CN105608722B - It is a kind of that pouch method and system are gone based on face key point automatically - Google Patents
It is a kind of that pouch method and system are gone based on face key point automatically Download PDFInfo
- Publication number
- CN105608722B CN105608722B CN201510945570.2A CN201510945570A CN105608722B CN 105608722 B CN105608722 B CN 105608722B CN 201510945570 A CN201510945570 A CN 201510945570A CN 105608722 B CN105608722 B CN 105608722B
- Authority
- CN
- China
- Prior art keywords
- pouch
- channel
- image
- area image
- new
- 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.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T11/00—2D [Two Dimensional] image generation
- G06T11/40—Filling a planar surface by adding surface attributes, e.g. colour or texture
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The invention belongs to image processing field, discloses a kind of automatic based on face key point and go pouch method and system, including step：Obtain input picture；Extract the masking-out figure and pouch area image in the pouch region of the input picture；The pouch area image is transformed into LAB color spaces, and isolates Color Channel L, channel A and channel B；Brightness adjustment curve is calculated by the channel L；Channel L is mapped by the brightness adjustment curve, obtains new tunnel L；New tunnel L, channel A and channel B are converted into rgb color space image；Gaussian Blur is carried out to the masking-out figure in the pouch region and obtains new masking-out figure；The pouch area image, rgb color space image and new masking-out figure are synthesized, new pouch area image is obtained；New pouch area image replaces pouch area image, obtains final image.The present invention allows users to the removal of one-key operation pouch, and the method simple and stable, treated, and image effect is natural.
Description
Technical field
The invention belongs to technical field of image processing, and pouch side is gone to automatically based on face key point more particularly to a kind of
Method and system.
Background technology
In recent years, with the development of science and technology the mobile devices such as smart mobile phone, tablet have become the essential number of people
Word converter tools.Along with the rise of smart machine, the demand of U.S. face self-timer also constantly increases, wherein going pouch function by wide
Big female user is pursued.
Currently used method is to need to remove area using finger click screen is specified by the way of clicking screen manually
Domain simultaneously carries out highlighting operation.This mode is in use often because maloperation needs to re-start pouch removal behaviour
Make so that go the process of pouch sufficiently complex, and pouch region can not be accurately positioned, there are the influences of isolated noise, to original
The color of figure can cause damages, and the image after beautification is made to seem very unnatural.
Invention content
To solve the above-mentioned problems, the present invention proposes that a kind of automatic based on face key point goes pouch method and system,
To realize that user is capable of the removal of one-key operation pouch, the method simple and stable, and treated image effect is natural.
In order to achieve the above objectives, the technical solution adopted by the present invention is：It is a kind of that pouch is gone based on face key point automatically
Method, the method includes the steps：
(1) input picture is obtained, 3 channel RGB images can be used in the input picture.
(2) the masking-out figure and pouch area image in the pouch region of the input picture are extracted.
(3) the pouch area image is transformed into LAB color spaces, and isolates Color Channel L, channel A and channel
B。
(4) brightness adjustment curve is calculated by the channel L.
(5) channel L is mapped by the brightness adjustment curve, obtains new tunnel L.
(6) new tunnel L, channel A and channel B are converted into rgb color space image.
(7) Gaussian Blur is carried out to the masking-out figure in the pouch region and obtains new masking-out figure.
(8) the pouch area image, rgb color space image and new masking-out figure are synthesized, new pouch area image is obtained.
(9) new pouch area image replaces pouch area image, obtains final image.
Further, the step (2) includes step：
(2.1) face critical point detection is carried out to the input picture, obtains face key point information.
(2.2) key point information of existing standard faces figure and the face key point information are mapped, is obtained
Mapping matrix.
(2.3) by mapping matrix, the external quadrilateral area of pouch in standard faces figure is mapped in input picture,
Obtain the mask figure in the pouch region in input picture.
(2.4) data in input picture in mask figure corresponding region are extracted, as pouch area image.
Further, the face key point information includes informer midpoint, a left side under the left eye exterior angle of left face part, left eye
Informer midpoint, right eye interior angle and right nasal fossa under angulus oculi medialis, left nose ditch and right eye exterior angle, right eye.
Further, the standard faces figure uses single channel standard faces figure, the single channel standard faces figure eye
Bag region is by calibration in advance, and it is 255 to be initialized as white and pixel value, and other regions are that black pixel value is 0.
Further, the step (4) includes step：
(4.1) statistics with histogram is carried out to the channel L, obtains statistical data.
(4.2) four groups of mappings pair are calculated according to the statistical data.
(4.3) according to four groups of mappings pair, brightness adjustment curve is obtained.
Further, the statistical data includes bright pixel value A ' and dark pixel values B '；Four groups of mappings are to respectively
For (L0,H0),(L1,H1),(L2,H2),(L3,H3), wherein L3=H3=255, L2=H2=A ', L1=B ', H1=A ' -0.4142
× (A '-B '), L0=0, H0=H1–B′×(A′-H1)/(A′-B′)。
Further, the step (4.3), including step：
(4.3.1) calculating matrix H：
Wherein hi=Hi+1-Li, i=0,1,2；
(4.3.2) calculating matrix M=[m1,m2]T；
(4.3.3) calculating matrix Y：
Y=6 × [(H2-H1)/h1-(H1–H0)/h0,(H3–H2)/h2-(H2–H1)/h1]T；
(4.3.4) solves equation H × M=Y, and enables m0=m3=0, obtain m1,m2Value；
(4.3.5) calculates the cubic polynomial coefficient a of each segment matched curvei,bi,ci,di；
Wherein, ai=Hi；
bi=(Hi+1-Hi)/hi-hi×mi/2-hi×(mi+1-mi)/6；
ci=mi/2；
di=(mi+1-mi)/(6hi)；
(4.3.6) is according to cubic polynomial coefficient ai,bi,ci,di, respectively in section [Li,Li+1] on calculate y values, it is specific public
Formula is：
Y=ai+bi×(x-xi)+ci×(x-xi)2+di×(x-xi)3, i=0,1,2；
(4.3.7) is brightness adjustment curve by the mapping of x to y.
Further, in the step (7), the Gaussian Blur carries out convolution with Gaussian template to image, described
Convolution is optimized using IIR filterings.
Further, in the step (8), new pouch area image is synthesized using composite formula.
On the other hand, the present invention also provides a kind of going pouch system automatically based on face key point, including：
Image input module：For obtaining input picture.
Extraction module：The masking-out figure and pouch area image in the pouch region for calculating and extracting the input picture.
LAB color space conversion modules：The pouch area image is transformed into LAB color spaces, and isolates color
Channel L, channel A and channel B.
Brightness adjusting section：Brightness adjustment curve is calculated and obtained, and channel L is reflected by the brightness adjustment curve
It penetrates, obtains new tunnel L.
Rgb color space conversion module：New tunnel L, channel A and channel B are converted into rgb color space image.
Gaussian Blur module：Gaussian Blur is carried out to the masking-out figure in the pouch region and obtains new masking-out figure.
Synthesis module：The pouch area image, rgb color space image and new masking-out figure are synthesized, new pouch area is obtained
Area image.
Image output module, new pouch area image replace pouch area image, obtain final image.
Using the advantageous effect of the technical program：
A kind of automatic based on face key point proposed by the invention goes pouch method, by key point, takes and a little reflects
The pouch region that the mode penetrated obtains is accurate；By generating brightness curve, make the image after brightness adjustment more naturally, and can
Reduce the influence of isolated noise；By being adjusted in LAB color spaces, the color loss of artwork is reduced；It is proposed by the invention
It is a kind of that pouch system is gone based on face key point automatically, method proposed by the invention can be coordinated to realize answering for this method
With.
Description of the drawings
Fig. 1 is a kind of automatic flow chart for going pouch method based on face key point of the present invention；
Fig. 2 is the method stream of the masking-out figure and pouch area image in the pouch region that the input picture is extracted in the present invention
Cheng Tu；
Fig. 3 is the method flow diagram that brightness adjustment curve is calculated in the present invention；
Fig. 4 is the method flow diagram according to mapping to calculating brightness adjustment curve in the present invention；
Fig. 5 is a kind of automatic structural schematic diagram for going pouch system based on face key point of the present invention.
Specific implementation mode
To make the objectives, technical solutions, and advantages of the present invention clearer, the present invention is made into one below in conjunction with the accompanying drawings
Step illustrates.
In the present embodiment, shown in Figure 1, it is a kind of that pouch method, the method are gone based on face key point automatically
Including step：
(1) input picture is obtained, 3 channel RGB images can be used in the input picture.
(2) the masking-out figure and pouch area image in the pouch region of the input picture are extracted.
As shown in Fig. 2, the step (2) includes step：
(2.1) face critical point detection is carried out to the input picture, obtains face key point information.
The face key point information includes informer midpoint, left eye interior angle, left nose under the left eye exterior angle of left face part, left eye
Informer midpoint, right eye interior angle and right nasal fossa under ditch and right eye exterior angle, right eye.
(2.2) key point information of existing standard faces figure and the face key point information are mapped, is obtained
Mapping matrix.
(2.3) by mapping matrix, the external quadrilateral area of pouch in standard faces figure is mapped in input picture,
Obtain the mask figure in the pouch region in input picture.
The standard faces figure uses single channel standard faces figure, single channel standard faces figure pouch region to pass through thing
It first demarcates, it is 255 to be initialized as white and pixel value, and other regions are that black pixel value is 0.
(2.4) data in input picture in mask figure corresponding region are extracted, as pouch area image.
(3) the pouch area image is transformed into LAB color spaces, and isolates Color Channel L, channel A and channel
B。
The specific method is as follows for conversion：
L=0.2126 × r+0.7152 × g+0.0722 × b.
A=1.4749 × (0.2213 × r-0.3390 × g+0.1177 × b)+0.5 × 255.
B=0.6245 × (0.1949 × r+0.6057 × g-0.8006 × b)+0.5 × 255.
Wherein, r, g, b are pixel value in pouch area image, and L, A, B is respectively the picture in channel L, channel A and channel B
Element value.
(4) brightness adjustment curve is calculated by the channel L, as shown in figure 3, including step：
(4.1) statistics with histogram is carried out to the channel L, obtains statistical data.
The statistical data includes bright pixel value A ' and dark pixel values B '；Wherein A ' is preceding 30% most bright part in the L of channel
The mean value of pixel, B ' are the mean value of preceding 30% most dark-part pixel in the L of channel.
(4.2) four groups of mappings pair are calculated according to the statistical data.
Four groups of mappings are to being respectively (L0,H0),(L1,H1),(L2,H2),(L3,H3), wherein L3=H3=255, L2=
H2=A ', L1=B ', H1=A ' -0.4142 × (A '-B '), L0=0, H0=H1–B′×(A′-H1)/(A′-B′)。
(4.3) according to four groups of mappings pair, brightness adjustment curve is obtained.
As shown in figure 4, including step：
(4.3.1) calculating matrix H：
Wherein hi=Hi+1-Li, i=0,1,2；
(4.3.2) calculating matrix M=[m1,m2]T；
(4.3.3) calculating matrix Y：
Y=6 × [(H2-H1)/h1-(H1–H0)/h0,(H3–H2)/h2-(H2–H1)/h1]T；
(4.3.4) solves equation H × M=Y, and enables m0=m3=0, obtain m1,m2Value；
(4.3.5) calculates the cubic polynomial coefficient a of each segment matched curvei,bi,ci,di；
Wherein, ai=Hi；
bi=(Hi+1-Hi)/hi-hi×mi/2-hi×(mi+1-mi)/6；
ci=mi/2；
di=(mi+1-mi)/(6hi)；
(4.3.6) is according to cubic polynomial coefficient ai,bi,ci,di, respectively in section [Li,Li+1] on calculate y values, it is specific public
Formula is：
Y=ai+bi×(x-xi)+ci×(x-xi)2+di×(x-xi)3, i=0,1,2；
(4.3.7) is brightness adjustment curve by the mapping of x to y.
(5) channel L is mapped by the brightness adjustment curve, obtains new tunnel L.
The brightness adjustment curve mapping process is that the value on abscissa is mapped to ordinate, is y=f with function representation
(x), x, y ∈ [0,255]；
That is Channel_L_new (i)=f (Channel_L (i)), Channel_L_new (i) and Channel_L (i) divide
Pixel value that Biao Shi be in new tunnel L and channel L.
(6) new tunnel L, channel A and channel B are converted into rgb color space image.
Conversion method is as follows：
R=L+ ((A-0.5 × 255) × 0.682353 × 3.07989502+ (B-0.5 × 255) × 0.607843 ×
0.542907715)。
G=L- ((A-0.5 × 255) × 0.682353 × 0.92089844+ (B-0.5 × 255) × 0.607843 ×
0.045196535)。
B=L+ ((A-0.5 × 255) × 0.682353 × 0.05310059- (B-0.5 × 255) × 0.607843 ×
1.151092529)。
Wherein L, A, B are respectively the value of image new tunnel L, channel A and the pixel in the B of channel, and r, g, b are that rgb color is empty
Between pixel in image value.
(7) Gaussian Blur is carried out to the masking-out figure in the pouch region and obtains new masking-out figure.
The Gaussian Blur carries out convolution with Gaussian template to image, and the convolution is carried out excellent using IIR filterings
Change.
Gaussian template can be described with following formula：
Convolution process is ∑ w (x, the y) * of R_mask_new (i, j)=1/ ∑s (w (x, y) * R_mask (i+x, j+y))；x,y
∈ [- 3 σ, 3 σ], namely ∑ summation range.
Wherein, R_mask_new (i, j) is the pixel value of i rows j row in new masking-out figure, and R_mask (i+x, j+y) is pouch
The pixel value that i+x rows j+y is arranged in the masking-out figure in region, σ take 10, and in order to accelerate arithmetic speed, convolution process was filtered using IIR
Journey optimizes
(8) the pouch area image, rgb color space image and new masking-out figure are synthesized, new pouch area image is obtained.
New pouch area image is synthesized using composite formula.
Composite formula is：(a×alpha+b×(255–alpha))/255.
Wherein, a is the pixel in the rgb color space image, and b is the pixel in the pouch area image, alpha
For the pixel in new masking-out figure.
(9) new pouch area image replaces pouch area image, obtains final image.
It is shown in Figure 5 based on identical inventive concept to coordinate the realization of the method for the present invention, the present invention also provides
It is a kind of that pouch system is gone based on face key point automatically, including：
Image input module：For obtaining input picture.
Extraction module：The masking-out figure and pouch area image in the pouch region for calculating and extracting the input picture.
LAB color space conversion modules：The pouch area image is transformed into LAB color spaces, and isolates color
Channel L, channel A and channel B.
Brightness adjusting section：Brightness adjustment curve is calculated and obtained, and channel L is reflected by the brightness adjustment curve
It penetrates, obtains new tunnel L.
Rgb color space conversion module：New tunnel L, channel A and channel B are converted into rgb color space image.
Gaussian Blur module：Gaussian Blur is carried out to the masking-out figure in the pouch region and obtains new masking-out figure.
Synthesis module：The pouch area image, rgb color space image and new masking-out figure are synthesized, new pouch area is obtained
Area image.
Image output module, new pouch area image replace pouch area image, obtain final image.
The above shows and describes the basic principles and main features of the present invention and the advantages of the present invention.The technology of the industry
Personnel are it should be appreciated that the present invention is not limited to the above embodiments, and the above embodiments and description only describe this
The principle of invention, without departing from the spirit and scope of the present invention, various changes and improvements may be made to the invention, these changes
Change and improvement all fall within the protetion scope of the claimed invention.The invention of this reality be claimed range by appended claims and
Its equivalent thereof.
Claims (7)
1. a kind of going pouch method automatically based on face key point, which is characterized in that the method includes the steps：
(1) input picture is obtained；
(2) the masking-out figure and pouch area image in the pouch region of the input picture are extracted；
(3) the pouch area image is transformed into LAB color spaces, and isolates Color Channel L, channel A and channel B；
(4) brightness adjustment curve, including step are calculated by the channel L：
(4.1) to the channel L carry out statistics with histogram, obtain statistical data, the statistical data include bright pixel value A ' and
Dark pixel values B '；
(4.2) four groups of mappings pair are calculated according to the statistical data, four groups of mappings are to being respectively (L0,H0),(L1,H1),
(L2,H2),(L3,H3), wherein L3=H3=255, L2=H2=A ', L1=B ', H1=A ' -0.4142 × (A '-B '), L0=0,
H0=H1–B′×(A′-H1)/(A′-B′)；
(4.3) according to four groups of mappings pair, brightness adjustment curve, including step are obtained：
Calculating matrix H：
Wherein hi=Hi+1-Li, i=0,1,2；
Calculating matrix M=[m1,m2]T；
Calculating matrix Y：
Y=6 × [(H2-H1)/h1-(H1–H0)/h0,(H3–H2)/h2-(H2–H1)/h1]T；
Equation H × M=Y is solved, and enables m0=m3=0, obtain m1,m2Value；
Calculate the cubic polynomial coefficient a of each segment matched curvei,bi,ci,di；
Wherein, ai=Hi；
bi=(Hi+1-Hi)/hi-hi×mi/2-hi×(mi+1-mi)/6；
ci=mi/2；
di=(mi+1-mi)/(6hi)；
According to cubic polynomial coefficient ai,bi,ci,di, respectively in section [Li,Li+1] on calculate y values, specific formula is：
Y=ai+bi×(x-xi)+ci×(x-xi)2+di×(x-xi)3, i=0,1,2；
It is brightness adjustment curve by the mapping of x to y；
(5) channel L is mapped by the brightness adjustment curve, obtains new tunnel L；
(6) new tunnel L, channel A and channel B are converted into rgb color space image；
(7) Gaussian Blur is carried out to the masking-out figure in the pouch region and obtains new masking-out figure；
(8) the pouch area image, rgb color space image and new masking-out figure are synthesized, new pouch area image is obtained；
(9) new pouch area image replaces pouch area image, obtains final image.
2. a kind of automatic based on face key point according to claim 1 goes pouch method, described its feature of step (2)
It is, including step：
Face critical point detection is carried out to the input picture, obtains face key point information；
The key point information of existing standard faces figure and the face key point information are mapped, mapping matrix is obtained；
By mapping matrix, the external quadrilateral area of pouch in standard faces figure is mapped in input picture, is inputted
The mask figure in the pouch region in image；
The data in mask figure corresponding region in input picture are extracted, as pouch area image.
3. a kind of automatic based on face key point according to claim 2 goes pouch method, which is characterized in that the people
Face key point information includes under the left eye exterior angle of left face part, left eye outside informer midpoint, left eye interior angle, left nose ditch and right eye
Informer midpoint, right eye interior angle and right nasal fossa under angle, right eye.
4. a kind of automatic based on face key point according to claim 3 goes pouch method, which is characterized in that the mark
Quasi- face figure uses single channel standard faces figure, and single channel standard faces figure pouch region is by calibration in advance, initialization
It is 255 for white and pixel value, other regions are that black pixel value is 0.
5. a kind of automatic based on face key point according to claim 1 goes pouch method, described its feature of step (7)
It is, the Gaussian Blur carries out convolution with Gaussian template to image, and the convolution is optimized using IIR filterings.
6. a kind of automatic based on face key point according to claim 1 goes pouch method, described its feature of step (8)
It is, new pouch area image is synthesized using composite formula.
7. based on automatic based on face key point described in claim 1 go pouch method it is a kind of based on face key point from
It is dynamic to go pouch system, which is characterized in that including,
Image input module：For obtaining input picture；
Extraction module：The masking-out figure and pouch area image in the pouch region for calculating and extracting the input picture；
LAB color space conversion modules：The pouch area image is transformed into LAB color spaces, and isolates Color Channel
L, channel A and channel B；
Brightness adjusting section：Brightness adjustment curve is calculated and is obtained, and channel L is mapped by the brightness adjustment curve,
Obtain new tunnel L；
Rgb color space conversion module：New tunnel L, channel A and channel B are converted into rgb color space image；
Gaussian Blur module：Gaussian Blur is carried out to the masking-out figure in the pouch region and obtains new masking-out figure；
Synthesis module：The pouch area image, rgb color space image and new masking-out figure are synthesized, new pouch administrative division map is obtained
Picture；
Image output module, new pouch area image replace pouch area image, obtain final image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510945570.2A CN105608722B (en) | 2015-12-17 | 2015-12-17 | It is a kind of that pouch method and system are gone based on face key point automatically |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510945570.2A CN105608722B (en) | 2015-12-17 | 2015-12-17 | It is a kind of that pouch method and system are gone based on face key point automatically |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105608722A CN105608722A (en) | 2016-05-25 |
| CN105608722B true CN105608722B (en) | 2018-08-31 |
Family
ID=55988637
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510945570.2A Active CN105608722B (en) | 2015-12-17 | 2015-12-17 | It is a kind of that pouch method and system are gone based on face key point automatically |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105608722B (en) |
Families Citing this family (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107424115B (en) * | 2017-05-31 | 2020-10-27 | 成都品果科技有限公司 | Skin color correction algorithm based on face key points |
| CN107657596A (en) * | 2017-09-26 | 2018-02-02 | 成都国翼电子技术有限公司 | A kind of Aerial Images color adjustment method based on man-machine interactively |
| CN107644407A (en) * | 2017-09-26 | 2018-01-30 | 成都国翼电子技术有限公司 | A kind of thin cloud minimizing technology of Aerial Images based on man-machine interactively |
| CN107680055A (en) * | 2017-09-26 | 2018-02-09 | 成都国翼电子技术有限公司 | A kind of Aerial Images haze minimizing technology based on man-machine interactively |
| CN107633492A (en) * | 2017-09-26 | 2018-01-26 | 成都国翼电子技术有限公司 | A kind of shadow of object fast positioning and the method removed |
| CN107578393B (en) * | 2017-09-26 | 2021-12-10 | 成都国翼电子技术有限公司 | Aerial image brightness adjusting method based on manual interaction |
| JP2019070870A (en) * | 2017-10-05 | 2019-05-09 | カシオ計算機株式会社 | Image processing device, image processing method and program |
| CN107862673B (en) * | 2017-10-31 | 2021-08-24 | 北京小米移动软件有限公司 | Image processing method and device |
| CN108898546B (en) * | 2018-06-15 | 2022-08-16 | 北京小米移动软件有限公司 | Face image processing method, device and equipment and readable storage medium |
| CN109919030B (en) * | 2019-01-31 | 2021-07-13 | 深圳和而泰数据资源与云技术有限公司 | Black eye type identification method and device, computer equipment and storage medium |
| CN110288512B (en) * | 2019-05-16 | 2023-04-18 | 成都品果科技有限公司 | Illumination remapping method, device, storage medium and processor for image synthesis |
| CN110363717B (en) * | 2019-06-28 | 2021-07-23 | 北京字节跳动网络技术有限公司 | Method, device, medium and electronic equipment for processing face image |
| CN111784604B (en) * | 2020-06-29 | 2022-02-18 | 北京字节跳动网络技术有限公司 | Image processing method, device, equipment and computer readable storage medium |
| CN111882627B (en) * | 2020-07-20 | 2024-08-20 | 广州市百果园信息技术有限公司 | Image processing method, video processing method, apparatus, device and storage medium |
| CN113298698B (en) * | 2021-04-30 | 2024-02-02 | 成都东方盛行电子有限责任公司 | Pouch removing method for face key points in non-woven engineering |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103914699A (en) * | 2014-04-17 | 2014-07-09 | 厦门美图网科技有限公司 | Automatic lip gloss image enhancement method based on color space |
| CN104537630A (en) * | 2015-01-22 | 2015-04-22 | 厦门美图之家科技有限公司 | Method and device for image beautifying based on age estimation |
| CN104574285A (en) * | 2013-10-23 | 2015-04-29 | 厦门美图网科技有限公司 | Method for automatically removing image black eyes |
| CN105096243A (en) * | 2015-09-10 | 2015-11-25 | 成都品果科技有限公司 | Method and system for achieving makeup effect by LM algorithm |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TWI520101B (en) * | 2014-04-16 | 2016-02-01 | 鈺創科技股份有限公司 | Method for making up skin tone of a human body in an image, device for making up skin tone of a human body in an image, method for adjusting skin tone luminance of a human body in an image, and device for adjusting skin tone luminance of a human body in |
-
2015
- 2015-12-17 CN CN201510945570.2A patent/CN105608722B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104574285A (en) * | 2013-10-23 | 2015-04-29 | 厦门美图网科技有限公司 | Method for automatically removing image black eyes |
| CN103914699A (en) * | 2014-04-17 | 2014-07-09 | 厦门美图网科技有限公司 | Automatic lip gloss image enhancement method based on color space |
| CN104537630A (en) * | 2015-01-22 | 2015-04-22 | 厦门美图之家科技有限公司 | Method and device for image beautifying based on age estimation |
| CN105096243A (en) * | 2015-09-10 | 2015-11-25 | 成都品果科技有限公司 | Method and system for achieving makeup effect by LM algorithm |
Non-Patent Citations (3)
| Title |
|---|
| 人脸图像中斑点自动去除系统的设计与实现;戴勇 等;《宁波工程学院学报》;20140331;第26卷(第1期);第47-50页 * |
| 基于个性化原型的人脸衰老图像合成;王章野 等;《电子学报》;20090430(第4A期);第118-124页 * |
| 基于照片的可编辑光照效果卡通人脸生成算法;宋阳 等;《图学学报》;20150228;第36卷(第1期);第2.4-2.5节 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105608722A (en) | 2016-05-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105608722B (en) | It is a kind of that pouch method and system are gone based on face key point automatically | |
| CN104200470B (en) | Blue screen image-matting method | |
| CN104952036B (en) | Method for beautifying faces and electronic equipment in a kind of instant video | |
| CN112287940A (en) | Semantic segmentation method of attention mechanism based on deep learning | |
| CN103020917B (en) | Method for restoring ancient Chinese calligraphy and painting images on basis of conspicuousness detection | |
| CN111402258A (en) | Image processing method, image processing device, storage medium and electronic equipment | |
| CN104574404B (en) | A kind of stereo-picture method for relocating | |
| CN108765358A (en) | The double light fusion methods and plug-in type thermal imager system of visible light and infrared light | |
| CN109359618A (en) | A kind of image processing method and its device, equipment and storage medium | |
| CN108564528A (en) | A kind of portrait photo automatic background weakening method based on conspicuousness detection | |
| CN107424133A (en) | Image defogging method, device, computer can storage medium and mobile terminals | |
| CN107622480A (en) | A kind of Kinect depth image Enhancement Method | |
| CN107204034A (en) | A kind of image processing method and terminal | |
| CN108961299B (en) | Foreground image obtaining method and device | |
| WO2023284401A1 (en) | Image beautification processing method and apparatus, storage medium, and electronic device | |
| Fang et al. | Single image dehazing and denoising with variational method | |
| CN104240259B (en) | High photographing instrument voucher intelligence cutting edge correction system and method based on contours segmentation | |
| WO2023056950A1 (en) | Image processing method and electronic device | |
| CN108596992B (en) | Rapid real-time lip gloss makeup method | |
| CN112686820A (en) | Virtual makeup method and device and electronic equipment | |
| CN108711160A (en) | A kind of Target Segmentation method based on HSI enhancement models | |
| CN104239883B (en) | Texture characteristic extracting method and device | |
| CN105787910A (en) | Method for optimizing calculation based on heterogeneous platform for human face area filtering method | |
| CN103455974B (en) | Image sketching style processing method | |
| CN109583341B (en) | Method and device for detecting multi-person skeleton key points of image containing portrait |
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 | ||
| CP02 | Change in the address of a patent holder |
Address after: 610041 the 13 floor of No. 1 middle Tianfu Avenue, No. 1268, high-tech zone, Chengdu, Sichuan. Patentee after: Chengdu PinGuo Digital Entertainment Ltd. Address before: 3, 13 floor, E zone, Tianfu Software Park, Chengdu hi tech Zone, Sichuan, 610000 Patentee before: Chengdu PinGuo Digital Entertainment Ltd. |
|
| CP02 | Change in the address of a patent holder | ||
| CB03 | Change of inventor or designer information |
Inventor after: Huang Liang Inventor after: Xu Hao Inventor after: Xu Ying Inventor after: Yang Jia Inventor before: Huang Liang |
|
| CB03 | Change of inventor or designer information |