CN108938396A - A kind of ear acupuncture point identification device and its method based on deep learning - Google Patents
A kind of ear acupuncture point identification device and its method based on deep learning Download PDFInfo
- Publication number
- CN108938396A CN108938396A CN201710880679.1A CN201710880679A CN108938396A CN 108938396 A CN108938396 A CN 108938396A CN 201710880679 A CN201710880679 A CN 201710880679A CN 108938396 A CN108938396 A CN 108938396A
- Authority
- CN
- China
- Prior art keywords
- ear
- acupuncture point
- deep learning
- ear acupuncture
- point position
- 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
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T11/00—2D [Two Dimensional] image generation
- G06T11/60—Editing figures and text; Combining figures or text
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T19/00—Manipulating 3D models or images for computer graphics
- G06T19/20—Editing of 3D images, e.g. changing shapes or colours, aligning objects or positioning parts
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
Abstract
The present invention provides a kind of ear acupuncture point identification device based on deep learning, comprising: for acquiring the acquisition module of ear's data;For storing the memory module of collected ear's data, for obtaining the deep learning network model of ear acupuncture point position according to ear's data;A kind of corresponding ear acupuncture point recognition methods of the ear acupuncture point identification device that the present invention also provides a kind of based on deep learning comprising: ear's data are identified by deep learning network model, and the step of exporting visual ear acupuncture point position.Depth learning technology is applied to ear acupuncture point identification positioning by the present invention, based on a large amount of standard ear acupuncture point locations drawing, reliable deep learning network model is established and had trained to deep learning, substantially increases the efficiency of acupuncture point identification, and acupuncture point identification positions more accurate, use easy to spread.Deep learning acupuncture point recognition methods of the invention is ear acupuncture point identification positioning or even a kind of innovation of acupuncture point localization method.
Description
Technical field
The present invention relates to deep learning fields, and in particular to a kind of ear acupuncture point identification device based on deep learning and its
Method.
Background technique
Auricular therapy is exactly one kind of Chinese medicine meridian therapy since ancient times, according to " vernacular essence translates The Yellow Emperor's Canon of Internal Medicine " (Xie Huabian
Write, Chinese medical book publishing house distribution, in January, 2008 first edition, CIP data: ISBN7-80171-282-6, I are white ..., and II thanks to-III
Interior warp-translation IV R221 China depository library CIP data core word (2008) the 106904th) volume 15 the 58th
(gas mansion opinion) is described, and the gallbladder channel of foot-Shaoyang, small intestine meridian and the positive tri-jiao channel of hand three share nine acupuncture points in ear;It was ground according to modern age
Study carefully, shares 6 running course of channel in numerous acupuncture points at the position for having corresponding whole body all on ear, ear, be that whole body is nearest away from brain
Acupuncture point compact district, the quick good effect in terms of analgesic, anti-inflammatory.
In order to position the ear acupuncture point, ancient Chinese medicine is employed many times pressing stimulation, determines acupuncture point position;In conjunction with existing scientific skill
Art, application No. is 200910235424.5 Chinese patents, disclose a kind of auricular point detection system, include the measurement concatenated mutually
The measurement probe pen being sequentially connected in series, RC oscillating circuit, partial pressure measuring circuit and inspection are contained in part and single chip part, the measurement part
Wave amplifying circuit;Single chip part contains the MCU single-chip microcontroller being sequentially connected in series and UART electrical level transferring chip, and is arranged at this
Signal detection module in MCU single-chip microcontroller.Its using measurement probe pen measure ear's resistance value, obtain ear resistance distribution map to
It shows measurement result, to improve dosing accuracy and precision, but is difficult to be promoted in implementation process.In order to make the ear acupuncture point
Positioning reaches unmanned and more accurately purpose, and application No. is 201410050231.3 Chinese patents, disclose a kind of human body
Ear acupuncture point positioning device.It solves existing acupuncture point localization method and needs to apply human body voltage and existing acupuncture point positioning dress
It sets the not applicable region to acupuncture point than comparatively dense and realizes the problem of being accurately positioned.Localization method includes: acquisition area to be targeted
Image;It selects area to be targeted and corresponding topical acupuncture point figure is read from the image library of acupuncture point according to the region;Obtain profile
Scheme and compare the profile diagram and local acupuncture point figure acquisition fits image;Selective positioning acupuncture point and existed according to the positioning acupuncture point
The position in image is fitted, position where control laser designator to acupuncture point undetermined issues instruction laser beam.It is adopted in positioning device
The position that part to be measured is fixed with bracket realizes Image Acquisition using Image Acquisition and acupuncture point instruction device and issues instruction laser
Beam projects the corresponding acupuncture point of ear;It further fits acupuncture point by the way of ear's contour fitting, and the ear acupuncture point positions not
Enough accurate, there is an urgent need to be improved.
