CN107137225A - Personalized Head And Face acupuncture point identification model is set up, the method and system of positioning - Google Patents
Personalized Head And Face acupuncture point identification model is set up, the method and system of positioning Download PDFInfo
- Publication number
- CN107137225A CN107137225A CN201710479753.9A CN201710479753A CN107137225A CN 107137225 A CN107137225 A CN 107137225A CN 201710479753 A CN201710479753 A CN 201710479753A CN 107137225 A CN107137225 A CN 107137225A
- Authority
- CN
- China
- Prior art keywords
- face
- head
- acupuncture point
- subject
- dimensional
- 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.)
- Granted
Links
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61H—PHYSICAL THERAPY APPARATUS, e.g. DEVICES FOR LOCATING OR STIMULATING REFLEX POINTS IN THE BODY; ARTIFICIAL RESPIRATION; MASSAGE; BATHING DEVICES FOR SPECIAL THERAPEUTIC OR HYGIENIC PURPOSES OR SPECIFIC PARTS OF THE BODY
- A61H39/00—Devices for locating or stimulating specific reflex points of the body for physical therapy, e.g. acupuncture
- A61H39/02—Devices for locating such points
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B33—ADDITIVE MANUFACTURING TECHNOLOGY
- B33Y—ADDITIVE MANUFACTURING, i.e. MANUFACTURING OF THREE-DIMENSIONAL [3-D] OBJECTS BY ADDITIVE DEPOSITION, ADDITIVE AGGLOMERATION OR ADDITIVE LAYERING, e.g. BY 3-D PRINTING, STEREOLITHOGRAPHY OR SELECTIVE LASER SINTERING
- B33Y50/00—Data acquisition or data processing for additive manufacturing
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B33—ADDITIVE MANUFACTURING TECHNOLOGY
- B33Y—ADDITIVE MANUFACTURING, i.e. MANUFACTURING OF THREE-DIMENSIONAL [3-D] OBJECTS BY ADDITIVE DEPOSITION, ADDITIVE AGGLOMERATION OR ADDITIVE LAYERING, e.g. BY 3-D PRINTING, STEREOLITHOGRAPHY OR SELECTIVE LASER SINTERING
- B33Y80/00—Products made by additive manufacturing
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Health & Medical Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Engineering & Computer Science (AREA)
- Manufacturing & Machinery (AREA)
- Materials Engineering (AREA)
- Rehabilitation Therapy (AREA)
- Physical Education & Sports Medicine (AREA)
- Pain & Pain Management (AREA)
- Epidemiology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
A kind of method and system set up, positioned the present invention relates to personalized Head And Face acupuncture point identification model, wherein method for building up includes：Handmarking is carried out to the Head And Face acupuncture point of human sample；The three-dimensional Head And Face information of each human sample of scanning collection, the three-dimensional Head And Face information includes the same Shen cun of labeled acupuncture point relative coordinate, the distance that acupuncture point is marked relative to annex bone and human sample；The three-dimensional Head And Face information is divided into Head And Face information training dataset and Head And Face information test data set according to a certain percentage；Head And Face acupuncture point automatic identification model is trained using the Head And Face information training dataset by deep learning algorithm；Based on specialty evaluation information and the Head And Face information test data set, Head And Face acupuncture point automatic identification model described in test optimization.
Description
Technical field
Built the invention belongs to the technical field of acupuncture point positioning, more particularly to a kind of personalized Head And Face acupuncture point identification model
Vertical, positioning method and system.
Background technology
The treatment methods such as points acupuncture, massage, infrared treatment and administration at present, in Chinese traditional treatment are so that it is succinct, see
Effect is fast, has no side effect and firmly gets people and like.Acupuncture point positioning is the basis for implementing Chinese medicine acupuncture massage and drug for point.Acupuncture point
Localization method mainly has method of anatomical landmark, proportional bone measurement and finger-cun measurement, and first two method is with body surface
Dissection and joint are that, according to searching acupuncture point, latter finds acupuncture point by itself Fingers cun.Traditional acupuncture point positioning is to pass through
The traditional Chinese physician of the high age and service seniority is according to personal experience and subordinate feels come what is determined, that is, to pass through later approach and carry out acupuncture point positioning.
However, for non-TCM Major or new scholar, the positioning at acupuncture point is often " knowing clearly in the heart, refer to lower hardly possible bright ", it is difficult to smart
Certainly position, it is difficult to reach preferable curative effect.
