CN104754221B - A kind of photographic method and mobile terminal - Google Patents
A kind of photographic method and mobile terminal Download PDFInfo
- Publication number
- CN104754221B CN104754221B CN201510106675.9A CN201510106675A CN104754221B CN 104754221 B CN104754221 B CN 104754221B CN 201510106675 A CN201510106675 A CN 201510106675A CN 104754221 B CN104754221 B CN 104754221B
- Authority
- CN
- China
- Prior art keywords
- face region
- human face
- mobile terminal
- depth
- field
- 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.)
- Expired - Fee Related
Links
- 238000000034 method Methods 0.000 title claims abstract description 37
- 230000009977 dual effect Effects 0.000 claims abstract description 73
- 230000001815 facial effect Effects 0.000 claims abstract description 32
- 230000000694 effects Effects 0.000 abstract description 13
- 230000006870 function Effects 0.000 description 10
- 238000010586 diagram Methods 0.000 description 8
- 238000001914 filtration Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 3
- 230000002146 bilateral effect Effects 0.000 description 2
- 238000005286 illumination Methods 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 210000004556 brain Anatomy 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 230000011514 reflex Effects 0.000 description 1
Abstract
The embodiment of the invention discloses a kind of photographic methods, including：N number of human face region in picture of finding a view that the dual camera of the mobile terminal absorbs is identified by the dual camera of mobile terminal, wherein N is the integer more than or equal to 1；Determine the depth of field of N number of human face region；Mill skin processing is carried out to N number of human face region according to the depth of field of each human face region in N number of human face region.The embodiment of the invention also provides a kind of mobile terminals.The depth of field for the human face region that mobile terminal absorbs can be determined by the dual camera of mobile terminal using the embodiment of the present invention, and mill skin processing is carried out to human face region according to the depth of field, to obtain facial image more better than the effect that original dual camera absorbs.
Description
Technical field
The present embodiments relate to technical field of image processing more particularly to a kind of photographic methods and mobile terminal.
Background technique
With the development of computer technology, the function of mobile terminal is also stronger and stronger, mobile terminal may be implemented communication,
Surf the Internet, watch movie, take pictures etc..Wherein, it in order to allow mobile terminal that can take the effect of single-lens reflex camera, also takes pictures to mobile terminal
Function carries out numerous studies, thus, relevant software of taking pictures of much taking pictures also is produced, such as U.S. face camera.
In the prior art, U.S. face camera can be realized the picture photographing get Geng Mei that finds a view for absorbing camera, but work as
Using U.S. face when carrying out mill skin, there are some problems, the case where yin-yang face such as occur, and reason is existing method
It is the region for going identification to need to grind skin according to the colour of skin, but when the dark portion of face will be ignored by algorithm, without grinding skin, this is just
Cause under certain lighting conditions, for example under the light condition of 45 degree of light, facial highlights has carried out mill skin, but dark portion is but full of
Noise leads to U.S. face poor effect.
Summary of the invention
The embodiment of the invention provides a kind of photographic method and mobile terminals, can change image under dark environment
U.S. face effect, improve user experience.
First aspect of the embodiment of the present invention provides a kind of photographic method, including step：
The N in picture of finding a view that the dual camera of the mobile terminal absorbs is identified by the dual camera of mobile terminal
A human face region, wherein N is the integer more than or equal to 1；
Determine the depth of field of N number of human face region；
N number of human face region is carried out at mill skin according to the depth of field of each human face region in N number of human face region
Reason.
Second aspect of the embodiment of the present invention provides a kind of mobile terminal, including：
Recognition unit identifies that the dual camera of the mobile terminal absorbs for the dual camera by mobile terminal
The N number of human face region found a view in picture, wherein N is the integer more than or equal to 1；
Determination unit, for determining the depth of field of N number of human face region；
Processing unit, for the depth of field according to each human face region in N number of human face region to N number of face area
Domain carries out mill skin processing.
Implement the embodiment of the present invention, has the advantages that：
The embodiment of the present invention identifies that the dual camera of the mobile terminal absorbs by the dual camera of mobile terminal
The N number of human face region found a view in picture, wherein N is the integer more than or equal to 1；Determine the depth of field of N number of human face region；
Mill skin processing is carried out to N number of human face region according to the depth of field of each human face region in N number of human face region.Using this
Inventive embodiments can determine the depth of field for the human face region that mobile terminal absorbs by the dual camera of mobile terminal, and according to scape
It is deep that mill skin processing is carried out to human face region, to obtain facial image more better than the effect that original dual camera absorbs, simultaneously
With interest, and user experience can be improved.
Detailed description of the invention
It to describe the technical solutions in the embodiments of the present invention more clearly, below will be to required in embodiment, description
The attached drawing used is briefly described, it should be apparent that, the accompanying drawings in the following description is only some realities of the embodiment of the present invention
Example is applied, it for those of ordinary skill in the art, without creative efforts, can also be according to these attached drawings
Obtain other attached drawings.
Fig. 1 is a kind of flow diagram of the first embodiment of photographic method provided in an embodiment of the present invention；
Fig. 2 is a kind of flow diagram of the second embodiment of photographic method provided in an embodiment of the present invention；
Fig. 3 is a kind of flow diagram of the 3rd embodiment of photographic method provided in an embodiment of the present invention；
Fig. 4 is a kind of flow diagram of the fourth embodiment of photographic method provided in an embodiment of the present invention；
Fig. 5 is a kind of structural schematic diagram of the first embodiment of mobile terminal provided in an embodiment of the present invention；
Fig. 6 is a kind of structural schematic diagram of the second embodiment of mobile terminal provided in an embodiment of the present invention；
Fig. 7 is a kind of structural schematic diagram of the 3rd embodiment of mobile terminal provided in an embodiment of the present invention；
Fig. 8 is a kind of structural schematic diagram of the fourth embodiment of mobile terminal provided in an embodiment of the present invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiment is only a part of the embodiment of the embodiment of the present invention, rather than whole implementation
Example.Based on the embodiment in the embodiment of the present invention, those of ordinary skill in the art institute without creative efforts
The every other embodiment obtained belongs to the range of protection of the embodiment of the present invention.
In realization, in the embodiment of the present invention, mobile terminal be can include but is not limited to：Laptop, mobile phone, plate electricity
Brain, intelligent wearable device etc..The system of mobile terminal refers to the operating system of equipment, can include but is not limited to：Android
System, Saipan system, Windows system, IOS (Mobile operating system of Apple Inc.'s exploitation), XP system, 8 system of windows
System etc..It should be noted that Android mobile terminal refers to that the mobile terminal of android system, Saipan mobile terminal refer to Saipan
Mobile terminal of system, etc..Above-mentioned mobile terminal is only citing, and non exhaustive, including but not limited to above-mentioned mobile terminal.
Combination of embodiment of the present invention Fig. 1 to Fig. 8 to a kind of photographic method provided in an embodiment of the present invention and mobile terminal into
Row description.
Referring to Fig. 1, Fig. 1 is a kind of process signal of the first embodiment of photographic method provided in an embodiment of the present invention
Figure.Photographic method as described in this embodiment, including step：
S101, the picture of finding a view that the dual camera of the mobile terminal absorbs is identified by the dual camera of mobile terminal
In N number of human face region, wherein N is integer more than or equal to 1.
Wherein, mobile terminal can be identified in the picture of finding a view that absorbs of dual camera of mobile terminal by dual camera
N number of human face region, N are the integer more than or equal to 1.Further, the dual camera of mobile terminal can be included for mobile terminal
Dual camera, for example, dual camera is embedded in the shell of mobile terminal, the dual camera of mobile terminal can be located at it is mobile eventually
The front at end or the behind of mobile terminal or the side of mobile terminal.Alternatively, the dual camera of mobile terminal can be movement
Terminal passes through wireless technology or the dual camera of USB technical controlling.
As a kind of possible embodiment, mobile terminal identifies the double of mobile terminal by the dual camera of mobile terminal
Before N number of human face region in what camera absorbed find a view picture, mobile terminal can start that implement institute of the embodiment of the present invention right
The software for the client answered.
As a kind of possible embodiment, the dual camera of mobile terminal may include, but are not limited to：Symmetry binocular
Camera or asymmetry binocular camera.
S102, the depth of field for determining N number of human face region.
Wherein, mobile terminal determines the depth of field of N number of human face region.Wherein, mobile terminal utilizes the double of the mobile terminal
The pixel difference between N number of facial image that each camera in camera absorbs determines each individual in N number of face
The depth of view information of the facial area of face.It is assumed that the dual camera of mobile terminal is respectively camera A and camera B, N 5,5
Human face region is respectively human face region A, human face region B, human face region C, human face region D, human face region E.For example, human face region
The depth of field of A can be according to the pixel difference between the human face region A that the human face region A that camera A takes and camera B take
Determine the depth of field of human face region A.
S103, N number of human face region is ground according to the depth of field of each human face region in N number of human face region
Skin processing.
Wherein, mobile terminal according to the depth of field of each human face region in N number of human face region to N number of human face region into
Row mill skin processing.The sequence from left to right that the facial image absorbed can be used in mobile terminal grinds N number of human face region
Skin processing.Alternatively, mobile terminal may compare the superiority and inferiority of N number of human face region, using the face area worst to N number of human face region effect
Domain starts to grind skin processing, then successively mill skin processing is carried out to the preferable human face region of human face region effect again, finally to face
Regional effect best's face region carries out mill skin processing.
The embodiment of the present invention identifies that the dual camera of the mobile terminal absorbs by the dual camera of mobile terminal
The N number of human face region found a view in picture, wherein N is the integer more than or equal to 1；Determine the depth of field of N number of human face region；
Mill skin processing is carried out to N number of human face region according to the depth of field of each human face region in N number of human face region.Using this
Inventive embodiments can determine the depth of field for the human face region that mobile terminal absorbs by the dual camera of mobile terminal, and according to scape
It is deep that mill skin processing is carried out to human face region, to obtain facial image more better than the effect that original dual camera absorbs, simultaneously
With interest, and user experience can be improved.