Summary of the invention
To solve the above problems, the ear acupuncture point identification device that the present invention provides a kind of based on deep learning and its side
Depth learning technology is applied to ear acupuncture point identification positioning, is based on a large amount of standard ear acupuncture point locations drawing, depth by method, the present invention
Study establishes and has trained reliable deep learning network model, substantially increases the efficiency of acupuncture point identification, and acupuncture point identification is fixed
More accurate, the use easy to spread in position.Deep learning acupuncture point recognition methods of the invention is ear acupuncture point identification positioning or even cave
A kind of innovation of position localization method.
To realize the technical purpose, the technical scheme is that a kind of ear acupuncture point identification based on deep learning
Device, comprising:
Acquisition module, for acquiring ear's data;
Deep learning network model is built in identification module, inside, for identification ear acupuncture point position.
Further, the identification module includes:
The input layer of deep learning network model is built in input module, inside, for collected to the acquisition module
Ear's data carry out data processing, obtain ear's structure of coordinatograph;
The hidden layer of deep learning network model is built in hidden layer module, inside, for being carried out according to ear's structure of coordinatograph
Identify ear acupuncture point position;
The visualization layer of deep learning network model is built in visualization model, inside, for ear's structure and ear cave
The coordinate of position position is exported in the form of visualizing coding.
Further, display equipment is set outside the visualization model and secondary coding device, secondary coding device is connected and driven
Acupoint stimulation device.
Further, the acquisition module is TOF depth camera, one kind of camera or scanner, the identification module position
In in cloud server.
A kind of ear acupuncture point recognition methods based on deep learning, comprising the following steps:
S1: acquisition ear's data;
S2: ear's data are identified by deep learning network model, and export visual ear acupuncture point position.
Further, the deep learning network model in the step S2 includes:
Input layer establishment step is sat for carrying out data processing to the collected ear's data of the acquisition module
Ear's structure of markization;
Hidden layer establishment step, for obtaining ear's structure of coordinatograph and the mapping relations of ear acupuncture point position;
Hidden layer training step, the mapping relations for ear's structure and ear acupuncture point position to coordinatograph be trained and
Amendment;
Visualization layer establishment step obtains visual ear acupuncture point position for the coordinate output to ear acupuncture point position
It sets.
Further, the input layer establishment step includes:
T1: establishing two-dimensional coordinate system, carries out two-dimensional coordinate to the collected two-dimensional surface ear image of acquisition module.
Further, the input layer establishment step includes:
B1: establishing two-dimensional coordinate system, carries out two-dimensional coordinate to the collected two-dimensional surface ear image of acquisition module.
B2: establishing three-dimensional system of coordinate, according to the collected depth data of acquisition module, in conjunction with the two-dimensional surface in step B1
Ear's image, to ear's structure three-dimensional coordinatograph.
Further, the hidden layer establishment step includes:
E1: using ear's structure of the coordinatograph in multiple step T1 or B2 as sample set, and each ear is demarcated
Standard acupuncture point position as sample canonical collection;
E2: in conjunction with sample set and sample canonical collection, by limited Boltzmann machine, layer-by-layer greed learns from bottom to top
To the sequence mapping relations of sample set and sample canonical collection, hidden layer network is constructed.
Further, the hidden layer training step includes:
P1: using ear's structure of the coordinatograph in multiple step T1 or B2 as test set, and each ear is demarcated
Standard acupuncture point position as testing standard collection;
P2: in conjunction with sample set and sample canonical collection, to the hidden layer network constructed in step E2, by under gradient from top to bottom
The supervised learning of drop, error are transmitted from up to down, are finely adjusted to each layer parameter of hidden layer network, constantly correction building hidden layer
Network.Obtain reliable hidden layer network model.
Further, the visualization layer establishment step, comprising:
A1: visualization coding is carried out to ear's structure of coordinatograph in the step T1 or B2;
A2: to the ear acupuncture point position coordinates exported in the step S2, and in ear acupuncture point coordinate and step A1
Ear's structure coordinate is consistent;
A3: visualization coding is carried out to the ear acupuncture point position coordinates in step A2.
Further, it in the visualization coding simultaneous transmission to display equipment of ear's structure and ear acupuncture point position, shows
After showing that equipment shows ear's structural perspective, the Overlapping display ear acupuncture point position on ear's structure chart;The ear acupuncture point position
The visualization coding set carries out secondary coding by secondary coding device, and drives acupoint stimulation device.
Further, the hidden layer establishment step further include: to ear's structure of the step T2 three-dimensional coordinate, by dividing
Class device carries out ear structural division domain to construct and train hidden layer network.
The beneficial effects of the present invention are:
Depth learning technology is applied to ear acupuncture point identification positioning by the present invention, is based on a large amount of standard ear acupuncture points position
Reliable deep learning network model is established and had trained to figure, deep learning, substantially increases the efficiency of acupuncture point identification, and acupuncture point
Identification positions more accurate, use easy to spread.Deep learning acupuncture point recognition methods of the invention is ear acupuncture point identification positioning,
Or even a kind of innovation of acupuncture point localization method.
Detailed description of the invention
Fig. 1 is the module principle figure of ear acupuncture point identification device of the present invention;
Fig. 2 is the structure principle chart of deep learning network model of the invention;
Fig. 3 is the structure chart of human body ear.
In figure: 1, helix, 2, first ear chamber, 3, navicula, 4, anthelix, 5, antitragus, 6, ear-lobe, 7, tragus, 8, helix
Foot, 9, fossa triangularis, 10, darwinian tubercle.
Specific embodiment
Technical solution of the present invention will be clearly and completely described below.
As shown in Figure 1, a kind of ear acupuncture point identification device based on deep learning, comprising:
Acquisition module, for acquiring ear's data;
Deep learning network model is built in identification module, inside, for identification ear acupuncture point position.
Further, the identification module includes:
The input layer of deep learning network model is built in input module, inside, for collected to the acquisition module
Ear's data carry out data processing, obtain ear's structure of coordinatograph;
The hidden layer of deep learning network model is built in hidden layer module, inside, for being carried out according to ear's structure of coordinatograph
Identify ear acupuncture point position;
The visualization layer of deep learning network model is built in visualization model, inside, for ear's structure and ear cave
The coordinate of position position is exported in the form of visualizing coding.
Further, display equipment is set outside the visualization model and secondary coding device, secondary coding device is connected and driven
Acupoint stimulation device.
Further, the acquisition module is TOF depth camera, one kind of camera or scanner, the identification module position
In in cloud server.The TOF depth camera passes through survey other than recording light intensity information in each pixel
The phase change amount of light wave is measured, while recording time of the light from light source to the pixel as depth data, therefore
TOF camera adds infrared ray artificial light sources, and TOF camera works in confined space, and it is too strong to avoid infrared ray under sunlight
Caused by interfere.
The scanner scans ear's Facad structure using strip movable light source, is irradiated on ear's Facad structure
Light passes through a very narrow gap after reflection, forms light belt, and pass through one group of reflective mirror, is focused by optical lens and entered
Spectroscope, tri- colour light bands of the RGB obtained by prism and redgreenblue filter are shone respectively on respective CCD, CCD
Rgb light band is changed into analog electronic signal, this signal is changed into digital electronic signal by A/D converter again, further obtains
Ear's direct picture.By adding the dot matrix projector on the scanner, the depth data in ear's direct picture is further obtained.
A kind of ear acupuncture point recognition methods based on deep learning, comprising the following steps:
S1: ear's data are acquired by acquisition module, ear's data include two-dimentional ear's image and each structure of ear
Depth data;
S2: ear's data are identified by deep learning network model, and export visual ear acupuncture point position.
Further, such as the deep learning network model in Fig. 2, when developing test, comprising the following steps:
Input layer establishment step is sat for carrying out data processing to the collected ear's data of the acquisition module
Ear's structure of markization;
Hidden layer establishment step, for obtaining ear's structure of coordinatograph and the mapping relations of ear acupuncture point position;
Hidden layer training step, the mapping relations for ear's structure and ear acupuncture point position to coordinatograph be trained and
Amendment;
Visualization layer establishment step obtains visual ear acupuncture point position for the coordinate output to ear acupuncture point position
It sets.
Further, as a kind of embodiment of the invention, the input layer establishment step includes:
T1: establishing two-dimensional coordinate system, carries out two-dimensional coordinate to the collected two-dimensional surface ear image of acquisition module.
T2: establishing three-dimensional system of coordinate, according to the collected depth data of acquisition module, in conjunction with the two-dimensional surface in step B1
Ear's image, to ear's structure three-dimensional coordinatograph.
Further, as another embodiment of the invention, the input layer establishment step includes:
B1: establishing two-dimensional coordinate system, carries out two-dimensional coordinate to the collected two-dimensional surface ear image of acquisition module;
B2: establishing three-dimensional system of coordinate, according to the collected depth data of acquisition module, in conjunction with the two dimension in the step B1
Plane ear image, to ear's structure three-dimensional coordinatograph.
Further, the hidden layer establishment step includes:
E1: in multiple step T1 or B2, ear's structure of two dimension or three-dimensional coordinate is marked as sample set
The standard acupuncture point position of fixed each ear is as sample canonical collection;
E2: in conjunction with sample set and sample canonical collection, by limited Boltzmann machine, layer-by-layer greed learns from bottom to top
To the sequence mapping relations of sample set and sample canonical collection, hidden layer network is constructed.Hidden layer, which is established, carries out depth by great amount of samples
Study, obtains more reliable mapping relations.
Further, the hidden layer training step includes:
P1: in multiple step T1 or B2, ear's structure of two dimension or three-dimensional coordinate is marked as test set
The standard acupuncture point position of fixed each ear is as testing standard collection;
P2: in conjunction with sample set and sample canonical collection, to the hidden layer network constructed in step E2, by under gradient from top to bottom
The supervised learning of drop, error are transmitted from up to down, are finely adjusted to each layer parameter of hidden layer network, constantly correction building hidden layer
Network obtains reliable hidden layer network model, so that ear acupuncture point identification positioning more accurateization.
Further, the visualization layer establishment step, comprising:
A1: in the step T1 or B2, ear's structure of two dimension or three-dimensional coordinate carries out visualization coding;
A2: to the ear acupuncture point position coordinates exported in the step S2, and in ear acupuncture point coordinate and step A1
Ear's structure coordinate is consistent;
A3: visualization coding is carried out to the ear acupuncture point position coordinates in step A2.
Further, it in the visualization coding simultaneous transmission to display equipment of ear's structure and ear acupuncture point position, shows
After showing equipment display two dimension or three-dimensional ear structural perspective, the Overlapping display ear in two dimension or three-dimensional ear structural perspective
Acupuncture point position;The visualization coding of the ear acupuncture point position carries out secondary coding by secondary coding device, and acupuncture point is driven to pierce
Excitation device.Visualization layer, which is realized, is intuitively presented to user for ear's two dimension or tomograph and the acupuncture point figure identified.
As a kind of embodiment of the invention, acquisition module is set in wearable earmuff, and acquisition module acquisition has deep
Ear's image of degree evidence, and ear's data are sent in the memory module of cloud server.
Input layer reads ear's data in memory module in trained deep learning network model, and carries out at data
Reason, obtains ear's structure of three-dimensional coordinate;The mapping relations that hidden layer learns according to depth greed, output ear acupuncture point are known
It is other as a result, being transmitted to user terminal after by the visualization of visualization layer coding, showing ear in the display equipment on user terminal
The location drawing of the three-dimensional figure and ear acupuncture point of portion's structure in three-dimensional figure, tester or user can be according in real world devices
Three-dimensional figure manually adjust acupuncture point position, further feed back to each layer parameter of deep learning network model, further increase model
Reliability.
The visualization coding of the ear acupuncture point position carries out secondary coding, the coding of secondary coding by secondary coding device
Signal can drive acupoint stimulation device stimulate into standard to acupuncture point.
As another embodiment of the invention, acquisition module is set in wearable earmuff, and acquisition module acquisition has
Ear's image of depth data, and ear's data are sent in the memory module of cloud server.The input of cloud server
Layer obtains also calculating using Canny edge detection outside two dimension or ear's structure of three-dimensional coordinate in addition to handling data
Method detects the edge of three-dimensional ear external and internal compositions, as shown in figure 3, carrying out being divided into helix 1, first to ear's structure using classifier
Ears' main regions such as ear chamber 2, navicula 3, anthelix 4, ear-lobe 6, tragus 7, crus helicis 8, fossa triangularis 9, darwinian tubercle 10.
When progress hidden layer is established, the mapping relations of acupuncture point coordinate and ear region structure coordinate are established to ear structural division domain, together
Reason carries out hidden layer training in a manner of subregional.This mode by ear's subregion reduces certain study operand, and more
It is theoretical to meet the proportional unit of body, body cun for carrying out acupuncture point positioning according to body structure in Chinese medicine.In the present embodiment, visualization can finally be passed through
The location drawing of the three-dimensional figure and block plan and ear acupuncture point of layer display ear's structure in three-dimensional figure.
For those of ordinary skill in the art, without departing from the concept of the premise of the invention, it can also do
Several modifications and improvements out, these are all within the scope of protection of the present invention.
Claims (13)
1. a kind of ear acupuncture point identification device based on deep learning characterized by comprising
Acquisition module, for acquiring ear's data;
Deep learning network model is built in identification module, inside, for identification ear acupuncture point position.
2. a kind of ear acupuncture point identification device based on deep learning according to claim 1, which is characterized in that the knowledge
Other module includes:
The input layer of deep learning network model is built in input module, inside, for the collected ear of the acquisition module
Data carry out data processing, obtain ear's structure of coordinatograph;
Hidden layer module, the hidden layer of deep learning network model is built in inside, for being identified according to ear's structure of coordinatograph
Ear acupuncture point position out;
The visualization layer of deep learning network model is built in visualization model, inside, for ear's structure and ear acupuncture point position
The coordinate set is exported in the form of visualizing coding.
3. a kind of ear acupuncture point identification device based on deep learning according to claim 2, which is characterized in that it is described can
Display equipment, secondary coding device, acupoint stimulation device are set depending on changing outside module, is connected by secondary coding device and drives acupoint stimulation
Device.
4. a kind of ear acupuncture point identification device based on deep learning according to claim 1, which is characterized in that described to adopt
Integrate module as one kind of TOF depth camera, camera or scanner, the identification module is located in cloud server.
5. a kind of ear acupuncture point recognition methods based on deep learning, which comprises the following steps:
S1: acquisition ear's data;
S2: ear's data are identified by deep learning network model, and export visual ear acupuncture point position.
6. a kind of ear acupuncture point recognition methods based on deep learning according to claim 5, which is characterized in that the step
Suddenly the deep learning network model in S2 includes:
Input layer establishment step obtains ear's structure of coordinatograph for carrying out data processing to collected ear's data;
Hidden layer establishment step, for obtaining ear's structure of coordinatograph and the mapping relations of ear acupuncture point position;
Hidden layer training step, the mapping relations for ear's structure and ear acupuncture point position to coordinatograph are trained and repair
Just;
Visualization layer establishment step obtains visual ear acupuncture point position for the coordinate output to ear acupuncture point position.
7. a kind of ear acupuncture point recognition methods based on deep learning according to claim 6, which is characterized in that described defeated
Entering a layer establishment step includes:
T1: establishing two-dimensional coordinate system, carries out two-dimensional coordinate to the collected two-dimensional surface ear image of acquisition module
8. a kind of ear acupuncture point recognition methods based on deep learning according to claim 6, which is characterized in that described defeated
Entering a layer establishment step includes:
B1: establishing two-dimensional coordinate system, carries out two-dimensional coordinate to the collected two-dimensional surface ear image of acquisition module.
B2: establishing three-dimensional system of coordinate, according to the collected depth data of acquisition module, in conjunction with the two-dimensional surface ear in step B1
Image, to ear's structure three-dimensional coordinatograph.
9. according to a kind of described in any item ear acupuncture point recognition methods based on deep learning of claim 7 or 8, feature exists
In the hidden layer establishment step includes:
E1: using ear's structure of the coordinatograph in multiple step T1 or B2 as sample set, and the mark of each ear is demarcated
Quasi- acupuncture point position is as sample canonical collection;
E2: in conjunction with sample set and sample canonical collection, by limited Boltzmann machine, successively greed study obtains sample from bottom to top
The sequence mapping relations of this collection and sample canonical collection construct hidden layer network.
10. a kind of ear acupuncture point recognition methods based on deep learning according to claim 9, which is characterized in that described
Hidden layer training step includes:
P1: using ear's structure of the coordinatograph in multiple step T1 or B2 as test set, and the mark of each ear is demarcated
Quasi- acupuncture point position is as testing standard collection;
P2: the hidden layer network constructed in step E2 is declined by gradient from top to bottom in conjunction with sample set and sample canonical collection
Supervised learning, error are transmitted from up to down, are finely adjusted to each layer parameter of hidden layer network, and hidden layer network is constantly corrected.
11. a kind of ear acupuncture point recognition methods based on deep learning according to claim 10, which is characterized in that described
Visualization layer establishment step, comprising:
A1: visualization coding is carried out to ear's structure of coordinatograph in the step T1 or B2;
A2: to the ear acupuncture point position coordinates exported in the step S2, and the ear in ear acupuncture point coordinate and step A1
Structure coordinate is consistent;
A3: visualization coding is carried out to the ear acupuncture point position coordinates in step A2.
12. a kind of ear acupuncture point recognition methods based on deep learning according to claim 11, which is characterized in that described
In the visualization coding simultaneous transmission to display equipment of ear's structure and ear acupuncture point position, display equipment shows ear's structure chart
Afterwards, the Overlapping display ear acupuncture point position on ear's structure chart;The visualization coding of the ear acupuncture point position passes through secondary volume
Code device carries out secondary coding, and drives acupoint stimulation device.
13. a kind of ear acupuncture point recognition methods based on deep learning according to claim 8, which is characterized in that described
Hidden layer establishment step further include: to ear's structure of the step T1 or B2 coordinatograph, by classifier, to ear structural division
Domain carries out constructing and training hidden layer network.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710880679.1A CN108938396A (en) | 2017-09-26 | 2017-09-26 | A kind of ear acupuncture point identification device and its method based on deep learning |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710880679.1A CN108938396A (en) | 2017-09-26 | 2017-09-26 | A kind of ear acupuncture point identification device and its method based on deep learning |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108938396A true CN108938396A (en) | 2018-12-07 |
Family
ID=64494808
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710880679.1A Pending CN108938396A (en) | 2017-09-26 | 2017-09-26 | A kind of ear acupuncture point identification device and its method based on deep learning |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108938396A (en) |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109730923A (en) * | 2019-03-04 | 2019-05-10 | 黑龙江中医药大学 | Assist ear acupuncture point automatic positioning equipment, positioning system and the localization method of Auricular point seed pressing |
CN110232318A (en) * | 2019-05-06 | 2019-09-13 | 平安科技(深圳)有限公司 | Acupuncture point recognition methods, device, electronic 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 |
CN110897865A (en) * | 2019-12-25 | 2020-03-24 | 中科彭州智慧产业创新中心有限公司 | Auricular point guiding device and method |
CN112330802A (en) * | 2020-11-05 | 2021-02-05 | 中国中医科学院中医药信息研究所 | Method and device for establishing dermatome model based on acupuncture points |
CN113807204A (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, equipment and storage medium |
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 |
CN114099322A (en) * | 2021-12-06 | 2022-03-01 | 贵州中医药大学第一附属医院 | Method for conveniently positioning auricular points |
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 |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1729959A (en) * | 2004-12-30 | 2006-02-08 | 中国科学院长春光学精密机械与物理研究所 | Intelligent massage device |
CN107137225A (en) * | 2017-06-22 | 2017-09-08 | 山东中医药大学 | Personalized Head And Face acupuncture point identification model is set up, the method and system of positioning |
-
2017
- 2017-09-26 CN CN201710880679.1A patent/CN108938396A/en active Pending
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1729959A (en) * | 2004-12-30 | 2006-02-08 | 中国科学院长春光学精密机械与物理研究所 | Intelligent massage device |
CN107137225A (en) * | 2017-06-22 | 2017-09-08 | 山东中医药大学 | Personalized Head And Face acupuncture point identification model is set up, the method and system of positioning |
Non-Patent Citations (1)
Title |
---|
柳杨: "《数字图像物体识别理论详解与实战》", 30 March 2018, 北京邮电大学出版社 * |
Cited By (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109730923B (en) * | 2019-03-04 | 2021-02-19 | 黑龙江中医药大学 | Ear acupoint automatic positioning device, positioning system and positioning method for assisting ear acupoint seed pressing |
CN109730923A (en) * | 2019-03-04 | 2019-05-10 | 黑龙江中医药大学 | Assist ear acupuncture point automatic positioning equipment, positioning system and the localization method of Auricular point seed pressing |
CN110232318A (en) * | 2019-05-06 | 2019-09-13 | 平安科技(深圳)有限公司 | Acupuncture point recognition methods, device, electronic 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 |
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 |
CN110897865A (en) * | 2019-12-25 | 2020-03-24 | 中科彭州智慧产业创新中心有限公司 | Auricular point guiding device and method |
CN112330802A (en) * | 2020-11-05 | 2021-02-05 | 中国中医科学院中医药信息研究所 | Method and device for establishing dermatome model based on acupuncture points |
CN112330802B (en) * | 2020-11-05 | 2023-08-01 | 中国中医科学院中医药信息研究所 | Acupoint-based dermatome model building method and device |
CN113807204A (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, equipment and storage medium |
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 |
CN114099322A (en) * | 2021-12-06 | 2022-03-01 | 贵州中医药大学第一附属医院 | Method for conveniently positioning auricular points |
CN114099322B (en) * | 2021-12-06 | 2023-05-26 | 贵州中医药大学第一附属医院 | Method for conveniently positioning auricular points |
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 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108938396A (en) | A kind of ear acupuncture point identification device and its method based on deep learning | |
CN108151671B (en) | A kind of 3 D digital imaging sensor, 3 D scanning system and its scan method | |
CN106469302B (en) | A kind of face skin quality detection method based on artificial neural network | |
CN110998223B (en) | Detector for determining the position of at least one object | |
Agudo et al. | A low-cost real color picker based on arduino | |
CN103914802B (en) | For the image selection using the depth information imported and the System and method for of masking | |
CN105066877B (en) | Tree measurement method based on intelligent terminal camera lens | |
CN107016697B (en) | A kind of height measurement method and device | |
CN106325509A (en) | Three-dimensional gesture recognition method and system | |
CN103606188A (en) | Geographical information on-demand acquisition method based on image point cloud | |
CN103973976B (en) | The conspicuousness extraction element and method of a kind of utilization optical imagery | |
CN109615601A (en) | A method of fusion colour and gray scale depth image | |
CN110074788A (en) | A kind of body data acquisition methods and device based on machine learning | |
CN108363964A (en) | A kind of pretreated wrinkle of skin appraisal procedure and system | |
Díaz-Barrancas et al. | Spectral color management in virtual reality scenes | |
CN103868500A (en) | Spectral three-dimensional imaging system and method | |
CN115170629A (en) | Wound information acquisition method, device, equipment and storage medium | |
KR102036043B1 (en) | Diagnosis Device of optical skin disease based Smartphone | |
CN108175535A (en) | A kind of dentistry spatial digitizer based on microlens array | |
Kubanek et al. | Device for acoustic support of orientation in the surroundings for blind people | |
CN107481243A (en) | Sheep body chi detection method based on sheep top view | |
Sun et al. | Soybean-MVS: annotated three-dimensional model dataset of whole growth period soybeans for 3D plant organ segmentation | |
CN103505218A (en) | Method for measuring focus tissue size through endoscope | |
Miyazaki et al. | Color photometric stereo using multi-band camera constrained by median filter and occluding boundary | |
CN105486408A (en) | Three-wavelength Stokes vector polarization measurement system and method bases on color CCD |
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: 20181207 |
|
RJ01 | Rejection of invention patent application after publication |