CN116824252A - Traditional Chinese medicine tongue color classification quantization method for hyperspectral tongue image - Google Patents
Traditional Chinese medicine tongue color classification quantization method for hyperspectral tongue image Download PDFInfo
- Publication number
- CN116824252A CN116824252A CN202310780874.2A CN202310780874A CN116824252A CN 116824252 A CN116824252 A CN 116824252A CN 202310780874 A CN202310780874 A CN 202310780874A CN 116824252 A CN116824252 A CN 116824252A
- Authority
- CN
- China
- Prior art keywords
- tongue
- hyperspectral
- color
- image
- chinese medicine
- 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.)
- Pending
Links
- 239000003814 drug Substances 0.000 title claims abstract description 67
- 238000000034 method Methods 0.000 title claims abstract description 59
- 238000013139 quantization Methods 0.000 title claims description 67
- 238000000926 separation method Methods 0.000 claims description 20
- 238000012549 training Methods 0.000 claims description 17
- 238000013527 convolutional neural network Methods 0.000 claims description 13
- 238000004590 computer program Methods 0.000 claims description 11
- 239000003086 colorant Substances 0.000 claims description 9
- 238000010276 construction Methods 0.000 claims description 9
- 238000004140 cleaning Methods 0.000 claims description 8
- 238000011426 transformation method Methods 0.000 claims description 5
- 238000011002 quantification Methods 0.000 abstract description 11
- 238000003745 diagnosis Methods 0.000 abstract description 8
- 238000011156 evaluation Methods 0.000 abstract description 7
- 238000004458 analytical method Methods 0.000 abstract description 4
- 238000013528 artificial neural network Methods 0.000 abstract description 3
- 230000008859 change Effects 0.000 abstract description 3
- 239000011248 coating agent Substances 0.000 description 16
- 238000000576 coating method Methods 0.000 description 16
- 238000010586 diagram Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000013136 deep learning model Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 230000008447 perception Effects 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 238000001228 spectrum Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 208000010798 Tongue disease Diseases 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000000701 chemical imaging Methods 0.000 description 1
- 238000007621 cluster analysis Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 231100000915 pathological change Toxicity 0.000 description 1
- 230000036285 pathological change Effects 0.000 description 1
- 239000000049 pigment Substances 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000004445 quantitative analysis Methods 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 208000011580 syndromic disease Diseases 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/30—Noise filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/56—Extraction of image or video features relating to colour
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/58—Extraction of image or video features relating to hyperspectral data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/774—Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/03—Recognition of patterns in medical or anatomical images
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A40/00—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production
- Y02A40/10—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production in agriculture
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Multimedia (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Medical Informatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Databases & Information Systems (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Molecular Biology (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Image Analysis (AREA)
- Spectroscopy & Molecular Physics (AREA)
Abstract
The application provides a traditional Chinese medicine tongue color classification quantification method of hyperspectral tongue image, which is based on the analysis result of the traditional Chinese medicine tongue diagnosis classification diagnosis, adds a tongue color classification prediction model and a tongue color quantification prediction model based on a deep convolution neural network, and can obtain the classification- > grading- > numerical quantification evaluation result of the tongue color of the traditional Chinese medicine by using the two prediction models obtained by the application, thereby being convenient for users to visually observe and compare the tongue color change.
Description
Technical Field
The present application relates to the field of computer vision; in particular to application of a computer image classification technology and a deep learning technology in the field of traditional Chinese medicine; more particularly, it relates to a method for classifying and quantifying tongue color of traditional Chinese medicine based on hyperspectral tongue image.
Background
The tongue diagnosis in traditional Chinese medicine is a way of knowing the pathological changes in the body through observing the tongue body and tongue coating. Along with the development of traditional Chinese medicine, the demands of standardization, informatization and the like of the traditional Chinese medicine are gradually increased, and the computer vision and computer image classification technology is applied to the field of the traditional Chinese medicine as a means capable of assisting in data acquisition and processing. The prior art has been applied to hyperspectral imagers to collect tongue images for analysis of the collected hyperspectral tongue images to develop further identification and classification.
For example, in chinese application application publication No. CN 109394182A, publication No. 2019.03.01: in a traditional Chinese medicine tongue color quantitative analysis method based on spectrum information, an attempt is made to provide quantitative data reference related to syndrome degree for clinic by using pigment concentration as a measurement means of traditional Chinese medicine tongue color; the proposal declares that the tongue redness and the tongue purple measurement value numerical axis are established aiming at the formation mechanism of tongue color of the traditional Chinese medicine; any tongue color can be calculated from the pixel concentrations to derive the magnitude on these axes.
However, in the existing classification methods, it is difficult for users to further intuitively judge or understand the meaning of the classification results, and the quantized values obtained through image analysis have a certain distance from the reference basis actually required in the clinical practice of traditional Chinese medicine in principle or medical aspects, so that the applicability is low.
Disclosure of Invention
Aiming at the limitations of the prior art, the application provides a traditional Chinese medicine tongue color classification quantization method of hyperspectral tongue image, which adopts the following technical scheme:
a method for constructing a traditional Chinese medicine tongue color classification quantization model of hyperspectral tongue image comprises the following steps:
s101, obtaining a hyperspectral tongue picture image sample calibrated according to a traditional Chinese medicine tongue picture, a preset quantized value and a color grade;
s104, training a preset deep convolutional neural network structure by taking the hyperspectral tongue image sample and the corresponding calibration result of the traditional Chinese medicine tongue image as training data to obtain a tongue color classification prediction model for predicting the color class of the hyperspectral tongue image;
s105, training a preset deep convolutional neural network structure by taking the hyperspectral tongue image sample and the corresponding calibration result of the quantized value and the color level as training data, and obtaining a tongue color quantized prediction model for predicting the quantized value and the color level of the hyperspectral tongue image.
Compared with the prior art, the tongue color classification prediction model and the tongue color quantification prediction model based on the deep convolutional neural network are added on the basis of the analysis result of the tongue diagnosis classification diagnosis of the traditional Chinese medicine, and the classification- > grading- > numerical quantification evaluation result of tongue colors of the traditional Chinese medicine can be obtained by using the two prediction models obtained by the method, so that the visual observation and comparison of tongue image changes can be conveniently carried out by a user.
As a preferred scheme, the color grade of the hyperspectral tongue picture sample calibration comprises a light second degree, a light first degree, a normal, a deep first degree and a deep second degree; wherein:
the quantized value corresponding to the hyperspectral tongue picture image sample marked as the faint second degree is-100;
the quantized value corresponding to the hyperspectral tongue picture image sample marked as the faint degree is-50;
the quantized value corresponding to the hyperspectral tongue image sample calibrated to be normal is 0;
the quantized value corresponding to the hyperspectral tongue picture image sample calibrated as the deep one degree is +50;
the corresponding quantization value of the hyperspectral tongue picture image sample marked as the deep second degree is +100.
As a preferred embodiment, after the step S101, the method further includes the following steps:
s102, data cleaning is carried out on the hyperspectral image sample: and deleting the noise wave band of the hyperspectral tongue image sample, and carrying out noise separation and energy concentration on the hyperspectral image sample by adopting a minimum noise separation and transformation method.
As a preferable scheme, in the calibration results of the traditional Chinese medicine tongue picture of the hyperspectral tongue picture image sample, the calibration results of tongue color comprise pale white tongue, pale red tongue, red tongue and purple tongue, and the calibration results of tongue fur color comprise white fur, yellow fur and gray and black fur.
Further, before the step S104, the method further includes the following steps:
s103, carrying out tongue fur separation operation on the hyperspectral tongue picture image sample, and identifying tongue fur areas and tongue fur areas in the hyperspectral tongue picture image sample.
A traditional Chinese medicine tongue color classification and quantization method of hyperspectral tongue image comprises the following steps:
s201, acquiring a hyperspectral tongue picture image to be processed;
s204, predicting the color class of the hyperspectral tongue picture image to be processed by using a tongue color classification prediction model obtained by the construction method of the traditional Chinese medicine tongue color classification quantization model of the hyperspectral tongue picture image;
s205, predicting the quantized value and the color grade of the hyperspectral tongue picture image to be processed by using a tongue color quantization prediction model obtained by the construction method of the traditional Chinese medicine tongue color classification quantization model of the hyperspectral tongue picture image.
Compared with the prior art, the tongue color classification prediction model and the tongue color quantification prediction model based on the deep convolutional neural network can obtain the classification- > numerical quantification evaluation result of the tongue color of the traditional Chinese medicine, and are convenient for a user to visually observe and compare the tongue image change.
As a preferable mode, in the step S205, the correspondence between the range of the predicted quantized values and the color level is as follows:
the quantized values are in a slight second degree between-125 and-75;
the quantitative value is a degree of deviation between-75 and-25;
the quantitative value is normal between-25 and +25;
the quantized value is a degree deeper between +25 and +75;
the quantization value is a deep second degree between +75 and +125.