Referring to Fig. 2, Fig. 2 is a kind of process signal of the second embodiment of photographic method provided in an embodiment of the present invention
Figure.As a kind of possible embodiment, photographic method as described in this embodiment is in embodiment described in Fig. 1
The specific refinement of step S101, including step：
S201, it is modeled using recognition of face library, to obtain the characteristic information of face.
Wherein, mobile terminal can be modeled using recognition of face library, and mobile terminal can be to a large amount of in recognition of face library
Facial image is analyzed, and the characteristic information of face is obtained.Further, the characteristic information of face may include, but are not limited to：
The profile information of face, the distance between two information, the percent information of face, the Skin Color Informations of face etc..
S202, the picture of finding a view absorbed according to the dual camera that the characteristic information of the face locks the mobile terminal
In N number of face facial range.
Wherein, the dual camera intake that mobile terminal can lock the mobile terminal according to the characteristic information of the face is arrived
Picture of finding a view in N number of face facial range.
The embodiment of the present invention is modeled using recognition of face library, to obtain the characteristic information of face；According to the face
Characteristic information identify the facial range of N number of face in picture of finding a view that the dual camera of the mobile terminal absorbs.It adopts
The image in face database can be modeled with the embodiment of the present invention to obtain face characteristic information, be believed according to face characteristic
Breath locking face range.
Referring to Fig. 3, Fig. 3 is a kind of process signal of the 3rd embodiment of photographic method provided in an embodiment of the present invention
Figure.Photographic method as described in this embodiment, including step：
S301, the picture of finding a view that the dual camera of the mobile terminal absorbs is identified by the dual camera of mobile terminal
In N number of human face region, wherein N is integer more than or equal to 1.
Wherein, the step S101 of the described embodiment of the present invention referring to Figure 1 is specifically described.
S302, the depth of field for determining N number of human face region.
Wherein, the step S102 of the described embodiment of the present invention referring to Figure 1 is specifically described.
S303, the depth of field of N number of human face region is divided into M depth of field grade, wherein M is positive integer.
Wherein, the depth of field of N number of human face region can be divided into M depth of field grade by mobile terminal, such as the scape of N number of human face region
It is deep, it is assumed that N 5 can find out the maximum numerical value of the depth of field and the smallest numerical value of the depth of field, by scape from the depth of field of 5 human face regions
Range between deep maximum numerical value and the smallest numerical value of the depth of field is divided into M grade, and M can be arranged by system, can also by with
Family needs to be configured.
S304, N number of human face region is carried out at mill skin using the corresponding M kind mill skin Processing Algorithm of M depth of field grade
Reason, wherein mill skin processing used in mill skin processing is carried out to the pixel j of the human face region i in N number of human face region and is calculated
The depth of field grade of method and the pixel j have a corresponding relationship, the M depth of field grade and the M kind grind skin Processing Algorithm it
Between correspond, the human face region i be N number of human face region in any one human face region, the pixel j is institute
State any one pixel in human face region i.
Wherein, mobile terminal grinds N number of human face region using the corresponding M kind mill skin Processing Algorithm of M depth of field grade
Skin processing.Further, mill used in mill skin processing is carried out to the pixel j of the human face region i in N number of human face region
Skin Processing Algorithm and the depth of field grade of the pixel j have corresponding relationship, and the M depth of field grade and the M kind are ground at skin
It is corresponded between adjustment method, the human face region i is any one human face region in N number of human face region, the picture
Vegetarian refreshments j is any one pixel in the human face region i.
The embodiment of the present invention identifies that the dual camera of the mobile terminal absorbs by the dual camera of mobile terminal
The N number of human face region found a view in picture, wherein N is the integer more than or equal to 1；Determine that the depth of field of N number of human face region will
The depth of field of N number of human face region is divided into M depth of field grade, wherein M is positive integer；Use the corresponding M of M depth of field grade
Kind mill skin Processing Algorithm carries out mill skin processing to N number of human face region, wherein to the face in N number of human face region
The pixel j of region i carries out mill skin Processing Algorithm used in mill skin processing with the depth of field grade of the pixel j with corresponding
Relationship corresponds between the M depth of field grade and M kind mill skin Processing Algorithm, and the human face region i is described N number of
Any one human face region in human face region, the pixel j are any one pixel in the human face region i.It adopts
The image that mobile terminal takes can be carried out to mill skin processing with the embodiment of the present invention, it is more better than original picture quality to obtain
Image.
Referring to Fig. 4, Fig. 4 is a kind of structural representation of the fourth embodiment of photographic method provided in an embodiment of the present invention
Figure.As a kind of possible embodiment, photographic method as described in this embodiment is implementation described in FIG. 1 to FIG. 3
The specific descriptions of mill skin Processing Algorithm in example, including step：
S401, all images in the facial image database are divided into M class image according to the first preset condition.
Wherein, all images in facial image database are divided into M class image according to the first preset condition by mobile terminal.Into one
Step ground, the first preset condition may include, but are not limited to：The size of shooting angle, uniform illumination degree, ambient brightness etc..
S402, the image in any sort i in the M class image is subjected to image procossing according to preset algorithm, wherein appoint
A kind of i is any sort in the M class image.
Wherein, the image of any sort i in M class image is carried out image procossing according to preset algorithm by mobile terminal, any
Class i is any sort in M class image, then any integer of the i between 1~M.Preset algorithm may include, but are not limited to：Histogram
Scheme equalization, bilateral filtering, navigational figure filtering (English：Guided Image Filtering), bilinear interpolation, zadeh
Transformation etc..
S403, by the image in any sort i according to preset algorithm carry out after image procossing obtained image with it is described
Image in any sort i is fitted analysis, to obtain the mill skin in any sort i in the M kind mill skin Processing Algorithm
Processing Algorithm.
Wherein, mobile terminal by the image in any sort i according to preset algorithm carry out after image procossing obtained image with
Image in any sort i is fitted analysis, to obtain the mill skin Processing Algorithm in any sort i in M kind mill skin Processing Algorithm.
Further, mobile terminal by the image in any sort i according to preset algorithm carry out after image procossing obtained image with it is any
Image in class i is fitted analysis, for example, the image in any sort i is carried out the image and any sort i that image procossing obtains
In image be fitted, obtain fitting function and harmonic coefficient ki, wherein fitting function can be shaped like y=ki*x+b, wherein
Ki is the corresponding adjustment factor of image in any sort i, and b is constant, as any sort i in M kind mill skin Processing Algorithm
In mill skin Processing Algorithm.Since ki value is different, M class corresponds to M fitting function.It can also be non-thread that M kind, which grinds skin Processing Algorithm,
Property function.
All images in the facial image database are divided into M class image according to the first preset condition by the embodiment of the present invention；
Image in any sort i in the M class image is subjected to image procossing according to preset algorithm, wherein any sort i is the M
Any sort in class image；By the image in any sort i according to preset algorithm carry out after image procossing obtained image with
Image in any sort i is fitted analysis, to obtain in any sort i in the M kind mill skin Processing Algorithm
Grind skin Processing Algorithm.Skin Processing Algorithm is ground using the available M kind of the embodiment of the present invention.
Referring to Fig. 5, Fig. 5 is a kind of structural representation of the first embodiment of mobile terminal provided in an embodiment of the present invention
Figure.Mobile terminal as described in this embodiment, it is specific as follows：
Recognition unit 501 identifies the dual camera intake of the mobile terminal for the dual camera by mobile terminal
To picture of finding a view in N number of human face region, wherein N is integer more than or equal to 1.
Wherein, recognition unit 501 can identify the picture of finding a view that the dual camera of mobile terminal absorbs by dual camera
In N number of human face region, N is integer more than or equal to 1.Further, the dual camera of mobile terminal can be mobile terminal
Included dual camera, for example, dual camera is embedded in the shell of mobile terminal, the dual camera of mobile terminal, which can be located at, to be moved
The front of dynamic terminal or the behind of mobile terminal or the side of mobile terminal.Alternatively, the dual camera of mobile terminal can be
Mobile terminal passes through wireless technology or the dual camera of USB technical controlling.
As a kind of possible embodiment, recognition unit 501 identifies mobile terminal by the dual camera of mobile terminal
The picture of finding a view that absorbs of dual camera in N number of human face region before, mobile terminal can start the implementation embodiment of the present invention
The software of corresponding client.
As a kind of possible embodiment, the dual camera of mobile terminal may include, but are not limited to：Symmetry binocular
Camera or asymmetry binocular camera.
Determination unit 502, for determining the depth of field of N number of human face region.
Wherein it is determined that unit 502 determines the depth of field of N number of human face region.Wherein, mobile terminal utilizes the mobile terminal
The pixel difference between N number of facial image that each camera in dual camera absorbs determines each in N number of face
The depth of view information of the facial area of face.It is assumed that the dual camera of mobile terminal is respectively camera A and camera B, N 5,5
A human face region is respectively human face region A, human face region B, human face region C, human face region D, human face region E.For example, face area
The depth of field of domain A can be according to the pixel difference between the human face region A that the human face region A that camera A takes and camera B take
The depth of field of different determining human face region A.
Processing unit 503, for the depth of field according to each human face region in N number of human face region to N number of people
Face region carries out mill skin processing.
Wherein, processing unit 503 is according to the depth of field of each human face region in N number of human face region to N number of face area
Domain carries out mill skin processing.The sequence from left to right of the facial image absorbed can be used to N number of human face region in processing unit 503
Carry out mill skin processing.Alternatively, processing unit 503 may compare the superiority and inferiority of N number of human face region, using to N number of human face region effect most
The human face region of difference starts to grind skin processing, then successively carries out mill skin processing to the preferable human face region of human face region effect again,
Mill skin processing finally is carried out to human face region effect best's face region.
