CN108961156A - The method and device of face image processing - Google Patents
The method and device of face image processing Download PDFInfo
- Publication number
- CN108961156A CN108961156A CN201810835926.0A CN201810835926A CN108961156A CN 108961156 A CN108961156 A CN 108961156A CN 201810835926 A CN201810835926 A CN 201810835926A CN 108961156 A CN108961156 A CN 108961156A
- Authority
- CN
- China
- Prior art keywords
- image
- processing
- detail pictures
- detail
- mill skin
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000012545 processing Methods 0.000 title claims abstract description 184
- 238000000034 method Methods 0.000 title claims abstract description 42
- 230000001815 facial effect Effects 0.000 claims abstract description 79
- 230000009466 transformation Effects 0.000 claims description 35
- 238000001914 filtration Methods 0.000 claims description 18
- 230000002146 bilateral effect Effects 0.000 claims description 12
- 238000010030 laminating Methods 0.000 claims description 5
- 238000003672 processing method Methods 0.000 claims description 4
- 239000010985 leather Substances 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 abstract description 10
- 230000007812 deficiency Effects 0.000 abstract 1
- 238000010586 diagram Methods 0.000 description 14
- 230000008569 process Effects 0.000 description 13
- 238000004891 communication Methods 0.000 description 9
- 239000012535 impurity Substances 0.000 description 7
- 239000011159 matrix material Substances 0.000 description 6
- 230000009471 action Effects 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 4
- 230000005236 sound signal Effects 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 230000001133 acceleration Effects 0.000 description 2
- 230000000712 assembly Effects 0.000 description 2
- 238000000429 assembly Methods 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 230000000717 retained effect Effects 0.000 description 2
- KLDZYURQCUYZBL-UHFFFAOYSA-N 2-[3-[(2-hydroxyphenyl)methylideneamino]propyliminomethyl]phenol Chemical compound OC1=CC=CC=C1C=NCCCN=CC1=CC=CC=C1O KLDZYURQCUYZBL-UHFFFAOYSA-N 0.000 description 1
- 241000209140 Triticum Species 0.000 description 1
- 235000021307 Triticum Nutrition 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 201000001098 delayed sleep phase syndrome Diseases 0.000 description 1
- 208000033921 delayed sleep phase type circadian rhythm sleep disease Diseases 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 239000012092 media component Substances 0.000 description 1
- 239000011148 porous material Substances 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/04—Context-preserving transformations, e.g. by using an importance map
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
Abstract
The disclosure is directed to a kind of method and devices of face image processing, belong to application of electronic technology field.This method comprises: carrying out the first mill skin processing to Initial Face image, base image is obtained；Based on Initial Face image, detail pictures, the textural characteristics for the skin which is used to reflect in Initial Face image are obtained；Second mill skin processing is carried out to the detail pictures, obtains target detail image；Target detail image and base image are overlapped processing, obtain target facial image.The problem of disclosure is able to solve during face image processing, lacks texture due to the necessary textural characteristics of treated facial image skin deficiencies.The disclosure is used for the processing of facial image.
Description
Technical field
This disclosure relates to field of image processing, in particular to a kind of method and device of face image processing.
Background technique
During carrying out U.S. face processing to facial image, face mill skin is the core function of U.S. face technology, it can be with
The details such as impurity, texture on skin are handled, picture is made to seem more attractive.
Currently, face mill skin technology generally uses edge preserving filter to realize, edge preserving filter is carried out to facial image
During processing, Initial Face image to be processed can be filtered, to obtain mill skin treated facial image.
However, when carrying out mill skin processing to facial image with edge preserving filter, it can be to the texture of the skin in facial image
Feature is smoothed, and is caused to grind skin treated skin and is lacked texture.
Summary of the invention
The embodiment of the present disclosure provides a kind of method and device of face image processing.It is able to solve asking for the prior art
Topic.The technical solution is as follows:
According to the first aspect of the embodiments of the present disclosure, a kind of method of face image processing is provided, comprising:
First mill skin processing is carried out to Initial Face image, obtains base image；
Based on the Initial Face image, detail pictures are obtained, the detail pictures are for reflecting the Initial Face figure
The textural characteristics of skin as in；
Second mill skin processing is carried out to the detail pictures, obtains target detail image；
The target detail image and the base image are overlapped processing, obtain target facial image.
Optionally, described to be based on the Initial Face image, obtain detail pictures, comprising:
The Initial Face image is made the difference with the base image, obtains the detail pictures.
Optionally, described that second mill skin processing is carried out to the detail pictures, obtain target detail image, comprising:
Nonlinear transformation is carried out to the detail pictures, obtains transformed detail pictures；
The second mill skin processing is carried out to the transformed detail pictures, obtains the target detail image.
Optionally, described that nonlinear transformation is carried out to the detail pictures, obtain transformed detail pictures, comprising:
Based on polynomial transformation formula, nonlinear transformation is carried out to the detail pictures, obtains transformed detail pictures,
The polynomial transformation formula are as follows:
Wherein, D1 is the ith pixel value of the transformed detail pictures, and the D is i-th of the detail pictures
Pixel value, a and b are preset non-zero transform coefficient, and 1≤i≤n, n are the sum of pixel value in the detail pictures.
