CN106557746A - A kind of tongue based on image recognition technology is as detection method and system - Google Patents
A kind of tongue based on image recognition technology is as detection method and system Download PDFInfo
- Publication number
- CN106557746A CN106557746A CN201611003430.4A CN201611003430A CN106557746A CN 106557746 A CN106557746 A CN 106557746A CN 201611003430 A CN201611003430 A CN 201611003430A CN 106557746 A CN106557746 A CN 106557746A
- Authority
- CN
- China
- Prior art keywords
- tongue
- view data
- default
- data
- image
- 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
- Image Analysis (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The present invention relates to medical instruments field, more particularly to a kind of tongue based on image recognition technology is as detection method and system, including S1, the first tongue view data of collection;S2, the first tongue view data to collecting carry out operation process;S3, the 3rd tongue view data and the tongue view data in default tongue image data base are contrasted one by one, calculated the similarity of the tongue view data in the 3rd tongue view data and default tongue image data base respectively;With the 4th tongue view data of the 3rd tongue view data similarity highest in S4, the acquisition tongue image data base, the corresponding tongue of the 4th tongue view data is obtained as examining report.Processed as the preliminary qualified criterion of tongue view data, then second operation through scratching picture and color correction by tongue length in time data, the illumination value of surrounding and tongue view data, improve the accuracy of successive image analysis contrast.
Description
Technical field
The present invention relates to medical instruments field, more particularly to a kind of tongue based on image recognition technology is as detection method and is
System.
Background technology
Show according to investigations, doctor (is primarily referred to as tongue color, tongue fur color, tongue fur by the tongue feature for checking patient
The feature such as thickness, tongue fur size, ecchymosis or impression feature, tongue side shape) can determine whether out patient basic body constitution attribute and
Some common patient's condition, such as dyspepsia, get angry, deficiency of kidney-QI, and dampness is again etc..Meanwhile, found according to long-term medical diagnosiss, tongue
There is incidence relation with human body viscera in head, so as to pass through to detect the color and texture of tongue, detect cardiopulmonary, taste, liver and gall,
The index of kidney, bladder.Existing inspection of the tongue quasi-instrument is mainly divided to two classes:One class, (needs by a period of time by special instrument
Professional operation training can just be operated) image is passed to computer end, doctor according to the image on computer draw basic body constitution judge and
The condition-inference of main organs.But diagnosis link still must rely on the doctor of specialty, range of application to be also limited to hospital, examine
Narrow range in.It is another kind of, by loaded down with trivial details questionnaire mode (generally requiring answer problem more than 60), so as to draw base
This body constitution judges that, as the attainment height of the subjective factorss and answer object basic medical knowledge of answer differs, its result is past
It is accurate toward being difficult to, and process is excessively loaded down with trivial details very long, and also this kind of mode for answering a questionnaire also cannot be to the feelings of patient's main organs
Condition is judged substantially.
There is presently no a kind of inspection of the tongue mode that simple to operate, process is brief, judgement is intelligent.
The content of the invention
The technical problem to be solved is:There is provided a kind of accuracy of detection the high tongue picture based on image recognition technology
Detection method and system.
In order to solve above-mentioned technical problem, the technical solution used in the present invention is:
A kind of tongue based on image recognition technology comprises the steps as detection method:
S1, the first tongue view data of collection, specifically include step:
S11, the real-time time data of acquisition, if the time data for getting is in the range of default time threshold, enter
Step S12;
S12, the illumination value for obtaining surrounding, if the illumination value for getting is in default illumination threshold range, enter
Step S13;
S13, acquisition tongue view data, in judging the tongue view data, whether tongue length is more than default tongue
Length threshold scope, if, it is determined that the tongue view data is used as the first qualified tongue view data;
S2, the first tongue view data to collecting are processed, and specifically include step:
S21, scratch as the first tongue view data, obtain the second tongue view data;
Second tongue view data described in S22, color correction, obtains the 3rd tongue view data;
S3, the 3rd tongue view data and the tongue view data in default tongue image data base are carried out into one
One contrast, calculates tongue view data in the 3rd tongue view data and default tongue image data base respectively
Similarity;
With the 4th tongue image of the 3rd tongue view data similarity highest in S4, the acquisition tongue image data base
Data;
Judge the 3rd tongue view data to the similarity of the 4th tongue view data whether more than default similar
Degree threshold range, if so, obtains the corresponding tongue of the 4th tongue view data as examining report.
Another technical scheme for adopting of the present invention for:
A kind of tongue based on image recognition technology as detecting system, including:Acquisition module, processing module, contrast module and
Acquisition module;
The acquisition module includes first acquisition unit, second acquisition unit and determining unit;
The first acquisition unit, for obtaining time data, if the time data for getting is in default time threshold
In the range of, into second acquisition unit;
The second acquisition unit, for obtaining the illumination value of surrounding, if the illumination value for getting is in default light
According in threshold range, into determining unit;
The determining unit, for obtaining tongue view data, judges in the tongue view data tongue length whether
More than default tongue length threshold scope, if, it is determined that the tongue view data is used as the first qualified tongue image
Data;
The processing module includes scratching as unit and color correction unit;
The stingy picture unit, for scratching as the first tongue view data, obtains the second tongue view data;
The color correction unit, for the second tongue view data described in color correction, obtains the 3rd tongue view data;
The contrast module, for by the tongue in the 3rd tongue view data and default tongue image data base
View data is contrasted one by one, is calculated in the 3rd tongue view data and default tongue image data base respectively
The similarity of tongue view data;
The acquisition module, for obtain in the tongue image data base with the 3rd tongue view data similarity highest
The 4th tongue view data, judge whether the 3rd tongue view data and the similarity of the 4th tongue view data are more than
Default similarity threshold scope, if so, obtains the corresponding tongue of the 4th tongue view data as examining report.
The beneficial effects of the present invention is:
The tongue based on image recognition technology that the present invention is provided as detection method and system, by time data, around ring
In the illumination value and tongue view data in border, tongue length is used as the preliminary qualified criterion of tongue view data, so as to carry
The accuracy of high successive image analysis contrast.By scratching as the first tongue view data, only tongue is carried out scratching picture, with avoid by
Lip portion includes analysis, obtains the second tongue view data, in conjunction with color correction technology, will collect from different luminous environments
Second tongue view data carries out colour correction, processes through second operation, can more improve the standard of successive image analysis contrast
True property.By contrast operation, with the 3rd tongue view data similarity highest the 4th in the acquisition tongue image data base
Tongue view data, and when the 3rd tongue view data is more than default similarity with the similarity of the 4th tongue view data
During threshold range, the 4th tongue view data of confirmation is immediate view data, now obtains the 4th tongue picture number
According to corresponding tongue as examining report, can be with reference to technologies such as language or printings, by tongue as examining report feeds back to user, whole operation
Process intelligence degree is high, and accuracy of detection is high.
Description of the drawings
Fig. 1 is a kind of tongue based on image recognition technology of the invention flow chart as the step of detection method;
Fig. 2 is a kind of tongue based on image recognition technology of the present invention as the structural representation of detecting system;
Label declaration:
1st, acquisition module;2nd, processing module;3rd, contrast module;4th, acquisition module.
Specific embodiment
By describing the technology contents of the present invention in detail, realizing purpose and effect, below in conjunction with embodiment and coordinate attached
Figure is explained.
The design of most critical of the present invention is:By time data, the illumination value of surrounding and tongue view data
Middle tongue length is used as the preliminary qualified criterion of tongue view data, then passes through at second operation for scratching picture and color correction
Reason, improves the accuracy of successive image analysis contrast.
Refer to Fig. 1 and Fig. 2, a kind of tongue based on image recognition technology that the present invention is provided as detection method, including
Following steps:
S1, the first tongue view data of collection, specifically include step:
S11, the real-time time data of acquisition, if the time data for getting is in the range of default time threshold, enter
Step S12;
S12, the illumination value for obtaining surrounding, if the illumination value for getting is in default illumination threshold range, enter
Step S13;
S13, acquisition tongue view data, in judging the tongue view data, whether tongue length is more than default tongue
Length threshold scope, if, it is determined that the tongue view data is used as the first qualified tongue view data;
S2, the first tongue view data to collecting are processed, and specifically include step:
S21, scratch as the first tongue view data, obtain the second tongue view data;
Second tongue view data described in S22, color correction, obtains the 3rd tongue view data;
S3, the 3rd tongue view data and the tongue view data in default tongue image data base are carried out into one
One contrast, calculates tongue view data in the 3rd tongue view data and default tongue image data base respectively
Similarity;
With the 4th tongue image of the 3rd tongue view data similarity highest in S4, the acquisition tongue image data base
Data;
Judge the 3rd tongue view data to the similarity of the 4th tongue view data whether more than default similar
Degree threshold range, if so, obtains the corresponding tongue of the 4th tongue view data as examining report.
Knowable to foregoing description, the beneficial effects of the present invention is:The tongue based on image recognition technology that the present invention is provided
As detection method, tongue figure is used as by tongue length in time data, the illumination value of surrounding and tongue view data
As the preliminary qualified criterion of data, so as to improve the accuracy of successive image analysis contrast.By scratching as the first tongue figure
As data, only tongue is carried out scratching picture, to avoid for lip portion including analysis, obtain the second tongue view data, in conjunction with
The the second tongue view data collected from different luminous environments is carried out colour correction by color correction technology, is operated through second
Process, can more improve the accuracy of successive image analysis contrast.By contrast operation, obtain in the tongue image data base with
The 4th tongue view data of 3rd tongue view data similarity highest, and when the 3rd tongue view data and the 4th tongue
When the similarity of view data is more than default similarity threshold scope, the 4th tongue view data of confirmation is immediate image
Data, now obtain the corresponding tongue of the 4th tongue view data as examining report, can be with reference to technologies such as language or printings, will
Tongue feeds back to user as examining report, and whole operation process intelligence degree is high, and accuracy of detection is high.
Further, step S13 is specially:
Obtain containing tongued view data;
Scratch as described containing tongued view data, obtain tongue view data;
The tongue view data is calculated with the ratio value containing tongued view data;
If the ratio value is more than default ratio value threshold range, the tongue being calculated in the tongue view data
Length;
Judge whether the tongue length in the tongue view data is more than default tongue length threshold scope, if so,
Then determine the tongue view data as the first qualified tongue view data.
Seen from the above description, the tongue view data that above-mentioned stingy picture is obtained refers to the only view data comprising tongue, with
Avoid for lip portion including analysis.By calculating the tongue view data and the ratio containing tongued view data
Whether value, and the tongue length in the calculated tongue view data, comprehensive descision tongue extension elongation are enough, if not
It is enough, (specially user is close to too or too remote) can be adjusted by voice message user such that it is able to get effective tongue figure
As data.
Further, step S13 also includes:
Judge in the tongue view data, to whether there is off-note point, if so, return to step S11.
Seen from the above description, by judging to whether there is off-note point in the tongue view data, it can be determined that
The materials such as whether foreign body on user's tongue, such as chewing gum or stain, if there is off-note point, return and reacquire tongue
Head view data.Wherein the determination methods of off-note point can be judged by rate of gray level.
Further, step S3 is specially:
The 3rd tongue view data and the tongue view data in default tongue image data base are carried out into Lab face
The colour space, color concentration degree, border color, edge shape, tongue fur impression, tongue fur color, tongue fur area, thickness of the tongue coating and tongue
Thickness is contrasted one by one, calculates the tongue image in the 3rd tongue view data and default tongue image data base respectively
The similarity of data.
Seen from the above description, by Lab color spaces, color concentration degree, border color, edge shape, tongue fur impression,
Tongue fur color, tongue fur area, thickness of the tongue coating and tongue thickness are contrasted one by one, can improve the accuracy of detection.
Refer to Fig. 2, a kind of tongue based on image recognition technology that the present invention is also provided as detecting system, including:Collection
Module 1, processing module 2, contrast module 3 and acquisition module 4;
The acquisition module 1 includes first acquisition unit, second acquisition unit and determining unit;
The first acquisition unit, for obtaining time data, if the time data for getting is in default time threshold
In the range of, into second acquisition unit;
The second acquisition unit, for obtaining the illumination value of surrounding, if the illumination value for getting is in default light
According in threshold range, into determining unit;
The determining unit, for obtaining tongue view data, judges in the tongue view data tongue length whether
More than default tongue length threshold scope, if, it is determined that the tongue view data is used as the first qualified tongue image
Data;
The processing module 2 includes scratching as unit and color correction unit;
The stingy picture unit, for scratching as the first tongue view data, obtains the second tongue view data;
The color correction unit, for the second tongue view data described in color correction, obtains the 3rd tongue view data;
The contrast module 3, for by the tongue in the 3rd tongue view data and default tongue image data base
Head view data is contrasted one by one, is calculated in the 3rd tongue view data and default tongue image data base respectively
Tongue view data similarity;
The acquisition module 4, for obtaining in the tongue image data base with the 3rd tongue view data similarity most
The 4th high tongue view data, judges whether the 3rd tongue view data is big with the similarity of the 4th tongue view data
In default similarity threshold scope, the corresponding tongue of the 4th tongue view data is if so, obtained as examining report.
Knowable to foregoing description, the beneficial effects of the present invention is:The tongue based on image recognition technology that the present invention is provided
As detecting system, tongue figure is used as by tongue length in time data, the illumination value of surrounding and tongue view data
As the preliminary qualified criterion of data, so as to improve the accuracy of successive image analysis contrast.By scratching as the first tongue figure
As data, only tongue is carried out scratching picture, to avoid for lip portion including analysis, obtain the second tongue view data, in conjunction with
The the second tongue view data collected from different luminous environments is carried out colour correction by color correction technology, is operated through second
Process, can more improve the accuracy of successive image analysis contrast.By contrast operation, obtain in the tongue image data base with
The 4th tongue view data of 3rd tongue view data similarity highest, and when the 3rd tongue view data and the 4th tongue
When the similarity of view data is more than default similarity threshold scope, the 4th tongue view data of confirmation is immediate image
Data, now obtain the corresponding tongue of the 4th tongue view data as examining report, can be with reference to technologies such as language or printings, will
Tongue feeds back to user as examining report, and whole operation process intelligence degree is high, and accuracy of detection is high.
Further, the determining unit, is additionally operable to obtain containing tongued view data;Scratch as described containing tongued
View data, obtains tongue view data;Calculate the tongue view data and the ratio containing tongued view data
Value;If the ratio value is more than default ratio value threshold range, the tongue length being calculated in the tongue view data;
Judge whether the tongue length in the tongue view data is more than default tongue length threshold scope, if, it is determined that institute
Tongue view data is stated as the first qualified tongue view data.
Seen from the above description, the tongue view data that above-mentioned stingy picture is obtained refers to the only view data comprising tongue, with
Avoid for lip portion including analysis.By calculating the tongue view data and the ratio containing tongued view data
Whether value, and the tongue length in the calculated tongue view data, comprehensive descision tongue extension elongation are enough, if not
It is enough, (specially user is close to too or too remote) can be adjusted by voice message user such that it is able to get effective tongue figure
As data.
Further, the determining unit, is additionally operable to judge with the presence or absence of off-note point in the tongue view data,
If so, return first acquisition unit.
Seen from the above description, by judging to whether there is off-note point in the tongue view data, it can be determined that
The materials such as whether foreign body on user's tongue, such as chewing gum or stain, if there is off-note point, return first and obtain single
Unit reacquires tongue view data.Wherein the determination methods of off-note point can be judged by rate of gray level.
Further, the contrast module, is additionally operable to the 3rd tongue view data and default tongue picture number
Lab color spaces, color concentration degree, border color, edge shape, tongue fur impression, tongue are carried out according to the tongue view data in storehouse
Coating colour coloured silk, tongue fur area, thickness of the tongue coating and tongue thickness are contrasted one by one, calculate respectively the 3rd tongue view data with it is pre-
If tongue image data base in tongue view data similarity.
Seen from the above description, by Lab color spaces, color concentration degree, border color, edge shape, tongue fur impression,
Tongue fur color, tongue fur area, thickness of the tongue coating and tongue thickness are contrasted one by one, can improve the accuracy of detection.
Fig. 1-2 is refer to, embodiments of the invention one are:
A kind of tongue based on image recognition technology that the present invention is provided comprises the steps as detection method:
S1, the first tongue view data of collection, specifically include step:
S11, the real-time time data of acquisition, if the time data for getting is in the range of default time threshold, enter
Step S12;
In the above-described embodiment, the time data is current time data, for example, at 10 points in the morning;It is wherein pre-
If time threshold scope be to arrive 12 noon or at 7 points in 2 pm to evening at 9 points in the morning, as limit user and arrive for 7 points at night
At 9 points in the morning and 12 noon do not carry out tongue picture acquisition within period 2 pm, according to clinical experience, at 9 points in the morning to noon
Tongue is obtained at 12 points in or 7 points of time periods of 2 pm to evening as data can improve accuracy rate.
S12, the illumination value for obtaining surrounding, if the illumination value for getting is in default illumination threshold range, enter
Step S13;
In the above-described embodiment, the illumination value for getting is the illumination value of the current surrounding for obtaining, as user
The illumination value of tongue surrounding, if illumination value is not in default illumination threshold range, returns S11, reacquires the time
Data, and illumination value is judged again, until illumination value is reached in default illumination threshold range, can just enter step S13.
S13, acquisition tongue view data, in judging the tongue view data, whether tongue length is more than default tongue
Length threshold scope, if, it is determined that the tongue view data is used as the first qualified tongue view data;The S13 tools
Body is:
Obtain containing tongued view data;
Scratch as described containing tongued view data, obtain tongue view data;
The tongue view data is calculated with the ratio value containing tongued view data;
If the ratio value is more than default ratio value threshold range, the tongue being calculated in the tongue view data
Length;
Judge whether the tongue length in the tongue view data is more than default tongue length threshold scope, if so,
Then determine the tongue view data as the first qualified tongue view data.
Wherein described S13 also includes:
Judge in the tongue view data, to whether there is off-note point, if so, return to step S11.
In the above-described embodiment, obtained containing tongued view data by photographic head, using picture technology is scratched, by tongue
Pluck out, obtain tongue view data, the tongue view data for obtaining refers to the only view data comprising tongue, to avoid lip
Include analysis in part.By image recognition technology, can calculate and scratch as the area of the only view data comprising tongue out,
Again with the areal calculation ratio value for not scratching picture view data before, as shared ratio.Wherein do not scratch as image before
The area of data can be obtained by the scanning area of photographic head.If the ratio value is more than default ratio value threshold range, i.e.,
When reaching requirement for ratio, the tongue length in the calculated tongue view data, comprehensive descision tongue extension elongation
It is whether enough, if not enough, (specially user is close to too or too remote) can be adjusted by voice message user such that it is able to got
The tongue view data of effect.
Also by judging to whether there is off-note point in the tongue view data on the basis of above-mentioned, it can be determined that
The materials such as whether foreign body on user's tongue, such as chewing gum or stain, if there is off-note point, return and reacquire tongue
Head view data.Wherein the determination methods of off-note point can be judged by rate of gray level.
S2, the first tongue view data to collecting are processed, and specifically include step:
S21, scratch as the first tongue view data, obtain the second tongue view data;Wherein only tongue is scratched
Picture, to avoid for lip portion including analysis;
Second tongue view data described in S22, color correction, obtains the 3rd tongue view data;With reference to color correction technology, will collection
Colour correction is carried out to the second tongue view data from different luminous environments, is processed through second operation, after more improving
The accuracy of continuous graphical analyses contrast.
S3, the 3rd tongue view data and the tongue view data in default tongue image data base are carried out into one
One contrast, calculates tongue view data in the 3rd tongue view data and default tongue image data base respectively
Similarity;The S3 is specially:
The 3rd tongue view data and the tongue view data in default tongue image data base are carried out into Lab face
The colour space, color concentration degree, border color, edge shape, tongue fur impression, tongue fur color, tongue fur area, thickness of the tongue coating and tongue
Thickness is contrasted one by one, calculates the tongue image in the 3rd tongue view data and default tongue image data base respectively
The similarity of data.
In the above-described embodiment, multiple tongue view data that are stored with tongue image data base and one-to-one
Tongue is as examining report;Above-mentioned tongue can provide the healthy living of personalization as examining report with reference to its sex, age bracket, chronic medical history
Instruction, such as diet, fruit, motion scheme, care plans, music scheme, mood regulation scheme etc..By Lab face
The colour space, color concentration degree, border color, edge shape, tongue fur impression, tongue fur color, tongue fur area, thickness of the tongue coating and tongue
Thickness is contrasted one by one, can improve the accuracy of detection.
With the 4th tongue image of the 3rd tongue view data similarity highest in S4, the acquisition tongue image data base
Whether data, judge the 3rd tongue view data with the similarity of the 4th tongue view data more than default similarity threshold
Value scope, if so, obtains the corresponding tongue of the 4th tongue view data as examining report.
The likelihood probability with typical tongue picture in tongue image data base can be drawn, so as to obtain various body constitution and related disease
The probability of disease.User can quickly obtain body constitution and the probability of disease judges report.
In sum, a kind of tongue based on image recognition technology that the present invention is provided as detection method and system, by when
Between in data, the illumination value of surrounding and tongue view data tongue length qualified sentence as tongue view data is preliminary
Calibration is accurate, so as to improve the accuracy of successive image analysis contrast.By scratching as the first tongue view data, only tongue is carried out
Stingy picture, to avoid for lip portion including analysis, obtains the second tongue view data, in conjunction with color correction technology, collection is arrived
Colour correction is carried out from the second tongue view data of different luminous environments, is processed through second operation, can more be improved subsequent figure
As the accuracy of analysis contrast.By contrast operation, with the 3rd tongue view data phase in the acquisition tongue image data base
Like degree the 4th tongue view data of highest, and when the 3rd tongue view data is big with the similarity of the 4th tongue view data
When default similarity threshold scope, the 4th tongue view data of confirmation is immediate view data, now obtains described
The corresponding tongue of 4th tongue view data, can be with reference to technologies such as language or printings, by tongue as examining report feeds back as examining report
To user, whole operation process intelligence degree is high, and accuracy of detection is high.
Embodiments of the invention are the foregoing is only, the scope of the claims of the present invention is not thereby limited, it is every using this
The equivalents made by bright description and accompanying drawing content, or the technical field of correlation is directly or indirectly used in, include in the same manner
In the scope of patent protection of the present invention.
Claims (8)
1. a kind of tongue based on image recognition technology is as detection method, it is characterised in that comprise the steps:
S1, the first tongue view data of collection, specifically include step:
S11, the real-time time data of acquisition, if the time data for getting is in the range of default time threshold, into step
S12;
S12, the illumination value for obtaining surrounding, if the illumination value for getting is in default illumination threshold range, into step
S13;
S13, acquisition tongue view data, in judging the tongue view data, whether tongue length is more than default tongue length
Threshold range, if, it is determined that the tongue view data is used as the first qualified tongue view data;
S2, the first tongue view data to collecting are processed, and specifically include step:
S21, scratch as the first tongue view data, obtain the second tongue view data;
Second tongue view data described in S22, color correction, obtains the 3rd tongue view data;
S3, the tongue view data in the 3rd tongue view data and default tongue image data base is carried out one a pair
Than calculating the 3rd tongue view data respectively similar to the tongue view data in default tongue image data base
Degree;
With the 4th tongue picture number of the 3rd tongue view data similarity highest in S4, the acquisition tongue image data base
According to;
Judge the 3rd tongue view data with the similarity of the 4th tongue view data whether more than default similarity threshold
Value scope, if so, obtains the corresponding tongue of the 4th tongue view data as examining report.
2. the tongue based on image recognition technology according to claim 1 is as detection method, it is characterised in that the step
S13 is specially:
Obtain containing tongued view data;
Scratch as described containing tongued view data, obtain tongue view data;
The tongue view data is calculated with the ratio value containing tongued view data;
If the ratio value is more than default ratio value threshold range, the tongue being calculated in the tongue view data is long
Degree;
Judge whether the tongue length in the tongue view data is more than default tongue length threshold scope, it is if so, then true
The fixed tongue view data is used as the first qualified tongue view data.
3. the tongue based on image recognition technology according to claim 2 is as detection method, it is characterised in that the step
S13 also includes:
Judge in the tongue view data, to whether there is off-note point, if so, return to step S11.
4. the tongue based on image recognition technology according to claim 1 is as detection method, it is characterised in that step S3
Specially:
The 3rd tongue view data is carried out into Lab colors sky with the tongue view data in default tongue image data base
Between, color concentration degree, border color, edge shape, tongue fur impression, tongue fur color, tongue fur area, thickness of the tongue coating and tongue thickness
Contrast one by one, calculate the tongue view data in the 3rd tongue view data and default tongue image data base respectively
Similarity.
5. a kind of tongue based on image recognition technology is as detecting system, it is characterised in that include:It is acquisition module, processing module, right
Than module and acquisition module;
The acquisition module includes first acquisition unit, second acquisition unit and determining unit;
The first acquisition unit, for obtaining time data, if the time data for getting is in default time threshold scope
It is interior, into second acquisition unit;
The second acquisition unit, for obtaining the illumination value of surrounding, if the illumination value for getting is in default illumination threshold
In the range of value, into determining unit;
The determining unit, for obtaining tongue view data, in judging the tongue view data, whether tongue length is more than
Default tongue length threshold scope, if, it is determined that the tongue view data is used as the first qualified tongue view data;
The processing module includes scratching as unit and color correction unit;
The stingy picture unit, for scratching as the first tongue view data, obtains the second tongue view data;
The color correction unit, for the second tongue view data described in color correction, obtains the 3rd tongue view data;
The contrast module, for by the tongue image in the 3rd tongue view data and default tongue image data base
Data are contrasted one by one, calculate the tongue in the 3rd tongue view data and default tongue image data base respectively
The similarity of view data;
The acquisition module, for obtain in the tongue image data base with the 3rd tongue view data similarity highest
Whether four tongue view data, judge the 3rd tongue view data with the similarity of the 4th tongue view data more than default
Similarity threshold scope, if so, obtain the corresponding tongue of the 4th tongue view data as examining report.
6. the tongue based on image recognition technology according to claim 5 is as detecting system, it is characterised in that the determination list
Unit, is additionally operable to obtain containing tongued view data;Scratch as described containing tongued view data, obtain tongue view data;
The tongue view data is calculated with the ratio value containing tongued view data;If the ratio value is more than default ratio
Example value threshold range, the tongue length being calculated in the tongue view data;Judge the tongue in the tongue view data
Whether head length be more than default tongue length threshold scope, if, it is determined that the tongue view data is used as qualified the
One tongue view data.
7. the tongue based on image recognition technology according to claim 6 is as detecting system, it is characterised in that the determination list
Unit, is additionally operable to judge in the tongue view data with the presence or absence of off-note point, if so, returns first acquisition unit.
8. the tongue based on image recognition technology according to claim 5 is as detecting system, it is characterised in that the contrast mould
Block, is additionally operable to for the 3rd tongue view data and the tongue view data in default tongue image data base to carry out Lab
Color space, color concentration degree, border color, edge shape, tongue fur impression, tongue fur color, tongue fur area, thickness of the tongue coating and tongue
Head thickness is contrasted one by one, calculates the tongue figure in the 3rd tongue view data and default tongue image data base respectively
As the similarity of data.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611003430.4A CN106557746A (en) | 2016-11-14 | 2016-11-14 | A kind of tongue based on image recognition technology is as detection method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611003430.4A CN106557746A (en) | 2016-11-14 | 2016-11-14 | A kind of tongue based on image recognition technology is as detection method and system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106557746A true CN106557746A (en) | 2017-04-05 |
Family
ID=58444824
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201611003430.4A Pending CN106557746A (en) | 2016-11-14 | 2016-11-14 | A kind of tongue based on image recognition technology is as detection method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106557746A (en) |
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108509905A (en) * | 2018-03-30 | 2018-09-07 | 百度在线网络技术(北京)有限公司 | Health state evaluation method, apparatus, electronic equipment and storage medium |
CN109040421A (en) * | 2018-06-15 | 2018-12-18 | 普联技术有限公司 | terminal drowning protection method and device |
CN110517239A (en) * | 2019-08-20 | 2019-11-29 | 东软医疗系统股份有限公司 | A kind of medical image detection method and device |
CN110786834A (en) * | 2019-12-09 | 2020-02-14 | 中电健康云科技有限公司 | Fatty liver prediction method based on tongue picture characteristics and BMI index |
CN111444970A (en) * | 2020-03-30 | 2020-07-24 | 崔书克 | Traditional Chinese medicine tongue picture analysis and recognition method and system based on image processing |
CN111724894A (en) * | 2019-11-06 | 2020-09-29 | 中国科学院上海微系统与信息技术研究所 | Data acquisition method, device, terminal and storage medium |
CN112022109A (en) * | 2020-11-06 | 2020-12-04 | 南京诺源医疗器械有限公司 | Medical fluorescence imaging image data acquisition system and acquisition method thereof |
CN113576405A (en) * | 2021-07-08 | 2021-11-02 | 智美康民(珠海)健康科技有限公司 | Tongue diagnosis basic information acquisition method and system, tongue diagnosis instrument and storage medium |
CN113837987A (en) * | 2020-12-31 | 2021-12-24 | 京东科技控股股份有限公司 | Tongue image acquisition method and device and computer equipment |
CN114087998A (en) * | 2021-11-25 | 2022-02-25 | 重庆海浦洛自动化科技有限公司 | Online film thickness detection system for cavity wax injection system |
WO2023029500A1 (en) * | 2021-08-30 | 2023-03-09 | 康键信息技术(深圳)有限公司 | Health scheme recommendation method and apparatus based on deep learning, and device and medium |
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 |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1512451A (en) * | 2002-12-28 | 2004-07-14 | ���ǵ�����ʽ���� | Method for extracting concerned area from tongue image and relative health monitoring method and device |
CN1830380A (en) * | 2006-04-20 | 2006-09-13 | 上海交通大学 | Tongue picture anulgis and diagnosis system of traditional Chinese medicine |
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 |
CN103957396A (en) * | 2014-05-14 | 2014-07-30 | 姚杰 | Image processing method and device used when tongue diagnosis is conducted with intelligent device and equipment |
-
2016
- 2016-11-14 CN CN201611003430.4A patent/CN106557746A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1512451A (en) * | 2002-12-28 | 2004-07-14 | ���ǵ�����ʽ���� | Method for extracting concerned area from tongue image and relative health monitoring method and device |
CN1830380A (en) * | 2006-04-20 | 2006-09-13 | 上海交通大学 | Tongue picture anulgis and diagnosis system of traditional Chinese medicine |
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 |
CN103957396A (en) * | 2014-05-14 | 2014-07-30 | 姚杰 | Image processing method and device used when tongue diagnosis is conducted with intelligent device and equipment |
Cited By (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108509905A (en) * | 2018-03-30 | 2018-09-07 | 百度在线网络技术(北京)有限公司 | Health state evaluation method, apparatus, electronic equipment and storage medium |
CN109040421A (en) * | 2018-06-15 | 2018-12-18 | 普联技术有限公司 | terminal drowning protection method and device |
CN110517239A (en) * | 2019-08-20 | 2019-11-29 | 东软医疗系统股份有限公司 | A kind of medical image detection method and device |
CN111724894A (en) * | 2019-11-06 | 2020-09-29 | 中国科学院上海微系统与信息技术研究所 | Data acquisition method, device, terminal and storage medium |
CN111724894B (en) * | 2019-11-06 | 2023-08-11 | 中国科学院上海微系统与信息技术研究所 | Data acquisition method, device, terminal and storage medium |
CN110786834A (en) * | 2019-12-09 | 2020-02-14 | 中电健康云科技有限公司 | Fatty liver prediction method based on tongue picture characteristics and BMI index |
CN111444970A (en) * | 2020-03-30 | 2020-07-24 | 崔书克 | Traditional Chinese medicine tongue picture analysis and recognition method and system based on image processing |
CN112022109A (en) * | 2020-11-06 | 2020-12-04 | 南京诺源医疗器械有限公司 | Medical fluorescence imaging image data acquisition system and acquisition method thereof |
CN113837987A (en) * | 2020-12-31 | 2021-12-24 | 京东科技控股股份有限公司 | Tongue image acquisition method and device and computer equipment |
CN113837987B (en) * | 2020-12-31 | 2023-11-03 | 京东科技控股股份有限公司 | Tongue image acquisition method and device and computer equipment |
CN113576405A (en) * | 2021-07-08 | 2021-11-02 | 智美康民(珠海)健康科技有限公司 | Tongue diagnosis basic information acquisition method and system, tongue diagnosis instrument and storage medium |
WO2023029500A1 (en) * | 2021-08-30 | 2023-03-09 | 康键信息技术(深圳)有限公司 | Health scheme recommendation method and apparatus based on deep learning, and device and medium |
CN114087998A (en) * | 2021-11-25 | 2022-02-25 | 重庆海浦洛自动化科技有限公司 | Online film thickness detection system for cavity wax injection system |
CN114087998B (en) * | 2021-11-25 | 2023-11-03 | 重庆海浦洛自动化科技有限公司 | Online film thickness detection system for cavity wax injection system |
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 |
---|---|---|
CN106557746A (en) | A kind of tongue based on image recognition technology is as detection method and system | |
US20230394660A1 (en) | Wound imaging and analysis | |
Dimauro et al. | A new method and a non-invasive device to estimate anemia based on digital images of the conjunctiva | |
Bevilacqua et al. | A novel approach to evaluate blood parameters using computer vision techniques | |
WO2021139471A1 (en) | Health status test method and device, and computer storage medium | |
JP6521845B2 (en) | Device and method for measuring periodic fluctuation linked to heart beat | |
US7248724B2 (en) | Method for monitoring wounds | |
US9984277B2 (en) | Systems, apparatus, and methods for analyzing blood cell dynamics | |
CN111128382B (en) | Artificial intelligence multimode imaging analysis device | |
WO2018098987A1 (en) | Image processing system and method for tongue diagnosis in traditional chinese medicine | |
EP3219251A1 (en) | Organ image capture device and program | |
Figueiredo et al. | Computer-assisted bleeding detection in wireless capsule endoscopy images | |
CN103892802A (en) | Novel tongue imaging intelligent auxiliary device | |
CN111950595A (en) | Liver focus image processing method, system, storage medium, program, and terminal | |
Zheng et al. | Corneal‐Smart Phone: A novel method to intelligently estimate postmortem interval | |
CN110456050B (en) | Portable intelligent digital parasite in vitro diagnostic instrument | |
Tania et al. | Computational complexity of image processing algorithms for an intelligent mobile enabled tongue diagnosis scheme | |
JP3548473B2 (en) | Method and apparatus for identifying arteriovenous of fundus image, recording medium and apparatus | |
Das et al. | Non-invasive haemoglobin estimation by observing nail color: A pca based approach | |
KR101551814B1 (en) | Method, system and recording medium for analysing tongue diagnosis using a quantifying evalution indicator of tongue diagnosis image | |
CN109711306B (en) | Method and equipment for obtaining facial features based on deep convolutional neural network | |
CN116092157A (en) | Intelligent facial tongue diagnosis method, system and intelligent equipment | |
Zhang et al. | Medical biometrics: computerized TCM data analysis | |
WO2013119102A1 (en) | Methodology and apparatus for objective and in vivo assessment of granulation tissue growth in chronic ulcers using digital imaging | |
CN115035086A (en) | Intelligent tuberculosis skin test screening and analyzing method and device based on deep learning |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170405 |
|
RJ01 | Rejection of invention patent application after publication |