Recognition unit of the embodiment of the present invention 501 identifies double camera shootings of the mobile terminal by the dual camera of mobile terminal
N number of human face region in picture of finding a view that head absorbs, wherein N is the integer more than or equal to 1；Determination unit 502 determines institute
State the depth of field of N number of human face region；Processing unit 503 is according to the depth of field of each human face region in N number of human face region to institute
It states N number of human face region and carries out mill skin processing.It can be determined by the dual camera of mobile terminal using the embodiment of the present invention mobile whole
The depth of field of the human face region absorbed is held, and mill skin processing is carried out to human face region according to the depth of field, to obtain than original double camera shootings
The better facial image of effect that head absorbs, while there is interest, and user experience can be improved.
Referring to Fig. 6, Fig. 6 is a kind of structural representation of the second embodiment of mobile terminal provided in an embodiment of the present invention
Figure.The recognition unit 501 of mobile terminal as described in this embodiment includes modeling unit 601 and lock cell 602, specifically such as
Under：
Modeling unit 601, for being modeled using recognition of face library, to obtain the characteristic information of face.
Wherein, modeling unit 601 can be modeled using recognition of face library, and mobile terminal can be to big in recognition of face library
Amount facial image is analyzed, and the characteristic information of face is obtained.Further, the characteristic information of face may include but not only limit
In：The profile information of face, the distance between two information, the percent information of face, the Skin Color Informations of face etc..
Lock cell 602 is absorbed according to the dual camera that the characteristic information of the face locks the mobile terminal
The N number of face found a view in picture.
Wherein, lock cell 602 can be taken the photograph according to the dual camera that the characteristic information of the face locks the mobile terminal
The facial range for the N number of face in picture of finding a view got.
Modeling unit of the embodiment of the present invention 601 is modeled using recognition of face library, to obtain the characteristic information of face；Lock
In the picture of finding a view that order member 602 is absorbed according to the dual camera that the characteristic information of the face locks the mobile terminal
N number of face.The image in face database can be modeled to obtain face characteristic information by using the embodiment of the present invention, according to
Face characteristic information locks face range.
Referring to Fig. 7, Fig. 7 is a kind of structural representation of the 3rd embodiment of mobile terminal provided in an embodiment of the present invention
Figure.The processing unit 503 of mobile terminal as described in this embodiment includes：Division unit 701 and mill skin unit 702, specifically
It is as follows：
Division unit 701, for the depth of field of N number of human face region to be divided into M depth of field grade, wherein M is positive whole
Number.
Wherein, the depth of field of N number of human face region can be divided into M depth of field grade by division unit 701, such as N number of human face region
The depth of field, it is assumed that N 5 can find out the maximum numerical value of the depth of field and the smallest numerical value of the depth of field from the depth of field of 5 human face regions,
Range between the maximum numerical value of the depth of field and the smallest numerical value of the depth of field is divided into M grade, M can be arranged by system, can also be with
It needs to be configured by user.
Skin unit 702 is ground, for grinding skin Processing Algorithm to N number of human face region using the corresponding M kind of M depth of field grade
Carry out mill skin processing, wherein to the pixel j of the human face region i in N number of human face region carry out mill skin processing used
Mill skin Processing Algorithm and the depth of field grade of the pixel j there is corresponding relationship, the M depth of field grade and the M kind are ground
It is corresponded between skin Processing Algorithm, the human face region i is any one human face region in N number of human face region, institute
Stating pixel j is any one pixel in the human face region i.
Wherein, mill skin unit 702 carries out N number of human face region using the corresponding M kind mill skin Processing Algorithm of M depth of field grade
Grind skin processing.Further, the pixel j of the human face region i in N number of human face region is carried out used in mill skin processing
The depth of field grade for grinding skin Processing Algorithm and the pixel j has corresponding relationship, and the M depth of field grade and the M kind grind skin
It is corresponded between Processing Algorithm, the human face region i is any one human face region in N number of human face region, described
Pixel j is any one pixel in the human face region i.
As a kind of possible embodiment, mill skin Processing Algorithm can be：Step 1：By the institute in the facial image database
There is image to be divided into M class image according to the first preset condition；Step 2：By the image in any sort i in the M class image according to
Preset algorithm carries out image procossing, wherein any sort i is any sort in the M class image；Step 3：By any sort i
In image carry out the image after image procossing in obtained image and any sort i according to preset algorithm and be fitted point
Analysis, to obtain the mill skin Processing Algorithm in any sort i in the M kind mill skin Processing Algorithm.Specifically, mobile terminal will
All images in facial image database are divided into M class image according to the first preset condition.Further, the first preset condition may include
But it is not limited only to：The size of shooting angle, uniform illumination degree, ambient brightness etc..Mobile terminal is by any in M class image
The image of class i carries out image procossing according to preset algorithm, and any sort i is any sort in M class image, then i is between 1~M
Any integer.Preset algorithm may include, but are not limited to：Histogram equalization, bilateral filtering, navigational figure filtering (English：
Guided Image Filtering), bilinear interpolation, zadeh transformation etc..Mobile terminal presses the image in any sort i
The image in the image and any sort i that obtain after image procossing is carried out according to preset algorithm and is fitted analysis, to obtain M kind mill skin
Mill skin Processing Algorithm in any sort i in Processing Algorithm.Further, mobile terminal is by the image in any sort i according to pre-
The image that imputation method carries out in the image obtained after image procossing and any sort i is fitted analysis, for example, by any sort i
Image carry out the obtained image of image procossing and be fitted with the image in any sort i, obtain fitting function and harmonic coefficient
Ki, wherein fitting function can be shaped like y=ki*x+b, wherein ki is the corresponding adjustment factor of image in any sort i, and b is normal
The mill skin Processing Algorithm in any sort i in number, as M kind mill skin Processing Algorithm.Since ki value is different, M class corresponds to M
A fitting function.It can also be nonlinear function that M kind, which grinds skin Processing Algorithm,.
The depth of field of N number of human face region is divided into M depth of field grade by division unit of the embodiment of the present invention 701, wherein
M is positive integer；Skin unit 702 is ground using the corresponding M kind mill skin Processing Algorithm of M depth of field grade to N number of human face region
Carry out mill skin processing, wherein carry out used in mill skin processing to the pixel j of the human face region i in N number of human face region
The depth of field grade for grinding skin Processing Algorithm and the pixel j has corresponding relationship, and the M depth of field grade and the M kind grind skin
It is corresponded between Processing Algorithm, the human face region i is any one human face region in N number of human face region, described
Pixel j is any one pixel in the human face region i.Mobile terminal can be taken using the embodiment of the present invention
Image carries out mill skin processing, to obtain than original picture quality better image.
Referring to Fig. 8, Fig. 8 is a kind of structural representation of the fourth embodiment of mobile terminal provided in an embodiment of the present invention
Figure.Mobile terminal as described in this embodiment includes：At least one input equipment 1000；At least one output equipment 2000；
At least one processor 3000, such as CPU；With memory 4000, above-mentioned input equipment 1000, output equipment 2000, processor
3000 and memory 4000 connected by bus 5000.
Wherein, above-mentioned input equipment 1000 can be touch panel, common PC, liquid crystal display, touch screen, push button etc..
Above-mentioned memory 4000 can be high speed RAM memory, can also be non-labile memory (non-volatile
), such as magnetic disk storage memory.Above-mentioned memory 4000 is used to store a set of program code, above-mentioned input equipment 1000, defeated
Equipment 2000 and processor 3000 are performed the following operations for calling the program code stored in memory 4000 out：
Above-mentioned processor 3000 identifies that the dual camera of the mobile terminal is taken the photograph for the dual camera by mobile terminal
The N number of human face region in picture of finding a view got, wherein N is the integer more than or equal to 1；
Above-mentioned processor 3000, is also used to：
Determine the depth of field of N number of human face region；
Above-mentioned processor 3000, is also used to：
It is modeled using recognition of face library, to obtain the characteristic information of face；
The N in picture of finding a view absorbed according to the dual camera that the characteristic information of the face locks the mobile terminal
The facial range of a face.
In some possible embodiments, above-mentioned processor 3000 is also used to：
The pixel difference between N number of facial image absorbed using each camera in the dual camera of the mobile terminal
The depth of field of the facial area of each face in different determination N number of face.
In some possible embodiments, above-mentioned processor 3000 is also used to：
The depth of field of N number of human face region is divided into M depth of field grade, wherein M is positive integer；
Mill skin is carried out to N number of human face region using the corresponding M kind mill skin Processing Algorithm of M depth of field grade to handle,
In, to the pixel j of the human face region i in N number of human face region carry out mill skin processing used in mill skin Processing Algorithm with
The depth of field grade of the pixel j has corresponding relationship, one between the M depth of field grade and M kind mill skin Processing Algorithm
One is corresponding, and the human face region i is any one human face region in N number of human face region, and the pixel j is the people
Any one pixel in the i of face region.
In some possible embodiments, above-mentioned processor 3000 is also used to：
All images in the facial image database are divided into M class image according to the first preset condition；
Image in any sort i in the M class image is subjected to image procossing according to preset algorithm, wherein any sort i
For any sort in the M class image；
Image in any sort i is subjected to the image obtained after image procossing and any sort according to preset algorithm
Image in i is fitted analysis, is calculated with obtaining the mill skin processing in any sort i in the M kind mill skin Processing Algorithm
Method.
As a kind of possible embodiment, the dual camera of mobile terminal can be symmetry binocular camera or asymmetric
Property binocular camera.
In the specific implementation, input equipment 1000 described in the embodiment of the present invention, output equipment 2000 and processor
3000 can be performed reality described in each embodiment of photographic method described in FIG. 1 to FIG. 4 provided in an embodiment of the present invention
Existing mode, also can be performed described in each embodiment of mobile terminal described in Fig. 5~Fig. 7 provided in an embodiment of the present invention
Mobile terminal implementation, details are not described herein.
Module or submodule in all embodiments of the embodiment of the present invention, can pass through universal integrated circuit, such as CPU
(Central Processing Unit, central processing unit), or pass through ASIC (Application Specific
Integrated Circuit, specific integrated circuit) it realizes.
The steps in the embodiment of the present invention can be sequentially adjusted, merged and deleted according to actual needs.
Unit in the device of that embodiment of the invention can be combined, divided and deleted according to actual needs.