Optionally, the first mill skin processing and the second mill skin processing are to protect side filtering processing；
Wherein, the first mill skin processing is bilateral filtering processing, Steerable filter processing or weighted least-squares processing；
The second mill skin processing is bilateral filtering processing, Steerable filter processing or weighted least-squares processing.
Optionally, the method also includes:
Image is acquired by camera assembly；
Recognition of face is carried out to acquired image；
When there are when facial image, will include the fate of facial image in acquired image for the acquired image
Image in domain is determined as Initial Face image.
According to the second aspect of an embodiment of the present disclosure, a kind of device of face image processing is provided, comprising:
First mill skin module is configured as carrying out Initial Face image the first mill skin processing, obtains base image；
Module is obtained, is configured as obtaining detail pictures, the detail pictures are for anti-based on the Initial Face image
Reflect the textural characteristics of the skin in the Initial Face image；
Second mill skin module is configured as carrying out the detail pictures the second mill skin processing, obtains target detail image；
Laminating module is configured as the target detail image and the base image being overlapped processing, obtains mesh
Mark facial image.
Optionally, the acquisition module, is configured as:
The Initial Face image is made the difference with the base image, obtains the detail pictures.
Optionally, the second mill skin module, comprising:
Transformation submodule is configured as carrying out nonlinear transformation to the detail pictures, obtains transformed detail pictures；
Leather module is ground, is configured as carrying out the transformed detail pictures the second mill skin processing, obtains institute
State target detail image.
Optionally, the transformation submodule, is configured as:
Based on polynomial transformation formula, nonlinear transformation is carried out to the detail pictures, obtains transformed detail pictures,
The polynomial transformation formula are as follows:
Wherein, D1 is the ith pixel value of the transformed detail pictures, and the D is i-th of the detail pictures
Pixel value, a and b are preset non-zero transform coefficient, and 1≤i≤n, n are the sum of pixel value in the detail pictures.
Optionally, the first mill skin processing and the second mill skin processing are to protect side filtering processing.
Wherein, the first mill skin processing is bilateral filtering processing, Steerable filter processing or weighted least-squares processing；
The second mill skin processing is bilateral filtering processing, Steerable filter processing or weighted least-squares processing.
Optionally, described device further include:
Acquisition module is configured as acquiring image by camera assembly；
Identification module is configured as carrying out recognition of face to acquired image；
Determining module is configured as to wrap in acquired image when the acquired image is there are when facial image
It includes the image in the presumptive area of facial image and is determined as Initial Face image.
According to the third aspect of an embodiment of the present disclosure, a kind of processing unit of facial image is provided, described device includes:
Processing component；
For storing the memory of the executable instruction of the processing component；
Wherein, the processing component is configured as executing the processing method of any facial image of first aspect.
According to a fourth aspect of embodiments of the present disclosure, a kind of computer readable storage medium is provided, it is described computer-readable
Instruction is stored in storage medium, when the readable storage medium storing program for executing is run on processing component, so that processing component executes the
On the one hand the processing method of any facial image.
The technical scheme provided by this disclosed embodiment can include the following benefits:
The method and device for the face image processing that embodiment of the disclosure provides can be carried out to Initial Face image
After grinding skin processing acquisition base image, the detail pictures for being able to reflect face dermatoglyph feature are obtained, by detail pictures
Mill skin processing is carried out, and will be overlapped through overground skin treated detail pictures with base image, target face can be obtained
Image, the skin in the target facial image have been effectively retained its textural characteristics, have increased skin on the basis of impurity is less
Texture.
It should be understood that the above general description and the following detailed description are merely exemplary, this can not be limited
It is open.
Detailed description of the invention
In order to illustrate more clearly of embodiment of the disclosure, attached drawing needed in embodiment description will be made below
Simply introduce, it should be apparent that, the accompanying drawings in the following description is only some embodiments of the present disclosure, common for this field
For technical staff, without creative efforts, it is also possible to obtain other drawings based on these drawings.
Fig. 1 is a kind of schematic diagram of Initial Face image shown according to an exemplary embodiment；
Fig. 2 is a kind of schematic diagram of base image shown according to an exemplary embodiment；
Fig. 3 is a kind of flow chart of face image processing process shown according to an exemplary embodiment；
Fig. 4 is the flow chart of another face image processing process shown according to an exemplary embodiment；
Fig. 5 is the flow chart of another face image processing process shown according to an exemplary embodiment；
Fig. 6 is a kind of schematic diagram of detail pictures shown according to an exemplary embodiment；
Fig. 7 is the flow chart of another face image processing process shown according to an exemplary embodiment；
Fig. 8 is a kind of schematic diagram of target detail image shown according to an exemplary embodiment；
Fig. 9 is a kind of schematic diagram of target facial image shown according to an exemplary embodiment；
Figure 10 is a kind of schematic diagram of the Initial Face image shown according to another exemplary embodiment；
It is intentional that Figure 11, which is a kind of target facial image for showing according to another exemplary embodiment,；
Figure 12 is a kind of block diagram of the processing unit of facial image shown according to an exemplary embodiment；
Figure 13 is the block diagram of the processing unit of another facial image shown according to an exemplary embodiment；
Figure 14 is the block diagram of the processing unit of another facial image shown according to an exemplary embodiment；
Figure 15 is the block diagram of the processing unit of another facial image shown according to an exemplary embodiment；
Figure 16 is a kind of block diagram of device for face image processing shown according to an exemplary embodiment.
The drawings herein are incorporated into the specification and forms part of this specification, and shows the implementation for meeting the disclosure
Example, and together with specification for explaining the principles of this disclosure.
Specific embodiment
In order to keep the purposes, technical schemes and advantages of the disclosure clearer, below in conjunction with attached drawing to the disclosure make into
It is described in detail to one step, it is clear that described embodiment is only disclosure some embodiments, rather than whole implementation
Example.It is obtained by those of ordinary skill in the art without making creative efforts based on the embodiment in the disclosure
All other embodiment belongs to the range of disclosure protection.
With the rapid development of image processing techniques, more and more people, can be right when shooting photo or Video chat
Facial image carries out U.S. face processing, and face mill skin is the core function of U.S. face technology, and existing face mill skin technology generally uses
Edge preserving filter realizes that edge preserving filter is that face grinds the core devices that skin technical functionality is realized in terminal, it is to face
Image in the process of processing, can carry out mill skin processing to Initial Face image to be processed, thus after obtaining mill skin processing
Facial image, still, edge preserving filter to facial image carry out mill skin processing when also can be to the texture of skin in facial image
Feature is smoothed, and so as to cause mill skin, treated that skin lacks texture due to having lacked necessary textural characteristics.
Referring to Figure 1 and Fig. 2, Fig. 1 are the schematic diagram of the Initial Face image of terminal acquisition, and Fig. 2 is edge preserving filter to Initial Face
Image carries out the schematic diagram of mill skin treated image.Fig. 2 in eliminating Fig. 1 on the basis of the impurity of Initial Face image,
Also some textural characteristics of skin are removed.
The embodiment of the present disclosure provides a kind of face image processing process, can solve the above problem, as shown in figure 3, the party
Method is applied to terminal, comprising:
Step 301 carries out the first mill skin processing to Initial Face image, obtains base image.
Step 302 is based on Initial Face image, obtains detail pictures, the detail pictures are for reflecting Initial Face image
In skin textural characteristics.
Step 303 carries out the second mill skin processing to detail pictures, obtains target detail image.
Target detail image and base image are overlapped processing by step 304, obtain target facial image.
In conclusion the face image processing process that the embodiment of the present disclosure provides, can carry out to Initial Face image
After grinding skin processing acquisition base image, the detail pictures for being able to reflect face dermatoglyph feature are obtained, by detail pictures
Mill skin processing is carried out, and will be overlapped through overground skin treated detail pictures with base image, target face can be obtained
Image, the skin in the target facial image have been effectively retained its textural characteristics, have increased skin on the basis of impurity is less
Texture.
The embodiment of the present disclosure provides a kind of face image processing process, and this method is applied in terminal, for example, the terminal can
Think mobile phone, terminal can be equipped with image processing program, and the image processing program is for executing subsequent face image processing side
Method.As shown in figure 4, this method comprises:
Step 401 obtains Initial Face image.
In the embodiments of the present disclosure, terminal obtain Initial Face image mode can there are many, for example, user can be from
Initial Face image is selected in the image being locally stored, correspondingly, terminal obtains the Initial Face based on the selection operation of user
Image；In another example user can execute shooting trigger action, correspondingly, terminal after detecting the shooting trigger action, is opened
Picture shooting assembly shoots to obtain Initial Face image by the picture shooting assembly.For example, the picture shooting assembly is front camera or postposition
Camera.
It should be noted that the image that terminal is shot by picture shooting assembly may not include facial image, and this public affairs
The face image processing process of offer is opened for facial image, if the image taken does not include facial image, accordingly
Processing be invalidation, in order to reduce invalidation, the image that terminal can obtain shooting be identified, such as Fig. 5 institute
Show, which may include:
Step 4011 acquires image by camera assembly.
Exemplary, user can execute shooting trigger action, correspondingly, terminal is after detecting the shooting trigger action,
Picture shooting assembly is opened, shoots to obtain image by the picture shooting assembly.
Step 4012 carries out recognition of face to acquired image.
Terminal can be by face recognition algorithms (also referred to as human Facial Image Recognition Algorithm or face recognition algorithm) to collected
Image carries out recognition of face.
Step 4013, when acquired image is there are when facial image, will be in acquired image including facial image
Image in presumptive area is determined as Initial Face image.
There are when facial image, will include the presumptive area of facial image in acquired image for terminal acquired image
In image be determined as Initial Face image, acquired image be not present facial image when, user can be prompted not acquire
To facial image, or repeat above-mentioned steps 4011 to 4013.
For example, it is assumed that the image that step 4011 acquires is the image in terminal as shown in Figure 1, it can be with by step 4012
Identification obtains in the image there are facial image, then terminal by include in the image facial image presumptive area in image it is true
It is set to Initial Face image.Exemplary, which can be the central area of acquired image, which has specified
Shape, the designated shape can be rectangle, round or ellipse etc..
Step 402 carries out the first mill skin processing to Initial Face image, obtains base image.
By taking Initial Face image is image shown in Fig. 1 terminal as an example, the processing of the first mill skin, obtained base are carried out to it
Plinth image can be the facial image as shown in Fig. 2 terminal.The first mill skin processing can be filtered to protect side, for example,
Bilateral filtering processing, Steerable filter processing or weighted least-squares processing.
Step 403 is based on Initial Face image, obtains detail pictures, the detail pictures are for reflecting Initial Face image
In skin textural characteristics.
Exemplary, which can be the features such as microgroove, pore, decree lip tattooing and/or the nasal fossa at canthus.
In the embodiments of the present disclosure, be based on Initial Face image, obtain detail pictures mode can there are many, for example,
In an optional implementation manner, by way of feature extraction, the texture extracted in image in Initial Face image is special
Sign, obtains detail pictures.In another optional implementation, Initial Face image can be made the difference with base image, be obtained
To detail pictures.It that is to say: H=A-B, wherein A is the pixel matrix of Initial Face image, and B is the pixel value of basic image
Matrix, H are the pixel matrix of detail pictures.
By taking Initial Face image is facial image shown in Fig. 1 terminal as an example, carry out what the first mill skin was handled to it
Base image can be to obtain detail pictures as shown in Fig. 2, the Initial Face image in Fig. 1 is made the difference with the base image in Fig. 2
It can be the image as shown in terminal in Fig. 6.
Step 404 carries out the second mill skin processing to detail pictures, obtains target detail image.
In the embodiments of the present disclosure, the second mill skin processing is carried out to detail pictures, the process for obtaining target detail image can
It is exemplary there are many, as shown in fig. 7, the process includes:
Step 4041 carries out nonlinear transformation to detail pictures, obtains transformed detail pictures.
It is exemplary, it is based on polynomial transformation formula, nonlinear transformation is carried out to detail pictures, obtains transformed detail view
Picture, the polynomial transformation formula are as follows:
Wherein, D1 is the ith pixel value of transformed detail pictures, and D is the ith pixel value of detail pictures, a and b
For preset non-zero transform coefficient, 1≤i≤n, n are the sum of pixel value in detail pictures.For transformed detail pictures
Each pixel value is all satisfied above-mentioned multinomial variation formula.It is exemplary, a=1024, b=512.
It should be noted that the number for the multinomial variation formula that the embodiment of the present disclosure provides is more than or equal to 2, it is above-mentioned more
Item formula variation formula only schematically illustrates, and can also have other forms, such as the formula can be 3 order polynomials or 4
Order polynomial.
The useful information in detail pictures can be activated by carrying out nonlinear transformation to detail pictures, inhibit wherein unrelated letter
Breath, improves the efficiency of subsequent processing, further increases the quality for the image that final process obtains.
Step 4042 carries out the second mill skin processing to transformed detail pictures, obtains target detail image.
Above-mentioned steps 403 are please referred to, although the textural characteristics of the skin in detail pictures reflection Initial Face image,
It is the textural characteristics close to real human face state, it is more coarse, it is not soft enough, still by the transformed detail pictures of step 4041
So there is a problem of corresponding, the embodiment of the present disclosure is handled by carrying out second mill skin to the transformed detail pictures, can will
Textural characteristics softization that the detail pictures are reflected, keeps it visually more aesthetically pleasing.The second mill skin processing can be guarantor side
Filtering processing.For example, bilateral filtering processing, Steerable filter processing or weighted least-squares processing.
It is exemplary, it is assumed that facial image shown by terminal is the detail pictures after nonlinear transformation in Fig. 6, to it
Carry out the image that the second target detail image for handling of mill skin can as shown in Figure 8 in terminal.
Target detail image and base image are overlapped processing by step 405, obtain target facial image.
Optionally, target detail image and base image can be overlapped processing, obtains target facial image, namely
It is E=F+B, which is the pixel matrix of target detail image, and B is the pixel matrix of basic image, and E is target face figure
The pixel matrix of picture.
With target detail image as shown in figure 8, base image is as shown in Fig. 2, the two is overlapped, obtained target person
Face image can be the facial image as shown in terminal in Fig. 9.
It should be noted that target facial image can also have other acquisition modes, for example, can be to target detail image
Preset transformation is carried out at least one of base image, is then overlapped processing again, the embodiment of the present disclosure does not do this
Limitation.
Step 406, displaying target facial image.
Optionally, terminal can be shown Initial Face image and target facial image jointly in user in the form of comparison
It is exemplary so that user can effectively see the effect of image procossing on interface, by Initial Face image and target facial image
Two regions of user interface are respectively displayed on, such as the region and lower half portion that are respectively displayed on the top half of user interface
Region；Optionally, terminal can be shown Initial Face image and target facial image jointly in user circle in the form of superposition
On face, so that user sees the effect of image procossing in a manner of more novel, for example, by target facial image with translucent
Form is superimposed upon on Initial Face image and shows；Optionally, terminal can also directly show target facial image in user circle
On face.Above-mentioned several optional ways are schematically illustrating for the disclosure, and the disclosure does not limit this.
For image shown in terminal by Initial Face image for Figure 10, to its people by step 401 to step 405
After face image grinds skin processing, the target facial image that terminal is shown is as shown in figure 11, and the skin in the target facial image is miscellaneous
On the basis of matter is less, the textural characteristics of face, such as the microgroove and lip nasal fossa feature at canthus are remained, the matter of skin is increased
Sense.
In conclusion the face image processing process that the embodiment of the present disclosure provides, terminal acquires image by camera assembly,
And after carrying out recognition of face to acquired image, by the image in the presumptive area in acquired image including facial image
It is determined as Initial Face image, and then the first mill skin processing is carried out to Initial Face image, obtains base image, then obtain energy
Enough reflect the detail pictures of the textural characteristics of the skin in the Initial Face image, and detail pictures are carried out at the second mill skin
Reason, obtains target detail image, finally, target detail image and base image are overlapped processing, obtains target face figure
Picture, the skin in the target facial image effectively remain its textural characteristics, increase skin on the basis of impurity is less
Texture.
The disclosure provides a kind of processing unit 50 of facial image, and as shown in figure 12, which includes:
First mill skin module 501 is configured as carrying out Initial Face image the first mill skin processing, obtains base image；
Module 502 is obtained, is configured as obtaining detail pictures based on the Initial Face image, the detail pictures are used
In the textural characteristics of the skin reflected in the Initial Face image；
Second mill skin module 503 is configured as carrying out the detail pictures the second mill skin processing, obtains target detail figure
Picture；
Laminating module 504 is configured as the target detail image and the base image being overlapped processing, obtain
Target facial image.
In conclusion the face image processing device that the embodiment of the present disclosure provides, the first mill skin module can be to initial people
Face image carries out the first mill skin processing, obtains base image, obtains module and is based on Initial Face image, acquisition is able to reflect described
The detail pictures of the textural characteristics of skin in Initial Face image, the second mill skin module can carry out the to the detail pictures
Two mill skin processing, obtain target detail image, and laminating module can carry out the target detail image and the base image
Superposition processing obtains target facial image, and the obtained skin in target facial image is on the basis of impurity is less, effectively
The textural characteristics for remaining skin increase the texture of skin.
Optionally, the acquisition module 502, is configured as:
The Initial Face image is made the difference with the base image, obtains the detail pictures.
Optionally, the second mill skin module 503, as shown in figure 13, which includes:
Transformation submodule 5031 is configured as carrying out nonlinear transformation to the detail pictures, obtains transformed details
Image；
Leather module 5032 is ground, is configured as carrying out the transformed detail pictures the second mill skin processing, obtain
To the target detail image.
Optionally, the transformation submodule 5031, is configured as:
Based on polynomial transformation formula, nonlinear transformation is carried out to the detail pictures, obtains transformed detail pictures,
The polynomial transformation formula are as follows:
Wherein, D1 is the ith pixel value of the transformed detail pictures, and the D is i-th of the detail pictures
Pixel value, a and b are preset non-zero transform coefficient, and 1≤i≤n, n are the sum of pixel value in the detail pictures.
Optionally, a=1024, b=512.
Optionally, the first mill skin processing and the second mill skin processing are to protect side filtering processing.
Optionally, the first mill skin processing is bilateral filtering processing, Steerable filter processing or weighted least-squares processing；
The second mill skin processing is bilateral filtering processing, Steerable filter processing or weighted least-squares processing.
Optionally, as shown in figure 14, the device 50 further include:
Acquisition module 505 is configured as acquiring image by camera assembly；
Identification module 506 is configured as carrying out recognition of face to acquired image；
Determining module 507 is configured as when the acquired image is there are when facial image, will be in acquired image
Image in presumptive area including facial image is determined as Initial Face image.
The face image processing device that the embodiment of the present disclosure provides, the image capture module in the device pass through camera assembly
Image is acquired, face recognition module can carry out recognition of face to acquired image, and determining module will be in acquired image
Image in presumptive area including facial image is determined as Initial Face image, and the first mill skin module can be to Initial Face figure
As carrying out the first mill skin processing, base image is obtained, module is obtained and is based on the Initial Face image, acquisition is able to reflect described
The detail pictures of the textural characteristics of skin in Initial Face image, the second mill skin module can carry out the to the detail pictures
Two mill skin processing, obtain target detail image, and laminating module can carry out the target detail image and the base image
Superposition processing obtains target facial image, and the obtained skin in target facial image is on the basis of impurity is less, effectively
The textural characteristics for remaining skin increase the texture of skin.
The embodiment of the present disclosure provides a kind of processing unit 60 of facial image, and as shown in figure 15, described device includes:
Processing component 601；
For storing the memory 602 of the executable instruction of the processing component；
Wherein, the processing component is configured as executing the processing for any facial image that the embodiment of the present disclosure provides
Method.
Figure 16 is a kind of block diagram of device 700 for face image processing shown according to an exemplary embodiment.Example
Such as, device 700 can be mobile phone, computer, digital broadcasting terminal, messaging device, game console, and plate is set
It is standby, Medical Devices, body-building equipment, personal digital assistant etc..
Referring to Fig.1 6, device 700 may include following one or more components: processing component 7002, memory 7004, electricity
Source component 7006, multimedia component 7008, audio component 7010, the interface 7012 of input/output (I/O), sensor module
7014 and communication component 7016.
The integrated operation of the usual control device 700 of processing component 7002, such as with display, telephone call, data communication, phase
Machine operation and record operate associated operation.Processing component 7002 may include that one or more processors 7020 refer to execute
It enables, to perform all or part of the steps of the methods described above.In addition, processing component 7002 may include one or more modules,
Convenient for the interaction between processing component 7002 and other assemblies.For example, processing component 7002 may include multi-media module, with side
Just the interaction between multimedia component 7008 and processing component 7002.
Memory 7004 is configured as storing various types of data to support the operation in device 700.These data
Example includes the instruction of any application or method for operating on device 700, contact data, telephone book data,
Message, picture, video etc..Memory 7004 can by any kind of volatibility or non-volatile memory device or they
Combination is realized, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), it is erasable can
Program read-only memory (EPROM), programmable read only memory (PROM), read-only memory (ROM), magnetic memory, flash memory
Reservoir, disk or CD.
Power supply module 7006 provides electric power for the various assemblies of device 700.Power supply module 7006 may include power management
System, one or more power supplys and other with for device 700 generate, manage, and distribute the associated component of electric power.
Multimedia component 7008 includes the screen of one output interface of offer between described device 700 and user.?
In some embodiments, screen may include liquid crystal display (LCD) and touch panel (TP).If screen includes touch panel,
Screen may be implemented as touch screen, to receive input signal from the user.Touch panel includes that one or more touch passes
Sensor is to sense the gesture on touch, slide, and touch panel.The touch sensor can not only sense touch or sliding is dynamic
The boundary of work, but also detect duration and pressure associated with the touch or slide operation.In some embodiments, more
Media component 7008 includes a front camera and/or rear camera.When device 700 is in operation mode, as shot mould
When formula or video mode, front camera and/or rear camera can receive external multi-medium data.Each preposition camera shooting
Head and rear camera can be a fixed optical lens system or have focusing and optical zoom capabilities.
Audio component 7010 is configured as output and/or input audio signal.For example, audio component 7010 includes a wheat
Gram wind (MIC), when device 700 is in operation mode, when such as call mode, recording mode, and voice recognition mode, microphone quilt
It is configured to receive external audio signal.The received audio signal can be further stored in memory 7004 or via communication
Component 7016 is sent.In some embodiments, audio component 7010 further includes a loudspeaker, is used for output audio signal.
I/O interface 7012 provides interface, above-mentioned peripheral interface module between processing component 7002 and peripheral interface module
It can be keyboard, click wheel, button etc..These buttons may include, but are not limited to: home button, volume button, start button and
Locking press button.
Sensor module 7014 includes one or more sensors, and the state for providing various aspects for device 700 is commented
Estimate.For example, sensor module 7014 can detecte the state that opens/closes of device 700, the relative positioning of component, such as institute
The display and keypad that component is device 700 are stated, sensor module 7014 can be with detection device 700 or 700 1, device
The position change of component, the existence or non-existence that user contacts with device 700,700 orientation of device or acceleration/deceleration and device
700 temperature change.Sensor module 7014 may include proximity sensor, be configured in not any physical contact
When detect the presence of nearby objects.Sensor module 7014 can also include optical sensor, such as CMOS or ccd image sensor,
For being used in imaging applications.In some embodiments, which can also include acceleration transducer, top
Spiral shell instrument sensor, Magnetic Sensor, pressure sensor or temperature sensor.
Communication component 7016 is configured to facilitate the communication of wired or wireless way between device 700 and other equipment.Dress
The wireless network based on communication standard, such as WiFi can be accessed by setting 700,2G or 3G or their combination.In an exemplary reality
It applies in example, communication component 7016 receives broadcast singal or the related letter of broadcast from external broadcasting management system via broadcast channel
Breath.In one exemplary embodiment, the communication component 7016 further includes near-field communication (NFC) module, to promote short distance logical
Letter.For example, radio frequency identification (RFID) technology, Infrared Data Association (IrDA) technology, ultra wide band (UWB) can be based in NFC module
Technology, bluetooth (BT) technology and other technologies are realized.
In the exemplary embodiment, device 700 can be believed by one or more application specific integrated circuit (ASIC), number
Number processor (DSP), digital signal processing appts (DSPD), programmable logic device (PLD), field programmable gate array
(FPGA), controller, microcontroller, microprocessor or other electronic components are realized, for executing the above method.
In the exemplary embodiment, a kind of non-transitorycomputer readable storage medium including instruction, example are additionally provided
It such as include the memory 7004 of instruction, above-metioned instruction can be executed by the processor 7020 of device 700 to complete the above method.Example
Such as, the non-transitorycomputer readable storage medium can be ROM, random access memory (RAM), CD-ROM, tape, soft
Disk and optical data storage devices etc..
A kind of non-transitorycomputer readable storage medium, when the instruction in the storage medium is by the processing of device 700
When device executes, so that the method that device 700 is able to carry out a kind of face image processing provided by the above embodiment.
About the device in above-described embodiment, wherein modules execute the concrete mode of operation in related this method
Embodiment in be described in detail, no detailed explanation will be given here.
Those skilled in the art after considering the specification and implementing the invention disclosed here, will readily occur to its of the disclosure
Its embodiment.This application is intended to cover any variations, uses, or adaptations of the disclosure, these modifications, purposes or
Person's adaptive change follows the general principles of this disclosure and including the undocumented common knowledge in the art of the disclosure
Or conventional techniques.The description and examples are only to be considered as illustrative, and the true scope and spirit of the disclosure are wanted by right
It asks and points out.
It should be understood that the present disclosure is not limited to the precise structures that have been described above and shown in the drawings, and
And various modifications and changes may be made without departing from the scope thereof.The scope of the present disclosure is only limited by the accompanying claims.
Claims (14)
1. a kind of processing method of facial image characterized by comprising
First mill skin processing is carried out to Initial Face image, obtains base image；
Based on the Initial Face image, detail pictures are obtained, the detail pictures are for reflecting in the Initial Face image
Skin textural characteristics；
Second mill skin processing is carried out to the detail pictures, obtains target detail image；
The target detail image and the base image are overlapped processing, obtain target facial image.
2. the method according to claim 1, wherein
It is described to be based on the Initial Face image, obtain detail pictures, comprising:
The Initial Face image is made the difference with the base image, obtains the detail pictures.
3. method according to claim 1 or 2, which is characterized in that
It is described that second mill skin processing is carried out to the detail pictures, obtain target detail image, comprising:
Nonlinear transformation is carried out to the detail pictures, obtains transformed detail pictures；
The second mill skin processing is carried out to the transformed detail pictures, obtains the target detail image.
4. according to the method described in claim 3, it is characterized in that,
It is described that nonlinear transformation is carried out to the detail pictures, obtain transformed detail pictures, comprising:
Based on polynomial transformation formula, nonlinear transformation is carried out to the detail pictures, obtains transformed detail pictures, it is described
Polynomial transformation formula are as follows:
Wherein, D1 is the ith pixel value of the transformed detail pictures, and the D is the ith pixel of the detail pictures
Value, a and b are preset non-zero transform coefficient, and 1≤i≤n, n are the sum of pixel value in the detail pictures.
5. the method according to claim 1, wherein
The first mill skin processing and the second mill skin processing are to protect side filtering processing；
Wherein, the first mill skin processing is bilateral filtering processing, Steerable filter processing or weighted least-squares processing；
The second mill skin processing is bilateral filtering processing, Steerable filter processing or weighted least-squares processing.
6. the method according to claim 1, wherein the method also includes:
Image is acquired by camera assembly；
Recognition of face is carried out to acquired image；
It, will be in the presumptive area in acquired image including facial image when the acquired image is there are when facial image
Image be determined as Initial Face image.
7. a kind of processing unit of facial image characterized by comprising
First mill skin module is configured as carrying out Initial Face image the first mill skin processing, obtains base image；
Module is obtained, is configured as obtaining detail pictures, the detail pictures are for reflecting institute based on the Initial Face image
State the textural characteristics of the skin in Initial Face image；
Second mill skin module is configured as carrying out the detail pictures the second mill skin processing, obtains target detail image；
Laminating module is configured as the target detail image and the base image being overlapped processing, obtains target person
Face image.
8. device according to claim 7, which is characterized in that
The acquisition module, is configured as:
The Initial Face image is made the difference with the base image, obtains the detail pictures.
9. device according to claim 7 or 8, which is characterized in that
The second mill skin module, comprising:
Transformation submodule is configured as carrying out nonlinear transformation to the detail pictures, obtains transformed detail pictures；
Leather module is ground, is configured as carrying out the transformed detail pictures the second mill skin processing, obtains the mesh
Mark detail pictures.
10. device according to claim 9, which is characterized in that
The transformation submodule, is configured as:
Based on polynomial transformation formula, nonlinear transformation is carried out to the detail pictures, obtains transformed detail pictures, it is described
Polynomial transformation formula are as follows:
Wherein, D1 is the ith pixel value of the transformed detail pictures, and the D is the ith pixel of the detail pictures
Value, a and b are preset non-zero transform coefficient, and 1≤i≤n, n are the sum of pixel value in the detail pictures.
11. device according to claim 7, which is characterized in that
The first mill skin processing and the second mill skin processing are to protect side filtering processing.
Wherein, the first mill skin processing is bilateral filtering processing, Steerable filter processing or weighted least-squares processing；
The second mill skin processing is bilateral filtering processing, Steerable filter processing or weighted least-squares processing.
12. device according to claim 7, which is characterized in that described device further include:
Acquisition module is configured as acquiring image by camera assembly；
Identification module is configured as carrying out recognition of face to acquired image；
Determining module is configured as when there are when facial image, will include people in acquired image for the acquired image
Image in the presumptive area of face image is determined as Initial Face image.
13. a kind of processing unit of facial image, which is characterized in that described device includes:
Processing component；
For storing the memory of the executable instruction of the processing component；
Wherein, the processing component is configured as the method that perform claim requires the processing of 1 to 6 any facial image.
14. a kind of computer readable storage medium, which is characterized in that instruction is stored in the computer readable storage medium,
When the readable storage medium storing program for executing is run on processing component, so that processing component is executed as described in claim 1 to 6 is any
The processing method of facial image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810835926.0A CN108961156B (en) | 2018-07-26 | 2018-07-26 | Method and device for processing face image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810835926.0A CN108961156B (en) | 2018-07-26 | 2018-07-26 | Method and device for processing face image |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108961156A true CN108961156A (en) | 2018-12-07 |
| CN108961156B CN108961156B (en) | 2023-03-14 |
Family
ID=64463925
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810835926.0A Active CN108961156B (en) | 2018-07-26 | 2018-07-26 | Method and device for processing face image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108961156B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110458771A (en) * | 2019-07-29 | 2019-11-15 | 深圳市商汤科技有限公司 | Image processing method and device, electronic equipment and storage medium |
| CN111127352A (en) * | 2019-12-13 | 2020-05-08 | 北京达佳互联信息技术有限公司 | Image processing method, device, terminal and storage medium |
| CN111798399A (en) * | 2020-07-10 | 2020-10-20 | 北京字节跳动网络技术有限公司 | Image processing method and device and electronic equipment |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2016145830A1 (en) * | 2015-08-19 | 2016-09-22 | 中兴通讯股份有限公司 | Image processing method, terminal and computer storage medium |
| CN106056562A (en) * | 2016-05-19 | 2016-10-26 | 京东方科技集团股份有限公司 | Face image processing method and device and electronic device |
| CN106447620A (en) * | 2016-08-26 | 2017-02-22 | 北京金山猎豹科技有限公司 | Face image polishing method and device, and terminal device |
| CN107798654A (en) * | 2017-11-13 | 2018-03-13 | 北京小米移动软件有限公司 | Image mill skin method and device, storage medium |
-
2018
- 2018-07-26 CN CN201810835926.0A patent/CN108961156B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2016145830A1 (en) * | 2015-08-19 | 2016-09-22 | 中兴通讯股份有限公司 | Image processing method, terminal and computer storage medium |
| CN106056562A (en) * | 2016-05-19 | 2016-10-26 | 京东方科技集团股份有限公司 | Face image processing method and device and electronic device |
| CN106447620A (en) * | 2016-08-26 | 2017-02-22 | 北京金山猎豹科技有限公司 | Face image polishing method and device, and terminal device |
| CN107798654A (en) * | 2017-11-13 | 2018-03-13 | 北京小米移动软件有限公司 | Image mill skin method and device, storage medium |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110458771A (en) * | 2019-07-29 | 2019-11-15 | 深圳市商汤科技有限公司 | Image processing method and device, electronic equipment and storage medium |
| CN110458771B (en) * | 2019-07-29 | 2022-04-08 | 深圳市商汤科技有限公司 | Image processing method and device, electronic equipment and storage medium |
| CN111127352A (en) * | 2019-12-13 | 2020-05-08 | 北京达佳互联信息技术有限公司 | Image processing method, device, terminal and storage medium |
| CN111798399A (en) * | 2020-07-10 | 2020-10-20 | 北京字节跳动网络技术有限公司 | Image processing method and device and electronic equipment |
| CN111798399B (en) * | 2020-07-10 | 2024-04-30 | 抖音视界有限公司 | Image processing method and device and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108961156B (en) | 2023-03-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105512605B (en) | Face image processing process and device | |
| CN106530227B (en) | Image recovery method and device | |
| CN105991930B (en) | Zoom processing method, device and the mobile terminal of dual camera | |
| CN105469356B (en) | Face image processing process and device | |
| CN104219445B (en) | Screening-mode method of adjustment and device | |
| CN104700353B (en) | Image filters generation method and device | |
| CN107122679A (en) | Image processing method and device | |
| CN107231505B (en) | Image processing method and device | |
| CN104484858B (en) | Character image processing method and processing device | |
| CN105631804B (en) | Image processing method and device | |
| CN106355549A (en) | Photographing method and equipment | |
| CN104933419B (en) | The method, apparatus and red film for obtaining iris image identify equipment | |
| CN104361558B (en) | Image processing method, device and equipment | |
| CN105426878B (en) | Face cluster method and device | |
| CN106600530B (en) | Picture synthesis method and device | |
| CN108961156A (en) | The method and device of face image processing | |
| CN106778773A (en) | The localization method and device of object in picture | |
| CN106778531A (en) | Face detection method and device | |
| CN105635452A (en) | Mobile terminal and contact person identification method thereof | |
| CN105094539B (en) | Reference information display methods and device | |
| CN104867112B (en) | Photo processing method and device | |
| CN107944367A (en) | Face critical point detection method and device | |
| CN107426489A (en) | Processing method, device and terminal during shooting image | |
| CN107911576A (en) | Image processing method, device and storage medium | |
| CN107085823A (en) | Face image processing process and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |