CN110363175A - Image processing method, device and electronic equipment - Google Patents
Image processing method, device and electronic equipment Download PDFInfo
- Publication number
- CN110363175A CN110363175A CN201910665032.6A CN201910665032A CN110363175A CN 110363175 A CN110363175 A CN 110363175A CN 201910665032 A CN201910665032 A CN 201910665032A CN 110363175 A CN110363175 A CN 110363175A
- Authority
- CN
- China
- Prior art keywords
- face
- key point
- sample data
- location information
- model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/172—Classification, e.g. identification
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Oral & Maxillofacial Surgery (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Geometry (AREA)
- Software Systems (AREA)
- Computer Graphics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Processing Or Creating Images (AREA)
Abstract
Image processing method, device and electronic equipment provided in an embodiment of the present invention, are related to technical field of image processing.Described image processing method includes: to generate three-dimensional face model according to the face direct picture of acquisition；The sample data including location information of face's key point under different angle is generated according to the three-dimensional face model；The location information for the face's key point being analysed in facial image is matched with the location information of face's key point in the sample data, obtains the shape information of face's organ in the facial image to be analyzed.By above-mentioned setting, can improve in the prior art due to needing to acquire the facial image under different angle and the problem of that there is human costs is high, low efficiency.
Description
Technical field
The present invention relates to technical field of image processing, set in particular to a kind of image processing method, device and electronics
It is standby.
Background technique
The face analysis to extend out from human face detection and tracing, is a kind of face character identification technology of refinement,
There is demand in the fields such as game interaction, beauty makeups, advertisement dispensing, market survey, future is in intelligent movable hardware terminal
Also it will obtain and widely use.Wherein, in the human face five-sense-organ shape the matching analysis based on key point, facial image will be tested
Face key point matched with the human face five-sense-organ key point in sample set, can be tested by the smallest matching error
The shape of facial image face.
But through inventor the study found that in the prior art, can also pass through to improve the matched accuracy of key point
The facial image of acquisition different angle carrys out additional sample collection.Thus, the problem of that there is human costs is high, low efficiency.
Summary of the invention
In view of this, the purpose of the present invention is to provide a kind of image processing method, device and electronic equipment, it is existing to improve
There is the problem of technology.
To achieve the above object, the embodiment of the present invention adopts the following technical scheme that
A kind of image processing method, comprising:
Three-dimensional face model is generated according to the face direct picture of acquisition；
The sample number including location information of face's key point under different angle is generated according to the three-dimensional face model
According to；
It is analysed to face's key point in the location information and the sample data of face's key point in facial image
Location information is matched, and the shape information of face's organ in the facial image to be analyzed is obtained.
It is described that three-dimensional face model is generated according to the face direct picture of acquisition in the embodiment of the present invention preferably selects
The step of, comprising:
Obtain multiple face direct pictures with different shape type face organ；
Three-dimensional face model is generated respectively according to the multiple face direct picture, is obtained multiple with different shape type
The three-dimensional face model of face's organ.
It is described that three-dimensional people is generated according to the multiple face direct picture respectively in the embodiment of the present invention preferably selects
The step of face model, comprising:
Obtain the location information of the corresponding face's key point of each face direct picture；
According to the location information of each face direct picture face's key point corresponding with the face direct picture point
It Sheng Cheng not three-dimensional face model.
It is described to obtain the corresponding face's key of each face direct picture in the embodiment of the present invention preferably selects
The step of location information of point, specifically:
Face's key is obtained by predetermined face's key point location model in each face direct picture
The location information of point.
In the embodiment of the present invention preferably selects, the sample data is multiple groups, and every group of sample data is according to wherein one
A three-dimensional face model generates, the location information of the face's key point being analysed in facial image and the sample data
The location information of middle face's key point is matched, and the step of the shape information of face's organ in the facial image to be analyzed is obtained
Suddenly, comprising:
It is analysed to face in the location information and predetermined one group of sample data of face's key point of facial image
The location information of key point is matched, and the angle information of the facial image to be analyzed is obtained；
Extract the location information of face's key point of facial image to be analyzed respectively, and and every group of sample data in it is described
The location information of the corresponding face's key point of angle information is matched, and the shape of the facial image face to be analyzed organ is obtained
Shape information.
In the embodiment of the present invention preferably selects, described image processing method further includes predefining one group of sample data
The step of, which includes:
One group of sample data is determined in multiple groups sample data based on the operation of user.
In the embodiment of the present invention preferably selects, described image processing method further includes predefining one group of sample data
The step of, which includes:
For each threedimensional model, the mean value of the similarity of the threedimensional model and other threedimensional models is calculated, is obtained multiple
Mean value；
The corresponding threedimensional model of mean value maximum in multiple mean values is determined as object module, and will be according to the object module
The sample data of generation is as predetermined one group of sample data.
The embodiment of the invention also provides a kind of image processing apparatus, comprising:
Three-dimensional face model generation module, for generating three-dimensional face model according to the face direct picture of acquisition；
Sample data generation module includes face's key point in different angle for being generated according to the three-dimensional face model
Under location information sample data；
In matching module, the location information of face's key point for being analysed in facial image and the sample data
The location information of face's key point is matched, and the shape information of face's organ in the facial image to be analyzed is obtained.
In the embodiment of the present invention preferably selects, the three-dimensional face model generation module includes:
Face direct picture acquisition submodule, for obtaining multiple faces front with different shape type face organ
Image；
Three-dimensional face model generates submodule, for generating three-dimensional face mould respectively according to the multiple face direct picture
Type obtains multiple three-dimensional face models with different shape type face organ.
The embodiment of the invention also provides a kind of electronic equipment, including memory and processor, the processor is for holding
The executable computer program stored in the row memory, to realize above-mentioned image processing method.
Image processing method, device and electronic equipment provided in an embodiment of the present invention generate three by face direct picture
Faceform is tieed up, the sample number including location information of face's key point under different angle is generated according to three-dimensional face model
According to, and matched with the location information of face's key point of facial image to be analyzed, to obtain face in facial image to be analyzed
The shape information of portion's organ.Therefore it may only be necessary to acquire face direct picture, avoids and need to pass through Image Acquisition in the prior art
The problem of facial image under equipment acquisition different angle carrys out additional sample collection, low efficiency high so as to improve human cost.
Detailed description of the invention
In order to illustrate the technical solution of the embodiments of the present invention more clearly, below will be to needed in the embodiment attached
Figure is briefly described, it should be understood that the following drawings illustrates only certain embodiments of the present invention, therefore is not construed as pair
The restriction of range for those of ordinary skill in the art without creative efforts, can also be according to this
A little attached drawings obtain other relevant attached drawings.
Fig. 1 is the structural block diagram of electronic equipment provided in an embodiment of the present invention.
Fig. 2 is the flow diagram of image processing method provided in an embodiment of the present invention.
Fig. 3 is the flow diagram of step S100 provided in an embodiment of the present invention.
Fig. 4 is the flow diagram of step S120 provided in an embodiment of the present invention.
Fig. 5 is the schematic diagram of face's key point in face direct picture provided in an embodiment of the present invention.
Fig. 6 is the schematic diagram of face's key point under face face image multi-angle provided in an embodiment of the present invention.
Fig. 7 is the structural block diagram of image processing apparatus provided in an embodiment of the present invention.
Icon: 10- electronic equipment；12- memory；14- processor；100- image processing apparatus；110- three-dimensional face mould
Type generation module；120- sample data generation module；130- matching module.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiment of the present invention, instead of all the embodiments.The present invention being usually described and illustrated herein in the accompanying drawings is implemented
The component of example can be arranged and be designed with a variety of different configurations.
Therefore, the detailed description of the embodiment of the present invention provided in the accompanying drawings is not intended to limit below claimed
The scope of the present invention, but be merely representative of selected embodiment of the invention.Based on the embodiments of the present invention, this field is common
Technical staff's every other embodiment obtained without making creative work belongs to the model that the present invention protects
It encloses.
It should also be noted that similar label and letter indicate similar terms in following attached drawing, therefore, once a certain Xiang Yi
It is defined in a attached drawing, does not then need that it is further defined and explained in subsequent attached drawing.
As shown in Figure 1, the embodiment of the invention provides a kind of electronic equipment 10.The electronic equipment 10 may include memory
12, processor 14 and image processing apparatus 100.It is directly or indirectly electrically connected between the memory 12 and processor 14,
To realize the transmission or interaction of data.For example, can be realized electrically by one or more communication bus or signal wire between each other
Connection.Described image processing unit 100 includes described at least one can be stored in the form of software or firmware (firmware)
Software function module in memory 12.The processor 14 is for executing the executable calculating stored in the memory 12
Machine program, for example, software function module included by described image processing unit 100 and computer program etc., to realize image
Processing method.
Wherein, the memory 12 may be, but not limited to, random access memory (Random Access Memory,
RAM), read-only memory (Read Only Memory, ROM), programmable read only memory (Programmable Read-Only
Memory, PROM), erasable read-only memory (Erasable Programmable Read-Only Memory, EPROM),
Electricallyerasable ROM (EEROM) (Electric Erasable Programmable Read-Only Memory, EEPROM) etc..
The processor 14 may be a kind of IC chip, the processing capacity with signal.Above-mentioned processor 14
It can be general processor, including central processing unit (Central Processing Unit, CPU), network processing unit
(Network Processor, NP), system on chip (System on Chip, SoC) etc..
It is appreciated that structure shown in FIG. 1 is only to illustrate, the electronic equipment 10 may also include more than shown in Fig. 1
Perhaps less component or with the configuration different from shown in Fig. 1.
In conjunction with Fig. 2, the embodiment of the present invention also provides a kind of image processing method that can be applied to above-mentioned electronic equipment 10.Its
In, method and step defined in the related process of described image processing method can be realized by the electronic equipment 10.Below will
Detailed process shown in Fig. 2 is described in detail.
Step S100 generates three-dimensional face model according to the face direct picture of acquisition.
In detail, the particular number of the face direct picture is unrestricted, can be set according to practical application request
It sets.For example, in one embodiment, the particular number of the face direct picture can be one.In another embodiment, described
The particular number of face direct picture can be multiple.
Step S200, being generated according to the three-dimensional face model includes location information of face's key point under different angle
Sample data.
In detail, the specific type of face's organ is unrestricted, can be configured according to practical application request.Example
Such as, in the present embodiment, face's organ may include at least one of eyebrow, eyes, nose and mouth.
Wherein, the specific angle of face's key point is unrestricted, can be configured according to practical application request.Example
Such as, in the present embodiment, the specific angle of face's key point may include the angle of both direction, respectively face upward head to low
Head and left side to right side.Wherein, because angle is continuously, the particular number of the angle can be according to practical application need
It asks and is configured, project to the three-dimensional face model on two-dimensional surface for example, 5 degree can be spaced, to generate corresponding face
The sample data of the location information of portion's key point.
Step S300 is analysed to face in the location information and the sample data of face's key point in facial image
The location information of key point is matched, and the shape information of face's organ in the facial image to be analyzed is obtained.
In detail, that location information is carried out matched concrete mode is unrestricted, can be carried out according to practical application request
Setting.For example, in the present embodiment, carrying out matched concrete mode can be Procrustes Analysis matching.
Wherein, the shape information is specially the shape of face's organ.For example, the shape of eyebrow may include standard eyebrow,
Arched eyebrows, flat eyebrow, knife eyebrow, straight eyebrows slanting upwards and outwards, distant mountain eyebrow or tall eyebrow.
With the above arrangement, only needing to acquire face direct picture to generate three-dimensional face model, according to three-dimensional face mould
Type generates the sample data including location information of face's key point under different angle, and the face with facial image to be analyzed
The location information of key point is matched, and to obtain the shape information of face's organ in facial image to be analyzed, is avoided existing
Need to acquire the facial image under different angle in technology by image capture device come additional sample collection, so as to improve manpower
The problem of at high cost, low efficiency.
In conjunction with Fig. 3, when the particular number of the face direct picture is multiple, the step S100 may include step
S110 and step S120, to obtain multiple three-dimensional face models, with the quantity of exptended sample data, thus improve it is matched accurate
Property, the accuracy for obtaining the shape information of face's organ in the facial image to be analyzed is higher.
Step S110 obtains multiple face direct pictures with different shape type face organ.
Wherein, since everyone face's organ is different, therefore, it is possible to be directed to multiple people, everyone people is obtained respectively
Face direct picture obtains multiple face direct pictures with different face's organs.
Step S120 generates three-dimensional face model according to the multiple face direct picture respectively, obtains multiple with not
The three-dimensional face model of similar shape type face organ.
Different based on the mode for generating three-dimensional face model, step S120 may include different step.For example, in one kind
In the example that can be substituted, in conjunction with Fig. 4 and Fig. 5, the step S120 may include step S121 and step S122.
Step S121 obtains the location information of the corresponding face's key point of each face direct picture.
Wherein, the location information can be specially the two-dimensional coordinate of face's key point.
The location information step for obtaining face's key point in each face direct picture, can be with specifically:
Face's key point is obtained by predetermined face's key point location model in each face direct picture
Location information.
Specifically, predetermined face's key point location model, the face can be obtained by way of deep learning
Key point location model can be indicated with function f (I), and face direct picture is inputted the location model, is exported as comprising two
Tie up the point set P (x, y) of coordinate.
Step S122, according to the position of each face direct picture face's key point corresponding with the face direct picture
Confidence breath generates three-dimensional face model respectively.
In detail, the concrete mode for generating three-dimensional face model is unrestricted, can be set according to practical application request
It sets.For example, in one embodiment, the face direct picture may include the depth information of face's organ, the face front elevation
As the location information of corresponding face's key point is specially the two-dimensional coordinate of face's key point, according to the depth information and
The corresponding three-dimensional face model of the facial image can be generated in two-dimensional coordinate.
Further, the particular number of the face direct picture be it is multiple when, the three-dimensional face model it is specific
Quantity be it is multiple, the corresponding sample data generated is multiple groups, and every group of sample data is according to one of three-dimensional face model
It generates (for example, as shown in fig. 6, one group of sample data may include facing upward head to 2 angles bowed on direction, respectively angle 1
With angle 2,5 angles on left side to right side direction, respectively angle A, angle B, angle C, angle D and angle E).
The step S300 may comprise steps of:
It is analysed to face in the location information and predetermined one group of sample data of face's key point of facial image
The location information of key point is matched, and the angle information of the facial image to be analyzed is obtained.Face to be analyzed is extracted respectively
The location information of face's key point of image, and and every group of sample data in face corresponding with angle information key point
Location information is matched, and the shape information of the facial image face to be analyzed organ is obtained.
In detail, every group of sample data includes the position of face key point of the corresponding three-dimensional face model under different angle
Confidence breath, that is to say, that the location information of face's key point of facial image to be analyzed can with it is multiple in multiple groups sample data
The location information of face's key point under angle is matched, to obtain the angle information of the facial image to be analyzed.
In order to improve operation efficiency, the location information of face's key point of facial image can be analysed to and predefined
One group of sample data in the location information of face's key point matched, wherein the smallest sample data of matching error is corresponding
Angle be facial image to be analyzed angle.
For example, the location information of face's key point of facial image can be analysed to respectively and in first group of sample data
The location information of face's key point is matched under 5 angles, and obtained matching error is respectively 3,2,4,6 and 10, wherein the
The corresponding error of two angles is minimum, hence, it can be determined that the angle of facial image to be analyzed is second angle.
The location information for being analysed to face's key point of facial image after determining angle and institute in every group of sample data
The location information for stating the corresponding face's key point of angle information is matched, and can be obtained by the smallest sample data of matching error
To the shape information of the facial image face to be analyzed organ.By Secondary Match, the angle of facial image to be analyzed is first determined
Degree determines the shape information of facial image face to be analyzed organ again, so that the data volume of operation is reduced, to improve operation effect
Rate.
For example, the location information of face's key point of facial image and two groups of samples under second angle can be analysed to
The location information of data face key point is matched respectively, and obtained matching error is respectively 2 and 1, and second group of error is most
It is small, hence, it can be determined that the shape information of facial image face to be analyzed organ is the lower second group of sample data face of second angle
The shape information of portion's organ.
Optionally, predefine one group of sample data specific steps it is unrestricted, can according to practical application request into
Row setting.For example, in one embodiment, the specific steps for predefining one group of sample data include: that the operation based on user exists
One group of sample data is determined in multiple groups sample data.
For example, user can select corresponding sample data by selection three-dimensional face model, it can also be directly in multiple groups
One group of sample data is determined in sample data.
In another embodiment, the specific steps of predetermined one group of sample data include:
Firstly, being directed to each threedimensional model, the mean value of the similarity of the threedimensional model and other threedimensional models is calculated, is obtained
Multiple mean values.Then, the corresponding threedimensional model of mean value maximum in multiple mean values is determined as object module.Finally, and by root
The sample data generated according to the object module is as predetermined one group of sample data.
For example, when the quantity of threedimensional model is three, respectively the first threedimensional model, the second threedimensional model and the three or three
Dimension module.The similarity of first threedimensional model and the second threedimensional model and third threedimensional model is respectively 5 and 6, is calculated
First similarity mean value is 5.5.The similarity of second threedimensional model and the first threedimensional model and third threedimensional model be respectively 5 and
3, the second similarity mean value being calculated is 4.Third threedimensional model and the first threedimensional model and the second threedimensional model it is similar
Degree is respectively 6 and 3, and the first similarity mean value being calculated is 4.5.Maximum mean value is the first similarity mean value, i.e., by the
One threedimensional model is determined as target three-dimensional.
In detail, one can be obtained most by way of calculating the similarity of threedimensional model and other threedimensional models
Representational threedimensional model is as object module, and using the sample data generated according to the object module as predetermined
One group of sample data obtains so that facial image to be analyzed and the progress of predetermined one group of sample data are matched more efficient
To angle information taking property of standard it is higher.
In conjunction with Fig. 7, the embodiment of the invention also provides a kind of image processing apparatus 100, can be applied to the electronics and set
Standby 10.Wherein, which may include three-dimensional face model generation module 110, sample data generation module
120 and matching module 130.
Three-dimensional face model generation module 110, for generating three-dimensional face model according to the face direct picture of acquisition.?
In the present embodiment, the three-dimensional face model generation module 110 can be used for executing step S100 shown in Fig. 2, about described
The related content of three-dimensional face model generation module 110 is referred to the description to step S100 above.
Sample data generation module 120 includes face's key point in difference for being generated according to the three-dimensional face model
The sample data of location information under angle.In the present embodiment, the sample data generation module 120 can be used for executing figure
Step S200 shown in 2, the related content about the sample data generation module 120 are referred to above to step S200's
Description.
Matching module 130, the location information and the sample number of face's key point for being analysed in facial image
It is matched according to the location information of middle face's key point, obtains the shape information of face's organ in the facial image to be analyzed.
In the present embodiment, the matching module 130 can be used for executing step S300 shown in Fig. 2, about the matching module 130
Related content be referred to the description to step S300 above.
Further, the three-dimensional face model generation module 110 may include face direct picture acquisition submodule and
Three-dimensional face model generates submodule.
Face direct picture acquisition submodule, for obtaining multiple faces front with different shape type face organ
Image.In the present embodiment, the face direct picture acquisition submodule can be used for executing step S110 shown in Fig. 3, close
The description to step S110 above is referred in the related content of the face direct picture acquisition submodule.
Three-dimensional face model generates submodule, for generating three-dimensional face mould respectively according to the multiple face direct picture
Type obtains multiple three-dimensional face models with different shape type face organ.In the present embodiment, the three-dimensional face mould
Type, which generates submodule, can be used for executing step S120 shown in Fig. 3, and the phase of submodule is generated about the three-dimensional face model
Hold inside the Pass and is referred to the description to step S120 above.
In conclusion image processing method provided in an embodiment of the present invention, device and electronic equipment 10, pass through face front
Image generates three-dimensional face model, and being generated according to three-dimensional face model includes location information of face's key point under different angle
Sample data, and matched with the location information of face's key point of facial image to be analyzed, to obtain face to be analyzed
The shape information of face's organ in image.Therefore it may only be necessary to acquire face direct picture, avoids and need to pass through in the prior art
Facial image under image capture device acquisition different angle carrys out additional sample collection, the high, low efficiency so as to improve human cost
The problem of.
The foregoing is only a preferred embodiment of the present invention, is not intended to restrict the invention, for the skill of this field
For art personnel, the invention may be variously modified and varied.All within the spirits and principles of the present invention, made any to repair
Change, equivalent replacement, improvement etc., should all be included in the protection scope of the present invention.
Claims (10)
1. a kind of image processing method characterized by comprising
Three-dimensional face model is generated according to the face direct picture of acquisition；
The sample data including location information of face's key point under different angle is generated according to the three-dimensional face model；
It is analysed to the position of face's key point in the location information and the sample data of face's key point in facial image
Information is matched, and the shape information of face's organ in the facial image to be analyzed is obtained.
2. image processing method as described in claim 1, which is characterized in that described to be generated according to the face direct picture of acquisition
The step of three-dimensional face model, comprising:
Obtain multiple face direct pictures with different shape type face organ；
Three-dimensional face model is generated respectively according to the multiple face direct picture, is obtained multiple with different shape type face
The three-dimensional face model of organ.
3. image processing method as claimed in claim 2, which is characterized in that described according to the multiple face direct picture point
Not Sheng Cheng three-dimensional face model the step of, comprising:
Obtain the location information of the corresponding face's key point of each face direct picture；
It is given birth to respectively according to the location information of each face direct picture face's key point corresponding with the face direct picture
At three-dimensional face model.
4. image processing method as claimed in claim 3, which is characterized in that described to obtain each face direct picture pair
The step of location information for the face's key point answered, specifically:
Face's key point is obtained by predetermined face's key point location model in each face direct picture
Location information.
5. the image processing method as described in claim 2-4 any one, which is characterized in that the sample data is multiple groups,
Every group of sample data is generated according to one of three-dimensional face model, the face's key point being analysed in facial image
Location information is matched with the location information of face's key point in the sample data, is obtained in the facial image to be analyzed
The step of shape information of face's organ, comprising:
It is crucial to be analysed to face in the location information and predetermined one group of sample data of face's key point of facial image
The location information of point is matched, and the angle information of the facial image to be analyzed is obtained；
Extract the location information of face's key point of facial image to be analyzed respectively, and and every group of sample data in the angle
The location information of the corresponding face's key point of information is matched, and the shape letter of the facial image face to be analyzed organ is obtained
Breath.
6. image processing method as claimed in claim 5, which is characterized in that further include the step for predefining one group of sample data
Suddenly, which includes:
One group of sample data is determined in multiple groups sample data based on the operation of user.
7. image processing method as claimed in claim 5, which is characterized in that further include the step for predefining one group of sample data
Suddenly, which includes:
For each threedimensional model, the mean value of the similarity of the threedimensional model and other threedimensional models is calculated, multiple mean values are obtained；
The corresponding threedimensional model of mean value maximum in multiple mean values is determined as object module, and will be generated according to the object module
Sample data as predetermined one group of sample data.
8. a kind of image processing apparatus characterized by comprising
Three-dimensional face model generation module, for generating three-dimensional face model according to the face direct picture of acquisition；
Sample data generation module includes face's key point under different angle for being generated according to the three-dimensional face model
The sample data of location information；
Matching module, location information and the face in the sample data of face's key point for being analysed in facial image
The location information of key point is matched, and the shape information of face's organ in the facial image to be analyzed is obtained.
9. image processing apparatus as claimed in claim 8, which is characterized in that the three-dimensional face model generation module includes:
Face direct picture acquisition submodule, for obtaining multiple face front elevations with different shape type face organ
Picture；
Three-dimensional face model generates submodule, for generating three-dimensional face model respectively according to the multiple face direct picture,
Obtain multiple three-dimensional face models with different shape type face organ.
10. a kind of electronic equipment, which is characterized in that including memory and processor, the processor is for executing the storage
The executable computer program stored in device, to realize image processing method described in claim 1-7 any one.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910665032.6A CN110363175A (en) | 2019-07-23 | 2019-07-23 | Image processing method, device and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910665032.6A CN110363175A (en) | 2019-07-23 | 2019-07-23 | Image processing method, device and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110363175A true CN110363175A (en) | 2019-10-22 |
Family
ID=68221281
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910665032.6A Pending CN110363175A (en) | 2019-07-23 | 2019-07-23 | Image processing method, device and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110363175A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110852332A (en) * | 2019-10-29 | 2020-02-28 | 腾讯科技（深圳）有限公司 | Training sample generation method and device, storage medium and electronic equipment |
| CN111583105A (en) * | 2020-05-14 | 2020-08-25 | 厦门美图之家科技有限公司 | Portrait generation method, device, equipment and storage medium |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101593365A (en) * | 2009-06-19 | 2009-12-02 | 电子科技大学 | A kind of method of adjustment of universal three-dimensional human face model |
| CN101593272A (en) * | 2009-06-18 | 2009-12-02 | 电子科技大学 | A kind of human face characteristic positioning method based on the ASM algorithm |
| CN102486868A (en) * | 2010-12-06 | 2012-06-06 | 华南理工大学 | Average face-based beautiful face synthesis method |
| CN104915634A (en) * | 2015-02-16 | 2015-09-16 | 百度在线网络技术（北京）有限公司 | Image generation method based on face recognition technology and apparatus |
| CN105654048A (en) * | 2015-12-30 | 2016-06-08 | 四川川大智胜软件股份有限公司 | Multi-visual-angle face comparison method |
| CN107729875A (en) * | 2017-11-09 | 2018-02-23 | 上海快视信息技术有限公司 | Three-dimensional face identification method and device |
| CN107992835A (en) * | 2017-12-11 | 2018-05-04 | 浙江大学 | A kind of glasses image-recognizing method |
| US20180158230A1 (en) * | 2016-12-06 | 2018-06-07 | Activision Publishing, Inc. | Methods and Systems to Modify a Two Dimensional Facial Image to Increase Dimensional Depth and Generate a Facial Image That Appears Three Dimensional |
| CN108921038A (en) * | 2018-06-07 | 2018-11-30 | 河海大学 | A kind of classroom based on deep learning face recognition technology is quickly called the roll method of registering |
| CN108961149A (en) * | 2017-05-27 | 2018-12-07 | 北京旷视科技有限公司 | Image processing method, device and system and storage medium |
| CN109359575A (en) * | 2018-09-30 | 2019-02-19 | 腾讯科技（深圳）有限公司 | Method for detecting human face, method for processing business, device, terminal and medium |
| CN109753873A (en) * | 2018-11-23 | 2019-05-14 | 合刃科技（武汉）有限公司 | Image processing method and relevant apparatus |
| CN109819313A (en) * | 2019-01-10 | 2019-05-28 | 腾讯科技（深圳）有限公司 | Method for processing video frequency, device and storage medium |
| CN109978989A (en) * | 2019-02-26 | 2019-07-05 | 腾讯科技（深圳）有限公司 | Three-dimensional face model generation method, device, computer equipment and storage medium |
-
2019
- 2019-07-23 CN CN201910665032.6A patent/CN110363175A/en active Pending
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101593272A (en) * | 2009-06-18 | 2009-12-02 | 电子科技大学 | A kind of human face characteristic positioning method based on the ASM algorithm |
| CN101593365A (en) * | 2009-06-19 | 2009-12-02 | 电子科技大学 | A kind of method of adjustment of universal three-dimensional human face model |
| CN102486868A (en) * | 2010-12-06 | 2012-06-06 | 华南理工大学 | Average face-based beautiful face synthesis method |
| CN104915634A (en) * | 2015-02-16 | 2015-09-16 | 百度在线网络技术（北京）有限公司 | Image generation method based on face recognition technology and apparatus |
| CN105654048A (en) * | 2015-12-30 | 2016-06-08 | 四川川大智胜软件股份有限公司 | Multi-visual-angle face comparison method |
| US20180158230A1 (en) * | 2016-12-06 | 2018-06-07 | Activision Publishing, Inc. | Methods and Systems to Modify a Two Dimensional Facial Image to Increase Dimensional Depth and Generate a Facial Image That Appears Three Dimensional |
| CN108961149A (en) * | 2017-05-27 | 2018-12-07 | 北京旷视科技有限公司 | Image processing method, device and system and storage medium |
| CN107729875A (en) * | 2017-11-09 | 2018-02-23 | 上海快视信息技术有限公司 | Three-dimensional face identification method and device |
| CN107992835A (en) * | 2017-12-11 | 2018-05-04 | 浙江大学 | A kind of glasses image-recognizing method |
| CN108921038A (en) * | 2018-06-07 | 2018-11-30 | 河海大学 | A kind of classroom based on deep learning face recognition technology is quickly called the roll method of registering |
| CN109359575A (en) * | 2018-09-30 | 2019-02-19 | 腾讯科技（深圳）有限公司 | Method for detecting human face, method for processing business, device, terminal and medium |
| CN109753873A (en) * | 2018-11-23 | 2019-05-14 | 合刃科技（武汉）有限公司 | Image processing method and relevant apparatus |
| CN109819313A (en) * | 2019-01-10 | 2019-05-28 | 腾讯科技（深圳）有限公司 | Method for processing video frequency, device and storage medium |
| CN109978989A (en) * | 2019-02-26 | 2019-07-05 | 腾讯科技（深圳）有限公司 | Three-dimensional face model generation method, device, computer equipment and storage medium |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110852332A (en) * | 2019-10-29 | 2020-02-28 | 腾讯科技（深圳）有限公司 | Training sample generation method and device, storage medium and electronic equipment |
| CN110852332B (en) * | 2019-10-29 | 2020-12-01 | 腾讯科技（深圳）有限公司 | Training sample generation method and device, storage medium and electronic equipment |
| WO2021082885A1 (en) * | 2019-10-29 | 2021-05-06 | 腾讯科技（深圳）有限公司 | Method and device for generating training sample for semantic segmentation model, storage medium, and electronic device |
| US11934485B2 (en) | 2019-10-29 | 2024-03-19 | Tencent Technology (Shenzhen) Company Limited | Method and apparatus for generating training sample of semantic segmentation model, storage medium, and electronic device |
| CN111583105A (en) * | 2020-05-14 | 2020-08-25 | 厦门美图之家科技有限公司 | Portrait generation method, device, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR102063037B1 (en) | Identity authentication method, terminal equipment and computer readable storage medium | |
| CN108701216B (en) | Face recognition method and device and intelligent terminal | |
| WO2018028546A1 (en) | Key point positioning method, terminal, and computer storage medium | |
| CN105740780B (en) | Method and device for detecting living human face | |
| CN103577815B (en) | A kind of face alignment method and system | |
| CN109408653A (en) | Human body hair style generation method based on multiple features retrieval and deformation | |
| CN105740779B (en) | Method and device for detecting living human face | |
| CN107609383A (en) | 3D face identity authentications and device | |
| CN107748869A (en) | 3D face identity authentications and device | |
| CN107633165A (en) | 3D face identity authentications and device | |
| CN105335722A (en) | Detection system and detection method based on depth image information | |
| CN107194361A (en) | Two-dimentional pose detection method and device | |
| CN109063695A (en) | A kind of face critical point detection method, apparatus and its computer storage medium | |
| CN108230383A (en) | Hand three-dimensional data determines method, apparatus and electronic equipment | |
| CN109858333A (en) | Image processing method, device, electronic equipment and computer-readable medium | |
| CN110675487A (en) | Three-dimensional face modeling and recognizing method and device based on multi-angle two-dimensional face | |
| CN109934196A (en) | Human face posture parameter evaluation method, apparatus, electronic equipment and readable storage medium storing program for executing | |
| CN108062544A (en) | For the method and apparatus of face In vivo detection | |
| CN110363175A (en) | Image processing method, device and electronic equipment | |
| JP2022540101A (en) | POSITIONING METHOD AND APPARATUS, ELECTRONIC DEVICE, COMPUTER-READABLE STORAGE MEDIUM | |
| CN110059579A (en) | For the method and apparatus of test alive, electronic equipment and storage medium | |
| CN112017212B (en) | Training and tracking method and system of face key point tracking model | |
| CN104331412B (en) | A kind of method that face retrieval is carried out in normalization three-dimensional face storehouse | |
| CN110007764B (en) | Gesture skeleton recognition method, device and system and storage medium | |
| Tang et al. | Research on 3D human pose estimation using RGBD camera |
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: 20191022 |
|
| RJ01 | Rejection of invention patent application after publication |