value is 11, and the b value is 26;
eighteen color patches with an L value of 67, an a value of 9, and a b value of 25;
nineteen color patches with an L value of 96, a value of 0, b value of 0;
the value of L of color block twenty is 81, the value of a is 0, and the value of b is 0;
the value of L of twenty one color blocks is 66, the value of a is 0, and the value of b is 0;
the value of L of twenty-two color blocks is 51, the value of a is 0, and the value of b is 1;
the value of L of twenty-three color blocks is 36, the value of a is 0, and the value of b is 0;
the value of L of twenty-four color blocks is 22, the value of a is 0, and the value of b is 0;
wherein, the color blocks one to three belong to white; the color blocks four to six belong to the normal color class; seven to nine color blocks belong to black; the color blocks ten to twelve belong to red; thirteen to fifteen color blocks belong to the yellow category; sixteen to eighteen color blocks belong to cyan; nineteen to twenty-four color patches belong to the gray class.
Example 2
A system using a standard color chart based on tongue and face images of traditional Chinese medicine is shown in FIG. 2, and comprises a central processing unit, and an image acquisition device, a data memory, a display device and a communication device which are respectively connected with the central processing unit;
the image acquisition device is used for acquiring a tongue surface image of the person to be detected and transmitting the information to the central processing unit, and the acquired tongue surface image of the person to be detected simultaneously comprises tongue surface image information of the person to be detected and image information of the standard color card;
the central processing unit is used for carrying out color correction on the acquired tongue surface image of the person to be detected, calling the standard color card in the data storage device and comparing the acquired tongue surface image of the person to be detected after the color correction to obtain the color classification of the tongue and the tongue surface of the person to be detected, and carrying out color correction on the acquired tongue surface image of the person to be detected refers to carrying out color correction on the acquired tongue surface image of the person to be detected based on the image information of the standard color card in the tongue surface image of the person to be detected and the actual image information of the standard color card;
the display device is used for displaying the tongue and face color classification of the person to be tested, which is obtained by the processing of the central processing unit;
the communication device is used for transmitting signals and data with the outside;
the data memory is used for storing the same standard color chart (standard color chart in fig. 2) based on tongue and face images of the chinese medicine as in example 1.
The control method of the above system, with the flowchart shown in fig. 3, includes the following steps:
(1) the image acquisition device acquires tongue surface images of the persons to be detected, and the acquired tongue surface image of any person to be detected simultaneously comprises tongue surface image information of the person to be detected and image information of the standard color card;
(2) the central processing unit carries out color correction to the tongue face image of the person to be measured who gathers, specifically is:
(2.1) taking i as the iteration number, and enabling the current iteration number i to be 1;
(2.2) adjusting the L value, the a value and the b value of the acquired tongue surface image of the person to be detected by using the color correction model;
(2.3) calculating the absolute value | L of the difference between the average L value, the average a value and the average b value of the image information of the Chinese medicine standard color chart in the adjusted acquired tongue surface image of the person to be detected and the actual image information of the Chinese medicine standard color chart1-L2|、|a1-a2I and | b1-b2L wherein L1、a1And b1Respectively the average L value, the average a value and the average b value of the image information of the Chinese medicine standard color chart in the tongue surface image of the person to be measured after adjustment, and L2、a2And b2Respectively an average L value, an average a value and an average b value of actual image information of the traditional Chinese medicine standard color card;
(2.4)|L1-L2|、|a1-a2i or I b1-b2If | > 3, making i ═ i +1, and returning to the step (2.1); otherwise, the color correction is finished, and the adjusted collected tongue surface image of the person to be detected is the tongue surface image of the person to be detected obtained through the color correction;
(3) the central processing unit compares the image after color correction with the actual image information of the standard color card, and finally obtains the color classification of the tongue and the face of the person to be detected, which specifically comprises the following steps:
(3.1) dividing the tongue surface image of the person to be detected obtained by the color correction to respectively obtain a surface image and a tongue image;
(3.2) extracting the average L value, the average a value and the average b value of the facial skin area in the facial image and the tongue body area in the tongue image;
(3.3) sequentially selecting all color blocks in the standard color card, and comparing the L value, the a value and the b value of the color blocks with the average L value, the average a value and the average b value of the facial skin area or the tongue body area extracted in the step (3.2);
(3.4) if the average L value, the average a value and the average b value of the facial skin area or the tongue body area are completely the same as the L value, the a value and the b value of a color block, classifying the color of the tongue and the face of the person to be detected as the color block, and if not, the average L value, the average a value and the average b value of the facial skin area or the tongue body area are positioned between the L value, the a value and the b value of the color block I and the color block II, and carrying out the next step;
(3.5) extracting the L value, the a value and the b value of the central position of the facial skin area or the tongue body area;
(3.6) calculating absolute values of differences among the L value, the a value and the b value of the color block I and the color block II and the central position of the facial skin area or the tongue body area extracted in the step (3.5) respectively;
and (3.7) if the absolute values of the differences between the color block I and the central positions of the facial skin region or the tongue body region extracted in the step (3.5) and the L value, the a value and the b value are smaller than the absolute values of the differences between the color block II and the central positions of the facial skin region or the tongue body region extracted in the step (3.5), classifying the colors of the tongue and the face of the person to be detected as the color block I, and otherwise, classifying the colors of the tongue and the face of the person to be detected as the color block I and the color block II.
100 persons to be tested who have judged the color of the tongue surface by the expert respectively hold the standard color card by hands to classify the color of the tongue and the surface by using the system, then the color classification of the tongue and the surface obtained by the system and the result obtained by the expert judgment are compared, and the matching degree of the result obtained by the system and the judgment of the expert is found to be 100%.
According to verification, the standard color chart based on tongue and surface images of the traditional Chinese medicine well makes up the defect that the existing field of tongue and surface diagnosis of the traditional Chinese medicine lacks relevant standards, and provides an objective, accurate and well-inherited evaluation standard for the tongue and surface diagnosis of the traditional Chinese medicine; the system which applies the standard color card based on the tongue and face images of the traditional Chinese medicine has the advantages of simple structure, low configuration, low cost and high automation degree, can well assist doctors in tongue and face diagnosis of the traditional Chinese medicine, and has great application prospect; the control method is simple, the correction result is accurate, and the comparison accuracy is high.
Although specific embodiments of the present invention have been described above, it will be appreciated by those skilled in the art that these embodiments are merely illustrative and various changes or modifications may be made without departing from the principles and spirit of the invention.

Claims (10)

1. A standard color card based on tongue and face images of traditional Chinese medicine is characterized in that the face color and the tongue color are classified based on a traditional Chinese medicine color diagnosis theory, tongue and face images are widely collected, are interpreted and classified by traditional Chinese medicine experts, are subjected to clustering analysis by a computer method, a plurality of clustered typical color patch Lab values which accord with the traditional Chinese medicine inspection five-color theory are selected, and are verified to obtain a standard color card color patch which can be used for marking the tongue color and the face color, and the standard color card color patch specifically comprises the following color patches:
the value of L of color block one is 61, the value of a is 14, and the value of b is 18;
the value of L of color block two is 65, the value of a is 15, and the value of b is 18;
the value of L of color block three is 69, the value of a is 15, and the value of b is 18;
the value of L of color block four is 56, the value of a is 17, and the value of b is 20;
the value of L of color block five is 67, the value of a is 19, and the value of b is 20;
the value of L of color block six is 62, the value of a is 18, and the value of b is 21;
the value of L of color block seven is 38, the value of a is 18, and the value of b is 19;
the value of L of color block eight is 45, the value of a is 19, and the value of b is 22;
the value of L of color block nine is 51, the value of a is 18, and the value of b is 23;
the value of L of color block ten is 66, the value of a is 21, and the value of b is 19;
the L value of color block eleven is 52, the a value is 20, and the b value is 19;
the value of L of color block twelve is 60, the value of a is 20, and the value of b is 18;
the value of L of color block thirteen is 51, the value of a is 14, and the value of b is 24;
the value of L of fourteen color blocks is 63, the value of a is 16, and the value of b is 23;
the value of L of color block fifteen is 57, the value of a is 16, and the value of b is 23;
the value of L of sixteen color blocks is 60, the value of a is 11, and the value of b is 27;
the L value of color block seventeen is 54, the a value is 11, and the b value is 26;
the color patch eighteen has an L value of 67, an a value of 9, and a b value of 25.
2. The standard color chart based on tongue and face images of traditional Chinese medicine according to claim 1, further comprising the following color patches:
nineteen color patches with an L value of 96, a value of 0, b value of 0;
the value of L of color block twenty is 81, the value of a is 0, and the value of b is 0;
the value of L of twenty one color blocks is 66, the value of a is 0, and the value of b is 0;
the value of L of twenty-two color blocks is 51, the value of a is 0, and the value of b is 1;
the value of L of twenty-three color blocks is 36, the value of a is 0, and the value of b is 0;
the twenty-four color blocks have an L value of 22, an a value of 0, and a b value of 0.
3. The standard color chart based on tongue and face images of traditional Chinese medicine according to claim 2, wherein one to three color blocks belong to white; the color blocks four to six belong to the normal color class; seven to nine color blocks belong to black; the color blocks ten to twelve belong to red; thirteen to fifteen color blocks belong to the yellow category; sixteen to eighteen color blocks belong to cyan; nineteen to twenty-four color patches belong to the gray class.
4. The system for applying the standard color chart based on the tongue and face images in the traditional Chinese medicine according to any one of claims 1 to 3, which is characterized by comprising a central processing unit, and an image acquisition device and a data memory which are respectively connected with the central processing unit;
the image acquisition device is used for acquiring a tongue surface image of a person to be detected and transmitting the information to the central processing unit;
the central processing unit is used for carrying out color correction on the acquired tongue surface image of the person to be detected, calling a standard color card in the data storage device and comparing the acquired tongue surface image of the person to be detected after the color correction, and obtaining the color classification of the tongue surface of the person to be detected;
the data memory is used for storing the standard color chart based on the tongue and face images of the traditional Chinese medicine according to any one of claims 1 to 3.
5. The system of claim 4, further comprising a display device and/or a communication device connected to the central processor;
the display device is used for displaying the tongue and face color classification of the person to be tested, which is obtained by the processing of the central processing unit;
the communication device is used for signal and data transmission with the outside.
6. The system according to claim 5, wherein the acquired tongue surface image of the person to be tested simultaneously comprises tongue surface image information of the person to be tested and image information of the standard color chart.
7. The system according to claim 6, wherein the color correction of the collected tongue surface image of the person under test means color correction of the collected tongue surface image of the person under test based on image information of a standard color chart in the tongue surface image of the person under test and actual image information of the standard color chart.
8. A method of controlling a system according to any one of claims 4 to 7, characterized by the steps of:
(1) the image acquisition device acquires tongue surface images of the persons to be detected, and the acquired tongue surface image of any person to be detected simultaneously comprises tongue surface image information of the person to be detected and image information of the standard color card;
(2) the central processing unit carries out color correction on the acquired tongue surface image of the person to be detected;
(3) and the central processing unit compares the image after color correction with the actual image information of the standard color card to finally obtain the color classification of the tongue and the face of the person to be detected.
9. The control method according to claim 8, wherein the step of performing color correction on the collected tongue surface image of the person to be measured comprises the steps of:
(2.1) taking i as the iteration number, and enabling the current iteration number i to be 1;
(2.2) adjusting the L value, the a value and the b value of the acquired tongue surface image of the person to be detected by using the color correction model;
(2.3) calculating the absolute value | L of the difference between the average L value, the average a value and the average b value of the image information of the Chinese medicine standard color chart in the adjusted acquired tongue surface image of the person to be detected and the actual image information of the Chinese medicine standard color chart1-L2|、|a1-a2I and | b1-b2L wherein L1、a1And b1Respectively the average L value, the average a value and the average b value of the image information of the Chinese medicine standard color chart in the tongue surface image of the person to be measured after adjustment, and L2、a2And b2Respectively an average L value, an average a value and an average b value of actual image information of the traditional Chinese medicine standard color card;
(2.4)|L1-L2|、|a1-a2i or I b1-b2If | > 3, making i ═ i +1, and returning to the step (2.1); and otherwise, completing the color correction, wherein the adjusted collected tongue surface image of the person to be detected is the tongue surface image of the person to be detected obtained through the color correction.
10. The control method according to claim 8, wherein the specific step of comparing the color-corrected picture with the actual image information of the standard color chart is:
(3.1) dividing the tongue surface image of the person to be detected obtained by the color correction to respectively obtain a surface image and a tongue image;
(3.2) extracting the average L value, the average a value and the average b value of the facial skin area in the facial image and the tongue body area in the tongue image;
(3.3) sequentially selecting all color blocks in the standard color card, and comparing the L value, the a value and the b value of the color blocks with the average L value, the average a value and the average b value of the facial skin area or the tongue body area extracted in the step (3.2);
(3.4) if the average L value, the average a value and the average b value of the facial skin area or the tongue body area are completely the same as the L value, the a value and the b value of a color block, classifying the color of the tongue and the face of the person to be detected as the color block, and if not, the average L value, the average a value and the average b value of the facial skin area or the tongue body area are positioned between the L value, the a value and the b value of the color block I and the color block II, and carrying out the next step;
(3.5) extracting the L value, the a value and the b value of the central position of the facial skin area or the tongue body area;
(3.6) calculating absolute values of differences among the L value, the a value and the b value of the color block I and the color block II and the central position of the facial skin area or the tongue body area extracted in the step (3.5) respectively;
and (3.7) if the absolute values of the differences between the color block I and the central positions of the facial skin region or the tongue body region extracted in the step (3.5) and the L value, the a value and the b value are smaller than the absolute values of the differences between the color block II and the central positions of the facial skin region or the tongue body region extracted in the step (3.5), classifying the colors of the tongue and the face of the person to be detected as the color block I, and otherwise, classifying the colors of the tongue and the face of the person to be detected as the color block I and the color block II.
CN201910798364.1A 2019-08-27 2019-08-27 Standard color card based on tongue and face images of traditional Chinese medicine and application thereof Active CN110495888B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910798364.1A CN110495888B (en) 2019-08-27 2019-08-27 Standard color card based on tongue and face images of traditional Chinese medicine and application thereof

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910798364.1A CN110495888B (en) 2019-08-27 2019-08-27 Standard color card based on tongue and face images of traditional Chinese medicine and application thereof

Publications (2)

Publication Number Publication Date
CN110495888A CN110495888A (en) 2019-11-26
CN110495888B true CN110495888B (en) 2022-03-29

Family

ID=68588664

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910798364.1A Active CN110495888B (en) 2019-08-27 2019-08-27 Standard color card based on tongue and face images of traditional Chinese medicine and application thereof

Country Status (1)

Country Link
CN (1) CN110495888B (en)

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111783793A (en) * 2020-06-04 2020-10-16 武汉纺织大学 Method for rapidly extracting color card image data
JP7136955B2 (en) * 2020-06-17 2022-09-13 Dic株式会社 Image display system and image display method
CN113724228B (en) * 2021-08-31 2024-05-10 平安科技(深圳)有限公司 Tongue color and tongue fur color identification method and device, computer equipment and storage medium
CN115601358B (en) * 2022-12-01 2023-03-28 合肥云诊信息科技有限公司 Tongue picture image segmentation method under natural light environment

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102509318A (en) * 2011-09-20 2012-06-20 哈尔滨工业大学 Special color correction card for digital image of human tongue and fabrication method for same
KR101331640B1 (en) * 2011-12-14 2013-11-20 한국 한의학 연구원 Apparatus and method for extracting stereoscopic informatio of tongue
CN104720813B (en) * 2015-03-12 2017-05-24 西安工程大学 Obtaining method of standard color atla for representing complexion and application of obtaining method
CN109920022B (en) * 2019-03-13 2023-05-09 杭州智数创联科技有限公司 Method for manufacturing digital printing small-color-difference color correction card

Also Published As

Publication number Publication date
CN110495888A (en) 2019-11-26

Similar Documents

Publication Publication Date Title
CN110495888B (en) Standard color card based on tongue and face images of traditional Chinese medicine and application thereof
CN109543719B (en) Cervical atypical lesion diagnosis model and device based on multi-modal attention model
Chiu A novel approach based on computerized image analysis for traditional Chinese medical diagnosis of the tongue
Pang et al. Tongue image analysis for appendicitis diagnosis
CN109670510A (en) A kind of gastroscopic biopsy pathological data screening system and method based on deep learning
CN112967285B (en) Chloasma image recognition method, system and device based on deep learning
CN104537373B (en) Sublingual vessel is diagnosed with multispectral sublingual image characteristic extracting method
TWI684997B (en) Establishing method of bone age assessment and height prediction model, bone age assessment and height prediction system, and bone age assessment and height prediction method
CN106821324A (en) A kind of lingual diagnosis auxiliary medical system based on lingual surface and sublingual comprehensive analysis
CN110189293A (en) Cell image processing method, device, storage medium and computer equipment
CN109242792B (en) White balance correction method based on white object
CN104825136A (en) Traditional Chinese medicine face region color portion information collection and analysis system and method
CN116152185A (en) Gastric cancer pathological diagnosis system based on deep learning
CN102136077B (en) Method for automatically recognizing lip color based on support vector machine
CN109711306B (en) Method and equipment for obtaining facial features based on deep convolutional neural network
CN104573668A (en) Automatic face color adaptability identification method based on spectral reflectivity
CN116453171A (en) Method and device for detecting blood vessel color in white eye area, electronic equipment and medium
CN111048202A (en) Intelligent traditional Chinese medicine diagnosis system and method thereof
CN113222061B (en) MRI image classification method based on two-way small sample learning
CN110251084A (en) A kind of detection of tongue picture and recognition methods based on artificial intelligence
CN113822881B (en) Method, system and storage medium for scar image scoring
CN115526888A (en) Eye pattern data identification method and device, storage medium and electronic equipment
CN114898862A (en) Cervical cancer computer-aided diagnosis method based on convolutional neural network and pathological section image
CN113034467B (en) Gray segmentation and Lab color clustering-based method for generating moles and moles with bright red
Azman et al. Disease Classification by Human Fingernail Colour Image Processing

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant
TR01 Transfer of patent right
TR01 Transfer of patent right

Effective date of registration: 20230427

Address after: 201203 Shanghai city Pudong New Area Cailun Road No. 1200

Patentee after: Shanghai University of Traditional Chinese Medicine

Address before: 201203 Shanghai city Pudong New Area Cailun Road No. 1200

Patentee before: Shanghai University of Traditional Chinese Medicine

Patentee before: SHANGHAI TAIYI HEALTH TECHNOLOGY Co.,Ltd.