With the development of electronics technology and computer technology, for solution, Traditional Chinese Medicine experts are difficult to accurate progress degree by no means
The problem of positioning, Li Yanze et al. proposes a kind of simple human acupuncture points recognizing therapeutic equipment, utilizes the non-acupuncture point point of human body and acupuncture point
The difference that point is presented in different impedances between magnitude of voltage passes through to body voltages value measurement progress acupuncture point location determination.It is Chinese special
Sharp document CN1111029C discloses a kind of according to divergence characterization detection human acupoint of the human acupoint to bipolarity detectable signal
Circuit, sample circuit is concatenated in its output loop the bi-polar current signal for flowing through human body rectification and sample, judged
When for divergence characteristic being acupuncture point feature, feedback circuit strengthens detection output automatically, increases the detectable signal to human acupoint
Intensity, increase measured acupuncture point sense, indicates acupuncture point point.But the method that above-mentioned use voltage signal carries out acupuncture point positioning has one
Determine problem, the above method needs to apply voltage to human body, there is certain potential safety hazard, and can only determine than larger acupuncture point.
Chinese patent literature CN103735407B proposes a kind of human body ear acupuncture point positioner, solves existing acupuncture point
Localization method needs to apply human body voltage and the inapplicable region to acupuncture point than comparatively dense of existing acupoint positioning device is realized
The problem of being accurately positioned.Localization method includes：Gather the image of area to be targeted；Select area to be targeted and according to the area
Corresponding topical acupuncture point figure is read from acupuncture point data storehouse in domain；Obtain profile diagram and contrast the profile diagram and local acupuncture point figure is obtained
Image must be fitted；Regioselective acupuncture point and according to the position of the positioning acupuncture point in image is fitted, control laser designator to
Position where acupuncture point undetermined sends instruction laser beam.The position of part to be measured is fixed in positioner using support, using image
Collection and acupuncture point instruction device realize IMAQ and send instruction laser beam projects to the corresponding acupuncture point of ear.However, above-mentioned
There is also certain deficiency for method：First, limitation is compared at position, it is impossible to suitable for human body Head And Face；Secondly, its positioning principle is
By the two-dimensional image of collection, by carrying out fitting to profile diagram based on the contour line in local acupuncture point figure
Positioned with image, but be due to human body be 3 D stereo structure, and the structure and three-dimensional conformation of different human body
Individuation difference is very big, simply fits to position acupuncture point by profile with plane picture, is extremely difficult to pinpoint mesh
's.
In addition, in the prior art, after the positioning of acupuncture point, almost neither one can have for the hommization of each individual
As directly applying to the mark system of the acupuncture point in acupuncture, massage and physiotherapeutic instruments or device after changing.
In summary, the problem of existing acupuncture point localization method can not be accurately positioned facial fine acupuncture point how is solved, with
And existing acupuncture point positioning and recognizing device is the problem of can not carry out personalized acupuncture point fixation and recognition, still lack effective solution party
Case.
The content of the invention
The present invention in order to solve the above problems, overcome in the prior art acupuncture point localization method can not be accurately positioned it is facial fine
The problem of acupuncture point, and there is provided one the problem of can not carry out personalized acupuncture point fixation and recognition for existing acupuncture point positioning and recognizing device
Plant the method and system that personalized Head And Face acupuncture point identification model is set up, positioned.
To achieve these goals, the present invention is using a kind of following technical scheme：
A kind of personalized Head And Face acupuncture point automatic identification method for establishing model, including：
Handmarking is carried out to the Head And Face acupuncture point of human sample；
The three-dimensional Head And Face information of each human sample of scanning collection, the three-dimensional Head And Face information includes labeled cave
The same Shen cun of position relative coordinate, the distance that acupuncture point is marked relative to annex bone and human sample；
The three-dimensional Head And Face letter is divided into Head And Face information training dataset and Head And Face information according to a certain percentage
Test data set；
Head And Face acupuncture point automatic identification mould is trained using the Head And Face information training dataset by deep learning algorithm
Type；
Based on specialty evaluation information and the Head And Face information test data set, Head And Face acupuncture point is automatic described in test optimization
Identification model.
Further, Head And Face acupuncture point is trained certainly using the Head And Face information training dataset by deep learning algorithm
Dynamic identification model includes：
The three-dimensional Head And Face information database with the human sample is set up, and it is smart to improve data by denoising
Degree；
The grid chart that threedimensional model is changed to two dimensional surface is built, the three-dimensional Head And Face information is projected by grid chart
To two dimensional surface, two-dimension human face image is set up；
According to the three-dimensional Head And Face information, isolated face depth map, the face depth map is two-dimensional depth figure
Picture；
Using the two-dimension human face image and face depth map as input, concatenated convolutional neutral net is trained, head are set up
Portion acupuncture point automatic identification model.
The present invention has also led to a kind of personalized Head And Face acupuncture point automatic identification localization method, including：
The three-dimensional Head And Face information of scanning collection subject；
The three-dimensional Head And Face model of subject is obtained to the three-dimensional Head And Face information progress digital reconstruction of the subject, by institute
State the three-dimensional Head And Face model of subject and be respectively converted into subject's two-dimension human face image, subject's face depth map, it is described tested
Person's face depth map is two dimensional image；
Subject's two-dimension human face image, subject's face depth map are known automatically as the Head And Face acupuncture point trained
The input of other model, obtains subject's face acupuncture point coordinate (x, y, z)；
According to subject's face acupuncture point coordinate, acupuncture point positioning is carried out on subject's Head And Face.
Further, according to subject's face acupuncture point coordinate, include carrying out acupuncture point positioning on subject's Head And Face：
Acupuncture point positioning is carried out on the three-dimensional Head And Face model of the subject；
Or acupuncture point positioning is carried out on subject's two-dimension human face image.
Further, the three-dimensional Head And Face information of subject is represented with digitised points data, and represents its shape with XYZ coordinate
Shape, 24 rgb values represent color.
Further, the three-dimensional Head And Face model of the subject and subject's two-dimension human face image are received；
Using the three-dimensional Head And Face physical model of three-dimensional printing equipment printing subject, acupuncture point is carried out on the physical model fixed
Position；
Or using plane printing device printing subject's two-dimension human face picture, acupuncture point positioning is carried out on the picture；
Present invention also offers a kind of personalized Head And Face acupuncture point automatic identification alignment system, including：
Acquisition module, three-dimensional Head And Face information and the three-dimensional Head And Face of subject for each human sample of scanning collection
Information, the three-dimensional Head And Face information of the human sample includes labeled acupuncture point relative coordinate, acupuncture point relative to annex bone
The distance of mark and the same Shen of human sample cun；
With
Model building module, the training module is configured as choosing head from the three-dimensional Head And Face information of human sample
Portion's information training dataset and Head And Face information test data set, by deep learning Algorithm for Training and optimize Head And Face acupuncture point from
Dynamic identification model；
With
Identify locating module, for the three-dimensional Head And Face Information base in the subject, carries out acupuncture point identification positioning.
Further, the model building module includes：
Training module, for training Head And Face cave using the Head And Face information training dataset by deep learning algorithm
Position automatic identification model；
Test module, for based on specialty evaluation information and the Head And Face information test data set, described in test optimization
Head And Face acupuncture point automatic identification model.
Further, the identify locating module includes shape localization unit, color positioning unit or sound positioning unit.
Further, in addition to three-dimensional printing equipment or plane printing device, subject is printed using three-dimensional printing equipment
Three-dimensional Head And Face physical model, carries out acupuncture point positioning on the physical model；
Or using plane printing device printing subject's two-dimension human face picture, acupuncture point positioning is carried out on the picture.
Beneficial effects of the present invention：
(1) present invention realizes individuation Head And Face acupuncture point contactless, without application and is accurately positioned, and will can position
As a result it is embodied, is applied directly among the operations such as acupuncture, massage, massage, administration and infrared treatment, has played the traditional Chinese medical science personalized
The value for the treatment of.
(2) present invention any to human body application need not be both potentially dangerous using the 3 D scanning system of Head And Face
Influence, and human body Head And Face can be obtained than flat scanning with many three-dimensional informations, is that acupuncture point is accurately positioned offer below
More Information bases；
(3) the 3 D stereo information of the invention by gathering human body Head And Face, the especially parameter such as bone mark, using depth
Learning method is spent to build Head And Face acupuncture point automatic identification and markup model, and by expert opinion come constantly improve model
Algorithm, this acupuncture point localization method is more nearly the idea and method of Traditional Chinese Medicine experts acupuncture point positioning, and accuracy is greatly improved.
(4) present invention also carries out the structure for positioning mark the reconstruct of 3-D view, is realized and is embodied by 3D printing, more
Plus it is directly perceived, and mask pattern can be printed, can apply at the mark of corresponding acupuncture point in mask pattern acupuncture, massage,
Infrared treatment and administration etc. are operated, and considerably increase the value of its personalized application.
Brief description of the drawings
Fig. 1 Head And Faces acupuncture point automatic identification training system schematic diagram；
Fig. 2 personalization Head And Faces acupuncture point localization method；
Fig. 3 human body Head And Faces acupuncture point identifies sketch；
Fig. 4 personalization Head And Face acupuncture point localization methods and schematic device；
Fig. 5 personalization Head And Face acupuncture point localization methods and device electrical connection and workflow diagram；
Wherein, 1.3D scanners fixed support, 2.3D scanners, 3. computer systems, 4.3D print carriages, 5.3D printings
Head, 6. chin straps
Embodiment：
The invention will be further described with embodiment below in conjunction with the accompanying drawings：
It is noted that described further below is all exemplary, it is intended to provide further instruction to the application.Unless another
Indicate, all technologies used herein and scientific terminology are with usual with the application person of an ordinary skill in the technical field
The identical meanings of understanding.
It should be noted that term used herein above is merely to describe embodiment, and be not intended to restricted root
According to the illustrative embodiments of the application.As used herein, unless the context clearly indicates otherwise, otherwise singulative
It is also intended to include plural form, additionally, it should be understood that, when in this manual using term "comprising" and/or " bag
Include " when, it indicates existing characteristics, step, operation, device, component and/or combinations thereof.
A kind of exemplary embodiments of the present invention are a kind of personalized Head And Face acupuncture point automatic identification method for establishing model, are such as schemed
Shown in 1, including：
Handmarking is carried out to the Head And Face acupuncture point of human sample：Before scanning to directly in the enterprising rower of human body Head And Face
Note, the relative coordinate at acupuncture point is obtained by 3-D scanning, while gathering distance and the individual that acupuncture point is marked relative to annex bone
With Shen cun (the same Shen cun method in the science of acupuncture and moxibustion), enough individuation information is obtained, the positioning for acupuncture point below is provided more
Useful information.
The three-dimensional Head And Face letter is divided into Head And Face information training dataset and Head And Face information according to a certain percentage
Test data set；
Head And Face acupuncture point automatic identification mould is trained using the Head And Face information training dataset by deep learning algorithm
Type；
Based on specialty evaluation information and the Head And Face information test data set, Head And Face acupuncture point is automatic described in test optimization
Identification model.
Wherein Head And Face acupuncture point is trained to know automatically using the Head And Face information training dataset by deep learning algorithm
Other model includes：
The three-dimensional Head And Face information database with the human sample is set up, and it is smart to improve data by denoising
Degree；
Wherein the three-dimensional Head And Face information database of human sample includes 200 people, 100 males and 100 women：
The grid chart that threedimensional model is changed to two dimensional surface is built, the three-dimensional Head And Face information is projected by grid chart
To two dimensional surface, two-dimension human face image is set up；
According to the three-dimensional Head And Face information, isolated face depth map；Face depth map obtain can be：Selection
100 people in three-dimensional Head And Face information database, 10 kinds of postures, totally 1000 samples, isolated face depth map；
Using the two-dimension human face image and face depth map as input, concatenated convolutional neutral net is trained, head are set up
Portion acupuncture point automatic identification model.Completing face key point is：Eyes, nose, the bilateral corners of the mouth and bone mark, the positioning at acupuncture point.
On the basis of Head And Face acupuncture point automatic identification model is established, the invention also provides a kind of personalized Head And Face
Acupuncture point automatic identification localization method, including：
The three-dimensional Head And Face information of scanning collection subject：Head is fixed on Fig. 4-6 chin strap by subject, and three-dimensional is swept
The camera (Fig. 4-2) for retouching instrument is scanned to human body Head And Face, is completed to catch the character of Head And Face by sensor, is produced
Set of number point data, and its shape is represented with XYZ coordinate, represent color with 24 rgb values.By these information transfers to meter
In calculation machine system (Fig. 5)；
The three-dimensional Head And Face model of subject is obtained to the three-dimensional Head And Face information progress digital reconstruction of the subject, by institute
State the three-dimensional Head And Face model of subject and be respectively converted into subject's two-dimension human face image, subject's face depth map, it is described tested
Person's face depth map is two dimensional image；
Subject's two-dimension human face image, subject's face depth map are known automatically as the Head And Face acupuncture point trained
The input of other model, obtains subject's face acupuncture point coordinate (x, y, z)；
According to subject's face acupuncture point coordinate, acupuncture point positioning is carried out on subject's Head And Face.
We can select to carry out acupuncture point positioning on the three-dimensional Head And Face model of the subject；It can also be selected in described
Acupuncture point positioning is carried out on subject's two-dimension human face image.
Further, we can be using the three-dimensional Head And Face physical model of three-dimensional printing equipment printing subject, in the reality
Acupuncture point positioning is carried out on body Model；
Three-dimensional Head And Face physical model includes the mask model of solid physical model and hollow out.
Or using plane printing device print subject's two-dimension human face picture, acupuncture point positioning is carried out on the picture；
As the hardware system for realizing the above method, the invention also provides a kind of system, including：
Acquisition module, three-dimensional Head And Face information and the three-dimensional Head And Face of subject for each human sample of scanning collection
Information, the three-dimensional Head And Face information of the human sample includes labeled acupuncture point relative coordinate, acupuncture point relative to annex bone
The distance of mark and the same Shen of human sample cun；
With
Model building module, the training module is configured as choosing head from the three-dimensional Head And Face information of human sample
Portion's information training dataset and Head And Face information test data set, by deep learning Algorithm for Training and optimize Head And Face acupuncture point from
Dynamic identification model；
With
Identify locating module, for the three-dimensional Head And Face Information base in the subject, carries out acupuncture point identification positioning.
Wherein model building module includes：
Training module, for training Head And Face cave using the Head And Face information training dataset by deep learning algorithm
Position automatic identification model；
Test module, for based on specialty evaluation information and the Head And Face information test data set, described in test optimization
Head And Face acupuncture point automatic identification model.
Identify locating module includes shape localization unit, color positioning unit or sound positioning unit.
Further, in order to print three-dimensional entity model or X-Y scheme, in addition to three-dimensional printing equipment or plane are beaten
Printing apparatus, the three-dimensional Head And Face physical model of subject is printed using three-dimensional printing equipment, and carrying out acupuncture point on the physical model determines
Position；
Or using plane printing device printing subject's two-dimension human face picture, acupuncture point positioning is carried out on the picture.
Finally, physical model can be used as the object of reference of individual acupuncture point positioning.
Mask model can be added directly at acupuncture point infrared facility be used for physiotherapy, acupuncture point gap can apply acupuncture,
The therapeutic modality such as massage or dosing.
The preferred embodiment of the application is the foregoing is only, the application is not limited to, for the skill of this area
For art personnel, the application can have various modifications and variations.It is all within spirit herein and principle, made any repair
Change, equivalent substitution, improvement etc., should be included within the protection domain of the application.
Claims (10)
1. a kind of personalized Head And Face acupuncture point automatic identification method for establishing model, it is characterised in that including：
Handmarking is carried out to the Head And Face acupuncture point of human sample；
The three-dimensional Head And Face information of each human sample of scanning collection, the three-dimensional Head And Face information includes labeled acupuncture point phase
To the proportional unit of body, body cun of coordinate, the distance that acupuncture point is marked relative to annex bone and human sample；
The three-dimensional Head And Face information is divided into Head And Face information training dataset according to a certain percentage and Head And Face information is surveyed
Try data set；
Head And Face acupuncture point automatic identification model is trained using the Head And Face information training dataset by deep learning algorithm；
Based on specialty evaluation information and the Head And Face information test data set, Head And Face acupuncture point automatic identification described in test optimization
Model.
2. according to the method described in claim 1, it is characterised in that instructed by deep learning algorithm using the Head And Face information
Practicing data set training Head And Face acupuncture point automatic identification model includes：
The three-dimensional Head And Face information database with the human sample is set up, and passes through denoising to improve data precision；
The grid chart that threedimensional model is changed to two dimensional surface is built, the three-dimensional Head And Face information is projected to two by grid chart
Dimensional plane, sets up two-dimension human face image；
According to the three-dimensional Head And Face information, isolated face depth map, the face depth map is two-dimensional depth image；
Using the two-dimension human face image and face depth map as input, concatenated convolutional neutral net is trained, Head And Face cave is set up
Position automatic identification model.
3. a kind of personalized Head And Face acupuncture point automatic identification localization method based on claim 1, it is characterised in that including：
The three-dimensional Head And Face information of scanning collection subject；
Digital reconstruction is carried out to the three-dimensional Head And Face information of the subject and obtains the three-dimensional Head And Face model of subject, will it is described by
Examination person's three-dimensional Head And Face model is respectively converted into subject's two-dimension human face image, subject's face depth map, the subject people
Face depth map is two dimensional image；
It regard subject's two-dimension human face image, subject's face depth map as the Head And Face acupuncture point automatic identification mould trained
The input of type, obtains subject's face acupuncture point coordinate（X, y, z）；
According to subject's face acupuncture point coordinate, acupuncture point positioning is carried out on subject's Head And Face.
4. method according to claim 3, it is characterised in that according to subject's face acupuncture point coordinate, in subject's head
Acupuncture point positioning is carried out on face to be included：
Acupuncture point positioning is carried out on the three-dimensional Head And Face model of the subject；
Or acupuncture point positioning is carried out on subject's two-dimension human face image.
5. method according to claim 3, it is characterised in that：The three-dimensional Head And Face information of subject is with digitised points data
Represent, and its shape is represented with XYZ coordinate, 24 rgb values represent color.
6. method according to claim 3, it is characterised in that also include：
Receive the three-dimensional Head And Face model of the subject and subject's two-dimension human face image；
Using the three-dimensional Head And Face physical model of three-dimensional printing equipment printing subject, acupuncture point positioning is carried out on the physical model；
Or using plane printing device printing subject's two-dimension human face picture, acupuncture point positioning is carried out on the picture.
7. a kind of personalized Head And Face acupuncture point automatic identification alignment system, it is characterised in that including：
Acquisition module, three-dimensional Head And Face information and the three-dimensional Head And Face letter of subject for each human sample of scanning collection
Breath, the three-dimensional Head And Face information of the human sample includes labeled acupuncture point relative coordinate, acupuncture point relative to annex bone mark
The distance of note and the same Shen of human sample cun；
With
Model building module, the training module is configured as choosing Head And Face letter from the three-dimensional Head And Face information of human sample
Training dataset and Head And Face information test data set are ceased, by deep learning Algorithm for Training and optimizes Head And Face acupuncture point and knows automatically
Other model；
With
Identify locating module, for the three-dimensional Head And Face Information base in the subject, carries out acupuncture point identification positioning.
8. system according to claim 7, it is characterised in that the model building module includes：
Training module, for training Head And Face acupuncture point certainly using the Head And Face information training dataset by deep learning algorithm
Dynamic identification model；
Test module, for based on specialty evaluation information and the Head And Face information test data set, head described in test optimization
Portion acupuncture point automatic identification model.
9. system according to claim 7, it is characterised in that the identify locating module includes shape localization unit, face
Color positioning unit or sound positioning unit.
10. system according to claim 7, it is characterised in that also including three-dimensional printing equipment or plane printing device, adopt
With the three-dimensional Head And Face physical model of three-dimensional printing equipment printing subject, acupuncture point positioning is carried out on the physical model；
Or using plane printing device printing subject's two-dimension human face picture, acupuncture point positioning is carried out on the picture.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710479753.9A CN107137225B (en) | 2017-06-22 | 2017-06-22 | Method and system for establishing and positioning personalized head and face acupoint recognition model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710479753.9A CN107137225B (en) | 2017-06-22 | 2017-06-22 | Method and system for establishing and positioning personalized head and face acupoint recognition model |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107137225A true CN107137225A (en) | 2017-09-08 |
| CN107137225B CN107137225B (en) | 2023-09-01 |
Family
ID=59782321
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710479753.9A Active CN107137225B (en) | 2017-06-22 | 2017-06-22 | Method and system for establishing and positioning personalized head and face acupoint recognition model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107137225B (en) |
Cited By (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107898626A (en) * | 2017-12-20 | 2018-04-13 | 大连交通大学 | A kind of binocular vision acupoint positioning instrument and its method of work |
| CN108158804A (en) * | 2017-12-15 | 2018-06-15 | 泗洪县正心医疗技术有限公司 | A kind of method and body surface vein mold that target positioning is realized based on body surface vein pattern |
| CN108514509A (en) * | 2018-03-30 | 2018-09-11 | 吴佳桐 | A kind of intelligence acupuncture point localization method |
| CN108765546A (en) * | 2018-04-18 | 2018-11-06 | 北京奇虎科技有限公司 | Acupuncture point detection method and device |
| CN108938396A (en) * | 2017-09-26 | 2018-12-07 | 炬大科技有限公司 | A kind of ear acupuncture point identification device and its method based on deep learning |
| CN109568123A (en) * | 2018-11-02 | 2019-04-05 | 广东数相智能科技有限公司 | A kind of acupuncture point localization method based on YOLO target detection |
| CN109939001A (en) * | 2019-04-02 | 2019-06-28 | 王云 | A kind of device for healing and training of Dysphagia After Stroke |
| CN110448453A (en) * | 2019-08-08 | 2019-11-15 | 杭州诚一文化创意有限公司 | A kind of smart machine and its method for facial point massage |
| CN110464633A (en) * | 2019-06-17 | 2019-11-19 | 深圳壹账通智能科技有限公司 | Acupuncture point recognition methods, device, equipment and storage medium |
| CN110613605A (en) * | 2019-08-29 | 2019-12-27 | 成都中医药大学 | Construction method of acupoint discrimination model, acupoint discrimination method and discrimination system |
| CN111028950A (en) * | 2019-12-26 | 2020-04-17 | 中科彭州智慧产业创新中心有限公司 | Three-dimensional human body meridian display method and system, electronic device and storage medium |
| CN111723700A (en) * | 2020-06-08 | 2020-09-29 | 国网河北省电力有限公司信息通信分公司 | Face recognition method and device and electronic equipment |
| CN112184705A (en) * | 2020-10-28 | 2021-01-05 | 成都智数医联科技有限公司 | Human body acupuncture point identification, positioning and application system based on computer vision technology |
| CN112519235A (en) * | 2020-12-23 | 2021-03-19 | 中科彭州智慧产业创新中心有限公司 | Rapid model preparation device and method based on 3D printing technology |
| CN113780250A (en) * | 2021-11-11 | 2021-12-10 | 四川大学 | End-to-end facial acupoint positioning method for small sample and electronic equipment |
| CN113807207A (en) * | 2021-08-30 | 2021-12-17 | 中科尚易健康科技(北京)有限公司 | Human body meridian recognition method and device based on multiple cameras and human body meridian conditioning equipment |
| CN113813169A (en) * | 2021-08-30 | 2021-12-21 | 中科尚易健康科技(北京)有限公司 | Model-degressive deep learning human body acupuncture point identification method and physical therapy equipment |
| CN113842116A (en) * | 2021-10-14 | 2021-12-28 | 北京鹰之眼智能健康科技有限公司 | Automatic positioning method and device for human acupuncture points and electronic equipment |
| CN113975152A (en) * | 2021-11-01 | 2022-01-28 | 潍坊信行中直医疗科技有限公司 | Personalized skin-piercing-branch positioning device based on 3D printing and manufacturing method thereof |
| CN116020094A (en) * | 2022-12-28 | 2023-04-28 | 四川省八一康复中心（四川省康复医院） | Adult swallowing rehabilitation training system with portable acupoint stimulation instrument and man-machine interaction |
| CN116364238A (en) * | 2023-05-26 | 2023-06-30 | 青岛市第五人民医院 | Acupuncture treatment system and method based on deep learning |
| CN117636446A (en) * | 2024-01-25 | 2024-03-01 | 江汉大学 | Face acupoint positioning method, acupuncture robot and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101958079A (en) * | 2010-07-22 | 2011-01-26 | 西北师范大学 | Positioning model of channel acupuncture point in three-dimensional virtual human anatomy texture and application thereof |
| CN102525795A (en) * | 2012-01-16 | 2012-07-04 | 沈阳理工大学 | Fast automatic positioning method of foot massaging robot |
| CN104207931A (en) * | 2013-06-05 | 2014-12-17 | 上海中医药大学 | Accurate human face acupuncture point locating and acupuncture and moxibustion prescription learning method |
| CN105653875A (en) * | 2016-01-19 | 2016-06-08 | 中国科学院微电子研究所 | Method and device for manufacturing human body meridian point model |
| CN105930810A (en) * | 2016-04-26 | 2016-09-07 | 北京工业大学 | Facial acupoint positioning method and positioning device based on feature point positioning algorithm |
-
2017
- 2017-06-22 CN CN201710479753.9A patent/CN107137225B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101958079A (en) * | 2010-07-22 | 2011-01-26 | 西北师范大学 | Positioning model of channel acupuncture point in three-dimensional virtual human anatomy texture and application thereof |
| CN102525795A (en) * | 2012-01-16 | 2012-07-04 | 沈阳理工大学 | Fast automatic positioning method of foot massaging robot |
| CN104207931A (en) * | 2013-06-05 | 2014-12-17 | 上海中医药大学 | Accurate human face acupuncture point locating and acupuncture and moxibustion prescription learning method |
| CN105653875A (en) * | 2016-01-19 | 2016-06-08 | 中国科学院微电子研究所 | Method and device for manufacturing human body meridian point model |
| CN105930810A (en) * | 2016-04-26 | 2016-09-07 | 北京工业大学 | Facial acupoint positioning method and positioning device based on feature point positioning algorithm |
Cited By (28)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108938396A (en) * | 2017-09-26 | 2018-12-07 | 炬大科技有限公司 | A kind of ear acupuncture point identification device and its method based on deep learning |
| CN108158804A (en) * | 2017-12-15 | 2018-06-15 | 泗洪县正心医疗技术有限公司 | A kind of method and body surface vein mold that target positioning is realized based on body surface vein pattern |
| CN108158804B (en) * | 2017-12-15 | 2021-09-14 | 苏州科灵医疗科技有限公司 | Body surface vein mold for realizing target positioning based on body surface vein characteristics and manufacturing method |
| CN107898626A (en) * | 2017-12-20 | 2018-04-13 | 大连交通大学 | A kind of binocular vision acupoint positioning instrument and its method of work |
| CN108514509A (en) * | 2018-03-30 | 2018-09-11 | 吴佳桐 | A kind of intelligence acupuncture point localization method |
| CN108765546A (en) * | 2018-04-18 | 2018-11-06 | 北京奇虎科技有限公司 | Acupuncture point detection method and device |
| CN109568123A (en) * | 2018-11-02 | 2019-04-05 | 广东数相智能科技有限公司 | A kind of acupuncture point localization method based on YOLO target detection |
| CN109939001A (en) * | 2019-04-02 | 2019-06-28 | 王云 | A kind of device for healing and training of Dysphagia After Stroke |
| CN110464633A (en) * | 2019-06-17 | 2019-11-19 | 深圳壹账通智能科技有限公司 | Acupuncture point recognition methods, device, equipment and storage medium |
| CN110448453A (en) * | 2019-08-08 | 2019-11-15 | 杭州诚一文化创意有限公司 | A kind of smart machine and its method for facial point massage |
| CN110613605B (en) * | 2019-08-29 | 2021-06-22 | 成都中医药大学 | Construction method of acupoint discrimination model, acupoint discrimination method and discrimination system |
| CN110613605A (en) * | 2019-08-29 | 2019-12-27 | 成都中医药大学 | Construction method of acupoint discrimination model, acupoint discrimination method and discrimination system |
| CN111028950A (en) * | 2019-12-26 | 2020-04-17 | 中科彭州智慧产业创新中心有限公司 | Three-dimensional human body meridian display method and system, electronic device and storage medium |
| CN111723700A (en) * | 2020-06-08 | 2020-09-29 | 国网河北省电力有限公司信息通信分公司 | Face recognition method and device and electronic equipment |
| CN112184705A (en) * | 2020-10-28 | 2021-01-05 | 成都智数医联科技有限公司 | Human body acupuncture point identification, positioning and application system based on computer vision technology |
| CN112519235A (en) * | 2020-12-23 | 2021-03-19 | 中科彭州智慧产业创新中心有限公司 | Rapid model preparation device and method based on 3D printing technology |
| CN113813169B (en) * | 2021-08-30 | 2023-12-01 | 中科尚易健康科技(北京)有限公司 | Model decreasing deep learning human body acupoint recognition method and physiotherapy equipment |
| CN113807207A (en) * | 2021-08-30 | 2021-12-17 | 中科尚易健康科技(北京)有限公司 | Human body meridian recognition method and device based on multiple cameras and human body meridian conditioning equipment |
| CN113813169A (en) * | 2021-08-30 | 2021-12-21 | 中科尚易健康科技(北京)有限公司 | Model-degressive deep learning human body acupuncture point identification method and physical therapy equipment |
| CN113842116A (en) * | 2021-10-14 | 2021-12-28 | 北京鹰之眼智能健康科技有限公司 | Automatic positioning method and device for human acupuncture points and electronic equipment |
| CN113842116B (en) * | 2021-10-14 | 2022-09-27 | 北京鹰之眼智能健康科技有限公司 | Automatic positioning method and device for human acupuncture points and electronic equipment |
| CN113975152A (en) * | 2021-11-01 | 2022-01-28 | 潍坊信行中直医疗科技有限公司 | Personalized skin-piercing-branch positioning device based on 3D printing and manufacturing method thereof |
| CN113975152B (en) * | 2021-11-01 | 2023-10-31 | 潍坊信行中直医疗科技有限公司 | Individualized skin penetrating and supporting positioning device based on 3D printing and manufacturing method thereof |
| CN113780250A (en) * | 2021-11-11 | 2021-12-10 | 四川大学 | End-to-end facial acupoint positioning method for small sample and electronic equipment |
| CN116020094A (en) * | 2022-12-28 | 2023-04-28 | 四川省八一康复中心（四川省康复医院） | Adult swallowing rehabilitation training system with portable acupoint stimulation instrument and man-machine interaction |
| CN116364238A (en) * | 2023-05-26 | 2023-06-30 | 青岛市第五人民医院 | Acupuncture treatment system and method based on deep learning |
| CN117636446A (en) * | 2024-01-25 | 2024-03-01 | 江汉大学 | Face acupoint positioning method, acupuncture robot and storage medium |
| CN117636446B (en) * | 2024-01-25 | 2024-05-07 | 江汉大学 | Face acupoint positioning method, acupuncture robot and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107137225B (en) | 2023-09-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107137225A (en) | Personalized Head And Face acupuncture point identification model is set up, the method and system of positioning | |
| DK2061556T3 (en) | PROCEDURE AND APPARATUS TO CORRECT A ERROR IN THE CO-REGISTRATION OF COORDINATE SYSTEMS USED TO REPRESENT OBJECTS UNDER NAVIGATED BRAIN STIMULATION | |
| CN110461227B (en) | Intracorporeal probe navigation by electrical self-sensing | |
| CN105852970B (en) | Neurosurgical Robot navigation positioning system and method | |
| Bert et al. | A phantom evaluation of a stereo‐vision surface imaging system for radiotherapy patient setup | |
| US10881353B2 (en) | Machine-guided imaging techniques | |
| CN110337312A (en) | The selection and placement of best deep brain stimulation electrode based on stimulus field modeling | |
| WO2016181320A1 (en) | Fiducial marking for image-electromagnetic field registration | |
| CN110074788B (en) | Body data acquisition method and device based on machine learning | |
| Noirhomme et al. | Registration and real-time visualization of transcranial magnetic stimulation with 3-D MR images | |
| CN108272502A (en) | A kind of ablation needle guiding operating method and system of CT three-dimensional imagings guiding | |
| CN110338841A (en) | The display processing method and 3-D supersonic imaging method and system of three-dimensional imaging data | |
| CN104274183A (en) | Motion information processing apparatus | |
| CN107497049A (en) | A kind of electromagnetic location air navigation aid and device for transcranial magnetic stimulation device | |
| WO2020211255A1 (en) | Human body shape and physique data acquisition method, device and storage medium | |
| CN105718730B (en) | The system of pain quantification appraisal procedure and implementation this method to subject | |
| CN107898626A (en) | A kind of binocular vision acupoint positioning instrument and its method of work | |
| CN206584354U (en) | Physical examination information acquisition system based on image recognition | |
| CN107049489A (en) | A kind of operation piloting method and system | |
| CN109091380A (en) | Traditional Chinese medicine system and method for realizing acupoint visualization by AR technology | |
| CN105617532B (en) | Transcranial magnetic stimulation localization method and system | |
| BR102018076393A2 (en) | COLOR-CODED FACIAL MAPS WITH DISTANCE BETWEEN EAR, NOSE AND THROAT BONES | |
| CN110477921B (en) | Height measurement method based on skeleton broken line Ridge regression | |
| CN106730422A (en) | A kind of method that people and body position fixing device deviation are measured in posture radiotherapy based under infrared guiding | |
| CN109934798A (en) | Internal object information labeling method and device, electronic equipment, storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |