CN109598297A - A kind of tongue fur tongue analysis method, system, computer equipment and storage medium - Google Patents
A kind of tongue fur tongue analysis method, system, computer equipment and storage medium Download PDFInfo
- Publication number
- CN109598297A CN109598297A CN201811443339.3A CN201811443339A CN109598297A CN 109598297 A CN109598297 A CN 109598297A CN 201811443339 A CN201811443339 A CN 201811443339A CN 109598297 A CN109598297 A CN 109598297A
- Authority
- CN
- China
- Prior art keywords
- tongue
- image
- fur
- nature
- pixel
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- 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
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
-
- 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
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/03—Recognition of patterns in medical or anatomical images
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a kind of tongue fur tongue analysis method, system, computer equipment and storage mediums.The described method includes: obtaining the image of the tongue region according to tongue location model from the face-image comprising tongue region;The tongue is separated from the image of the tongue region using oval template, forms tongue image;The tongue image is divided into tongue nature image and tongue fur image according to coating nature separation algorithm;The tongue nature image is matched with tongue color disaggregated model, the tongue fur image prestored with tongue fur color classification model, the tongue nature classification and tongue fur classification are obtained.The speed and accuracy that tongue fur is separated with tongue nature in image can be improved using this method.
Description
Technical field
The present invention relates to technical field of image processing, and more particularly, to a kind of tongue fur tongue analysis method, be
System, computer equipment and storage medium.
Background technique
With people to health increasingly attention, rarity of the Chinese medicine as the Chinese nation, while doctor trained in Western medicine is prevailing in
Doctor also becomes by high praise.Observation can be divided into facial diagnosis and lingual diagnosis in Chinese medicine, and the state of human body can pass through face and tongue
Color and form show, the form of lingual diagnosis Main Diagnosis tongue nature and tongue fur, color judge property, the disease of disease with this
The shallow depth of gesture, the prosperity and decline of qi and blood and actual situation of internal organs etc..Traditional lingual diagnosis mainly passes through the shape that doctor checks the tongue of patient
State, color, to judge the type and severity of disease.
With the gradually development of Morden Image Processing Technology, the artificial intelligence technologys such as machine learning and deep learning it is continuous
Maturation, depth convolutional neural networks start to be applied among TCM tongue diagnosis, and produce a variety of methods.But due to tongue body shape
Different, during image processing techniques is used for lingual diagnosis, following problem occur: tongue body color is very close to lip
And face color, cause existing many tongue body segmentation effects unsatisfactory;Coating nature separates more by spies such as tongue body surface colors
The influence of sign, separating effect are far not fully up to expectations.
Summary of the invention
Based on this, this application provides the tongue fur tongue analysis sides that one kind can separate tongue fur tongue nature fast and accurately
Method, system, computer equipment and storage medium.
A kind of tongue fur tongue analysis method, which comprises
According to tongue location model from the face-image comprising tongue region, the image of the tongue region is obtained;
The tongue is separated from the image of the tongue region using oval template, forms tongue image;
The tongue image is divided into tongue nature image and tongue fur image according to coating nature separation algorithm;
By the tongue nature image and the tongue color disaggregated model, the tongue fur image and the tongue fur color classification model that prestore
It is matched, obtains the tongue nature classification and tongue fur classification.
The tongue location model, tongue color disaggregated model and tongue fur color classification mould in one of the embodiments,
Type is obtained by multiple training samples using lightweight depth convolutional neural networks model training.
Tongue fur tongue analysis method in one of the embodiments, further include: acquisition includes the face-image of tongue region.
In one of the embodiments, the lightweight depth convolutional neural networks model include: SqueezeNet,
At least one of MobileNet, ShuffleNet, Xception and SSD.
It is described in one of the embodiments, that the tongue image is divided by tongue nature image and tongue according to coating nature separation algorithm
Tongue fur image, comprising:
By the tongue image be divided into the root of the tongue, in tongue, the tip of the tongue, left tongue five bands of position in, right tongue;
Three classes pixel will be divided into using clustering algorithm according to the pixel of different location in the tongue image;
Location region is located at the root of the tongue, the pixel definition in tongue is tongue fur pixel, the tongue fur pixel is covered
Image be tongue fur image;
It is tongue nature pixel, the image that the tongue nature pixel is covered by the pixel definition that location region is located at the tip of the tongue
For tongue nature image;
It is background pixel, the image that the background pixel is covered by the pixel definition that location region is located at tongue side
For background image.
The clustering algorithm is K-means clustering algorithm in one of the embodiments,.
Tongue color disaggregated model and tongue fur color classification model are led to by multiple training samples in one of the embodiments,
Machine learning method is crossed to be classified to obtain.
A kind of tongue fur tongue analysis system, the system comprises:
Tongue region image collection module, for according to tongue location model from the face-image comprising tongue region,
Obtain the image of the tongue region;
Tongue image separation module, for being separated the tongue from the image of the tongue region using oval template
Out, tongue image is formed;
Tongue fur tongue nature separation module, for the tongue image to be divided into tongue nature image and tongue fur according to coating nature separation algorithm
Image;
Matching module, for by the tongue nature image and the tongue color disaggregated model, the tongue fur image and the tongue that prestore
Tongue fur color classification model is matched, and the tongue nature classification and tongue fur classification are obtained.
A kind of computer equipment, including memory and processor, the memory are stored with computer program, the processing
Device performs the steps of when executing the computer program
According to tongue location model from the face-image comprising tongue region, the image of the tongue region is obtained;
The tongue is separated from the image of the tongue region using oval template, forms tongue image;
The tongue image is divided into tongue nature image and tongue fur image according to coating nature separation algorithm;
By the tongue nature image and the tongue color disaggregated model, the tongue fur image and the tongue fur color classification model that prestore
It is matched, obtains the tongue nature classification and tongue fur classification.
A kind of computer readable storage medium, is stored thereon with computer program, and the computer program is held by processor
It is performed the steps of when row
According to tongue location model from the face-image comprising tongue region, the image of the tongue region is obtained;
The tongue is separated from the image of the tongue region using oval template, forms tongue image;
The tongue image is divided into tongue nature image and tongue fur image according to coating nature separation algorithm;
By the tongue nature image and the tongue color disaggregated model, the tongue fur image and the tongue fur color classification model that prestore
It is matched, obtains the tongue nature classification and tongue fur classification.
Above-mentioned tongue fur tongue analysis method, system, computer equipment and storage medium, by oval template by tongue figure
As separating from the image of tongue region, the separation of tongue image, then the tongue nature by prestoring can be fast and accurately realized
Color classification model, tongue fur color classification model classify respectively to tongue nature and tongue fur, realize fast and accurately to lingual diagnosis figure
The automatic segmentation of picture.
Detailed description of the invention
By reference to the following drawings, exemplary embodiments of the present invention can be more fully understood by:
Fig. 1 is the flow diagram of tongue fur tongue analysis method in one embodiment;
Fig. 2 is the flow diagram of coating nature separation method in one embodiment;
Fig. 3 is one embodiment SSD network frame figure;
Fig. 4 is five band of position schematic diagrames of one embodiment tongue image;
Fig. 5 is the structural block diagram of tongue fur tongue analysis system in one embodiment;
Fig. 6 is the internal structure chart of computer equipment in one embodiment.
Specific embodiment
Exemplary embodiments of the present invention are introduced referring now to the drawings, however, the present invention can use many different shapes
Formula is implemented, and is not limited to the embodiment described herein, and to provide these embodiments be at large and fully disclose
The present invention, and the scope of the present invention is sufficiently conveyed to person of ordinary skill in the field.Show for what is be illustrated in the accompanying drawings
Term in example property embodiment is not limitation of the invention.In the accompanying drawings, identical cells/elements use identical attached
Icon note.
Unless otherwise indicated, term (including scientific and technical terminology) used herein has person of ordinary skill in the field
It is common to understand meaning.Further it will be understood that with the term that usually used dictionary limits, should be understood as and its
The context of related fields has consistent meaning, and is not construed as Utopian or too formal meaning.
In one embodiment, as shown in Figure 1, providing a kind of tongue fur tongue analysis method, the method includes the steps:
Step S110 obtains the tongue according to the tongue location model prestored from the face-image comprising tongue region
The image in portion region.
Specifically, the face-image comprising tongue region to be inputted to the tongue location model prestored, tongue region is exported
Image.
Wherein, the tongue location model uses lightweight depth convolutional neural networks model training by multiple training samples
It obtains.Multiple training samples can be carried out more wheel marks by medical practitioner and be generated.The lightweight depth convolutional neural networks model
It include: at least one of SqueezeNet, MobileNet, ShuffleNet, Xception and SSD.
Wherein, tongue positioning is referred to using depth convolutional neural networks SSD (Single Shot MultiBox
Detector, single-lens more box detectors) specific location of tongue is found out in the face-image comprising tongue region, it include tongue
The width and height of portion region top left corner apex coordinate and tongue, the basic network in SSD used herein is SqueezeNet, and
And corresponding limitation has been done in the size of positioning target.
Specifically, SSD network frame figure is as shown in figure 3, as seen from the figure, before input picture (Input Image)
The corresponding positioning target area of target alignment layers (Conv layers) in face is smaller, and candidate region (#defboxes) is more, needs
Many calculation amounts are wanted, only need to calculate four target alignment layers (four targets positioning as shown in Figure 3 below in the present embodiment
Layer), so that candidate region quantity is a from conventional SSD candidate target region number 8732 (5776+2166+600+150+36+4)
It is a to be reduced to 790 (600+150+36+4), considerably reduces calculation amount.
In the present embodiment, using partitioning algorithm time-consuming in the conventional lingual diagnosis method of object localization method SSD replacement, and by
Bigger in the accounting of known tongue region in the input image, the application further limits the target for needing to position in SSD
Size, so that the performance of algorithm be effectively promoted.
Step S120 is separated the tongue from the image of the tongue region using oval template, forms tongue
Portion's image.
Wherein, when separating tongue image by oval template, compared with traditional image segmentation algorithm, reduce consumption
When.Because the tongue image of almost all people is all comparatively close to ellipse, using oval template segmentation effect it is ideal and
Efficiently, more accurate tongue fur pixel and tongue nature pixel can be extracted.Although dividing method can dismiss a small amount of tongue side point in this way,
But the disturbing factors such as neck, clothes can be effectively excluded in this way, classifying for subsequent tongue nature, it is good to have laid with tongue fur classification
Basis.
The tongue image is divided into tongue nature image and tongue fur image according to coating nature separation algorithm by step S130.
Wherein, the pixel of the tongue nature image is not identical as the pixel of the tongue fur image, therefore, in the processed of image
Image separation can be carried out according to the difference of the two pixel in journey.
Step S140, by the tongue nature image and the tongue color disaggregated model, the tongue fur image and the tongue fur face that prestore
Colour sorting model is matched, and the tongue nature classification and tongue fur classification are obtained.
Tongue color disaggregated model and tongue fur color classification model are adopted by multiple training samples in one of the embodiments,
It is obtained with lightweight depth convolutional neural networks model training.The lightweight depth convolutional neural networks model includes:
At least one of SqueezeNet, MobileNet, ShuffleNet, Xception and SSD.In the present embodiment, OpenCV is used
Dnn module call multiple tongue color disaggregated model and tongue fur color classification models of having trained to carry out tongue nature classification and tongue
Tongue fur classification.
Tongue color disaggregated model and tongue fur color classification model are led to by multiple training samples in one of the embodiments,
Machine learning method is crossed to be trained to obtain.The machine learning method includes that (SupportVector Machine is supported SVM
Vector machine).
The tongue color disaggregated model includes light white, light red, pale purple, red, dark red and deep red in one of the embodiments,
At least one of color subclass, the tongue fur color classification model include white, yellow, yellowish-white phase and and at least one of greyish black subclass.
In one of the embodiments, in step S110, a kind of tongue fur tongue analysis method further comprises the steps of: acquisition and includes
The face-image of tongue region.Wherein, the face-image comprising tongue region can be acquired by camera.
Above-mentioned tongue fur tongue analysis method is isolated tongue image from the image of tongue region by oval template
Come, can fast and accurately realize the separation of tongue image, then tongue color disaggregated model, tongue fur color classification by prestoring
Model classifies respectively to tongue nature and tongue fur, realizes fast and accurately to the automatic segmentation of lingual diagnosis image.
In one of the embodiments, as shown in Fig. 2, in step s 130, it is described will be described according to coating nature separation algorithm
Tongue image is divided into tongue nature image and tongue fur image, comprising:
Step S131, by the tongue image be divided into the root of the tongue, in tongue, the tip of the tongue, left tongue five bands of position in, right tongue.
Specifically, as shown in figure 4, tongue image can be divided into five regions as shown in the figure.
Step S132 will be divided into three classes pixel using clustering algorithm according to the pixel of different location in the tongue image.
It wherein, can be by pixel come to tongue nature, tongue fur since the color of image difference of tongue nature, tongue fur and background is larger
Classify with background.It include tongue nature pixel, tongue fur pixel and background pixel in three classes pixel, the clustering algorithm is K-
Means clustering algorithm.Wherein, K-means clustering algorithm has used Ohta with Lab phase to tie not instead of on RGB color
The characteristic color space of conjunction, the characteristic color space and RGB color conversion formula that Ohta and Lab are combined are as follows:
T1=(2R-G-B)/2
T2=(a+128)/256
T3=(b+128)/256
Wherein, T1、T2、T3For the orthogonal characteristic in the characteristic color space combined Ohta and Lab, R, G, B are tradition RGB
Color characteristic, a, b be Lab color characteristic, R be red, G be green, B be blue, a indicate from carmetta to green model
It encloses, b indicates the range from yellow to blue.
Location region is located at the root of the tongue by step S133, the pixel definition in tongue is tongue fur pixel, the tongue fur picture
The image that element is covered is tongue fur image.
Wherein, it is tongue fur pixel that position, which includes the root of the tongue, the pixel definition in tongue, in three classes pixel.
The pixel definition that location region is located at the tip of the tongue is tongue nature pixel, the tongue nature pixel institute by step S134
The image of covering is tongue nature image.
Wherein, it is tongue nature pixel that position, which includes the pixel definition of the tip of the tongue, in three classes pixel.
The pixel definition that location region is located at tongue side is background pixel, the background pixel institute by step S135
The image of covering is background image.
Wherein, it is background pixel that position, which only includes the pixel definition on tongue side, in three classes pixel.
A kind of tongue fur tongue analysis method of the application, by experimental verification, in the consumption of lingual diagnosis classifying quality, a whole set of algorithm
When and the same person consistency that section is repeatedly diagnosed at the same time in terms of, all obtain good performance.The application
On the basis of lightweight depth convolutional neural networks, by using various technological means, it is time-consuming to solve current lingual diagnosis method
The problem that too big and tongue segmentation effect is bad and coating nature classification is inaccurate.
In one embodiment, as shown in figure 5, providing a kind of tongue fur tongue analysis system, the system comprises: tongue
Area image obtains module 210, tongue image separation module 220, tongue fur tongue nature separation module 230 and matching module 240.Its
In:
Tongue region image collection module 210, for according to tongue location model from the face-image comprising tongue region
In, obtain the image of the tongue region.
Tongue image separation module 220, for using oval template by the tongue from the image of the tongue region
It separates, forms tongue image.
Wherein, when separating tongue image by oval template, compared with traditional image segmentation algorithm, reduce consumption
When.Because the tongue image of almost all people is all comparatively close to ellipse, using oval template segmentation effect it is ideal and
Efficiently, more accurate tongue fur pixel and tongue nature pixel can be extracted.Although dividing method can dismiss a small amount of tongue side point in this way,
But the disturbing factors such as neck, clothes can be effectively excluded in this way, classifying for subsequent tongue nature, it is good to have laid with tongue fur classification
Basis.
Tongue fur tongue nature separation module 230, for according to coating nature separation algorithm by the tongue image be divided into tongue nature image and
Tongue fur image.
Matching module 240, for by the tongue nature image with prestore tongue color disaggregated model, the tongue fur image with
Tongue fur color classification model is matched, and the tongue nature classification and tongue fur classification are obtained.
The tongue fur tongue nature separation module 230 includes: area division unit in one of the embodiments, is used for institute
State tongue image be divided into the root of the tongue, in tongue, the tip of the tongue, left tongue five bands of position in, right tongue;Pixel classifications unit is used for institute
It states in tongue image and three classes pixel is divided into using clustering algorithm according to the pixel of different location;Tongue fur image segmentation unit, is used for
Location region is located at the root of the tongue, the pixel definition in tongue is tongue fur pixel, the image that the tongue fur pixel is covered is
Tongue fur image;Tongue nature image segmentation unit, the pixel definition for location region to be located to the tip of the tongue are tongue nature pixel, institute
Stating the image that tongue nature pixel is covered is tongue nature image;Background image cutting unit, for location region to be located at tongue
The pixel definition on side is background pixel, and the image that the background pixel is covered is background image.
Specific about tongue fur tongue analysis system limits the limit that may refer to above for tongue fur tongue analysis method
Fixed, details are not described herein.Modules in above-mentioned tongue fur tongue analysis system can fully or partially through software, hardware and its
Combination is to realize.Above-mentioned each module can be embedded in the form of hardware or independently of in the processor in computer equipment, can also be with
It is stored in the memory in computer equipment in a software form, in order to which processor calls the above modules of execution corresponding
Operation.
In one embodiment, a kind of computer equipment is provided, which can be server, internal junction
Composition can be as shown in Figure 6.The computer equipment include by system bus connect processor, memory, network interface and
Database.Wherein, the processor of the computer equipment is for providing calculating and control ability.The memory packet of the computer equipment
Include non-volatile memory medium, built-in storage.The non-volatile memory medium is stored with operating system, computer program and data
Library.The built-in storage provides environment for the operation of operating system and computer program in non-volatile memory medium.The calculating
The database of machine equipment is used to store the face image data of tongue region.The network interface of the computer equipment is used for and outside
Terminal by network connection communication.To realize a kind of tongue fur tongue analysis method when the computer program is executed by processor.
It will be understood by those skilled in the art that structure shown in Fig. 6, only part relevant to application scheme is tied
The block diagram of structure does not constitute the restriction for the computer equipment being applied thereon to application scheme, specific computer equipment
It may include perhaps combining certain components or with different component layouts than more or fewer components as shown in the figure.
In one embodiment, a kind of computer equipment, including memory and processor, the memory are stored with calculating
Machine program, the processor perform the steps of when executing the computer program
According to tongue location model from the face-image comprising tongue region, the image of the tongue region is obtained;
The tongue is separated from the image of the tongue region using oval template, forms tongue image;
The tongue image is divided into tongue nature image and tongue fur image according to coating nature separation algorithm;
By the tongue nature image and the tongue color disaggregated model, the tongue fur image and the tongue fur color classification model that prestore
It is matched, obtains the tongue nature classification and tongue fur classification.
In one embodiment, a kind of computer readable storage medium is stored thereon with computer program, the computer
It is performed the steps of when program is executed by processor
According to tongue location model from the face-image comprising tongue region, the image of the tongue region is obtained;
The tongue is separated from the image of the tongue region using oval template, forms tongue image;
The tongue image is divided into tongue nature image and tongue fur image according to coating nature separation algorithm;
By the tongue nature image and the tongue color disaggregated model, the tongue fur image and the tongue fur color classification model that prestore
It is matched, obtains the tongue nature classification and tongue fur classification.
The present invention is described by reference to a small amount of embodiment.However, it is known in those skilled in the art, as
Defined by subsidiary Patent right requirement, in addition to the present invention other embodiments disclosed above equally fall in it is of the invention
In range.
Normally, all terms used in the claims are all solved according to them in the common meaning of technical field
It releases, unless in addition clearly being defined wherein.All references " one/described/be somebody's turn to do [device, component etc.] " are all opened ground
At least one example being construed in described device, component etc., unless otherwise expressly specified.Any method disclosed herein
Step need not all be run with disclosed accurate sequence, unless explicitly stated otherwise.
Claims (10)
1. a kind of tongue fur tongue analysis method, which is characterized in that the described method includes:
According to the tongue location model prestored from the face-image comprising tongue region, the image of the tongue region is obtained;
The tongue is separated from the image of the tongue region using oval template, forms tongue image;
The tongue image is divided into tongue nature image and tongue fur image according to coating nature separation algorithm;
The tongue nature image is carried out with the tongue color disaggregated model, the tongue fur image and tongue fur color classification model prestored
Matching obtains the tongue nature classification and tongue fur classification.
2. the method according to claim 1, wherein the tongue location model, tongue color disaggregated model and
Tongue fur color classification model is obtained by multiple training samples using lightweight depth convolutional neural networks model training.
3. the method according to claim 1, wherein further include:
Acquisition includes the face-image of tongue region.
4. according to the method described in claim 2, it is characterized in that, the lightweight depth convolutional neural networks model includes:
At least one of SqueezeNet, MobileNet, ShuffleNet, Xception and SSD.
5. the method according to claim 1, wherein described divide the tongue image according to coating nature separation algorithm
For tongue nature image and tongue fur image, comprising:
By the tongue image be divided into the root of the tongue, in tongue, the tip of the tongue, left tongue five bands of position in, right tongue;
Three classes pixel will be divided into using clustering algorithm according to the pixel of different location in the tongue image;Wherein, three classes pixel
In include tongue nature pixel, tongue fur pixel and background pixel;
Location region is located at the root of the tongue, the pixel definition in tongue is tongue fur pixel, the figure that the tongue fur pixel is covered
As being tongue fur image;
It is tongue nature pixel by the pixel definition that location region is located at the tip of the tongue, the image that the tongue nature pixel is covered is tongue
Matter image;
It is background pixel by the pixel definition that location region is located at tongue side, the image that the background pixel is covered is back
Scape image.
6. according to the method described in claim 5, it is characterized in that, the clustering algorithm is K-means clustering algorithm.
7. the method according to claim 1, wherein tongue color disaggregated model and tongue fur color classification model by
Multiple training samples are trained to obtain by machine learning method.
8. a kind of tongue fur tongue analysis system, which is characterized in that the system comprises:
Tongue region image collection module, for from the face-image comprising tongue region, being obtained according to tongue location model
The image of the tongue region;
Tongue image separation module, for being isolated the tongue from the image of the tongue region using oval template
Come, forms tongue image;
Tongue fur tongue nature separation module, for the tongue image to be divided into tongue nature image and tongue fur figure according to coating nature separation algorithm
Picture;
Matching module, for by the tongue nature image and the tongue color disaggregated model, the tongue fur image and the tongue fur face that prestore
Colour sorting model is matched, and the tongue nature classification and tongue fur classification are obtained.
9. a kind of computer equipment, including memory and processor, the memory are stored with computer program, feature exists
In the step of processor realizes any one of claims 1 to 7 the method when executing the computer program.
10. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer program
The step of method described in any one of claims 1 to 7 is realized when being executed by processor.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811443339.3A CN109598297A (en) | 2018-11-29 | 2018-11-29 | A kind of tongue fur tongue analysis method, system, computer equipment and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811443339.3A CN109598297A (en) | 2018-11-29 | 2018-11-29 | A kind of tongue fur tongue analysis method, system, computer equipment and storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109598297A true CN109598297A (en) | 2019-04-09 |
Family
ID=65960074
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811443339.3A Pending CN109598297A (en) | 2018-11-29 | 2018-11-29 | A kind of tongue fur tongue analysis method, system, computer equipment and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109598297A (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110929740A (en) * | 2019-11-21 | 2020-03-27 | 中电健康云科技有限公司 | LGBM model-based tongue quality and tongue coating separation method |
CN111192244A (en) * | 2019-12-25 | 2020-05-22 | 新绎健康科技有限公司 | Method and system for determining tongue characteristics based on key points |
CN111209801A (en) * | 2019-12-24 | 2020-05-29 | 新绎健康科技有限公司 | Traditional Chinese medicine fat tongue identification method and device |
CN112614106A (en) * | 2020-12-23 | 2021-04-06 | 新绎健康科技有限公司 | Method and system for determining tongue color and coating color based on color space |
CN112613557A (en) * | 2020-12-23 | 2021-04-06 | 新绎健康科技有限公司 | Method and system for classifying tongue proper and tongue coating based on deep learning |
CN113160973A (en) * | 2021-04-15 | 2021-07-23 | 武汉未康未病医学有限公司 | Tongue observation App qi blood and body fluid mathematical model |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103745217A (en) * | 2013-12-31 | 2014-04-23 | 北京工业大学 | Automatic analysis method of tongue color and coating color in traditional Chinese medicine based on image retrieval |
CN104537379A (en) * | 2014-12-26 | 2015-04-22 | 上海大学 | High-precision automatic tongue partition method |
-
2018
- 2018-11-29 CN CN201811443339.3A patent/CN109598297A/en active Pending
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103745217A (en) * | 2013-12-31 | 2014-04-23 | 北京工业大学 | Automatic analysis method of tongue color and coating color in traditional Chinese medicine based on image retrieval |
CN104537379A (en) * | 2014-12-26 | 2015-04-22 | 上海大学 | High-precision automatic tongue partition method |
Non-Patent Citations (2)
Title |
---|
WEI LIU ET AL.: ""SSD: Single Shot MultiBox Detector"" * |
邹丰美 等: ""基于GVF-Snake模型的中医舌体分割"" * |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110929740A (en) * | 2019-11-21 | 2020-03-27 | 中电健康云科技有限公司 | LGBM model-based tongue quality and tongue coating separation method |
CN111209801A (en) * | 2019-12-24 | 2020-05-29 | 新绎健康科技有限公司 | Traditional Chinese medicine fat tongue identification method and device |
CN111192244A (en) * | 2019-12-25 | 2020-05-22 | 新绎健康科技有限公司 | Method and system for determining tongue characteristics based on key points |
CN111192244B (en) * | 2019-12-25 | 2023-09-29 | 新绎健康科技有限公司 | Method and system for determining tongue characteristics based on key points |
CN112614106A (en) * | 2020-12-23 | 2021-04-06 | 新绎健康科技有限公司 | Method and system for determining tongue color and coating color based on color space |
CN112613557A (en) * | 2020-12-23 | 2021-04-06 | 新绎健康科技有限公司 | Method and system for classifying tongue proper and tongue coating based on deep learning |
CN112613557B (en) * | 2020-12-23 | 2023-03-24 | 新绎健康科技有限公司 | Method and system for classifying tongue proper and tongue coating based on deep learning |
CN113160973A (en) * | 2021-04-15 | 2021-07-23 | 武汉未康未病医学有限公司 | Tongue observation App qi blood and body fluid mathematical model |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109598297A (en) | A kind of tongue fur tongue analysis method, system, computer equipment and storage medium | |
Plissiti et al. | Sipakmed: A new dataset for feature and image based classification of normal and pathological cervical cells in pap smear images | |
US10943346B2 (en) | Multi-sample whole slide image processing in digital pathology via multi-resolution registration and machine learning | |
US9741137B2 (en) | Image-based color palette generation | |
US9245350B1 (en) | Image-based color palette generation | |
Chan et al. | Texture-map-based branch-collaborative network for oral cancer detection | |
Liu | Stbi-yolo: A real-time object detection method for lung nodule recognition | |
CN106097354B (en) | A kind of hand images dividing method of combining adaptive Gauss Face Detection and region growing | |
CN109272513B (en) | Depth camera-based hand and object interactive segmentation method and device | |
Lu et al. | Robust 3D organ localization with dual learning architectures and fusion | |
Chang et al. | Automatic cardiac MRI segmentation and permutation-invariant pathology classification using deep neural networks and point clouds | |
WO2021076605A1 (en) | Weakly supervised multi-task learning for cell detection and segmentation | |
CN111681247B (en) | Lung lobe lung segment segmentation model training method and device | |
CN112102332A (en) | Cancer WSI segmentation method based on local classification neural network | |
CN115965607A (en) | Intelligent traditional Chinese medicine tongue diagnosis auxiliary analysis system | |
CN110648336B (en) | Method and device for dividing tongue texture and tongue coating | |
CN106600524A (en) | Image processing method and terminal | |
US20240054639A1 (en) | Quantification of conditions on biomedical images across staining modalities using a multi-task deep learning framework | |
Li et al. | Region focus network for joint optic disc and cup segmentation | |
Banerjee et al. | A CADe system for gliomas in brain MRI using convolutional neural networks | |
Li et al. | Research on data analysis network of TCM tongue diagnosis based on deep learning technology | |
CN112560911A (en) | Tongue image classification method and system in traditional Chinese medicine | |
CN109635866B (en) | Method of processing an intestinal image | |
CN113538398B (en) | Tongue fur classification method, device, equipment and medium based on feature matching | |
CN110020673A (en) | A kind of method of HSV color space color identification and noise filtering |
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 |