CN106846281A - image beautification method and terminal device - Google Patents
image beautification method and terminal device Download PDFInfo
- Publication number
- CN106846281A CN106846281A CN201710139599.0A CN201710139599A CN106846281A CN 106846281 A CN106846281 A CN 106846281A CN 201710139599 A CN201710139599 A CN 201710139599A CN 106846281 A CN106846281 A CN 106846281A
- Authority
- CN
- China
- Prior art keywords
- image
- texture
- bilateral filtering
- flat site
- face
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 83
- 238000001914 filtration Methods 0.000 claims abstract description 44
- 230000002146 bilateral effect Effects 0.000 claims abstract description 43
- 230000014759 maintenance of location Effects 0.000 claims abstract description 11
- 230000006870 function Effects 0.000 claims description 33
- 230000000694 effects Effects 0.000 claims description 14
- 238000004422 calculation algorithm Methods 0.000 claims description 6
- 238000004040 coloring Methods 0.000 claims description 4
- 238000001514 detection method Methods 0.000 claims description 4
- 238000010606 normalization Methods 0.000 claims description 4
- 238000013519 translation Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 description 7
- 230000008859 change Effects 0.000 description 5
- 238000003860 storage Methods 0.000 description 5
- 230000008901 benefit Effects 0.000 description 4
- 238000005315 distribution function Methods 0.000 description 4
- 230000002087 whitening effect Effects 0.000 description 4
- 238000005457 optimization Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000007423 decrease Effects 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 230000003255 anti-acne Effects 0.000 description 1
- 230000003796 beauty Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 239000002537 cosmetic Substances 0.000 description 1
- 230000001186 cumulative effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000001815 facial effect Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20024—Filtering details
- G06T2207/20028—Bilateral filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30196—Human being; Person
- G06T2207/30201—Face
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Image Processing (AREA)
Abstract
The invention provides a kind of image beautification method and terminal device, it is related to Mobile solution technical field, for beautifying to the face-image in terminal device, the method includes：Obtain the texture of image；The fringe region of the texture is made a distinction with flat site by bilateral filtering method；According to the edge retention performance of the bilateral filtering method, retain the pixel color value information of the fringe region；Gaussian Blur treatment is carried out to the flat site, Gaussian Blur result is obtained, it is too low to solve present in prior art image beautification software for editing performance, makes cpu performance exorbitant expenditure, and mobile terminal is hot, the technical problem that power consumption is sharply increased.
Description
Technical field
The present invention relates to Mobile solution technical field, more particularly, to a kind of image beautification method and terminal device.
Background technology
At present, with the development of smart mobile phone, mobile phone auto heterodyne, live etc. have been that a mobile subscriber being in daily use uses
Scene.Existing intelligent terminal passes through U.S. face software, and can be directed to the facial image autodyned carries out beautification editor, in mobile phone
Or can complete to grind the effect of skin U.S. face on live platform.
U.S. face is the software that a face to people is beautified, U.S. face instrument included whitening, mill skin, anti-acne, cosmetic,
The functions such as self-made face pack, natural beauty, are not limited by place, time, space, it is not necessary to networking just can beautifying picture, be use
The condition that family is provided convenience.U.S. face camera is a client software for autodyning, and possesses automatic U.S.'s flesh and intelligence U.S. type
Function, overturn tradition and take pictures effect, automatic U.S. face that can be quickly.
But, the performance of existing image beautification software for editing is too low, makes mobile terminal exorbitant expenditure, due to matching somebody with somebody for mobile terminal
Put uneven, the consumption of central processing unit (Central Processing Unit, abbreviation CPU) performance can cause mobile terminal
Hot, power consumption is sharply increased.
The content of the invention
In view of this, it is existing to solve it is an object of the invention to provide a kind of image beautification method and terminal device
The beautification of image present in technology software for editing performance is too low, makes cpu performance exorbitant expenditure, and mobile terminal is hot, and power consumption is drastically
Increased technical problem.
In a first aspect, the embodiment of the invention provides a kind of image beautification method, methods described is used in terminal device
Face-image beautified, the method includes：
Obtain the texture of image；
The fringe region of the texture is made a distinction with flat site by bilateral filtering method；
According to the edge retention performance of the bilateral filtering method, retain the pixel color value information of the fringe region；
Gaussian Blur treatment is carried out to the flat site, Gaussian Blur result is obtained.
With reference in a first aspect, the embodiment of the invention provides the first possible implementation method of first aspect, wherein,
After the texture for obtaining image, also include：
Recognize the face position in the texture.
With reference in a first aspect, the embodiment of the invention provides second possible implementation method of first aspect, wherein, institute
The face position in the identification texture is stated, specially：
According to threshold value skin color model criterion, the face position in the texture is recognized by Face Detection.
With reference in a first aspect, the embodiment of the invention provides the third possible implementation method of first aspect, wherein, institute
It is the color mode based on RGB to state threshold value skin color model criterion；
The criterion of identification is specially：R>95 and G>40 and B>20 and R>G and R>B and Max (R, G, B)-Min (R, G, B)>
15 and Abs (R-G)>15；
Wherein, R is red index value, and G is green index value, and B is blue index value, and Max is to take max function, Min
To take minimum value function, Abs is the function that takes absolute value.
With reference in a first aspect, the embodiment of the invention provides the 4th kind of possible implementation method of first aspect, wherein, institute
State the fringe region of the texture is made a distinction with flat site by bilateral filtering method, specially：
The fringe region at the face position is made a distinction with flat site by bilateral filtering method.
With reference in a first aspect, the embodiment of the invention provides the 5th kind of possible implementation method of first aspect, wherein, institute
The algorithm for stating bilateral filtering method is specially：
WhereinIt is the effect formula of image normalization；
σsIt is the standard deviation of spatial domain Gaussian function；
σrIt is the standard deviation of codomain Gaussian function；
Ω is the domain of definition of convolution, and the convolution is to characterize function by upset and the lap area of translation；
X, y are stochastic variable；
W is weight coefficient.
With reference in a first aspect, the embodiment of the invention provides the 6th kind of possible implementation method of first aspect, wherein, institute
State carries out Gaussian Blur treatment to the flat site, specially：
In the flat site, the pixel colour of the texture is adjusted according to Gaussian curve.
With reference in a first aspect, the embodiment of the invention provides the 7th kind of possible implementation method of first aspect, wherein, also
Including：
Precision to the coloring programming language of the Gaussian Blur result is optimized, and obtains image beautification result.
With reference in a first aspect, the embodiment of the invention provides the 8th kind of possible implementation method of first aspect, wherein, institute
Stating image includes dynamic image and still image.
Second aspect, the embodiment of the present invention also provides a kind of image beautification terminal device, including：It is texture acquirement module, double
Side filtration module；
The texture acquirement module is used to obtain the texture of image；
The bilateral filtering module is used to carry out the fringe region of the texture with flat site by bilateral filtering method
Distinguish；
The bilateral filtering module is additionally operable to the edge retention performance according to the bilateral filtering method, retains the marginal zone
The pixel color value information in domain；
The bilateral filtering module is additionally operable to carry out Gaussian Blur treatment to the flat site, obtains Gaussian Blur treatment
As a result.
Technical scheme provided in an embodiment of the present invention brings following beneficial effect：Image provided in an embodiment of the present invention is beautiful
In change method, the texture of image is obtained first, the fringe region of texture is made a distinction with flat site by bilateral filtering method,
Edge retention performance according to bilateral filtering method, retains the pixel color value information of fringe region, and Gaussian mode is carried out to flat site
Paste treatment, obtains Gaussian Blur result, retains and to flat site Gauss by border area pixels colour information
The differentiation processing procedure of Fuzzy Processing, realization is not processed fringe region, reduces CPU consumption, improves image beautification editor
The performance of software, reduces the consumption of mobile terminal performance, so as to solve the beautification of image present in prior art software for editing
Performance is too low, makes cpu performance exorbitant expenditure, and mobile terminal is hot, the technical problem that power consumption is sharply increased.
Other features and advantages of the present invention will be illustrated in the following description, also, the partly change from specification
Obtain it is clear that or being understood by implementing the present invention.The purpose of the present invention and other advantages are in specification, claims
And specifically noted structure is realized and obtained in accompanying drawing.
To enable the above objects, features and advantages of the present invention to become apparent, preferred embodiment cited below particularly, and coordinate
Appended accompanying drawing, is described in detail below.
Brief description of the drawings
In order to illustrate more clearly of the specific embodiment of the invention or technical scheme of the prior art, below will be to specific
The accompanying drawing to be used needed for implementation method or description of the prior art is briefly described, it should be apparent that, in describing below
Accompanying drawing is some embodiments of the present invention, for those of ordinary skill in the art, before creative work is not paid
Put, other accompanying drawings can also be obtained according to these accompanying drawings.
Fig. 1 shows the flow chart of the image beautification method that the embodiment of the present invention one is provided；
Fig. 2 shows the flow chart of the image beautification method that the embodiment of the present invention two is provided；
Fig. 3 shows that a kind of image that the embodiment of the present invention three is provided beautifies the structural representation of terminal device；
Fig. 4 shows that a kind of image that the embodiment of the present invention three is provided beautifies another structural representation of terminal device.
Icon：1- images beautify terminal device；11- texture acquirement modules；12- bilateral filtering modules；13- face recognition moulds
Block；14- result optimizing modules.
Specific embodiment
To make the purpose, technical scheme and advantage of the embodiment of the present invention clearer, below in conjunction with accompanying drawing to the present invention
Technical scheme be clearly and completely described, it is clear that described embodiment is a part of embodiment of the invention, rather than
Whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art are not making creative work premise
Lower obtained every other embodiment, belongs to the scope of protection of the invention.
The performance of existing image beautification software for editing is too low at present, makes mobile terminal exorbitant expenditure, due to matching somebody with somebody for mobile terminal
Put uneven, the consumption of cpu performance can cause that mobile terminal is hot, and power consumption is sharply increased, and based on this, the embodiment of the present invention is carried
A kind of image beautification method and terminal device for supplying, can solve the beautification of image present in prior art software for editing performance
It is too low, make cpu performance exorbitant expenditure, mobile terminal is hot, the technical problem that power consumption is sharply increased.
For ease of understanding the present embodiment, first to a kind of image beautification method disclosed in the embodiment of the present invention with
And terminal device describes in detail.
Embodiment one：
A kind of image beautification method provided in an embodiment of the present invention, can be used to carry out U.S. to the face-image in terminal device
Change or mill skin, as shown in figure 1, the method is comprised the following steps：
S11：Obtain the texture of image.
Specifically, the subset (the OpenGL for Embedded Systems, letter that pass through graphics application program DLL
Claim OpenGL ES) obtain the texture of camera preview image.Wherein, image includes dynamic image and still image, therefore, image
It can be the pattern of picture and video.
Wherein, in OpenGL ES across programming language, the professional graphic package interface of cross-platform DLL specification
(Open Graphics Library, abbreviation OpenGL), is applied to 3-D view or two dimensional image, is powerful One function, adjusts
With convenient underlying graphics storehouse.Therefore, OpenGL ES are OpenGL 3-D graphic application programming interfaces (Application
Programming Interface, abbreviation API) subset, for mobile phone, palm PC (Personal Digital
Assistant, abbreviation PDA) and the embedded device such as game host and design.
For API, it is some pre-defined functions, it is therefore an objective to provides application program and is based on certain software with developer
Or hardware is able to access one group of ability of routine, and source code, or the details for understanding internal work mechanism need not be accessed.
It should be noted that texture refers to textures inside game making, game making needs to use substantial amounts of picture materials,
Especially 3D game, can deposit picture to texture the inside when game making, can be read during running game.
S12：The fringe region of texture is made a distinction with flat site by bilateral filtering method.
S13：Edge retention performance according to bilateral filtering method, retains the pixel color value information of fringe region.
The edge retention performance of the bilateral filtering method in the embodiment of the present invention, mainly combines by during convolution
, come what is realized, typical kernel function is gauss of distribution function for spatial domain function and codomain kernel function.
In the present embodiment, the specific algorithm of the bilateral filtering method being related in step S12 and S13 is：WhereinIt is image
Normalized effect formula.Image normalization refers to the treatment conversion that series of standards has been carried out to image, is allowed to be transformed to one
The process of fixed standard form, the standard picture is referred to as normalized image, and original image can be obtained by after some treatment
Various duplicate pictures, these images are in the standard drawing by that can obtain same form after the treatment of the image normalization of identical parameters
Picture.
Wherein, the σ in algorithmsIt is the standard deviation of spatial domain Gaussian function, σrIt is the standard deviation of codomain Gaussian function, Ω is volume
Long-pending domain of definition, convolution is to characterize function by upset and the lap area of translation, and f (x) is gauss of distribution function,
It is cumulative distribution function, x, y are stochastic variable, and w is weight coefficient.
Therefore, in the flat site of image, the value changes very little of f (y)-f (x), corresponding codomain weight close to 1, this
Time-space domain weight plays a major role, equivalent to directly carrying out Gaussian Blur to this region.And in the fringe region of image, f (y)-f
X () has larger difference, now codomain coefficient can decline, and causes the decline of whole kernel function distribution herein, so as to maintain
The detailed information at edge.Therefore, the algorithm constitutes weight information by a Gaussian component and gradient component, realizes obscuring with this
While smoothed image, retain the function at edge.
S14：Gaussian Blur treatment is carried out to flat site, Gaussian Blur result is obtained.
It is further Gaussian Blur treatment to be carried out to flat site, specially：In flat site, according to Gaussian curve
Adjust the pixel colour of texture.
For prior art, although graphic process unit (Graphics Processing Unit, abbreviation GPU) filter
Substantially U.S. face mill bark effect substantially can be realized, but the essence of mill skin is the fuzzy of image, is only then only examined with GPU filters
The distance weighting between pixel is considered, the characteristics of do not account for difference between pixel.For example, the color of the eye of people and people's face skin
It is widely different, i.e., there is difference, the eye of people and people's face if only with GPU filters between the color of black and application on human skin
Edge between skin can also be obscured, and this is apparently not the result that user wants.
In the present embodiment, the image beautification method provided by the present embodiment, with bilateral filtering method, it is contemplated that color
Difference, its pixel value is also the weighted average of peripheral image vegetarian refreshments, and weight is also Gaussian function, is solved similar
The problem that edge between the eye and people's face skin of people can be obscured, and final from actual effect, it in combination with
Space length and pixel value difference in itself between pixel, realize preferably mill bark effect.
Embodiment two：
A kind of image beautification method provided in an embodiment of the present invention, can be directed to camera U.S. face software of android mobile terminal,
As shown in Fig. 2 the method is comprised the following steps：
S101：Obtain the texture of image.
S102：Face position in identification texture.
As the another embodiment of the present embodiment, according to threshold value skin color model criterion, line is recognized by Face Detection
Face position in reason.Wherein, threshold value skin color model criterion is the color mode based on RGB.Criterion of identification is specially：R>95 and
G>40 and B>20 and R>G and R>B and Max (R, G, B)-Min (R, G, B)>15 and Abs (R-G)>15.
Wherein, R is red index value, and G is green index value, and B is blue index value, and Max is to take max function, Min
To take minimum value function, Abs is the function that takes absolute value.
As the preferred embodiment of the present embodiment, with the threshold value skin color model criterion based on RGB color, can be with
The more accurate face position obtained in real time camera, can effectively reduce the execution time of program, reduce CPU consumption, with
The performance that image beautifies software for editing is improved, the consumption of mobile terminal performance is reduced.
S1021：Non- face position is not processed.
It should be noted that by not processing to non-face position, the consumption of graphic process unit is reduced with this, figure is improved
As the performance of beautification software for editing, the consumption of mobile terminal performance is reduced.
S1022：Bilateral filtering is carried out to face position.
Specifically, the fringe region at face position is made a distinction with flat site by bilateral filtering method, and according to double
The edge retention performance of side filter method, retains the pixel color value information of fringe region, while carrying out Gaussian Blur to flat site
Treatment, obtains Gaussian Blur result.
Therefore, the mill skin of the colour of skin is carried out on the basis of after being recognized to face position, with bilateral filtering algorithm to face
Position is processed, that is, realize that the effect of skin is ground in whitening.
S1023：Optimization OpenGL, completes camera U.S. face mill skin.
Gaussian Blur treatment is being carried out to flat site, is being obtained after Gaussian Blur result, can also included：To height
The precision of the coloring programming language of this Fuzzy Processing result is optimized, and obtains image beautification result.
As a preferred scheme, finally optimize shading language (the OpenGL Shading Language, letter of OpenGL
Claim GLSL) precision realize the GPU programmings of tinter, reach the U.S. face mill skin of optimization and reduce the purpose of CPU consumption.
Image beautification method provided in an embodiment of the present invention can based on mobile terminal real time camera U.S. face mill skin realize,
The method can be related to Mobile solution or field of play.
Existing camera U.S. face mill skin method, that is, enable and complete mill skin U.S. face effect by mobile phone or live platform, but
The configuration of the terminal devices such as mobile phone often exorbitant expenditure, particularly Android mobile phone is uneven, causes the hot power consumption urgency of mobile phone
Increase severely and add.The camera U.S. face provided by the present embodiment grinds skin method, improves its performance, reduces disappearing for CPU handset capabilities
Consumption, it is to avoid the generation of the hot phenomenon of mobile phone.And finally see U.S. face mill bark effect it is more natural, be not all of all obscuring
State, reaches intersection and does not obscure, clear and obvious.
Embodiment three：
Image provided in an embodiment of the present invention beautifies terminal device 1, as shown in figure 3, the terminal device includes：Texture acquirement
Module 11 and bilateral filtering module 12.
It should be noted that texture acquirement module 11 is used to obtain the texture of image.Specifically, texture acquirement module 11 is logical
The subset for crossing graphics application program DLL obtains the texture of camera preview image.Wherein, image include dynamic image with it is quiet
State image, therefore, image can be the pattern of picture and video.
It is further that bilateral filtering module 12 is used for the fringe region and flat site to texture by bilateral filtering method
Make a distinction, bilateral filtering module 12 is additionally operable to the edge retention performance according to bilateral filtering method, retain the pixel of fringe region
Colour information, wherein, the edge retention performance of bilateral filtering method be mainly by combine during convolution spatial domain function and
Come what is realized, typical kernel function is gauss of distribution function to codomain kernel function.
Used as the another embodiment of the present embodiment, bilateral filtering module 12 is additionally operable to carry out Gaussian mode to flat site
Paste treatment, obtains Gaussian Blur result.In flat site, bilateral filtering module 12 adjusts the picture of texture according to Gaussian curve
Plain color value.
In the present embodiment, terminal device 1 is beautified by image and uses bilateral filtering method, it is contemplated that the difference of color, it
Pixel value is also the weighted average of peripheral image vegetarian refreshments, and weight is also Gaussian function, solve the eye of similar people with
The problem that edge between people's face skin can be obscured, and it is final from actual effect, and it is in combination with space between pixel
Distance and pixel value difference in itself, realize preferably mill bark effect.
As shown in figure 4, image beautification terminal device 1 can also include face recognition module 13, for recognizing texture in
Face position.Face recognition module 13 recognizes the face position in texture according to threshold value skin color model criterion by Face Detection.
Wherein, threshold value skin color model criterion is the color mode based on RGB.
Used as the preferred embodiment of the present embodiment, image beautification terminal device 1 can also include result optimizing module 14,
As shown in figure 4, result optimizing module 14 is used to optimize the precision of the coloring programming language of Gaussian Blur result, obtain
Beautify result to image, reach the U.S. face mill skin of optimization and reduce the purpose of CPU consumption.
It should be noted that image beautification terminal device 1 can realize the U.S. face whitening effect of mobile terminal camera, master is reached
It is in real time the face whitening of main broadcaster U.S. while broadcasting explanation.
Image provided in an embodiment of the present invention beautifies terminal device, and the image beautification method provided with above-described embodiment has
Identical technical characteristic, so can also solve identical technical problem, reaches identical technique effect.
Image beautification method and the computer program product of terminal device that the embodiment of the present invention is provided, including storage
The computer-readable recording medium of program code, the instruction that described program code includes can be used to perform previous methods embodiments
Described in method, implement can be found in embodiment of the method, will not be repeated here.
If the function is to realize in the form of SFU software functional unit and as independent production marketing or when using, can be with
Storage is in a computer read/write memory medium.Based on such understanding, technical scheme is substantially in other words
The part contributed to prior art or the part of the technical scheme can be embodied in the form of software product, the meter
Calculation machine software product is stored in a storage medium, including some instructions are used to so that a computer equipment (can be individual
People's computer, server, or network equipment etc.) perform all or part of step of each embodiment methods described of the invention.
And foregoing storage medium includes：USB flash disk, mobile hard disk, read-only storage (ROM, Read-Only Memory), arbitrary access are deposited
Reservoir (RAM, Random Access Memory), magnetic disc or CD etc. are various can be with the medium of store program codes.
Finally it should be noted that：Embodiment described above, specific embodiment only of the invention, is used to illustrate the present invention
Technical scheme, rather than its limitations, protection scope of the present invention is not limited thereto, although with reference to the foregoing embodiments to this hair
It is bright to be described in detail, it will be understood by those within the art that：Any one skilled in the art
The invention discloses technical scope in, it can still modify to the technical scheme described in previous embodiment or can be light
Change is readily conceivable that, or equivalent is carried out to which part technical characteristic；And these modifications, change or replacement, do not make
The essence of appropriate technical solution departs from the spirit and scope of embodiment of the present invention technical scheme, should all cover in protection of the invention
Within the scope of.Therefore, protection scope of the present invention described should be defined by scope of the claims.
Claims (10)
1. a kind of image beautification method, methods described is used to beautify the face-image in terminal device, it is characterised in that
The method includes：
Obtain the texture of image；
The fringe region of the texture is made a distinction with flat site by bilateral filtering method；
According to the edge retention performance of the bilateral filtering method, retain the pixel color value information of the fringe region；
Gaussian Blur treatment is carried out to the flat site, Gaussian Blur result is obtained.
2. image beautification method according to claim 1, it is characterised in that after the texture of the acquisition image, also
Including：
Recognize the face position in the texture.
3. image beautification method according to claim 2, it is characterised in that the portion of face in the identification texture
Position, specially：
According to threshold value skin color model criterion, the face position in the texture is recognized by Face Detection.
4. image beautification method according to claim 3, it is characterised in that the threshold value skin color model criterion is to be based on
The color mode of RGB；
The criterion of identification is specially：R>95 and G>40 and B>20 and R>G and R>B and Max (R, G, B)-Min (R, G, B)>15 and
Abs(R-G)>15；
Wherein, R is red index value, and G is green index value, and B is blue index value, and to take max function, Min is to take to Max
Minimum value function, Abs is the function that takes absolute value.
5. image beautification method according to claim 2, it is characterised in that it is described by bilateral filtering method to the texture
Fringe region made a distinction with flat site, specially：
The fringe region at the face position is made a distinction with flat site by bilateral filtering method.
6. the image beautification method according to claim any one of 1-5, it is characterised in that the algorithm of the bilateral filtering method
Specially：
WhereinIt is the effect formula of image normalization；
σsIt is the standard deviation of spatial domain Gaussian function；
σrIt is the standard deviation of codomain Gaussian function；
Ω is the domain of definition of convolution, and the convolution is to characterize function by upset and the lap area of translation；
X, y are stochastic variable；
W is weight coefficient.
7. the image beautification method according to claim any one of 1-5, it is characterised in that described to enter to the flat site
The treatment of row Gaussian Blur, specially：
In the flat site, the pixel colour of the texture is adjusted according to Gaussian curve.
8. the image beautification method according to claim any one of 1-5, it is characterised in that also include：
Precision to the coloring programming language of the Gaussian Blur result is optimized, and obtains image beautification result.
9. the image beautification method according to claim any one of 1-5, it is characterised in that described image includes dynamic image
With still image.
10. a kind of image beautifies terminal device, it is characterised in that including：Texture acquirement module, bilateral filtering module；
The texture acquirement module is used to obtain the texture of image；
The bilateral filtering module is used to make a distinction the fringe region of the texture with flat site by bilateral filtering method；
The bilateral filtering module is additionally operable to the edge retention performance according to the bilateral filtering method, retains the fringe region
Pixel color value information；
The bilateral filtering module is additionally operable to carry out Gaussian Blur treatment to the flat site, obtains Gaussian Blur treatment knot
Really.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710139599.0A CN106846281A (en) | 2017-03-09 | 2017-03-09 | image beautification method and terminal device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710139599.0A CN106846281A (en) | 2017-03-09 | 2017-03-09 | image beautification method and terminal device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106846281A true CN106846281A (en) | 2017-06-13 |
Family
ID=59144208
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710139599.0A Pending CN106846281A (en) | 2017-03-09 | 2017-03-09 | image beautification method and terminal device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106846281A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107610042A (en) * | 2017-08-23 | 2018-01-19 | 维沃移动通信有限公司 | A kind of image beautification method and mobile terminal |
| CN108121957A (en) * | 2017-12-19 | 2018-06-05 | 北京麒麟合盛网络技术有限公司 | The method for pushing and device of U.S. face material |
| CN108769520A (en) * | 2018-05-31 | 2018-11-06 | 康键信息技术（深圳）有限公司 | Electronic device, image processing method and computer readable storage medium |
| CN109377450A (en) * | 2018-08-24 | 2019-02-22 | 南京理工大学 | A kind of edge-protected denoising method |
| CN111863232A (en) * | 2020-08-06 | 2020-10-30 | 罗春华 | Remote disease intelligent diagnosis system based on block chain and medical image |
| CN112150393A (en) * | 2020-10-12 | 2020-12-29 | 深圳数联天下智能科技有限公司 | Face image buffing method and device, computer equipment and storage medium |
| CN112258411A (en) * | 2020-10-22 | 2021-01-22 | 浙江大学 | Shader automatic filtering method, device and system based on function approximation of definition domain and value domain |
| CN113763285A (en) * | 2021-09-27 | 2021-12-07 | 北京市商汤科技开发有限公司 | Image processing method and device, electronic equipment and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101404082A (en) * | 2008-11-14 | 2009-04-08 | 深圳市迅雷网络技术有限公司 | Portrait buffing method and apparatus |
| CN104992421A (en) * | 2015-07-09 | 2015-10-21 | 西安电子科技大学 | OpenCL-based parallel optimization method of image de-noising algorithm |
| CN105279746A (en) * | 2014-05-30 | 2016-01-27 | 西安电子科技大学 | Multi-exposure image integration method based on bilateral filtering |
| CN105787888A (en) * | 2014-12-23 | 2016-07-20 | 联芯科技有限公司 | Human face image beautifying method |
| CN106339993A (en) * | 2016-08-26 | 2017-01-18 | 北京金山猎豹科技有限公司 | Human face image polishing method and device and terminal device |
-
2017
- 2017-03-09 CN CN201710139599.0A patent/CN106846281A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101404082A (en) * | 2008-11-14 | 2009-04-08 | 深圳市迅雷网络技术有限公司 | Portrait buffing method and apparatus |
| CN105279746A (en) * | 2014-05-30 | 2016-01-27 | 西安电子科技大学 | Multi-exposure image integration method based on bilateral filtering |
| CN105787888A (en) * | 2014-12-23 | 2016-07-20 | 联芯科技有限公司 | Human face image beautifying method |
| CN104992421A (en) * | 2015-07-09 | 2015-10-21 | 西安电子科技大学 | OpenCL-based parallel optimization method of image de-noising algorithm |
| CN106339993A (en) * | 2016-08-26 | 2017-01-18 | 北京金山猎豹科技有限公司 | Human face image polishing method and device and terminal device |
Non-Patent Citations (2)
| Title |
|---|
| 博客园: "O(l)复杂度之双边滤波算法的原理、流程、实现及效果", 《博客园 HTTPS://WWW.CNBLOGS.COM/IMAGESHOP/P/3406823.HTML》 * |
| 周芹芹等: "脸部美化的自适应算法研究", 《江汉大学学报（自然科学版）》 * |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107610042A (en) * | 2017-08-23 | 2018-01-19 | 维沃移动通信有限公司 | A kind of image beautification method and mobile terminal |
| CN108121957A (en) * | 2017-12-19 | 2018-06-05 | 北京麒麟合盛网络技术有限公司 | The method for pushing and device of U.S. face material |
| CN108121957B (en) * | 2017-12-19 | 2021-09-03 | 麒麟合盛网络技术股份有限公司 | Method and device for pushing beauty material |
| CN108769520B (en) * | 2018-05-31 | 2021-04-13 | 康键信息技术（深圳）有限公司 | Electronic device, image processing method, and computer-readable storage medium |
| CN108769520A (en) * | 2018-05-31 | 2018-11-06 | 康键信息技术（深圳）有限公司 | Electronic device, image processing method and computer readable storage medium |
| CN109377450A (en) * | 2018-08-24 | 2019-02-22 | 南京理工大学 | A kind of edge-protected denoising method |
| CN109377450B (en) * | 2018-08-24 | 2021-12-10 | 南京理工大学 | Edge protection denoising method |
| CN111863232B (en) * | 2020-08-06 | 2021-02-19 | 深圳市柯尼达巨茂医疗设备有限公司 | Remote disease intelligent diagnosis system based on block chain and medical image |
| CN111863232A (en) * | 2020-08-06 | 2020-10-30 | 罗春华 | Remote disease intelligent diagnosis system based on block chain and medical image |
| CN112150393A (en) * | 2020-10-12 | 2020-12-29 | 深圳数联天下智能科技有限公司 | Face image buffing method and device, computer equipment and storage medium |
| CN112258411A (en) * | 2020-10-22 | 2021-01-22 | 浙江大学 | Shader automatic filtering method, device and system based on function approximation of definition domain and value domain |
| CN113763285A (en) * | 2021-09-27 | 2021-12-07 | 北京市商汤科技开发有限公司 | Image processing method and device, electronic equipment and storage medium |
| CN113763285B (en) * | 2021-09-27 | 2024-06-11 | 北京市商汤科技开发有限公司 | Image processing method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106846281A (en) | image beautification method and terminal device | |
| US10922860B2 (en) | Line drawing generation | |
| CN108205804B (en) | Image processing method and device and electronic equipment | |
| CN106920211A (en) | U.S. face processing method, device and terminal device | |
| CN108701217A (en) | A kind of face complexion recognition methods, device and intelligent terminal | |
| US8896622B2 (en) | Methods and apparatus for marker-based stylistic rendering | |
| CN104067311A (en) | Digital makeup | |
| CN108229279A (en) | Face image processing process, device and electronic equipment | |
| CN104346136A (en) | Method and device for picture processing | |
| CN104517265A (en) | Intelligent buffing method and intelligent buffing device | |
| Chen et al. | Face illumination manipulation using a single reference image by adaptive layer decomposition | |
| CN107369133A (en) | A kind of facial image beautification method and device | |
| CN108648163A (en) | A kind of Enhancement Method and computing device of facial image | |
| CN110838084A (en) | Image style transfer method and device, electronic equipment and storage medium | |
| CN110992247A (en) | Method and system for realizing special effect of straightening hair of portrait photo | |
| Yang et al. | Training with augmented data: Gan-based flame-burning image synthesis for fire segmentation in warehouse | |
| CN108921798A (en) | The method, apparatus and electronic equipment of image procossing | |
| Gai et al. | Artistic low poly rendering for images | |
| CN114581979A (en) | Image processing method and device | |
| CN112215776B (en) | Portrait peeling method, electronic device and computer-readable storage medium | |
| Pu et al. | Fractional-order retinex for adaptive contrast enhancement of under-exposed traffic images | |
| CN110895789B (en) | Face beautifying method and device | |
| CN110298807A (en) | Based on the domain the NSCT infrared image enhancing method for improving Retinex and quantum flora algorithm | |
| DiPaola | Painterly rendered portraits from photographs using a knowledge-based approach | |
| CN113379623B (en) | Image processing method, device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170613 |