Those of ordinary skill in the art will appreciate that realizing all or part of the process in above-described embodiment method, being can be with
Relevant hardware is instructed to complete by computer program, the program, which can be stored in a computer and can spend, takes storage medium
In, the program is when being executed, it may include such as the process of the embodiment of above-mentioned each method.Wherein, the storage medium can be magnetic
Dish, CD, read-only memory (Read-Only Memory, ROM) or random access memory (Random Access
Memory, abbreviation RAM) etc..
Above disclosed is only preferred embodiment of the embodiment of the present invention, certainly cannot be of the invention real to limit with this
The interest field of example is applied, therefore according to equivalent variations made by claim of the embodiment of the present invention, still belongs to the embodiment of the present invention and contained
The range of lid.
Claims (8)
1. a kind of photographic method, which is characterized in that including：
N number of people in picture of finding a view that the dual camera of the mobile terminal absorbs is identified by the dual camera of mobile terminal
Face region, wherein N is the integer more than or equal to 1；
Determine the depth of field of N number of human face region；
Mill skin processing is carried out to N number of human face region according to the depth of field of each human face region in N number of human face region；Packet
It includes：The depth of field of N number of human face region is divided into M depth of field grade, wherein M is positive integer；Use M depth of field grade pair
The M kind mill skin Processing Algorithm answered carries out mill skin processing to N number of human face region, wherein to the people in N number of human face region
The pixel j of face region i carry out mill skin processing used in mill skin Processing Algorithm and the pixel j depth of field grade have pair
It should be related to, be corresponded between the M depth of field grade and M kind mill skin Processing Algorithm, the human face region i is the N
Any one human face region in a human face region, the pixel j are any one pixel in the human face region i.
2. the method as described in claim 1, which is characterized in that the dual camera by mobile terminal identifies the movement
N number of human face region in what the dual camera of terminal absorbed find a view picture, including：
It is modeled using recognition of face library, to obtain the characteristic information of face；
The N number of people in picture of finding a view absorbed according to the dual camera that the characteristic information of the face locks the mobile terminal
The facial range of face.
3. such as the described in any item methods of claims 1 or 2, which is characterized in that the scape of determination N number of human face region
It is deep, including：
The pixel difference between N number of facial image absorbed using each camera in the dual camera of the mobile terminal is true
The depth of field of the facial area of each face in fixed N number of face.
4. such as the described in any item methods of claims 1 or 2, the dual camera includes：Symmetry binocular camera is non-right
Title property binocular camera.
5. a kind of mobile terminal, which is characterized in that including：
Recognition unit identifies that the dual camera of the mobile terminal absorbed finds a view for the dual camera by mobile terminal
N number of human face region in picture, wherein N is the integer more than or equal to 1；
Determination unit, for determining the depth of field of N number of human face region；
Processing unit, for according to the depth of field of each human face region in N number of human face region to N number of human face region into
Row mill skin processing, wherein the processing unit includes division unit and mill skin unit；The division unit is used for will be described N number of
The depth of field of human face region is divided into M depth of field grade, wherein M is positive integer；The mill skin unit is used for using M depth of field etc.
The corresponding M kind mill skin Processing Algorithm of grade carries out mill skin processing to N number of human face region, wherein to N number of human face region
In human face region i pixel j carry out mill skin processing used in mill skin Processing Algorithm and the pixel j depth of field grade
With corresponding relationship, corresponded between the M depth of field grade and M kind mill skin Processing Algorithm, the human face region i is
Any one human face region in N number of human face region, the pixel j are any one picture in the human face region i
Vegetarian refreshments.
6. mobile terminal as claimed in claim 5, which is characterized in that the recognition unit includes：
Modeling unit, for being modeled using recognition of face library, to obtain the characteristic information of face；
Lock cell, the picture of finding a view absorbed according to the dual camera that the characteristic information of the face locks the mobile terminal
In N number of face.
7. such as the described in any item mobile terminals of claim 5 or 6, which is characterized in that the determination unit is specifically used for：
The each facial image in N number of facial image absorbed using each camera in the dual camera of the mobile terminal
Between pixel difference determine each face in N number of face facial area the depth of field.
8. such as the described in any item mobile terminals of claim 5 or 6, the dual camera includes：Symmetry binocular camera or
Asymmetry binocular camera.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510106675.9A CN104754221B (en) | 2015-03-11 | 2015-03-11 | A kind of photographic method and mobile terminal |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510106675.9A CN104754221B (en) | 2015-03-11 | 2015-03-11 | A kind of photographic method and mobile terminal |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104754221A CN104754221A (en) | 2015-07-01 |
| CN104754221B true CN104754221B (en) | 2018-11-16 |
Family
ID=53593263
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510106675.9A Expired - Fee Related CN104754221B (en) | 2015-03-11 | 2015-03-11 | A kind of photographic method and mobile terminal |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104754221B (en) |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105513007A (en) * | 2015-12-11 | 2016-04-20 | 惠州Tcl移动通信有限公司 | Mobile terminal based photographing beautifying method and system, and mobile terminal |
| CN105825485B (en) * | 2016-03-30 | 2018-12-21 | 努比亚技术有限公司 | A kind of image processing system and method |
| CN105744171B (en) * | 2016-03-30 | 2019-03-08 | 联想(北京)有限公司 | A kind of image processing method and electronic equipment |
| CN106162148A (en) * | 2016-09-14 | 2016-11-23 | 宇龙计算机通信科技(深圳)有限公司 | The method of a kind of mobile terminal shooting image, system and mobile terminal |
| CN106973227A (en) * | 2017-03-31 | 2017-07-21 | 努比亚技术有限公司 | Intelligent photographing method and device based on dual camera |
| CN107680128B (en) * | 2017-10-31 | 2020-03-27 | Oppo广东移动通信有限公司 | Image processing method, image processing device, electronic equipment and computer readable storage medium |
| CN110417990B (en) * | 2019-03-25 | 2020-07-24 | 浙江麦知网络科技有限公司 | APP starting system based on target analysis |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103413270A (en) * | 2013-08-15 | 2013-11-27 | 北京小米科技有限责任公司 | Method and device for image processing and terminal device |
| CN103632165A (en) * | 2013-11-28 | 2014-03-12 | 小米科技有限责任公司 | Picture processing method, device and terminal equipment |
| CN103685926A (en) * | 2012-09-21 | 2014-03-26 | 宏达国际电子股份有限公司 | Method for image processing of face regions and electronic device by using the same |
| CN104375797A (en) * | 2014-11-17 | 2015-02-25 | 联想(北京)有限公司 | Information processing method and electronic equipment |
| CN104394308A (en) * | 2014-11-28 | 2015-03-04 | 广东欧珀移动通信有限公司 | Method of taking pictures in different perspectives with double cameras and terminal thereof |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8520059B2 (en) * | 2010-03-24 | 2013-08-27 | Fujifilm Corporation | Stereoscopic image taking apparatus |
-
2015
- 2015-03-11 CN CN201510106675.9A patent/CN104754221B/en not_active Expired - Fee Related
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103685926A (en) * | 2012-09-21 | 2014-03-26 | 宏达国际电子股份有限公司 | Method for image processing of face regions and electronic device by using the same |
| CN103413270A (en) * | 2013-08-15 | 2013-11-27 | 北京小米科技有限责任公司 | Method and device for image processing and terminal device |
| CN103632165A (en) * | 2013-11-28 | 2014-03-12 | 小米科技有限责任公司 | Picture processing method, device and terminal equipment |
| CN104375797A (en) * | 2014-11-17 | 2015-02-25 | 联想(北京)有限公司 | Information processing method and electronic equipment |
| CN104394308A (en) * | 2014-11-28 | 2015-03-04 | 广东欧珀移动通信有限公司 | Method of taking pictures in different perspectives with double cameras and terminal thereof |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104754221A (en) | 2015-07-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104754221B (en) | A kind of photographic method and mobile terminal | |
| KR102444085B1 (en) | Portable communication apparatus and method for displaying images thereof | |
| US11532180B2 (en) | Image processing method and device and storage medium | |
| CN109961406B (en) | Image processing method and device and terminal equipment | |
| CN105282430B (en) | Electronic device using composition information of photograph and photographing method using the same | |
| JP5996013B2 (en) | Method, apparatus and computer program product for parallax map estimation of stereoscopic images | |
| US20180025478A1 (en) | Electronic device for processing image | |
| US20150244916A1 (en) | Electronic device and control method of the same | |
| US10674066B2 (en) | Method for processing image and electronic apparatus therefor | |
| WO2016110188A1 (en) | Method and electronic device for aesthetic enhancements of face in real-time video | |
| KR102547104B1 (en) | Electronic device and method for processing plural images | |
| CN109767466B (en) | Picture rendering method and device, terminal and corresponding storage medium | |
| KR20150077646A (en) | Image processing apparatus and method | |
| US20180159971A1 (en) | Method and apparatus for generating unlocking interface, and electronic device | |
| CN107690804B (en) | Image processing method and user terminal | |
| EP3086245A1 (en) | Method and device for sharing picture | |
| CN105791793A (en) | Image processing method and electronic device | |
| CN107730443B (en) | Image processing method and device and user equipment | |
| WO2018133305A1 (en) | Method and device for image processing | |
| CN112734661A (en) | Image processing method and device | |
| CN109089042B (en) | Image processing mode identification method and device, storage medium and mobile terminal | |
| CN105786986A (en) | Picture finding method and device | |
| CN105893578A (en) | Method and device for selecting photos | |
| CN110689565B (en) | Depth map determination method and device and electronic equipment | |
| CN106331486A (en) | Image processing method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP01 | Change in the name or title of a patent holder |
Address after: Changan town in Guangdong province Dongguan 523860 usha Beach Road No. 18 Patentee after: GUANGDONG OPPO MOBILE TELECOMMUNICATIONS Corp.,Ltd. Address before: Changan town in Guangdong province Dongguan 523860 usha Beach Road No. 18 Patentee before: GUANGDONG OPPO MOBILE TELECOMMUNICATIONS Corp.,Ltd. |
|
| CP01 | Change in the name or title of a patent holder | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20181116 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |