CN116128814A - Standardized acquisition method and related device for tongue diagnosis image - Google Patents
Standardized acquisition method and related device for tongue diagnosis image Download PDFInfo
- Publication number
- CN116128814A CN116128814A CN202211640992.5A CN202211640992A CN116128814A CN 116128814 A CN116128814 A CN 116128814A CN 202211640992 A CN202211640992 A CN 202211640992A CN 116128814 A CN116128814 A CN 116128814A
- Authority
- CN
- China
- Prior art keywords
- tongue
- image
- matching value
- acquisition
- diagnosis
- 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
- 238000003745 diagnosis Methods 0.000 title claims abstract description 70
- 238000000034 method Methods 0.000 title claims abstract description 47
- 238000004364 calculation method Methods 0.000 claims description 13
- 238000000605 extraction Methods 0.000 claims description 9
- 238000009499 grossing Methods 0.000 claims description 5
- 210000002105 tongue Anatomy 0.000 description 286
- 230000008569 process Effects 0.000 description 13
- 239000011248 coating agent Substances 0.000 description 9
- 238000000576 coating method Methods 0.000 description 9
- 238000004458 analytical method Methods 0.000 description 4
- 238000001514 detection method Methods 0.000 description 4
- 238000001914 filtration Methods 0.000 description 4
- 238000004422 calculation algorithm Methods 0.000 description 3
- 238000004590 computer program Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000007781 pre-processing Methods 0.000 description 3
- 230000009466 transformation Effects 0.000 description 3
- 239000003086 colorant Substances 0.000 description 2
- 210000003205 muscle Anatomy 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 208000024891 symptom Diseases 0.000 description 2
- 208000035126 Facies Diseases 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 239000012141 concentrate Substances 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000001815 facial effect Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000012925 reference material Substances 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 210000005181 root of the tongue Anatomy 0.000 description 1
- 210000000697 sensory organ Anatomy 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000003746 surface roughness Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
- G06T7/0014—Biomedical image inspection using an image reference approach
-
- G06T5/70—
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H30/00—ICT specially adapted for the handling or processing of medical images
- G16H30/20—ICT specially adapted for the handling or processing of medical images for handling medical images, e.g. DICOM, HL7 or PACS
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
Abstract
The application relates to a standardized acquisition method and a related device of tongue diagnosis images, wherein the method comprises the following steps: acquiring continuous multi-frame tongue diagnosis acquisition images; responding to the acquired tongue diagnosis acquisition image, analyzing the tongue diagnosis acquisition image, and determining that the image comprises a mouth and a tongue; extracting and analyzing the tongue diagnosis acquisition image, and extracting a plurality of mouth characteristic areas and tongue characteristic areas; analyzing each mouth characteristic region and each tongue characteristic region to obtain a corresponding tongue characteristic model; and obtaining a plurality of model parameters based on the tongue characteristic model, obtaining a matching value based on model parameter operation, and determining a tongue diagnosis image determination result based on the matching value. The tongue diagnosis method has the advantages of being convenient for patients to quickly provide standard tongue diagnosis images and improving tongue diagnosis efficiency.
Description
Technical Field
The application relates to the field of image detection, in particular to a standardized acquisition method and a related device for tongue diagnosis images.
Background
With the advent of the medical automation age, online pharmacy and hospitals gradually open the functions of automatic consultation, automatic prescription and the like. For example, by carrying out image acquisition and feature recognition on the facial facies of a person, the associated symptoms possibly related to the patient can be primarily judged.
The features of the face are mainly concentrated in the five sense organs, are located on the skin, are uniformly distributed on the whole, and have small adjacent feature interference, so that the image acquisition of the face is mature at present. However, for tongue diagnosis, the tongue features include tongue shape, tongue length, tongue width, tongue thickness, color, surface roughness, tongue coating distribution, tongue coating shape, tongue coating color, etc., and various features are concentrated on small tongue heads, so that standardized acquisition of tongue images is particularly important.
In the actual operation process, some patients find that the tongue is involuntarily rolled, the tongue is too short to spit out, the left and right sides are inclined or the surface of the tongue is not facing the lens, so that the posture adjustment is required to be continuously carried out so as to achieve the standard posture. However, since the tongue is relatively small and concentrates various features, it is difficult for a patient to adhere to the tongue to maintain the same shape and then take a picture at the time of image acquisition, and if the image acquired by the tongue is not standard, it is difficult to match with standard templates in a database at a later stage for feature recognition.
Disclosure of Invention
In order to facilitate a patient to quickly provide standard tongue diagnosis images and improve tongue diagnosis efficiency, the application provides a standardized acquisition method and a related device of tongue diagnosis images.
In a first aspect, the present application provides a standardized acquisition method for tongue diagnosis images, which adopts the following technical scheme:
a standardized acquisition method of tongue diagnosis images comprises the following steps:
image acquisition is carried out in real time to obtain continuous multi-frame tongue diagnosis acquisition images;
responding to the acquired tongue diagnosis acquisition image, analyzing the tongue diagnosis acquisition image, and determining that the image comprises a mouth and a tongue;
extracting and analyzing the tongue diagnosis acquisition image, and extracting a plurality of mouth characteristic areas and tongue characteristic areas;
analyzing each mouth characteristic region and each tongue characteristic region to obtain a corresponding tongue characteristic model;
and obtaining a plurality of model parameters based on the tongue characteristic model, obtaining a matching value based on model parameter operation, and determining a tongue diagnosis image determination result based on the matching value.
By adopting the technical scheme, real-time image acquisition is carried out, and continuous multi-frame pictures are obtained, so that when a patient adjusts for many times according to requirements, tongue diagnosis images meeting requirements can be obtained in the tongue change process. And analyzing the tongue diagnosis image to obtain a mouth and a tongue in the tongue diagnosis acquisition image. The mouth is used for establishing a standard coordinate system to provide a reference for the position of the tongue, so that a tongue characteristic model based on the mouth reference is obtained. Compared with the scheme that the tongue is based on the self-established reference, the scheme can be compatible with the differences generated by different tongue shapes, and meanwhile the standardization degree is improved. Based on a plurality of model parameters obtained in the tongue characteristic model, different indexes can be respectively matched, and each matching value is synthesized to calculate whether the tongue diagnosis acquisition image meets the standard. In summary, by the standardized acquisition method of the tongue diagnosis image, standardized input of the tongue diagnosis image can be conveniently and rapidly carried out, standard tongue diagnosis images can be conveniently and rapidly provided by patients, and tongue diagnosis efficiency is improved.
Optionally, the step of extracting and analyzing the tongue diagnosis acquisition image to extract a plurality of mouth feature areas and tongue feature areas includes:
acquiring a plurality of preset mouth recognition models and tongue recognition models;
and obtaining a mouth characteristic region and a tongue characteristic region based on a preset mouth recognition model, wherein the mouth characteristic region distinguishes an upper lip from a lower lip.
By adopting the technical scheme, the characteristic region is selected on the tongue diagnosis acquisition image by using the preset recognition characteristic model, for example, the preset mouth recognition model has the characteristics of teeth, lips and the like, the preset tongue recognition characteristic model has the characteristics of tongue tips, tongue edges, tongue middle parts, tongue roots or other parts and the like, for example, the tongue middle parts and the tongue roots have the characteristics of tongue surface concave-convex, tongue coating colors, tongue coating distribution, tongue coating shapes and the like, and the tongue edges have the characteristics of tongue thickness and the like. Through the preset recognition feature models, comprehensive selection and judgment can be performed, so that the recognition capability of the mouth and the tongue is improved.
Optionally, the step of analyzing each mouth feature area and each tongue feature area to obtain a corresponding tongue feature model includes:
obtaining a longitudinal center axis based on the relative positions of the upper lip and the lower lip, wherein the upper lip and the lower lip are symmetrical based on the longitudinal center axis;
demarcating the tongue image into a left tongue image and a right tongue image based on a longitudinal medial axis;
and respectively carrying out edge extraction on the left tongue image and the right tongue image to obtain a tongue edge contour feature model.
By adopting the technical scheme, as the lips of most people are vertically symmetrical and laterally symmetrical, the characteristic points are picked up based on the relative positions of the upper lip and the lower lip according to the preset, and the longitudinal center axis is generated. Whereas standard tongue images of a person require symmetry, elongation, tongue facing the photographing lens. Therefore, the longitudinal center axis is taken as a reference to define the tongue image into the left tongue image and the right tongue image, and then the left tongue image and the right tongue image are respectively subjected to edge extraction, so that the identification, the matching and/or the judgment of the image characteristics can be conveniently carried out.
Optionally, the step of obtaining a plurality of model parameters based on the tongue feature model, obtaining a matching value based on the model parameter operation, and determining a tongue diagnosis image determination result based on the matching value includes:
smoothing the tongue image edge, calculating the curvature degree of the left tongue image edge and the right tongue image edge to judge tongue shape, and taking the curvature extremum of the tongue image edge as the tongue tip; among these, tongue shapes include conventional tongue shapes and split tongue shapes.
By adopting the technical scheme, the conventional tongue shape is provided with a single tongue tip, and the tongue shape is provided with double tongue tips, and the muscles of the tongue can respectively control the tongues at two sides to do unsynchronized movement. Therefore, the curvature extremum of the tongue image edge is taken as the tongue tip, the split tongue shape can be identified, and two tongue tips can be obtained. The smoothing process can greatly reduce noise caused by uneven tongue image edges.
Optionally, the step of obtaining a plurality of model parameters based on the tongue feature model, obtaining a matching value based on the model parameter operation, and determining a tongue diagnosis image determination result based on the matching value further includes:
calculating the symmetry degree of the left tongue image edge and the right tongue image edge to obtain a first matching value;
and calculating the length-width ratio of the left tongue image edge to the right tongue image edge to obtain a second matching value.
By adopting the technical scheme, the first matching value is used for representing the symmetry degree of the tongue, and the second matching value is used for representing the extension length of the tongue.
Optionally, the step of calculating the symmetry degree of the left tongue image edge and the right tongue image edge to obtain the first matching value includes:
collecting a plurality of calculation points along the longitudinal center axis, and respectively making vertical lines of the longitudinal center axis from the calculation points to the two sides until the left tongue image edge and the right tongue image edge;
calculating the length ratio of the vertical lines at two sides of the same calculation point, judging whether the ratio result falls within a preset threshold value interval, if so, taking the ratio result as a qualified point, otherwise, taking the ratio result as an unqualified point;
the ratio of the number of fit points to the number of non-fit points is calculated as a first matching value.
By adopting the technical scheme, when the actual symmetrical central axis of the tongue is coincident with the longitudinal central axis determined by the lip, the length ratio of the vertical lines on the two sides of the same calculation point can basically fall within a preset threshold value interval. Since the human tongue is not absolutely symmetrical, by calculating the ratio of the fit points to the unfit points, the effect of a portion of the asymmetrical area can be eliminated.
Optionally, the step of calculating the aspect ratio of the left tongue image edge to the right tongue image edge to obtain the second matching value includes:
generating a reference axis parallel to the longitudinal central axis based on the position of the tongue tip;
collecting a plurality of reference points along a reference axis, and respectively making vertical lines from the reference points to two sides until the adjacent tongue image edge and a longitudinal center axis are reached;
and calculating the ratio of the sum of the vertical lines on two sides of the same reference point to the distance from the reference point to the corresponding tongue tip of the reference axis, and taking the ratio as a second matching value.
By adopting the technical scheme, after the tongue image is symmetrical, a reference axis which runs on the longitudinal center axis is generated based on the tongue tip, and for the conventional tongue shape, the reference axis is one, and for the tongue shape of the separated tongue, the reference axis is two. The second matching values calculated for the conventional tongue shape and the split tongue shape are different in corresponding judging ranges, the second matching value calculated for the conventional tongue shape is generally twice as large as the second matching value calculated for the split tongue shape, and the end point value of the matching range of the second matching value calculated for the conventional tongue shape is also twice as large as the end point value of the matching range of the second matching value calculated for the split tongue shape.
Optionally, the step of obtaining a plurality of model parameters based on the tongue feature model, obtaining a matching value based on the model parameter operation, and determining a tongue diagnosis image determination result based on the matching value includes:
and when each relevance value is larger than a corresponding preset threshold value or the relevance values are weighted and calculated to be larger than the preset threshold value, determining the image as a standardized tongue diagnosis image.
By adopting the technical scheme, whether the first matching value is larger than a first preset threshold value is judged, and if yes, the left tongue image and the right tongue image are symmetrical. And meanwhile, judging whether the ratio is smaller than a second preset threshold value, and if so, judging the length standard of the tongue characteristic model of the tongue image.
In a second aspect, the present application provides an electronic device, which adopts the following technical scheme:
an electronic device, comprising:
one or more processors;
a memory;
one or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the one or more processors, the one or more applications configured to:
the standardized acquisition method of the tongue diagnosis image is executed.
In a third aspect, the present application provides a computer readable storage medium, which adopts the following technical scheme:
a computer readable storage medium storing a computer program capable of being loaded by a processor and executing the method as described above.
The storage medium stores at least one instruction, at least one program, a set of codes, or a set of instructions that are loaded and executed by the processor to implement:
the standardized acquisition method of the tongue diagnosis image is as above.
Drawings
Fig. 1 is a flowchart of a standardized acquisition method of tongue diagnosis images in an embodiment of the present application.
Fig. 2 is a schematic flow chart of the step S3 in the embodiment of the present application.
Fig. 3 is a schematic flow chart of the step S4 in the embodiment of the present application.
Fig. 4 is a schematic flow chart of the step S52 in the embodiment of the present application.
Fig. 5 is a schematic flow chart of the step S53 in the embodiment of the present application.
Detailed Description
The present application is described in further detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application.
Fig. 1 is a flowchart of a standardized acquisition method of tongue diagnosis images in an embodiment. It should be understood that, although the steps in the flowcharts of fig. 1-5 are shown in order as indicated by the arrows, these steps are not necessarily performed in order as indicated by the arrows; the steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders; and at least some of the steps in fig. 1-5 may include multiple sub-steps or stages that are not necessarily performed at the same time, but may be performed at different times, nor do the order in which the sub-steps or stages are performed necessarily performed in sequence, but may be performed alternately or alternately with at least a portion of the sub-steps or stages of other steps or other steps.
In addition, the reference numerals of the steps in the embodiment are only for convenience of description, and do not represent limitation of the execution sequence of the steps, and the execution sequence of the steps may be adjusted or simultaneously performed according to the needs in practical application, and these adjustments or substitutions are all within the protection scope of the present invention.
In the following description, for purposes of explanation, numerous specific details are set forth in order to provide a thorough understanding of the inventive concepts. As part of this specification, some of the drawings of the present disclosure represent structures and devices in block diagram form in order to avoid obscuring the principles of the disclosure. In the interest of clarity, not all features of an actual implementation are necessarily described. Furthermore, the language used in the present disclosure has been principally selected for readability and instructional purposes, and may not have been selected to delineate or circumscribe the inventive subject matter, resort to the requisite claims to determine such inventive subject matter. Reference in the present disclosure to "one embodiment" or "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment, and multiple references to "one embodiment" or "an embodiment" should not be understood as necessarily all referring to the same embodiment.
The terms "a," "an," and "the" are not intended to refer to a singular entity, but rather include the general class of which a particular example may be used for illustration, unless clearly defined. Thus, the use of the terms "a" or "an" may mean any number of at least one, including "one", "one or more", "at least one", and "one or more than one". The term "or" means any of the alternatives and any combination of alternatives, including all alternatives, unless alternatives are explicitly indicated as mutually exclusive. The phrase "at least one of" when combined with a list of items refers to a single item in the list or any combination of items in the list. The phrase does not require all of the listed items unless specifically so defined.
The tongue diagnosis image recognition mainly comprises five stages of tongue diagnosis image acquisition, tongue image detection, image preprocessing, feature extraction, feature matching and recognition, and first, the five stages are briefly introduced.
Tongue diagnosis image acquisition is to acquire tongue images through a camera lens, for example, when a user is in the shooting range of the camera lens, the camera lens can record face images with tongues.
The tongue image detection is mainly used for preprocessing tongue image recognition, namely accurately calibrating the position and the size of the tongue in an image and extracting the needed information.
The image preprocessing has the functions of performing light compensation, gray level transformation, histogram equalization, normalization, geometric correction, filtering, noise filtering, sharpening and the like on the image, and is a process of processing the image based on the tongue image detection result and finally serving for feature extraction.
Image feature extraction, also called tongue characterization, is a process of modeling tongue features, and aims to extract features (such as visual features, pixel statistics features, tongue image transformation coefficient features, tongue image algebraic features and the like) usable by a tongue recognition system, so as to provide a sufficient amount of reference data for subsequent matching and recognition.
The matching and identification are that the characteristic data of the extracted tongue image and the characteristic templates stored in the database are searched and matched, and when the similarity exceeds the threshold value, the result obtained by matching is output; tongue recognition is to compare the tongue features to be recognized with the obtained tongue feature templates, and judge the shape of the tongue according to the similarity degree so as to be matched with related symptoms.
In the whole identification process, the precondition is that the collected tongue image is required to be standardized, otherwise misdiagnosis is easy to occur.
The embodiment of the application discloses a standardized acquisition method of tongue diagnosis images. Referring to fig. 1, the standardized acquisition method of the tongue diagnosis image comprises the following steps:
s1, acquiring continuous multi-frame tongue diagnosis acquisition images.
In this step, the computer acquires a continuous multi-frame tongue diagnosis acquisition image, and in different embodiments, the image may be acquired based on a pre-recorded video, where the image acquisition refers to frame extraction processing from the video according to a preset step size. In other embodiments, the image may be image captured based on obtaining video in real time.
S2, responding to the acquired tongue diagnosis acquisition image, analyzing the tongue diagnosis acquisition image, and determining that the image comprises a mouth and a tongue.
And the server or the intelligent terminal and the like can start to analyze the image in response to the acquired tongue diagnosis acquisition image, the analysis aims at determining whether tongue and mouth exist in the tongue diagnosis acquisition image, if the tongue and the mouth exist, the subsequent steps are continuously executed based on the frame of image, and if the tongue and the mouth do not exist, the next frame of image is processed until standardized acquisition is completed.
The analysis process mainly provides reference materials for subsequent comparison, so that in the analysis process, light compensation, gray level transformation, histogram equalization, normalization, geometric correction, filtering, noise filtering, sharpening and the like are required to be carried out on the image, and the purpose is to remove part of interference factors and facilitate the subsequent recognition process.
S3, extracting and analyzing the tongue diagnosis acquisition image, and extracting a plurality of mouth characteristic areas and tongue characteristic areas.
Optionally, S3 includes the following sub-steps:
s31, acquiring a plurality of preset mouth recognition models and tongue recognition models.
S32, obtaining a mouth characteristic region and a tongue characteristic region based on a preset mouth recognition model, wherein the mouth characteristic region is used for distinguishing an upper lip from a lower lip.
The characteristic region is selected on the acquired image by using a preset recognition characteristic model, for example, the preset mouth recognition model has the characteristics of teeth, lips and the like, the preset tongue recognition characteristic model has the characteristics of tongue tips, tongue edges, tongue middle parts, tongue roots or other parts and the like, for example, the tongue middle parts and the tongue roots have the characteristics of tongue surface concave-convex, tongue coating colors, tongue coating distribution, tongue coating shapes and the like, and the tongue edges have the characteristics of tongue thickness and the like. Through the preset recognition feature models, comprehensive selection and judgment can be performed, so that the recognition capability of the mouth and the tongue is improved.
When the preset recognition feature model is used, a fuzzy algorithm can be used as an algorithm for recognizing the feature region, and the basic processes of common fuzzy algorithms such as mean value fuzzy, gaussian fuzzy and the like are all to calculate a certain area around a pixel, accumulate certain feature values of related pixels and apply corresponding weights, and then obtain a result value.
S4, analyzing each mouth characteristic region and each tongue characteristic region to obtain a corresponding tongue characteristic model.
And analyzing the tongue diagnosis image to obtain a mouth and a tongue in the tongue diagnosis acquisition image. The mouth is used for establishing a standard coordinate system to provide a reference for the position of the tongue, so that a tongue characteristic model based on the mouth reference is obtained. Compared with the scheme that the tongue is based on the self-established reference, the scheme can be compatible with the differences generated by different tongue shapes, and meanwhile the standardization degree is improved. In the process of analysis, each characteristic region of the tongue, such as the tip, edge, middle and root of the tongue, is decomposed, and belongs to the portrait, but in the subsequent comparison process, the final recognition result is affected by the independent comparison.
Optionally, S4 includes the following sub-steps:
s41, obtaining a longitudinal center axis based on the relative positions of the upper lip and the lower lip, wherein the upper lip and the lower lip are symmetrical based on the longitudinal center axis.
S42, demarcating the tongue image into a left tongue image and a right tongue image based on a longitudinal center axis.
S43, respectively carrying out edge extraction on the left tongue image and the right tongue image to obtain a tongue edge contour feature model.
By adopting the technical scheme, as the lips of most people are vertically symmetrical and laterally symmetrical, the characteristic points are picked up based on the relative positions of the upper lip and the lower lip according to the preset, and the longitudinal center axis is generated. Whereas standard tongue images of a person require symmetry, elongation, tongue facing the photographing lens. Therefore, the longitudinal center axis is taken as a reference to define the tongue image into the left tongue image and the right tongue image, and then the left tongue image and the right tongue image are respectively subjected to edge extraction, so that the identification, the matching and/or the judgment of the image characteristics can be conveniently carried out.
S5, obtaining a plurality of model parameters based on the tongue characteristic model, obtaining a matching value based on model parameter operation, and determining a tongue diagnosis image determination result based on the matching value.
The model parameters refer to tongue shape, tongue length, tongue width, tongue thickness and other parameters, and whether the obtained tongue diagnosis image is standard can be judged by carrying out operation on the parameters.
Optionally, S5 includes the following sub-steps:
s51, carrying out tongue shape judgment on tongue image edge smoothing processing, calculating curvature degrees of the left tongue image edge and the right tongue image edge, and taking the curvature extremum of the tongue image edge as a tongue tip; among these, tongue shapes include conventional tongue shapes and split tongue shapes.
The conventional tongue shape is provided with a single tongue tip, and for the tongue shape of the tongue, the tongue shape is provided with double tongue tips, and the muscles of the tongue can respectively control the tongue on two sides to do asynchronous movement. Therefore, the curvature extremum of the tongue image edge is taken as the tongue tip, the split tongue shape can be identified, and two tongue tips can be obtained. The smoothing process can greatly reduce noise caused by uneven tongue image edges.
S52, calculating symmetry degrees of the left tongue image edge and the right tongue image edge to obtain a first matching value.
Optionally, S52 includes the steps of:
s521, collecting a plurality of calculation points along the longitudinal center axis, and respectively making vertical lines of the longitudinal center axis from the calculation points to the two sides until the left tongue image edge and the right tongue image edge.
When the actual symmetrical center axis of the tongue coincides with the longitudinal center axis determined by the lip, the length ratio of the perpendicular lines on both sides of the same calculation point basically falls within a preset threshold value interval. Since the human tongue is not absolutely symmetrical, it is necessary to detect the tongue width on both sides of the central axis.
S522, calculating the length ratio of the vertical lines on two sides of the same calculation point, judging whether the ratio result falls in a preset threshold value interval, if so, taking the ratio result as a qualified point, and otherwise, taking the ratio result as an unqualified point.
The predetermined threshold interval is an adaptive compensation for measurement errors and physiological errors, for example, the predetermined threshold interval is set (0.95,1.05). For the vertical lines on two sides of the same drop foot, when the ratio of the vertical lines is within a preset threshold value interval, the left tongue image and the right tongue image are symmetrical on two sides of the drop foot.
S523, calculating the number ratio of the fit points to the non-fit points as a first matching value.
Similarly, since the tongue of the person is not completely symmetrical, setting the non-fit point can eliminate the influence of a part of the asymmetrical area or the false recognition factor.
S53, calculating the length-width ratio of the left tongue image edge and the right tongue image edge to obtain a second matching value.
Optionally, S53 includes the following steps:
s531, generating a reference axis parallel to the longitudinal center axis based on the position of the tongue tip.
By adopting the technical scheme, after the tongue image is symmetrical, a reference axis which runs on the longitudinal center axis is generated based on the tongue tip, and for the conventional tongue shape, the reference axis is one, and for the tongue shape of the separated tongue, the reference axis is two.
S532, collecting a plurality of reference points along a reference axis, and respectively making vertical lines from the reference points to two sides until the adjacent tongue image edge and the longitudinal center axis.
In different embodiments, the calculation points may be acquired uniformly on the reference axis, or may be acquired according to the sparse-dense or the dense-dense. For different acquisition positions. The width of a human tongue is smallest at the tip and largest at the root, so that the width becomes gradually smaller in a direction approaching the tip along the reference axis.
S533, calculating the ratio of the sum of the vertical lines on the two sides of the same reference point to the distance from the reference point to the corresponding tongue tip of the reference axis, and taking the ratio as a second matching value.
The second matching values calculated for the conventional tongue shape and the split tongue shape are different in corresponding judging ranges, the second matching value calculated for the conventional tongue shape is generally twice as large as the second matching value calculated for the split tongue shape, and the end point value of the matching range of the second matching value calculated for the conventional tongue shape is also twice as large as the end point value of the matching range of the second matching value calculated for the split tongue shape. For example, the second match value required for a conventional tongue should be less than one half and the second match value required for a split tongue should be less than one quarter.
S54, determining the image as a standardized tongue diagnosis image when each relevance value is greater than a corresponding preset threshold value or the relevance values are weighted and calculated to be greater than the preset threshold value.
For example, in this step, it may be determined whether the first matching value is greater than a first preset threshold, if so, whether the left tongue image and the right tongue image are symmetrical is determined, and if so, whether the ratio is smaller than a second preset threshold is determined, and if so, the length standard of the tongue feature model of the tongue image is determined, the image is determined to be a standardized tongue diagnosis image.
In addition, the method can also be performed by using a weighted calculation mode, for example, for the correlation degree between the first matching value and the preset threshold value, the second matching value and the preset threshold value are given different weights, then the two values are weighted and summed, whether the two values fall on one preset threshold value is judged, if yes, the image is determined to be a standardized tongue diagnosis image, and if not, the image is determined to be not the standardized tongue diagnosis image.
The embodiment of the application also discloses an electronic device, which comprises a memory and a processor, wherein the memory stores a computer program which can be loaded by the processor and execute the standardized acquisition method of the tongue diagnosis image. The execution main body of the method of the embodiment may be a control device, the control device is arranged on an electronic device, the current device may be an electronic device such as a mobile phone, a tablet computer, a notebook computer and the like with a WIFI function, and the execution main body of the method of the embodiment may also be a CPU (central processing unit ) of the electronic device directly.
The embodiment of the application also discloses a computer readable storage medium which stores a computer program capable of being loaded by a processor and executing the standardized acquisition method of the tongue diagnosis image. From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a storage medium (e.g. ROM/RAM, magnetic disk, optical disk) as above, including several instructions for causing a device (which may be a mobile phone, a computer, a server, a controlled terminal, or a network device, etc.) to perform the method of each embodiment of the present application.
The foregoing are all preferred embodiments of the present application, and are not intended to limit the scope of the present application in any way, therefore: all equivalent changes in structure, shape and principle of this application should be covered in the protection scope of this application.
Claims (10)
1. The standardized acquisition method of the tongue diagnosis image is characterized by comprising the following steps of:
acquiring continuous multi-frame tongue diagnosis acquisition images;
responding to the acquired tongue diagnosis acquisition image, analyzing the tongue diagnosis acquisition image, and determining that the image comprises a mouth and a tongue;
extracting and analyzing the tongue diagnosis acquisition image, and extracting a plurality of mouth characteristic areas and tongue characteristic areas;
analyzing each mouth characteristic region and each tongue characteristic region to obtain a corresponding tongue characteristic model;
and obtaining a plurality of model parameters based on the tongue characteristic model, obtaining a matching value based on model parameter operation, and determining a tongue diagnosis image determination result based on the matching value.
2. The standardized collection method of tongue diagnostic images according to claim 1, wherein the step of extracting and analyzing the tongue diagnostic collected images to extract a plurality of mouth feature areas and tongue feature areas comprises:
acquiring a plurality of preset mouth recognition models and tongue recognition models;
and obtaining a mouth characteristic region and a tongue characteristic region based on a preset mouth recognition model, wherein the mouth characteristic region distinguishes an upper lip from a lower lip.
3. The method for standardized acquisition of tongue diagnostic images according to claim 2, wherein the step of analyzing each mouth feature region and each tongue feature region to obtain a corresponding tongue feature model comprises:
obtaining a longitudinal center axis based on the relative positions of the upper lip and the lower lip, wherein the upper lip and the lower lip are symmetrical based on the longitudinal center axis;
demarcating the tongue image into a left tongue image and a right tongue image based on a longitudinal medial axis;
and respectively carrying out edge extraction on the left tongue image and the right tongue image to obtain a tongue edge contour feature model.
4. The method for standardized acquisition of tongue diagnostic images according to claim 3, wherein the step of obtaining a plurality of model parameters based on the tongue feature model, obtaining a matching value based on the model parameter operation, and determining a tongue diagnostic image determination result based on the matching value comprises:
smoothing the tongue image edge, calculating the curvature degree of the left tongue image edge and the right tongue image edge to judge tongue shape, and taking the curvature extremum of the tongue image edge as the tongue tip; among these, tongue shapes include conventional tongue shapes and split tongue shapes.
5. The method for standardized acquisition of tongue diagnostic images according to claim 4, wherein the step of obtaining a plurality of model parameters based on the tongue feature model, obtaining a matching value based on the model parameter operation, and determining a tongue diagnostic image determination result based on the matching value further comprises:
calculating the symmetry degree of the left tongue image edge and the right tongue image edge to obtain a first matching value;
and calculating the length-width ratio of the left tongue image edge to the right tongue image edge to obtain a second matching value.
6. The method for standardized acquisition of tongue diagnostic images according to claim 5, wherein the step of calculating the degree of symmetry between the left tongue image edge and the right tongue image edge to obtain the first matching value comprises:
collecting a plurality of calculation points along the longitudinal center axis, and respectively making vertical lines of the longitudinal center axis from the calculation points to the two sides until the left tongue image edge and the right tongue image edge;
calculating the length ratio of the vertical lines at two sides of the same calculation point, judging whether the ratio result falls within a preset threshold value interval, if so, taking the ratio result as a qualified point, otherwise, taking the ratio result as an unqualified point;
the ratio of the number of fit points to the number of non-fit points is calculated as a first matching value.
7. The method for standardized acquisition of tongue diagnostic images of claim 5, wherein the step of calculating the aspect ratio of the left tongue image edge to the right tongue image edge to obtain the second matching value comprises:
generating a reference axis parallel to the longitudinal central axis based on the position of the tongue tip;
collecting a plurality of reference points along a reference axis, and respectively making vertical lines from the reference points to two sides until the adjacent tongue image edge and a longitudinal center axis are reached;
and calculating the ratio of the sum of the vertical lines on two sides of the same reference point to the distance from the reference point to the corresponding tongue tip of the reference axis, and taking the ratio as a second matching value.
8. The method for standardized acquisition of tongue diagnostic images according to claim 4, wherein the step of obtaining a plurality of model parameters based on the tongue feature model, obtaining a matching value based on the model parameter operation, and determining a tongue diagnostic image determination result based on the matching value comprises:
and when each relevance value is larger than a corresponding preset threshold value or the relevance values are weighted and calculated to be larger than the preset threshold value, determining the image as a standardized tongue diagnosis image.
9. An electronic device, comprising:
one or more processors;
a memory;
one or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the one or more processors, the one or more applications configured to:
a standardized acquisition method of a tongue diagnostic image according to any of the claims 1 to 8 is performed.
10. A computer-readable storage medium storing at least one instruction, at least one program, code set, or instruction set, the at least one instruction, the at least one program, the code set, or instruction set being loaded and executed by the processor to implement:
a method of standardized acquisition of lingual images according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211640992.5A CN116128814A (en) | 2022-12-20 | 2022-12-20 | Standardized acquisition method and related device for tongue diagnosis image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211640992.5A CN116128814A (en) | 2022-12-20 | 2022-12-20 | Standardized acquisition method and related device for tongue diagnosis image |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116128814A true CN116128814A (en) | 2023-05-16 |
Family
ID=86293842
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211640992.5A Pending CN116128814A (en) | 2022-12-20 | 2022-12-20 | Standardized acquisition method and related device for tongue diagnosis image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116128814A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116646062A (en) * | 2023-06-08 | 2023-08-25 | 南京大经中医药信息技术有限公司 | Intelligent auxiliary analysis system for traditional Chinese medicine tongue diagnosis instrument |
| CN117522865A (en) * | 2024-01-03 | 2024-02-06 | 长春中医药大学 | Traditional Chinese medicine health monitoring system based on image recognition technology |
-
2022
- 2022-12-20 CN CN202211640992.5A patent/CN116128814A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116646062A (en) * | 2023-06-08 | 2023-08-25 | 南京大经中医药信息技术有限公司 | Intelligent auxiliary analysis system for traditional Chinese medicine tongue diagnosis instrument |
| CN116646062B (en) * | 2023-06-08 | 2023-12-22 | 南京大经中医药信息技术有限公司 | Intelligent auxiliary analysis system for traditional Chinese medicine tongue diagnosis instrument |
| CN117522865A (en) * | 2024-01-03 | 2024-02-06 | 长春中医药大学 | Traditional Chinese medicine health monitoring system based on image recognition technology |
| CN117522865B (en) * | 2024-01-03 | 2024-03-22 | 长春中医药大学 | Traditional Chinese medicine health monitoring system based on image recognition technology |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116128814A (en) | Standardized acquisition method and related device for tongue diagnosis image | |
| US9317761B2 (en) | Method and an apparatus for determining vein patterns from a colour image | |
| CN107766819B (en) | Video monitoring system and real-time gait recognition method thereof | |
| Datcu et al. | Noncontact automatic heart rate analysis in visible spectrum by specific face regions | |
| CN110930374A (en) | Acupoint positioning method based on double-depth camera | |
| US20120157800A1 (en) | Dermatology imaging device and method | |
| US20220036058A1 (en) | Method and Apparatus for Privacy Protected Assessment of Movement Disorder Video Recordings | |
| CN109215763A (en) | A kind of emotional health monitoring method and system based on facial image | |
| CN109934118A (en) | A kind of hand back vein personal identification method | |
| CN111829661A (en) | Forehead temperature measurement method and system based on face analysis | |
| CN112069986A (en) | Machine vision tracking method and device for eye movements of old people | |
| CN111310798B (en) | Method for constructing facial bradykinesia detection model based on geometric features and texture features | |
| CN114894337A (en) | Temperature measurement method and device for outdoor face recognition | |
| JP2005250712A (en) | Figure attribute identification method and its system | |
| JPH11161791A (en) | Individual identification device | |
| CN111862118B (en) | Pressure sore staging training method, staging method and staging system | |
| CN108921010A (en) | A kind of pupil detection method and detection device | |
| CN112382390A (en) | Method, system and storage medium for generating health assessment report | |
| CN110321781B (en) | Signal processing method and device for non-contact measurement | |
| CN116092157A (en) | Intelligent facial tongue diagnosis method, system and intelligent equipment | |
| CN116030503A (en) | Gate control system and method based on palm vein technology | |
| CN115147769A (en) | Physiological parameter robustness detection method based on infrared video | |
| Mercan et al. | The use of pseudo-landmarks for craniofacial analysis: A comparative study with l 1-regularized logistic regression | |
| CN113570545A (en) | Visual identification pain grading assessment method | |
| CN112329640A (en) | Facial nerve palsy disease rehabilitation detection system based on eye muscle movement analysis |
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 |