The application also includes the following:
a traditional Chinese medicine tongue color classification quantization system of hyperspectral tongue image comprises a hyperspectral tongue image acquisition module, a color class prediction module and a quantization value and color grade prediction module; wherein:
the hyperspectral tongue image acquisition module is used for acquiring hyperspectral tongue image to be processed;
the color type prediction module is used for predicting the color type of the hyperspectral tongue picture image to be processed by using a tongue color classification prediction model obtained by the construction method of the traditional Chinese medicine tongue color classification quantization model of the hyperspectral tongue picture image;
the quantization value and color grade prediction module is used for predicting the quantization value and color grade of the hyperspectral tongue picture image to be processed by using a tongue color quantization prediction model obtained by the construction method of the traditional Chinese medicine tongue color classification quantization model of the hyperspectral tongue picture image.
A computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements a method of constructing a model for the classification quantization of chinese medicine tongue color for hyperspectral tongue images as described above, and/or a method of classification quantization of chinese medicine tongue color for hyperspectral tongue images as described above.
A computer device comprising a storage medium, a processor, and a computer program stored in the storage medium and executable by the processor; when the computer program is executed by a processor, the method for constructing the traditional Chinese medicine tongue color classification quantization model of the hyperspectral tongue image and/or the method for traditional Chinese medicine tongue color classification quantization of the hyperspectral tongue image are/is realized.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the embodiments will be briefly described below, it being understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and other related drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of a method for constructing a quantitative model of classification of Chinese traditional tongue color of hyperspectral tongue image provided in embodiment 1 of the present application;
FIG. 2 is a second flow chart of the method for constructing the model for classifying and quantifying the tongue color of the traditional Chinese medicine based on the hyperspectral tongue image according to embodiment 1 of the present application;
FIG. 3 is a third flow chart of the method for constructing the model for classifying and quantifying the tongue color of the traditional Chinese medicine based on the hyperspectral tongue image according to the embodiment 1 of the present application;
FIG. 4 is a flow chart of a method for constructing a quantitative model of classification of Chinese traditional tongue color of hyperspectral tongue image provided in embodiment 1 of the present application;
fig. 5 is a schematic flow chart of a method for classifying and quantifying tongue colors in traditional Chinese medicine according to the hyperspectral tongue image provided in embodiment 2 of the present application;
FIG. 6 is a second flow chart of the method for classifying and quantifying tongue colors in TCM according to the hyperspectral tongue image provided by embodiment 2 of the present application;
fig. 7 is a schematic diagram of the composition of the tongue color classification quantization system of the hyperspectral tongue image according to embodiment 3 of the present application;
FIG. 8 is a second schematic diagram of the system for classifying and quantifying tongue colors in TCM according to the hyperspectral tongue image according to embodiment 3 of the present application;
icon: 1. a spectrum tongue image acquisition module; 2. a data cleaning module; 3. a moss separating module; 4. a color class prediction module; 5. and a quantization value and color grade prediction module.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present application more apparent, the technical solutions of the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application, and it is apparent that the described embodiments are some embodiments of the present application, but not all embodiments of the present application. The components of the embodiments of the present application generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations.
Thus, the following detailed description of the embodiments of the application, as presented in the figures, is not intended to limit the scope of the application, as claimed, but is merely representative of selected embodiments of the application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
It should be noted that: like reference numerals and letters denote like items in the following figures, and thus once an item is defined in one figure, no further definition or explanation thereof is necessary in the following figures.
In the description of the present application, it should be understood that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element. The specific meaning of the above terms in the present application will be understood in specific cases by those of ordinary skill in the art.
Some embodiments of the present application are described in detail below with reference to the accompanying drawings. The embodiments described below and features of the embodiments may be combined with each other without conflict.
Example 1
Referring to fig. 1, the method for constructing the traditional Chinese medicine tongue color classification quantization model of the hyperspectral tongue image comprises the following steps:
s101, obtaining a hyperspectral tongue picture image sample calibrated according to a traditional Chinese medicine tongue picture, a preset quantized value and a color grade;
s104, training a preset deep convolutional neural network structure by taking the hyperspectral tongue image sample and the corresponding calibration result of the traditional Chinese medicine tongue image as training data to obtain a tongue color classification prediction model for predicting the color class of the hyperspectral tongue image;
s105, training a preset deep convolutional neural network structure by taking the hyperspectral tongue image sample and the corresponding calibration result of the quantized value and the color level as training data, and obtaining a tongue color quantized prediction model for predicting the quantized value and the color level of the hyperspectral tongue image.
Compared with the prior art, the tongue color classification prediction model and the tongue color quantification prediction model based on the deep convolutional neural network are added on the basis of the analysis result of the tongue diagnosis classification diagnosis of the traditional Chinese medicine, and the classification- > grading- > numerical quantification evaluation result of tongue colors of the traditional Chinese medicine can be obtained by using the two prediction models obtained by the method, so that the visual observation and comparison of tongue image changes can be conveniently carried out by a user.
Specifically, the developer of this embodiment uses cluster analysis to determine boundaries of classifications of tongue colors, uses the description rule of tongue color types in tongue diagnosis of traditional Chinese medicine as a psychological perception evaluation guiding basis, uses a sensory equidistant method to establish a psychological perception equidistant scale for each classification, uses a one-dimensional magnitude to simply and intuitively describe tongue color attributes and the degree of deviation from a certain reference color, and determines reference values of different tongue color grades.
Specifically, the source of the hyperspectral tongue image sample can come from an existing database, or an existing hyperspectral imaging device can be used for collecting images of experimental volunteers, and the hyperspectral tongue image is obtained after the traditional Chinese medicine clinician finishes tongue color calibration.
The steps S104 and S105 are not strictly sequential, and may be performed simultaneously or sequentially, and the difference in numerical sizes is only used to distinguish the two steps.
As a preferred embodiment, the deep convolutional neural network structure may be a res net based deep convolutional neural network structure.
More specifically, as a preferred embodiment, the color level of the hyperspectral tongue image sample calibration includes a lighter second degree, a lighter first degree, a normal, a darker first degree, and a darker second degree; wherein:
the quantized value corresponding to the hyperspectral tongue picture image sample marked as the faint second degree is-100;
the quantized value corresponding to the hyperspectral tongue picture image sample marked as the faint degree is-50;
the quantized value corresponding to the hyperspectral tongue image sample calibrated to be normal is 0;
the quantized value corresponding to the hyperspectral tongue picture image sample calibrated as the deep one degree is +50;
the corresponding quantization value of the hyperspectral tongue picture image sample marked as the deep second degree is +100.
Due to the factors of an imaging system and the influence of external environment, certain noise exists in the image; if the hyperspectral tongue image obtained in the step S1 is not subjected to data cleaning or denoising, as a preferred embodiment, referring to fig. 2, after the step S101, the method further includes the following steps:
s102, data cleaning is carried out on the hyperspectral image sample: and deleting the noise wave band of the hyperspectral tongue image sample, and carrying out noise separation and energy concentration on the hyperspectral image sample by adopting a minimum noise separation and transformation method.
Specifically, the first 10 wave bands and the last 10 wave bands can be deleted, and then the noise separation and the energy concentration are carried out on the hyperspectral image sample by adopting a minimum noise separation method so as to achieve the purpose of removing the noise in the wave bands.
As a preferred embodiment, in the calibration results of the traditional Chinese medicine tongue picture of the hyperspectral tongue picture image sample, the calibration results of tongue color include pale white tongue, pale red tongue, red tongue and purple tongue, and the calibration results of tongue fur color include white fur, yellow fur and gray and black fur.
In particular, regarding the above examples of hyperspectral tongue picture images of specific tongue color and tongue fur color, each is at least 200 cases.
Further, referring to fig. 3 or fig. 4, before the step S104, the method further includes the following steps:
s103, carrying out tongue fur separation operation on the hyperspectral tongue picture image sample, and identifying tongue fur areas and tongue fur areas in the hyperspectral tongue picture image sample.
Specifically, in the process of calibrating the hyperspectral tongue image sample, firstly, calibrating the tongue color and the tongue coating color, and distinguishing the tongue color of pale white tongue, pale red tongue, purple tongue and the like from the tongue coating color of white coating, yellow coating, gray black coating and the like; and then, on the basis of tongue color classification, calibrating the five different color degrees (the light second degree, the light first degree, the normal, the deep first degree and the deep second degree), wherein the light first degree is calibrated to be-50, the light second degree is calibrated to be-100, the deep first degree is calibrated to be 50, and the deep second degree is calibrated to be 100 according to the special values of normal calibration of 0. When training is carried out on the subsequent deep convolutional neural network model, numerical results with tongue color degree of 10, 81 and 43 are learned by oneself.
As an alternative embodiment, the tongue coating separation operation may use an existing 3D U-net based deep learning model for segmentation and identification of tongue regions and tongue coating regions.
In an embodiment, in order to further improve accuracy of subsequent quantization, the tongue color quantization prediction model may be further split into a tongue color quantization model and a tongue fur color quantization model; in other words, in the step S105, it can be specifically divided into two steps:
s1051, training a preset deep convolution neural network structure by taking the tongue fur area identified from the hyperspectral tongue picture image sample and the calibration result of the corresponding quantized value and the color grade as training data, and obtaining a tongue fur color quantization model for predicting the quantized value and the color grade of the tongue fur area of the hyperspectral tongue picture image.
S1052, training a preset deep convolution neural network structure by taking the tongue region identified from the hyperspectral tongue image sample and the calibration result of the corresponding quantized value and color grade as training data, and obtaining a tongue color quantization model for predicting the quantized value and color grade of the tongue region of the hyperspectral tongue image.
Example 2
Referring to fig. 5, the method for classifying and quantifying the tongue color of the traditional Chinese medicine of the hyperspectral tongue image comprises the following steps:
s201, acquiring a hyperspectral tongue picture image to be processed;
s204, predicting the color class of the hyperspectral tongue picture image to be processed by using a tongue color classification prediction model obtained by the construction method of the traditional Chinese medicine tongue color classification quantization model of the hyperspectral tongue picture image described in the embodiment 1;
s205, predicting the quantized value and the color grade of the hyperspectral tongue picture image to be processed by using a tongue color quantization prediction model obtained by the construction method of the traditional Chinese medicine tongue color classification quantization model of the hyperspectral tongue picture image described in the embodiment 1.
Compared with the prior art, the tongue color classification prediction model and the tongue color quantification prediction model based on the deep convolutional neural network can obtain the classification- > numerical quantification evaluation result of the tongue color of the traditional Chinese medicine, and are convenient for a user to visually observe and compare the tongue image change.
As a preferred embodiment, in the step S205, the correspondence between the range of the predicted quantized values and the color level is as follows:
the quantized values are in a slight second degree between-125 and-75;
the quantitative value is a degree of deviation between-75 and-25;
the quantitative value is normal between-25 and +25;
the quantized value is a degree deeper between +25 and +75;
the quantization value is a deep second degree between +75 and +125.
Thus, using the method for classifying and quantifying tongue color in traditional Chinese medicine of hyperspectral tongue image of the present embodiment, a tongue color similar to "tongue color" can be obtained: red tongue, moderate, 55; the color of the moss: the quantitative prediction results of the yellow tongue coating, the severe degree and 87' can be intuitively judged by a user based on the results, so that the quantitative prediction method is more suitable for clinical curative effect evaluation.
As a preferred embodiment, referring to fig. 6, the following steps may be further included after the step S201:
s202, data cleaning is carried out on the hyperspectral image: and deleting the noise wave band of the hyperspectral tongue image, and carrying out noise separation and energy concentration on the hyperspectral image by adopting a minimum noise separation and transformation method.
S203, performing tongue coating separation operation on the hyperspectral tongue picture image, and identifying tongue coating areas and tongue quality areas in the hyperspectral tongue picture image.
As an alternative embodiment, the tongue coating separation operation may use an existing 3D U-net based deep learning model for segmentation and identification of tongue regions and tongue coating regions.
As a preferred embodiment, in order to further improve accuracy of classification quantization, in the step S205, a split tongue color quantization prediction model may be used to predict a quantization value and a color level of the hyperspectral tongue image to be processed, that is, a tongue color quantization model may be used to predict a quantization value and a color level of a tongue region of the hyperspectral tongue image to be processed, and a tongue fur color quantization model may be used to predict a quantization value and a color level of a tongue fur region of the hyperspectral tongue image to be processed.
Example 3
Referring to fig. 7, the system for classifying and quantifying tongue colors of traditional Chinese medicine of hyperspectral tongue image comprises a hyperspectral tongue image acquisition module 1, a color class prediction module 4 and a quantized value and color grade prediction module 5; wherein:
the hyperspectral tongue image acquisition module 1 is used for acquiring hyperspectral tongue image to be processed;
the color class prediction module 4 is configured to predict a color class of the hyperspectral tongue picture image to be processed by using a tongue color classification prediction model obtained by the method for constructing a traditional Chinese medicine tongue color classification quantization model of the hyperspectral tongue picture image described in embodiment 1;
the quantization value and color level prediction module 5 is configured to predict the quantization value and color level of the hyperspectral tongue image to be processed by using the tongue color quantization prediction model obtained by the method for constructing the hyperspectral tongue image classification quantization model in traditional Chinese medicine as described in embodiment 1.
As a preferred embodiment, referring to fig. 8, the method may further include:
the data cleaning module 2 is used for cleaning the data of the hyperspectral image: and deleting the noise wave band of the hyperspectral tongue image, and carrying out noise separation and energy concentration on the hyperspectral image by adopting a minimum noise separation and transformation method.
And the tongue coating separation module 3 is used for carrying out tongue coating separation operation on the hyperspectral tongue picture image and identifying tongue coating areas and tongue quality areas in the hyperspectral tongue picture image.
Example 4
A computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements a method of constructing a model for the quantization of the chinese tongue color classification of hyperspectral tongue image as described in example 1, and/or a method of the quantization of the chinese tongue color classification of hyperspectral tongue image as described in example 2.
Example 5
A computer device comprising a storage medium, a processor, and a computer program stored in the storage medium and executable by the processor; the computer program, when executed by a processor, implements the method of constructing a model for classifying and quantifying the tongue color of traditional Chinese medicine of hyperspectral tongue image as described in example 1, and/or the method of classifying and quantifying the tongue color of traditional Chinese medicine of hyperspectral tongue image as described in example 2.
In the embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other manners. The apparatus embodiments described above are merely illustrative, for example, of the flowcharts and block diagrams in the figures that illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods and computer program products according to embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
In addition, functional modules in the embodiments of the present application may be integrated together to form a single part, or each module may exist alone, or two or more modules may be integrated to form a single part. The functions provided by the present application may be stored in one storage medium if implemented in the form of software functional modules and sold or used as a separate product. Based on such understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution in the form of a software product stored in a readable storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in the embodiments of the present application. And the aforementioned readable storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
The above description is merely illustrative of various embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily think about variations or substitutions within the scope of the present application, and the application is intended to be covered by the scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.
Claims (10)
1. The method for constructing the traditional Chinese medicine tongue color classification quantization model of the hyperspectral tongue image is characterized by comprising the following steps of:
s101, obtaining a hyperspectral tongue picture image sample calibrated according to a traditional Chinese medicine tongue picture, a preset quantized value and a color grade;
s104, training a preset deep convolutional neural network structure by taking the hyperspectral tongue image sample and the corresponding calibration result of the traditional Chinese medicine tongue image as training data to obtain a tongue color classification prediction model for predicting the color class of the hyperspectral tongue image;
s105, training a preset deep convolutional neural network structure by taking the hyperspectral tongue image sample and the corresponding calibration result of the quantized value and the color level as training data, and obtaining a tongue color quantized prediction model for predicting the quantized value and the color level of the hyperspectral tongue image.
2. The method for constructing a traditional Chinese medicine tongue color classification quantization model of a hyperspectral tongue image according to claim 1, wherein the color level of the hyperspectral tongue image sample calibration comprises a bias second degree, a bias first degree, a normal bias first degree and a bias second degree; wherein:
the quantized value corresponding to the hyperspectral tongue picture image sample marked as the faint second degree is-100;
the quantized value corresponding to the hyperspectral tongue picture image sample marked as the faint degree is-50;
the quantized value corresponding to the hyperspectral tongue image sample calibrated to be normal is 0;
the quantized value corresponding to the hyperspectral tongue picture image sample calibrated as the deep one degree is +50;
the corresponding quantization value of the hyperspectral tongue picture image sample marked as the deep second degree is +100.
3. The method for constructing a quantitative model for classifying tongue colors in traditional Chinese medicine based on hyperspectral tongue images according to claim 1, further comprising the following steps after step S101:
s102, data cleaning is carried out on the hyperspectral image sample: and deleting the noise wave band of the hyperspectral tongue image sample, and carrying out noise separation and energy concentration on the hyperspectral image sample by adopting a minimum noise separation and transformation method.
4. The method for constructing a model for classifying and quantifying the tongue color of a traditional Chinese medicine according to claim 1, wherein in the result of the calibration of the tongue color of the hyperspectral tongue image sample, the result of the calibration of the tongue color comprises pale tongue, pale red tongue, red tongue and purple tongue, and the result of the calibration of the tongue fur color comprises white fur, yellow fur and gray fur.
5. The method for constructing a quantitative model for classifying tongue colors in traditional Chinese medicine based on hyperspectral tongue images according to claim 4, further comprising the following steps before step S104:
s103, carrying out tongue fur separation operation on the hyperspectral tongue picture image sample, and identifying tongue fur areas and tongue fur areas in the hyperspectral tongue picture image sample.
6. A traditional Chinese medicine tongue color classification and quantization method of hyperspectral tongue image is characterized by comprising the following steps:
s201, acquiring a hyperspectral tongue picture image to be processed;
s204, predicting the color class of the hyperspectral tongue picture image to be processed by using a tongue color classification prediction model obtained by the construction method of the traditional Chinese medicine tongue color classification quantization model of the hyperspectral tongue picture image according to any one of claims 1 to 5;
s205, predicting a quantization value and a color level of the hyperspectral tongue image to be processed by using a tongue color quantization prediction model obtained by the method for constructing the hyperspectral tongue image traditional Chinese medicine tongue color classification quantization model according to any one of claims 1 to 5.
7. The method according to claim 6, wherein in step S205, the correspondence between the range of predicted quantized values and the color level is as follows:
the quantized values are in a slight second degree between-125 and-75;
the quantitative value is a degree of deviation between-75 and-25;
the quantitative value is normal between-25 and +25;
the quantized value is a degree deeper between +25 and +75;
the quantization value is a deep second degree between +75 and +125.
8. The traditional Chinese medicine tongue color classification quantization system of the hyperspectral tongue image is characterized by comprising a hyperspectral tongue image acquisition module (1), a color class prediction module (4) and a quantization value and color class prediction module (5); wherein:
the hyperspectral tongue image acquisition module (1) is used for acquiring hyperspectral tongue image to be processed;
the color class prediction module (4) is used for predicting the color class of the hyperspectral tongue picture image to be processed by using a tongue color classification prediction model obtained by the construction method of the traditional Chinese medicine tongue color classification quantization model of the hyperspectral tongue picture image according to any one of claims 1 to 5;
the quantization value and color grade prediction module (5) is used for predicting the quantization value and color grade of the hyperspectral tongue picture image to be processed by using a tongue color quantization prediction model obtained by the construction method of the traditional Chinese medicine tongue color classification quantization model of the hyperspectral tongue picture image according to any one of claims 1 to 5.
9. A computer-readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements a method of constructing a model for the quantization of the chinese tongue color classification of hyperspectral tongue images according to any one of claims 1 to 5, and/or a method of the quantization of the chinese tongue color classification of hyperspectral tongue images according to claim 6 or 7.
10. A computer device comprising a storage medium, a processor, and a computer program stored in the storage medium and executable by the processor; the computer program, when executed by a processor, implements a method for constructing a model for quantifying the tongue color classification of a hyperspectral tongue image according to any one of claims 1 to 5, and/or a method for quantifying the tongue color classification of a hyperspectral tongue image according to claim 6 or 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310780874.2A CN116824252A (en) | 2023-06-28 | 2023-06-28 | Traditional Chinese medicine tongue color classification quantization method for hyperspectral tongue image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310780874.2A CN116824252A (en) | 2023-06-28 | 2023-06-28 | Traditional Chinese medicine tongue color classification quantization method for hyperspectral tongue image |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116824252A true CN116824252A (en) | 2023-09-29 |
Family
ID=88119877
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310780874.2A Pending CN116824252A (en) | 2023-06-28 | 2023-06-28 | Traditional Chinese medicine tongue color classification quantization method for hyperspectral tongue image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116824252A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117593591A (en) * | 2024-01-16 | 2024-02-23 | 天津医科大学总医院 | Tongue picture classification method based on medical image segmentation |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20140140934A (en) * | 2013-05-30 | 2014-12-10 | 상지대학교산학협력단 | Method, system and recording medium for analysing tongue diagnosis using a quantifying evalution indicator of tongue diagnosis image |
| CN107330889A (en) * | 2017-07-11 | 2017-11-07 | 北京工业大学 | A kind of traditional Chinese medical science tongue color coating colour automatic analysis method based on convolutional neural networks |
| CN109394182A (en) * | 2018-12-12 | 2019-03-01 | 北京工业大学 | A kind of Chinese medicine tongue colo(u)r specification analysis method based on spectral information |
| CN110189383A (en) * | 2019-06-27 | 2019-08-30 | 合肥云诊信息科技有限公司 | Chinese medicine tongue color coating colour quantitative analysis method based on machine learning |
| CN111259954A (en) * | 2020-01-15 | 2020-06-09 | 北京工业大学 | Hyperspectral traditional Chinese medicine tongue coating and tongue quality classification method based on D-Resnet |
| CN113724228A (en) * | 2021-08-31 | 2021-11-30 | 平安科技（深圳）有限公司 | Tongue color and coating color identification method and device, computer equipment and storage medium |
-
2023
- 2023-06-28 CN CN202310780874.2A patent/CN116824252A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20140140934A (en) * | 2013-05-30 | 2014-12-10 | 상지대학교산학협력단 | Method, system and recording medium for analysing tongue diagnosis using a quantifying evalution indicator of tongue diagnosis image |
| CN107330889A (en) * | 2017-07-11 | 2017-11-07 | 北京工业大学 | A kind of traditional Chinese medical science tongue color coating colour automatic analysis method based on convolutional neural networks |
| CN109394182A (en) * | 2018-12-12 | 2019-03-01 | 北京工业大学 | A kind of Chinese medicine tongue colo(u)r specification analysis method based on spectral information |
| CN110189383A (en) * | 2019-06-27 | 2019-08-30 | 合肥云诊信息科技有限公司 | Chinese medicine tongue color coating colour quantitative analysis method based on machine learning |
| CN111259954A (en) * | 2020-01-15 | 2020-06-09 | 北京工业大学 | Hyperspectral traditional Chinese medicine tongue coating and tongue quality classification method based on D-Resnet |
| CN113724228A (en) * | 2021-08-31 | 2021-11-30 | 平安科技（深圳）有限公司 | Tongue color and coating color identification method and device, computer equipment and storage medium |
Non-Patent Citations (3)
| Title |
|---|
| DONG ZHANG ET AL.: "Tongue colour and coating prediction in traditional Chinese medicine based on visible hyperspectral imaging", 《IET IMAGE PROCESSING》, pages 2265 - 2270 * |
| 张冬 等: "基于高光谱图像技术的中医舌诊客观化研究展望", 《中国中医基础医学杂志》, vol. 25, no. 9, pages 2 * |
| 钟振: "基于深度学习的中医舌象分割与识别实验研究", 《中国优秀硕士学位论文全文数据库 医药卫生科技辑》, pages 3 - 4 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117593591A (en) * | 2024-01-16 | 2024-02-23 | 天津医科大学总医院 | Tongue picture classification method based on medical image segmentation |
| CN117593591B (en) * | 2024-01-16 | 2024-05-31 | 天津医科大学总医院 | Tongue picture classification method based on medical image segmentation |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Groen et al. | From image statistics to scene gist: evoked neural activity reveals transition from low-level natural image structure to scene category | |
| Le Hégarat-Mascle et al. | Automatic change detection by evidential fusion of change indices | |
| KR101000492B1 (en) | Apparatus and method for diagnosis of psychological symptoms corresponding to analysis of coloring patterns in art therapy assessment and medium of recording its program | |
| Rahim et al. | Joint prediction of multiple scores captures better individual traits from brain images | |
| JP5058064B2 (en) | Picture therapy pattern selection and arrangement, color painting analysis method, psychological symptom diagnosis method based on picture therapy pattern analysis, and recording medium on which a program for doing this is recorded | |
| US11430232B2 (en) | Method for splitting one or more images of a sample into image data split according to dyes, computer program, computer-readable medium storing the program and system for performing the method | |
| CN116824252A (en) | Traditional Chinese medicine tongue color classification quantization method for hyperspectral tongue image | |
| CN116849612B (en) | Multispectral tongue picture image acquisition and analysis system | |
| JP2008086479A (en) | Physical activity measuring system | |
| Tello-Mijares et al. | A novel method for the separation of overlapping pollen species for automated detection and classification | |
| Tirado et al. | Bruise dating using deep learning | |
| Yakno et al. | Dorsal hand vein image enhancement using fusion of CLAHE and fuzzy adaptive gamma | |
| Dessouky et al. | Computer-aided diagnosis system for Alzheimer’s disease using different discrete transform techniques | |
| Zhu et al. | Detecting abnormality in optic nerve head images using a feature extraction analysis | |
| CN116469579A (en) | Brain state monitoring method, equipment, storage medium and device | |
| Rezaei et al. | Detecting alterations in historical violins with optical monitoring | |
| Nakhaeizadeh et al. | Cognitive bias in sex estimation: The influence of context on forensic decision-making | |
| Weisser et al. | Know What You Don’t Know: Assessment of Overlooked Microplastic Particles in FTIR Images | |
| CN113702328A (en) | Method, device, equipment and storage medium for analyzing properties of product oil | |
| Subbaraya et al. | Probabilistic principal component analysis and long short-term memory classifier for automatic detection of Alzheimer’s disease using MRI brain images | |
| CN113140290A (en) | Model training method and device, focus identification method and electronic equipment | |
| Arslan et al. | Automation of cluster extraction in fundus autofluorescence images of geographic atrophy | |
| Kchaou et al. | Two image quality assessment methods based on evidential modeling and uncertainty: application to automatic iris identification systems | |
| CN113030060A (en) | Drug Raman spectrum identification method based on convolutional neural network | |
| KR100935014B1 (en) | Method for prediction of symptom corresponding to analysis of coloring patterns in art therapy assessment and medium of recording its program |
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 |