CN109953743A - Chinese medicine image surface acquisition and analysis device and method - Google Patents
Chinese medicine image surface acquisition and analysis device and method Download PDFInfo
- Publication number
- CN109953743A CN109953743A CN201711410285.6A CN201711410285A CN109953743A CN 109953743 A CN109953743 A CN 109953743A CN 201711410285 A CN201711410285 A CN 201711410285A CN 109953743 A CN109953743 A CN 109953743A
- Authority
- CN
- China
- Prior art keywords
- face
- image
- skin
- chinese medicine
- obtains
- 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
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/0059—Measuring for diagnostic purposes; Identification of persons using light, e.g. diagnosis by transillumination, diascopy, fluorescence
- A61B5/0062—Arrangements for scanning
- A61B5/0064—Body surface scanning
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/0059—Measuring for diagnostic purposes; Identification of persons using light, e.g. diagnosis by transillumination, diascopy, fluorescence
- A61B5/0077—Devices for viewing the surface of the body, e.g. camera, magnifying lens
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/48—Other medical applications
- A61B5/4854—Diagnosis based on concepts of traditional oriental medicine
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Medical Informatics (AREA)
- General Health & Medical Sciences (AREA)
- Pathology (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Biophysics (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- Physics & Mathematics (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- Alternative & Traditional Medicine (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physiology (AREA)
- Psychiatry (AREA)
- Signal Processing (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Image Analysis (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
It includes digital camera that the present invention, which provides a kind of Chinese medicine image surface acquisition and analysis device and method, the device, and the method comprising the steps of: constructing the optical imaging system of digital camera;Human face data is acquired using the optical imaging system of digital camera, obtains face two dimensional image;Affine transformation is carried out to face two dimensional image, obtains the multi-view image of three different points of view of face;Stereo reconstruction is carried out to the multi-view image of three different points of view of face, obtains face 3-D image;Face detection is carried out to face each section region of face 3-D image;The skin chunk that viscera corresponds to five parts of face is extracted from the face 3-D image of positioning;The dominant hue for extracting each skin chunk obtains the main pixel of skin chunk, and seeks Skin Color Information of the mean value of main pixel as each skin chunk.The present invention can obtain complete face information building facial image, carry out the division of internal organs reflecting regional to facial image to extract complexion information, improve the accuracy of Chinese medicine facial diagnosis.
Description
Technical field
The present invention relates to the technical field of Chinese medicine facial diagnosis analysis of information collection more particularly to a kind of Chinese medicine image surface collection analysis
Device and method.
Background technique
The marrow of traditional Chinese medicine is " diagnosis and treatment based on an overall analysis of the illness and the patient's condition ", and " hope, hear, asking, cutting " four kinds of diagnostic methods are that completion is " dialectical to apply
Control " important evidence." prestige " is one of most important content of the Chinese medicine four methods of diagnosis, Chinese medicine facial diagnosis be it is the most commonly used in Chinese medicine " observation " and
The degree of most one of the diagnostic method of clinical value, modernization has extremely far-reaching meaning to the development of entire traditional Chinese medicine
Justice.Traditional Chinese medicine thinks that human body is an organic whole, mirror of the face like reflecting physiological pathology of human body, inspection of five apertures
Expression variation, can directly examine the lesion situation of the vital organs of the human body.Traditional observation is sentenced by the visual observation of doctor
Disconnected analysis, and use language verbal description, subjective dependence is strong, lack objectify, the foundation of quantification.Observation is related to locating for patient
Environment, the state of mind, the experience of doctor and subjective factor etc. are caused to the differentiation result of the image surface colour of skin because people varies in different localities.
Further, since being limited by many conditions, Chinese medicine is difficult to the accurately data such as record and depositary's dignity picture for a long time, this is faced
Bed, teaching, scientific research bring many inconvenience, are also unfavorable for academic exchange, so that Chinese medicine is developed slowly in Modern Information.
Summary of the invention
The main purpose of the present invention is to provide a kind of Chinese medicine image surface acquisition and analysis device and methods, it is intended to existing Chinese medicine face
It examines in informationization and obtains the problem that image surface information does not cause facial diagnosis accuracy lower comprehensively using facial diagnosis equipment.
To achieve the above object, the present invention provides a kind of Chinese medicine image surface acquisition and analysis device, a kind of Chinese medicine image surface acquisition point
Analysis apparatus including digital camera, communication unit, the processor for being adapted for carrying out various computer program instructions and is suitable for storing more
The memory of computer program instructions, the computer program instructions are loaded by processor and are executed following steps: building number
The optical imaging system of code camera;Using the human face data of the optical imaging system acquisition user of digital camera, face two is obtained
Tie up image;Affine transformation is carried out to face two dimensional image, obtains the multi-view image of three different points of view of face;Utilize multiple views
Stereo matching method carries out stereo reconstruction to the multi-view image of three different points of view of face, obtains face 3-D image;Using product
Sciagraphy is divided to carry out Face detection to face each section region of face 3-D image;Model is corresponded to from positioning according to facial internal organs
Face 3-D image extract viscera and correspond to the skin chunks of five parts of face;The dominant hue for extracting each skin chunk obtains
The main pixel of each skin chunk, and seek Skin Color Information of the mean value of main pixel as each skin chunk.
Further, the computer program instructions are also executed the following steps: by processor load by the face three of user
The Skin Color Information for tieing up image and each skin chunk is stored in memory and is shown over the display.
Further, the digital camera includes circular cone internal reflector, camera lens and microcontroller, wherein the structure
The step of building the optical imaging system of digital camera includes the following steps: the resolution ratio that camera lens are turned up by microcontroller;
Lens barrel regulating command is generated according to the distance between face and camera lens, microcontroller adjusts taper according to lens barrel regulating command
Optical tube length between reflecting mirror and camera lens.
Further, described that Face detection is carried out using face each section region of the integral projection method to face 3-D image
Specific implementation step are as follows: face 3-D image is converted into grayscale image;Integral projection is carried out in the horizontal direction for grayscale image
Integral curve is obtained, first apparent trough corresponds to the left margin of face, the last one apparent wave on integral curve
Paddy corresponds to the right margin of face;The right boundary and then the secondary integral projection that part is carried out to gray level image of face are obtained,
Four troughs are oriented on integral curve, respectively obtain the position of eyebrow, eyes, nostril and mouth.
Further, the skin chunk of five parts is forehead, left cheek, nasal surface, five right cheek, chin Typical Areas
The dominant hue in domain, each skin chunk obtains the main pixel of the skin chunk, Mei Yipi using the domain color description of MEPG-7
The mean value of the main pixel of skin block is calculated using HSV space model.
The present invention also provides a kind of Chinese medicine image surface capturing analysis methods, are applied in Chinese medicine image surface acquisition and analysis device, should
Chinese medicine image surface acquisition and analysis device includes digital camera, and the method comprising the steps of: constructing the optical imaging system of digital camera;Benefit
With the human face data of the optical imaging system acquisition user of digital camera, face two dimensional image is obtained;To face two dimensional image into
Row affine transformation obtains the multi-view image of three different points of view of face;Using multi-viewpoint three-dimensional matching method to face three not
Multi-view image with viewpoint carries out stereo reconstruction, obtains face 3-D image;Using integral projection method to face 3-D image
Face each section region carry out Face detection;Model, which is corresponded to, according to facial internal organs extracts human body from the face 3-D image of positioning
Internal organs correspond to the skin chunk of five parts of face;The dominant hue for extracting each skin chunk obtains the main pixel of each skin chunk,
And seek Skin Color Information of the mean value of main pixel as each skin chunk.
Further, the Chinese medicine image surface capturing analysis method further includes following steps: by the face three-dimensional figure of user
Picture and the Skin Color Information of each skin chunk are stored in memory and are shown over the display.
Further, the digital camera includes circular cone internal reflector, camera lens and microcontroller, wherein the structure
The step of building the optical imaging system of digital camera includes the following steps: the resolution ratio that camera lens are turned up by microcontroller;
Lens barrel regulating command is generated according to the distance between face and camera lens, microcontroller adjusts taper according to lens barrel regulating command
Optical tube length between reflecting mirror and camera lens.
Further, described that Face detection is carried out using face each section region of the integral projection method to face 3-D image
Specific implementation step are as follows: face 3-D image is converted into grayscale image;Integral projection is carried out in the horizontal direction for grayscale image
Integral curve is obtained, first apparent trough corresponds to the left margin of face, the last one apparent wave on integral curve
Paddy corresponds to the right margin of face;The right boundary and then the secondary integral projection that part is carried out to gray level image of face are obtained,
Four troughs are oriented on integral curve, respectively obtain the position of eyebrow, eyes, nostril and mouth.
Further, the skin chunk of five parts is forehead, left cheek, nasal surface, five right cheek, chin Typical Areas
The dominant hue in domain, each skin chunk obtains the main pixel of the skin chunk, Mei Yipi using the domain color description of MEPG-7
The mean value of the main pixel of skin block is calculated using HSV space model.
Compared to the prior art, Chinese medicine image surface acquisition and analysis device of the present invention and method, due in capture face figure
Optical imaging system is constructed when picture and obtains clearly face two dimensional image, and Three-dimensional Gravity is carried out to face according to face two dimensional image
Structure obtains face 3-D image, can be realized all structures, texture and the depth that face is obtained in single face two dimensional image
Information, to keep the face information obtained more complete.In addition, the feature of present invention combination face is anti-to facial image progress internal organs
Reflecting region division is five representative region skin chunks, and carries out analysis complexion to the complexion information of five representative region skin chunks
Information, can satisfy the demand that doctor carries out Chinese medicine facial diagnosis to a certain extent, and auxiliary traditional Chinese medicine diagnosis improves Chinese medicine facial diagnosis knot
The accuracy of fruit.
Detailed description of the invention
Fig. 1 is the structure block diagram of the preferred embodiment of Chinese medicine image surface acquisition and analysis device of the present invention;
Fig. 2 is the flow chart of the preferred embodiment of Chinese medicine image surface capturing analysis method of the present invention.
The embodiments will be further described with reference to the accompanying drawings for the realization, the function and the advantages of the object of the present invention.
Specific embodiment
It is of the invention to reach the technical means and efficacy that predetermined goal of the invention is taken further to illustrate, below in conjunction with
Attached drawing and preferred embodiment, to a specific embodiment of the invention, structure, feature and its effect, detailed description are as follows.It should manage
Solution, the specific embodiments described herein are merely illustrative of the present invention, is not intended to limit the present invention.
Shown in referring to Fig.1, Fig. 1 is the structure box signal of the preferred embodiment of Chinese medicine image surface acquisition and analysis device of the present invention
Figure.In the present embodiment, the Chinese medicine image surface acquisition and analysis device 1 includes, but is not only limited to, digital camera 2, Chinese medicine image surface
Acquisition analysis system 10, executes various computer program instructions at the memory 11 suitable for storing a plurality of computer program instructions
Processor 12 and display 13.Preferably, the digital camera 2 acquires the human face data of user and is sent to processor 1, institute
Stating digital camera 2 includes, but is not only limited to, microcontroller 20, circular cone internal reflector 21 and camera lens 22, the microcontroller
Device 20 is connected on processor 12 by signal wire, and the connection between the circular cone internal reflector 21 and camera lens 22 is using existing
There is the geometry radial connection structure of camera lens barrel rotary type in technology, the present embodiment does not repeat specifically.The present invention combines
Reflected refraction knowledge in geometry radial structure, optics constructs digital phase using circular cone internal reflector 21 and camera lens 22
The optical imaging system of machine 2.In addition, the digital camera 2 further includes the primary element structure of digital camera in the prior art, example
Such as power supply, USB interface.
In the present embodiment, the memory 11 can be a kind of read only memory ROM, random access memory ram, electrically erasable
Memory write EEPROM, flash memory FLASH, disk or CD etc..The processor 12 is a kind of central processing unit
(CPU), microcontroller (MCU), data processing chip or information process unit having data processing function.The display
Device 13 is the display screen containing LCD or LED display module, and face 3-D image and face for showing user correspond to internal organs
Lesion reflects the Skin Color Information of the skin chunk in area.
In the present embodiment, the program that the Chinese medicine image surface acquisition analysis system 10 is made of various computer program instructions
Module composition, including but not limited to, optical imagery module 101, image surface building module 102, face segmentation module 103 and skin
Color extraction module 104.The so-called module of the present invention refers to that one kind can be executed by processor 11 and can complete fixed function
Series of computation machine program instruction section, be stored in memory 10, the function of each module illustrated below in conjunction with Fig. 2
Energy.
Refering to what is shown in Fig. 2, being the flow chart of the preferred embodiment of Chinese medicine image surface capturing analysis method of the present invention.In this implementation
In example, the various method and steps of the Chinese medicine image surface capturing analysis method are realized by computer software programs, the computer
Software program is stored in computer readable storage medium (such as memory 11) in the form of computer program instructions, computer
Readable storage medium storing program for executing may include: read-only memory, random access memory, disk or CD etc., the computer program instructions energy
It is enough to be loaded by processor (such as processor 12) and execute following steps S21 to step S28.
Step S21 constructs the optical imaging system of digital camera 2;In the present embodiment, optical imagery module 101 constructs
The optical imaging system of digital camera 2.Specifically, optical imagery module 101 construct digital camera 2 optical imaging system according to
Following steps realize: step a, by microcontroller 20 be turned up camera lens 22 resolution ratio, digital camera 2 need to face into
Row repeatedly imaging, in face imaging process, not only face can be imaged in actual view, the void reflected by taper reflection 21
Quasi- viewpoint can also be imaged face.In the present embodiment, the resolution ratio of camera lens 22 can be turned up in optical imagery module 101,
Thus digital camera 2 can be made to obtain more pixels, that is, obtain more face informations, and then is three-dimensional for reconstruct face
Image provides sufficient characteristic point;Step b generates regulating command, microcontroller according to the distance between face and camera lens 22
Device 20 adjusts the optical tube length between taper reflection 21 and camera lens 22 according to regulating command.In the present embodiment, optics
The optical imaging system that image-forming module 101 constructs digital camera 2 needs hollow rotational symmetry mirror, due to the view of taper reflection 22
Field is relatively large, therefore optical imagery module 101 generates regulating command, microcontroller according to the distance between face and camera lens 22
Suitable optical tube length is adjusted according to regulating command adjusting to improve the albedo of mirror surface in device 20, guarantees to obtain face information
Integrality.
Step S22 obtains face X-Y scheme using the human face data of the optical imaging system acquisition user of digital camera 2
Picture;In the present embodiment, when the face of user is close to camera lens 22 and presses the camera shooting button of digital camera 2, image surface structure
Block 102 is modeled using the human face data of the optical imaging system acquisition user of digital camera 2, obtains face two dimensional image.
Step S23 carries out affine transformation to face two dimensional image, obtains the multi-view image of three different points of view of face;
Specifically, since light is after taper internal reflector 21, multi-view image is formed in digital camera 2, the light on face only passes through
The i.e. reachable imaging focal plane of primary event is crossed, to complete Multi-visual point image.In the present embodiment, image surface constructs module 102
Affine transformation is carried out to the face two dimensional image of acquisition, the radial line in face two dimensional image is extracted in affine transformation and along water
Square to formed a new image, new image is divided into three parts in proportion in the horizontal direction according to Multi-visual point image principle,
Three viewpoints for respectively corresponding digital camera 2, to obtain the multi-view image of three different points of view of face.
Step S24 carries out three-dimensional weight using multi-view image of the multi-viewpoint three-dimensional matching method to three different points of view of face
Structure obtains face 3-D image;In the present embodiment, image surface building module 102 is using multi-viewpoint three-dimensional matching method to obtaining
The multi-view image of three different points of view of face carries out stereo reconstruction, obtains the corresponding depth information of two-dimension human face pixel, i.e.,
It can obtain the face 3-D image with face three-dimensional structure.The multi-viewpoint three-dimensional matching method is in the prior art to multiple views
Image carries out the common technology of stereo reconstruction, this example does not repeat specifically.
Step S25 carries out Face detection using face each section region of the integral projection method to face 3-D image;At this
In embodiment, face divides module 103 and carries out face using face each section region of the integral projection method to face 3-D image
Positioning, the integral projection method are that the algorithm of grey scale change Min-max is found for gray level image.Specifically, face is divided
Module 103 carries out Face detection using face each section region of the integral projection method to face 3-D image and implements step
Are as follows: face 3-D image is converted into grayscale image, integral projection is carried out in the horizontal direction for grayscale image and obtains integral curve;?
First apparent trough corresponds to the left margin of face on integral curve, the last one apparent trough corresponds to the right side of face
Boundary;The right boundary and then the secondary integral projection for carrying out part to gray level image of face are obtained, is equally had on integral curve
Four apparent troughs, respectively obtain the position of eyebrow, eyes, nostril and mouth.
Step S26 corresponds to model according to facial internal organs and extracts five partial responses from oriented face 3-D image
Skin chunk;In the present embodiment, face segmentation module 103 using facial internal organs correspond to model according to orient eyebrow, eyes,
Five forehead, left cheek, nasal surface, right cheek, chin representative regions are extracted from face 3-D image in nostril and the position of mouth
Skin chunk.In theory of traditional Chinese medical science, human face region is divided into five parts in traditional Chinese medical science field, and it is pre- that the face internal organs correspond to model
It is first stored in memory 11, the prespecified each part of face corresponds to the lesion reflecting regional of different internal organs, and dirty
The lesion of internal organs can change the variation of the color of face corresponding region, therefore a facial image, not need using whole works
For diagnostic characteristic, it is only necessary to a part of skin chunk of corresponding region, therefore the present invention by face figure be divided into forehead, left cheek,
Five nasal surface, right cheek, chin representative regions, and need to extract the skin chunk of five partial responses.
Step S27, the dominant hue for extracting each skin chunk obtains the main pixel for accounting for main component, and seeks main pixel
Skin Color Information of the mean value as each skin chunk.Since the color resolution of human face region is easy to be influenced by other factors,
Such as black mole, the biggish freckle of density etc., therefore after the skin chunk for extracting corresponding internal organs region, need to reject the black mole on face
With the influence of blackspot, its interference is effectively avoided.Due to still accounting for sub-fraction pixel for black mole and blackspot Relative Skin region
Point, therefore in this embodiment, skin cluster module 104 extracts the master of each skin chunk using the domain color description of MEPG-7
Tone, so that the main pixel that the skin chunk accounts for main component is obtained, using HSV (Hue, Saturation, Value) spatial mode
Type seeks Skin Color Information of the mean value of main pixel as each skin chunk.The present invention extracts five skins to every width facial image
Block, each skin chunk mean value state its color value, i.e., spy of the one 15 dimension color vector as the facial image with three amounts
Levy vector.It is influenced to mitigate illumination bring, the present invention seeks color lump mean value using HSV space model, as each skin
The Skin Color Information of block.The HSV space model is a kind of color space created according to the intuitive nature of color, in this model
The parameter of color is respectively: tone (H), saturation degree (S), lightness (V), is capable of the colour of skin of each skin chunk of directviewing description, such as
Normal color, black, cyan, redness of the skin or complexion, white, yellow etc..
The Skin Color Information of the face 3-D image of user and each skin chunk is stored in memory 11 and shown by step S28
Show on the monitor 13;In the present embodiment, skin cluster module 104 is by the face 3-D image of user and each skin chunk
Skin Color Information is stored in memory 11 and shows that on the monitor 13, doctor is by watching the viscera lesions reflecting regional pair of user
The Skin Color Information for each skin chunk answered is doctor so that doctor be assisted to understand whether internal organs occur lesion and severity
Clinical diagnosis (such as lesion situation of diagnosis internal organs) is carried out to user, Chinese medicine facial diagnosis foundation is provided.
Chinese medicine image surface acquisition and analysis device of the present invention and method, due to when capturing facial image construct optics at
Picture system obtains clearly face two dimensional image, and carries out three-dimensionalreconstruction to face according to face two dimensional image and obtain face three-dimensional
Image can be realized all structures, texture and the depth information that face is obtained in single face two dimensional image, to make to obtain
Face information it is more complete.In addition, the feature of present invention combination face, which carries out internal organs reflecting regional to facial image, is divided into five
A representative region skin chunk, and analysis complexion information is carried out to the complexion information of five representative region skin chunks, in certain journey
It can satisfy the demand that doctor carries out Chinese medicine facial diagnosis on degree, auxiliary traditional Chinese medicine diagnosis improves the accuracy of Chinese medicine facial diagnosis result.
It will be understood by those skilled in the art that all or part of the steps of various methods can pass through in above embodiment
Relative program instruction is completed, which can store in computer readable storage medium, and storage medium may include: read-only deposits
Reservoir, random access memory, disk or CD etc..
The above is only a preferred embodiment of the present invention, is not intended to limit the scope of the invention, all to utilize this hair
Equivalent structure or equivalent flow shift made by bright specification and accompanying drawing content is applied directly or indirectly in other relevant skills
Art field, is included within the scope of the present invention.
Claims (10)
1. a kind of Chinese medicine image surface acquisition and analysis device, including digital camera, it is adapted for carrying out the processing of various computer program instructions
Device and the memory suitable for storing a plurality of computer program instructions, which is characterized in that the computer program instructions are by handling
Device loads and executes following steps:
Construct the optical imaging system of digital camera;
Using the human face data of the optical imaging system acquisition user of digital camera, face two dimensional image is obtained;
Affine transformation is carried out to face two dimensional image, obtains the multi-view image of three different points of view of face;
Stereo reconstruction is carried out using multi-view image of the multi-viewpoint three-dimensional matching method to three different points of view of face, obtains face three
Tie up image;
Face detection is carried out using face each section region of the integral projection method to face 3-D image;
Model, which is corresponded to, according to facial internal organs extracts the skin that viscera corresponds to five parts of face from the face 3-D image of positioning
Skin block;
The dominant hue for extracting each skin chunk obtains the main pixel of each skin chunk, and seeks the mean value of main pixel as every
The Skin Color Information of one skin chunk.
2. Chinese medicine image surface acquisition and analysis device as described in claim 1, which is characterized in that the computer program instructions by
Reason device load, which is also executed the following steps:, is stored in memory for the Skin Color Information of the face 3-D image of user and each skin chunk
In and show over the display.
3. Chinese medicine image surface acquisition and analysis device as described in claim 1, which is characterized in that the digital camera includes in circular cone
Reflecting mirror, camera lens and microcontroller, wherein the step of optical imaging system of the building digital camera includes following step
It is rapid:
The resolution ratio of camera lens is turned up by microcontroller;
Lens barrel regulating command is generated according to the distance between face and camera lens, microcontroller is adjusted according to lens barrel regulating command
Optical tube length between taper reflection and camera lens.
4. Chinese medicine image surface acquisition and analysis device as described in claim 1, which is characterized in that described to use integral projection method to people
Face each section region of face 3-D image carries out the specific implementation step of Face detection are as follows:
Face 3-D image is converted into grayscale image;
It carries out integral projection in the horizontal direction for grayscale image and obtains integral curve, first apparent trough on integral curve
The left margin of face is corresponded to, the last one apparent trough corresponds to the right margin of face;
The right boundary and then the secondary integral projection for carrying out part to gray level image of face are obtained, is oriented on integral curve
Four troughs, respectively obtain the position of eyebrow, eyes, nostril and mouth.
5. Chinese medicine image surface acquisition and analysis device as claimed in claim 4, which is characterized in that the skin chunk of five parts is
Five forehead, left cheek, nasal surface, right cheek, chin representative regions, the dominant hue of each skin chunk use the domain color of MEPG-7
Description obtains the main pixel of the skin chunk, and the mean value of the main pixel of each skin chunk calculated using HSV space model
It obtains.
6. a kind of Chinese medicine image surface capturing analysis method is applied in Chinese medicine image surface acquisition and analysis device, Chinese medicine image surface acquisition point
Analysis apparatus includes digital camera, which is characterized in that the method comprising the steps of:
Construct the optical imaging system of digital camera;
Using the human face data of the optical imaging system acquisition user of digital camera, face two dimensional image is obtained;
Affine transformation is carried out to face two dimensional image, obtains the multi-view image of three different points of view of face;
Stereo reconstruction is carried out using multi-view image of the multi-viewpoint three-dimensional matching method to three different points of view of face, obtains face three
Tie up image;
Face detection is carried out using face each section region of the integral projection method to face 3-D image;
Model, which is corresponded to, according to facial internal organs extracts the skin that viscera corresponds to five parts of face from the face 3-D image of positioning
Skin block;
The dominant hue for extracting each skin chunk obtains the main pixel of each skin chunk, and seeks the mean value of main pixel as every
The Skin Color Information of one skin chunk.
7. Chinese medicine image surface capturing analysis method as claimed in claim 6, which is characterized in that this method further includes following steps:
The face 3-D image of user and the Skin Color Information of each skin chunk are stored in memory and shown over the display.
8. Chinese medicine image surface capturing analysis method as claimed in claim 6, which is characterized in that the digital camera includes in circular cone
Reflecting mirror, camera lens and microcontroller, wherein the step of optical imaging system of the building digital camera includes following step
It is rapid:
The resolution ratio of camera lens is turned up by microcontroller;
Lens barrel regulating command is generated according to the distance between face and camera lens, microcontroller is adjusted according to lens barrel regulating command
Optical tube length between taper reflection and camera lens.
9. Chinese medicine image surface capturing analysis method as claimed in claim 6, which is characterized in that described to use integral projection method to people
Face each section region of face 3-D image carries out the specific implementation step of Face detection are as follows:
Face 3-D image is converted into grayscale image;
It carries out integral projection in the horizontal direction for grayscale image and obtains integral curve, first apparent trough on integral curve
The left margin of face is corresponded to, the last one apparent trough corresponds to the right margin of face;
The right boundary and then the secondary integral projection for carrying out part to gray level image of face are obtained, is oriented on integral curve
Four troughs, respectively obtain the position of eyebrow, eyes, nostril and mouth.
10. Chinese medicine image surface capturing analysis method as claimed in claim 9, which is characterized in that the skin chunk of five parts
For five forehead, left cheek, nasal surface, right cheek, chin representative regions, the dominant hue of each skin chunk uses the main face of MEPG-7
Color description obtains the main pixel of the skin chunk, and the mean value of the main pixel of each skin chunk uses HSV space model meter
It obtains.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711410285.6A CN109953743A (en) | 2017-12-23 | 2017-12-23 | Chinese medicine image surface acquisition and analysis device and method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711410285.6A CN109953743A (en) | 2017-12-23 | 2017-12-23 | Chinese medicine image surface acquisition and analysis device and method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109953743A true CN109953743A (en) | 2019-07-02 |
Family
ID=67020049
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711410285.6A Pending CN109953743A (en) | 2017-12-23 | 2017-12-23 | Chinese medicine image surface acquisition and analysis device and method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109953743A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111227795A (en) * | 2020-01-13 | 2020-06-05 | 天津众阳科技有限公司 | Method for extracting color change information of human face reflection area |
CN113197549A (en) * | 2021-04-29 | 2021-08-03 | 南通大学 | System for diagnosing diseases through face recognition technology |
-
2017
- 2017-12-23 CN CN201711410285.6A patent/CN109953743A/en active Pending
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111227795A (en) * | 2020-01-13 | 2020-06-05 | 天津众阳科技有限公司 | Method for extracting color change information of human face reflection area |
CN111227795B (en) * | 2020-01-13 | 2022-07-22 | 天津众阳科技有限公司 | Method for extracting color change information of human face reflection area |
CN113197549A (en) * | 2021-04-29 | 2021-08-03 | 南通大学 | System for diagnosing diseases through face recognition technology |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10667697B2 (en) | Identification of posture-related syncope using head-mounted sensors | |
US9445713B2 (en) | Apparatuses and methods for mobile imaging and analysis | |
CN105392423B (en) | The motion tracking system of real-time adaptive motion compensation in biomedical imaging | |
EP3046478B1 (en) | Image analysis techniques for diagnosing diseases | |
JP2019525786A (en) | System and method for automatically detecting, locating, and semantic segmentation of anatomical objects | |
CN107909622B (en) | Model generation method, medical imaging scanning planning method and medical imaging system | |
JP4692526B2 (en) | Gaze direction estimation apparatus, gaze direction estimation method, and program for causing computer to execute gaze direction estimation method | |
CN110490860A (en) | Diabetic retinopathy recognition methods, device and electronic equipment | |
US20220125280A1 (en) | Apparatuses and methods involving multi-modal imaging of a sample | |
JP4936491B2 (en) | Gaze direction estimation apparatus, gaze direction estimation method, and program for causing computer to execute gaze direction estimation method | |
CN109215104B (en) | Brain structure image display method and device for transcranial stimulation treatment | |
Liu et al. | Multimodal MRI brain tumor image segmentation using sparse subspace clustering algorithm | |
CN110472546B (en) | Infant non-contact eye movement feature extraction device and method | |
CN109953743A (en) | Chinese medicine image surface acquisition and analysis device and method | |
CN105426808B (en) | Sagittal line drift measurement method and system in brain | |
Bucioli et al. | Holographic real time 3D heart visualization from coronary tomography for multi-place medical diagnostics | |
CN116997928A (en) | Method and apparatus for generating anatomical model using diagnostic image | |
KR102433473B1 (en) | Method, apparatus and computer program for providing augmented reality based medical information of patient | |
US20220137909A1 (en) | Method and product for multi-device ai linkage displaying of a vrds 4d medical image | |
KR102495889B1 (en) | Method for detecting facial wrinkles using deep learning-based wrinkle detection model trained according to semi-automatic labeling and apparatus for the same | |
CN109961843A (en) | Chinese medicine facial diagnosis information remote acquisition system and method | |
WO2017017590A1 (en) | Apparatus and method for detection, quantification and classification of epidermal lesions | |
Tang et al. | Unity Human Eye Model for Gaze Tracking with a Query-Driven Dynamic Vision Sensor | |
Cheng et al. | MCSTransWnet: A new deep learning process for postoperative corneal topography prediction based on raw multimodal data from the Pentacam HR system | |
WO2022173056A1 (en) | Skin state inference method, device, program, system, trained model generation method, and trained model |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20190702 |
|
WD01 | Invention patent application deemed withdrawn after publication |