CN107180415A - Skin landscaping treatment method and device in a kind of image - Google Patents
Skin landscaping treatment method and device in a kind of image Download PDFInfo
- Publication number
- CN107180415A CN107180415A CN201710202767.6A CN201710202767A CN107180415A CN 107180415 A CN107180415 A CN 107180415A CN 201710202767 A CN201710202767 A CN 201710202767A CN 107180415 A CN107180415 A CN 107180415A
- Authority
- CN
- China
- Prior art keywords
- skin
- image
- pixel
- colourity
- chromatic value
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 65
- 230000000694 effects Effects 0.000 claims abstract description 39
- 238000004737 colorimetric analysis Methods 0.000 claims abstract description 35
- 230000003796 beauty Effects 0.000 claims description 15
- 239000003086 colorant Substances 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 6
- 230000002087 whitening effect Effects 0.000 abstract description 10
- 241000209140 Triticum Species 0.000 abstract description 4
- 235000021307 Triticum Nutrition 0.000 abstract description 4
- 229910000906 Bronze Inorganic materials 0.000 abstract description 3
- 239000010974 bronze Substances 0.000 abstract description 3
- KUNSUQLRTQLHQQ-UHFFFAOYSA-N copper tin Chemical compound [Cu].[Sn] KUNSUQLRTQLHQQ-UHFFFAOYSA-N 0.000 abstract description 3
- 230000008569 process Effects 0.000 description 8
- 238000006243 chemical reaction Methods 0.000 description 6
- 230000008859 change Effects 0.000 description 5
- 238000009826 distribution Methods 0.000 description 4
- 239000011159 matrix material Substances 0.000 description 4
- 238000005457 optimization Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 238000001914 filtration Methods 0.000 description 2
- 230000004927 fusion Effects 0.000 description 2
- 206010040829 Skin discolouration Diseases 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000037310 combination skin Effects 0.000 description 1
- 239000012141 concentrate Substances 0.000 description 1
- 238000005520 cutting process Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 230000000116 mitigating effect Effects 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 230000000007 visual effect 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
- G06T5/90—Dynamic range modification of images or parts thereof
- G06T5/92—Dynamic range modification of images or parts thereof based on global image properties
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
Abstract
The embodiments of the invention provide skin landscaping treatment method and device in a kind of image, wherein method includes:According to skin colorimetry model, the skin mask of pending image is generated;The pixel that confidence level in skin mask is more than predetermined threshold value is defined as to the skin area of pending image;Adjust brightness and the colourity of the skin area of pending image, the image after generation skin beautification so that the skin area of pending image reach needed for brightness and colourity.Skin landscaping treatment method and device in the image of the embodiment of the present invention, it can make the pending image comprising skin area that there is natural colour of skin whitening effect, and, brightness and the colourity of skin area are adjusted by presetting colour of skin style, it can further generate with the personalized landscaping treatment effect image such as the pale colour of skin, the ruddy colour of skin, the wheat colour of skin, bronze colour of skin, improve Consumer's Experience.
Description
Technical field
The present invention relates to technical field of image processing, skin landscaping treatment method and dress in more particularly to a kind of image
Put.
Background technology
With development in science and technology, intelligent terminal possesses increasing function.User can not only be taken pictures by intelligent terminal,
Can also be by net cast come interactive with other people.In order to be able to obtain the auto heterodyne effect of satisfaction, user is often to photo or video
In face-image carry out landscaping treatment so that photo have effect more attractive in appearance, it is popular for, it is this in image
The process that the human body skin area such as face and neck, arm carries out landscaping treatment is U.S. face.
Existing landscaping treatment method, the brightness by lifting skin area reaches the effect of skin-whitening.But, it is this
U.S. face method, when luminance raising is smaller, skin whitening effects are limited, when luminance raising is excessive, easily produce chromatic distortion
Phenomenon.
To sum up, the existing landscaping treatment method by lifting the brightness of skin area, it is difficult to reach natural colour of skin whitening
Effect.
The content of the invention
The purpose of the embodiment of the present invention is to provide skin landscaping treatment method and device in a kind of image, to realize beautification
Image after processing has the purpose of natural colour of skin whitening effect.Concrete technical scheme is as follows:
A kind of skin landscaping treatment method in image, methods described includes:
According to skin colorimetry model, the skin mask of pending image is generated, the skin colourity model table shows skin-color
Degree and the corresponding relation of confidence level, the skin mask represent each pixel putting for skin area in the pending image
Reliability;
The pixel that confidence level in the skin mask is more than predetermined threshold value is defined as to the skin region of the pending image
Domain;
Adjust brightness and the colourity of the skin area of the pending image, the image after generation skin beautification so that institute
State pending image skin area reach needed for brightness and colourity.
Preferably, it is described according to skin colorimetry model, before the skin mask for generating pending image, skin in described image
Skin landscaping treatment method also includes:
Several skin colourity sample images are obtained, the skin colourity sample image is the image for determining skin area;
The Colour result of skin area, obtains the skin colourity in several described skin colourity sample images of statistics
Model.
Preferably, it is described according to skin colorimetry model, the skin mask of pending image is generated, including:
Obtain the chromatic value of each pixel of the pending image;
The corresponding confidence level of chromatic value of each pixel is searched in the skin colorimetry model, the confidence level is made
For the pixel value of each pixel;
According to the pixel value of each pixel, the skin mask of the pending image is generated.
Preferably, the brightness of the skin area of the adjustment pending image and colourity, after generation skin beautification
Image, including:
The pending image is changed to Lab color spaces;
Each pixel of the skin area of the pending image in Lab color spaces is adjusted by the first preset algorithm
Brightness, obtains in the skin area of the pending image brightness value after the adjustment of each pixel, so that the pending image
The brightness of each pixel meets pre-set skin beautification brightness effects in skin area;
The color of each pixel of the skin area of the pending image in Lab color spaces is adjusted by presetting chromatic value
Degree, obtains in the skin area of the pending image chromatic value after the adjustment of each pixel, so that the skin of the pending image
The colourity of each pixel is migrated to the default chromatic value in skin region, and the default chromatic value is the fair-complexioned colourity of natural beauty
Value;
By brightness value after the adjustment of each pixel in the skin area of the pending image and adjustment after chromatic value change to
The parameter of each pixel of skin area in rgb color space, generation rgb color space;
The skin area in the pending image is handled by the second preset algorithm, obtained after skin beautification
Image, second preset algorithm is:
IB(x, y)=I (x, y) (1-M (x, y))+I ' (x, y) M (x, y), wherein, IB(x, y) is after beautifying through skin
Image pixel parameter, I (x, y) be pending image in skin area pixel parameter, M (x, y) represent
The pixel value of pixel in skin mask, I ' (x, y) represents skin region in the rgb color space after brightness and colourity adjustment
The parameter of the pixel in domain, the parameter of the pixel is made up of brightness and colourity.
Preferably, it is described to adjust the skin area of the pending image in Lab color spaces by presetting chromatic value
Each pixel colourity, obtain in the skin area of the pending image chromatic value after the adjustment of each pixel, including:
The a passage colourity averages and b passage colourity averages of the skin area of the pending image are calculated respectively;
Calculate the first default chromatic value and the difference of a passages colourity average, and will the described first default chromatic value and
The difference of a passages colourity average presets color with a passage chromatic value sums as a passages chromatic value after adjustment, described first
Angle value is to represent with the fair-complexioned a passages chromatic value of natural beauty;
Calculate the second default chromatic value and the difference of the b passages colourity average, and will the described second default chromatic value and
The difference of the b passages colourity average presets color with b passage chromatic value sums as b passages chromatic value after adjustment, described second
Angle value is to represent with the fair-complexioned b passages chromatic value of natural beauty.
Preferably, it is described that the pixel that confidence level in the skin mask is more than predetermined threshold value is defined as the pending figure
After the skin area of picture, skin landscaping treatment method also includes in described image:
Brightness and the colourity of the skin area, the U.S. of generation with different colour of skin styles are adjusted according to different colour of skin styles
Image after change, the different colour of skin styles are purported skin brightness and the combination of colourity, so that the image after the beautification reaches
To default colour of skin style.
A kind of skin landscaping treatment device in image, described device includes:
Generation module, for according to skin colorimetry model, generating the skin mask of pending image, the skin colourity mould
Type represents the corresponding relation of skin colourity and confidence level, and the skin mask represents that each pixel is in the pending image
The confidence level of skin area;
Determining module, it is described pending for confidence level in the skin mask to be defined as more than the pixel of predetermined threshold value
The skin area of image;
First adjusting module, brightness and colourity for the skin area that adjusts the pending image, generation skin is beautiful
Image after change so that the skin area of the pending image reach needed for brightness and colourity.
Preferably, the landscaping treatment device also includes:
Acquisition module, for obtaining several skin colourity sample images, the skin colourity sample image is determination skin
The image in region;
Statistical module, the Colour result for counting skin area in several described skin colourity sample images, is obtained
To the skin colorimetry model.
Preferably, the generation module, is specifically included:
Acquisition submodule, the chromatic value of each pixel for obtaining the pending image;
Search submodule, the corresponding confidence of chromatic value for searching each pixel in the skin colorimetry model
Degree, using the confidence level as each pixel pixel value;
Submodule is generated, for the pixel value according to each pixel, the skin for generating the pending image is covered
Mould.
Preferably, first adjusting module, is specifically included:
First transform subblock, for the pending image to be changed to Lab color spaces;
First adjustment submodule, for adjusting the skin area of the pending image by the first preset algorithm in Lab
The brightness of each pixel in color space, obtains in the skin area of the pending image brightness value after the adjustment of each pixel,
So that the brightness of each pixel meets pre-set skin beautification brightness effects in the skin area of the pending image;
Second adjustment submodule, for adjusting the skin area of the pending image in Lab colors by presetting chromatic value
The colourity of each pixel in color space, obtains in the skin area of the pending image chromatic value after the adjustment of each pixel, with
The colourity of each pixel in the skin area of the pending image is set to be migrated to the default chromatic value, the default chromatic value is
The fair-complexioned chromatic value of natural beauty;
Second transform subblock, for by brightness value after the adjustment of each pixel in the skin area of the pending image and
Chromatic value changes the parameter that each pixel of skin area in rgb color space is generated to rgb color space after adjustment;
Submodule is handled, for being handled by the second preset algorithm the skin area in the pending image,
The image after skin beautification is obtained, second preset algorithm is:
IB(x, y)=I (x, y) (1-M (x, y))+I ' (x, y) M (x, y), wherein, IB(x, y) is after beautifying through skin
Image pixel parameter, I (x, y) be pending image in skin area pixel parameter, M (x, y) represent
The pixel value of pixel in skin mask, I ' (x, y) represents skin in the rgb color space that the second transform subblock is converted to
The parameter of the pixel in skin region.
Preferably, the second adjustment submodule, is specifically included:
First computing unit, a passage colourity averages and b for the skin area that calculates the pending image respectively is logical
Road colourity average;
Second computing unit, for calculating the first default chromatic value and the difference of a passages colourity average, and will be described
First default chromatic value and the difference and a passage chromatic value sums of a passages colourity average are used as a passages colourity after adjustment
Value, the described first default chromatic value is to represent with the fair-complexioned a passages chromatic value of natural beauty;
3rd computing unit, for calculating the second default chromatic value and the difference of the b passages colourity average, and will be described
Second default chromatic value and the difference and b passage chromatic value sums of the b passages colourity average are used as b passages colourity after adjustment
Value, the described second default chromatic value is to represent with the fair-complexioned b passages chromatic value of natural beauty.
Preferably, the landscaping treatment device, further comprises:
Second adjusting module, brightness and colourity for adjusting the skin area according to different colour of skin styles, generation tool
There is an image after the beautification of different colour of skin styles, the different colour of skin styles are purported skin brightness and the combination of colourity, so that
Image after the beautification reaches default colour of skin style.
Skin landscaping treatment method and device in image provided in an embodiment of the present invention, is treated by the generation of skin colorimetry model
The skin mask of image is handled, the skin area of pending image is determined further according to skin mask, and then adjust skin area
Brightness and colourity, make the pending image comprising skin area have natural colour of skin whitening effect.Also, pass through skin mask
And brightness and the colourity of default colour of skin style adjustment skin area, can further it generate with the pale colour of skin, the ruddy colour of skin, small
The personalized landscaping treatment effect image such as the wheat colour of skin, bronze colour of skin, improves Consumer's Experience.Certainly, any of the present invention is implemented
Product or method must be not necessarily required to while reaching all the above advantage.
Brief description of the drawings
In order to illustrate more clearly about the embodiment of the present invention or technical scheme of the prior art, below will be to embodiment or existing
There is the accompanying drawing used required in technology description to be briefly described, it should be apparent that, drawings in the following description are only this
Some embodiments of invention, for those of ordinary skill in the art, on the premise of not paying creative work, can be with
Other accompanying drawings are obtained according to these accompanying drawings.
Fig. 1 for the embodiment of the present invention image in skin landscaping treatment method a kind of schematic flow sheet;
Fig. 2 for the embodiment of the present invention image in skin landscaping treatment method another schematic flow sheet;
Fig. 3 for the embodiment of the present invention image in skin landscaping treatment method another schematic flow sheet;
Fig. 4 for the embodiment of the present invention image in skin landscaping treatment device a kind of structural representation;
Fig. 5 for the embodiment of the present invention image in skin landscaping treatment device another structural representation.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete
Site preparation is described, it is clear that described embodiment is only a part of embodiment of the invention, rather than whole embodiments.Based on this
Embodiment in invention, the every other reality that those of ordinary skill in the art are obtained under the premise of creative work is not made
Example is applied, the scope of protection of the invention is belonged to.
Embodiment of the method one
A kind of specific embodiment of skin landscaping treatment method in image provided in an embodiment of the present invention, with reference to Fig. 1, Fig. 1
For a kind of schematic flow sheet of skin landscaping treatment method in the image of the embodiment of the present invention, including:
S101, according to skin colorimetry model, generate the skin mask of pending image, wherein, skin colourity model table is shown
The corresponding relation of skin colourity and confidence level, skin mask represents the confidence that each pixel in pending image is skin area
Degree.
Skin colorimetry model is a kind of model for being used to represent skin colourity and confidence level relation, usually, in image
Skin area has obvious difference with background, but skin color difference is not obvious between different personages, therefore can pass through
One unified model goes the colourity of skin in correspondence image.Skin beautification method is typically merely by lifting skin in conventional images
The brightness in region reaches landscaping effect, but there is the problem of landscaping effect is unnatural.And the embodiment of the present invention passes through skin colourity
Model generates the skin mask of pending image, so that carry out brightness common to image and colourity adjustment, reach nature whitening skin
The effect of color.Specifically, skin colorimetry model can be 256*256 matrix, the x directions correspondence Cr values of matrix, matrix
Y directions correspondence Cb values, each the chromatic value of position is in the range of [0,1], i.e., each in skin colorimetry model in matrix
The value of position represents that Cr=m and Cb=n color belongs to the probability of skin area.Skin colorimetry model can be pre-stored in locally
In memory, sample image in-time generatin can also be passed through.Wherein, the skin colorimetry model in local storage is pre-stored in, directly
Connect to call and can be used;The skin colorimetry model of in-time generatin, alternatively, the skin landscaping treatment in image of the embodiment of the present invention
Before method, its generating process is:
First, several skin colourity sample images are obtained, skin colourity sample image is for determining skin area colourity
Image, and several skin colourity sample images can cover diversified personage, for example man, woman, children, youth,
Middle age, old man etc. have the colony of different skin characteristic, and therefore, enough personage's samples result in more accurately skin-color
Spend model.Simultaneously as same width picture colourity and brightness under different illumination conditions are different, therefore several skin colourities
Sample image also covers the character image under different photoenvironments, such as room fluorescent lights, the personage under indoor incandescent lamp
Image, the character image of outdoor fine day, the character image at outdoor cloudy day etc..
Then, the Colour result of skin area in several skin colourity sample images is counted, skin colourity mould is obtained
Type.Wherein, Colour result is counted and generates skin colorimetry model, be specifically as follows:
The skin area in several skin colourity sample images is identified, general use manually identifies, it is possible to increase mark
Know the degree of accuracy, certainly, also can automatically be identified using computer;
Skin colourity sample image after mark is changed to YCbCr space, so as to obtain skin area in YCbCr space
Distribution situation;
Distribution situation using model of ellipse to skin area in YCbCr space is fitted, the oval skin model of generation,
As skin colorimetry model.Alternatively, skin colorimetry model is further smoothed, by cutting in skin colorimetry model
Variate is changed into gradual change value, the border of skin area in skin colorimetry model is shown not lofty.Generally entered using gaussian filtering
Row smoothing processing, gaussian filtering is the common method in image procossing, be will not be repeated here.
The skin mask of pending image is the single channel image of a width and pending image same size, in skin mask
In, each position has chromatic value, can using the chromatic value as skin in image confidence level.Prior art is general
Brightness adjustment is directly carried out to the skin area in image, and the embodiment of the present invention first passes through skin mask and determines skin in image
Skin region, then brightness raising and colourity optimization are carried out to skin area, more accurate effect of optimization can be reached.Alternatively,
The specific generating process of skin mask is:
Obtain the chromatic value of each pixel of pending image.Specifically, pending image can be changed to YCbCr
Color space, so, if during skin colorimetry model is also YCbCr color spaces, it is possible to easily in same color space
It is middle to be operated.It is because figure skin especially Asian skin's color using YCbCr color spaces in the embodiment of the present invention
Spend the distribution being distributed in the color space more and concentrate, be easy to make a distinction with non-skin region.Color space conversion side
It is owned by France in prior art, will not be repeated here.
The corresponding confidence level of chromatic value of each pixel is searched in skin colorimetry model, confidence level is regard as each picture
The pixel value of vegetarian refreshments.Alternatively, by taking pending image slices vegetarian refreshments P as an example, pixel P Cb-Cr values (i.e. chromatic value) for (86,
105) confidence level that its chromatic value in skin colorimetry model is all the confidence level, as point P of (86,105), is searched, this is put
Reliability as point P pixel value.
According to the pixel value of each pixel, the skin mask of pending image is generated.Specially:To in pending image
Each pixel is searched and obtains corresponding pixel value, and the pixel value of all pixels point is constituted and gathered, just generates and waits to locate
Manage the skin mask of image.
S102, the pixel that confidence level in skin mask is more than predetermined threshold value is defined as the skin area of pending image.
Skin mask is to represent that each pixel is the confidence level of skin area in pending image, alternatively, is passed through
Confidence level and predetermined threshold value are contrasted, you can whether be skin area, if the confidence level of a certain pixel is big if judging pixel
In predetermined threshold value, then judge that the pixel belongs to skin area pixel, all pixels for being determined as skin area are constituted
Set, the skin area of as pending image.Generally, the size of predetermined threshold value by technical staff according to practical operation require into
Row adjustment.
S103, the brightness of the skin area of the pending image of adjustment and colourity, the image after generation skin beautification so that treat
Processing image skin area reach needed for brightness and colourity.
Skin beautification method in conventional images, image landscaping effect is reached typically merely by the brightness of lifting skin area,
But, due to being only to carry out simply luminance raising to skin area, often there is landscaping effect in the image after beautification
Unnatural the problem of.Usually, the Colour for the skin whitening that people observe by the naked eye is in typical number range,
In the embodiment of the present invention, the skin area colourity of pending image is adjusted to default value scope, and to the bright of skin area
Degree is lifted, i.e. required colourity and brightness, so as to reach the beautification purpose to skin.
Alternatively, brightness and the colourity of the skin area of pending image are adjusted, the image after skin beautification is generated, specifically
For:
S1031, pending image changed to Lab color spaces.
In the embodiment of the present invention, pending image is changed to Lab color spaces and carries out brightness and the regulation of colourity, this is
Because Lab color spaces are a kind of colour models set up based on human visual experience, are easy to the luminance component and color to image
Spend component progress individually-edited.
S1032, the skin area of pending image adjusted in Lab color spaces by the first preset algorithm
The brightness of each pixel, obtains in the skin area of pending image brightness value after the adjustment of each pixel, so that pending image
Skin area in each pixel brightness meet pre-set skin beautification brightness effects.First preset algorithm is expressed as:Wherein, L is luminance channel (L * channel) brightness value before adjustment, and L ' is adjustment
Luminance channel (L * channel) brightness value afterwards, α and β are adjustment factor, and α typical value can for 0~2, β typical value
Think 4~6.
S1033, by presetting chromatic value adjust each pixel of the skin area of pending image in Lab color spaces
Colourity, obtains in the skin area of pending image chromatic value after the adjustment of each pixel, so that the skin area of pending image
In the colourity of each pixel migrated to default chromatic value, wherein, it is the fair-complexioned chromatic value of natural beauty to preset chromatic value.
Alternatively, the specific adjustment process of pending image chroma is:
The a passage colourity averages and b passage colourity averages of the skin area of pending image are calculated respectively, are designated as respectively
With
The first default chromatic value and the difference of a passage colourity averages are calculated, and chromatic value and a passage colourities are preset by first
The difference of average is with a passage chromatic value sums as a passages chromatic value after adjustment, and the first default chromatic value is to represent having certainly
Right U.S. fair-complexioned a passages chromatic value.It is embodied as:Wherein, a is a passage colors before adjustment
Angle value, a ' is a passage chromatic values after adjustment,It is a passage colourity averages before adjustment, atThe first default chromatic value, i.e., it is pre-
If a passage chromatic values with skin landscaping effect, atTypical value can be 10, certainly, atCan be by technical staff's root
Factually border landscaping effect is set.
The second default chromatic value and the difference of b passage colourity averages are calculated, and chromatic value and b passage colourities are preset by second
The difference of average is with b passage chromatic value sums as b passages chromatic value after adjustment, and the second default chromatic value is to represent having certainly
Right U.S. fair-complexioned b passages chromatic value.It is embodied as:Wherein, b is the b passage colors before adjustment
Angle value, b ' is the b passage chromatic values after adjustment,It is the b passage colourity averages before adjustment, btSecond default chromatic value, that is, preset
The b passage chromatic values with skin landscaping effect, btTypical value can be 8, certainly, btCan by technical staff according to
Actual landscaping effect is set.
S1034, by brightness value after the adjustment of each pixel in the skin area of pending image and adjustment after chromatic value change
To rgb color space, the parameter of each pixel of skin area in rgb color space is generated.
Specifically, by the brightness value after adjustment and chromatic value L ', a ', b ' conversions to rgb color space, you can obtain waiting to locate
Each pixel is in the adjusting parameter of rgb color space in the skin area of reason image, and specific conversion method is prior art, herein not
Repeat again.
S1035, by the second preset algorithm the skin area in pending image is handled, obtained after skin beautification
Image, the second preset algorithm is:
IB(x, y)=I (x, y) (1-M (x, y))+I ' (x, y) M (x, y), wherein, IB(x, y) is after beautifying through skin
Image pixel parameter, I (x, y) be pending image in skin area pixel parameter, M (x, y) represent
The pixel value of pixel in skin mask, I ' (x, y) represents skin region in the rgb color space after brightness and colourity adjustment
The parameter of the pixel in domain.
After being handled by the second preset algorithm the skin area in pending image, figure can also be further adjusted
The contrast of picture, the output effect of the image after optimization skin beautification.
Image after being beautified by the second preset algorithm by pending image and through skin carries out fusion treatment, by this
After treatment effect, output image not only compared to pending image have beautification effect, and compared to beautifying through skin after
Image landscaping effect can be more naturally, natural landscaping effect therefore, it is possible to improve image, makes picture be closer to nature
The whitening colour of skin.
The inventive method embodiment one, the skin mask of pending image is generated by skin colorimetry model, so that it is determined that
The skin area gone out in pending image, and then to carrying out brightness adjustment by skin area determined by skin mask, reach
The effect of the brightness of skin area is lifted, then colourity adjustment is carried out to skin area, so that the colourity of skin area tool reaches institute
The colourity needed, so that the image after processing has natural colour of skin whitening effect.
Embodiment of the method two
Another specific embodiment of skin landscaping treatment method in image provided in an embodiment of the present invention, with reference to Fig. 2, figure
2 for the embodiment of the present invention image in skin landscaping treatment method another schematic flow sheet, in the base of embodiment of the method one
On plinth, further comprise:
S104, the brightness according to different colour of skin styles adjustment skin area and colourity, generation have different colour of skin styles
Image after beautification, different colour of skin styles be purported skin brightness and the combination of colourity so that beautification after image reach it is default
Colour of skin style.
This step is located at after the S102 of embodiment of the method one, daily landscaping treatment application scenario, except being carried out to image
Whitening is handled, can also be further according to image of the hobby generation with different colour of skin styles of user, so that the figure after beautification
As reaching default colour of skin style, wherein, default colour of skin style typically has:The pale colour of skin, the ruddy colour of skin, the wheat colour of skin, bronze skin
Color etc..Specifically generating process is:
S1041, each pixel by the skin area of the pending image of the 3rd preset algorithm adjustment in Lab color spaces
Brightness, brightness value after each pixel is adjusted according to default colour of skin style is obtained in the skin area of pending image, so as to wait to locate
The brightness for managing each pixel in the skin area of image meets the skin beautification brightness effects of default colour of skin style.3rd preset algorithm
It is expressed as:Wherein, for the luminance channel before adjustment, (L leads to L
Road) brightness value, L ' is luminance channel (L * channel) brightness value after adjustment,It is the L * channel luminance mean value before adjustment, LtIt is default
Colour of skin style landscaping effect brightness value, α and β are adjustment factor, and α typical value can be able to be for 0~2, β typical value
4~6.
S1042, calculate respectively pending image skin area a passage colourity averages and b passage colourity averages, respectively
It is designated asWith
S1043, the difference for calculating the 3rd default chromatic value and a passage colourity averages, and the 3rd default chromatic value is led to a
The difference of road colourity average is with a passage chromatic value sums as a passages chromatic value after adjustment, and the 3rd default chromatic value is to represent
A passage chromatic values with different colour of skin styles.It is embodied as:Wherein, a is a before adjustment
Passage chromatic value, a ' is a passage chromatic values after adjustment,It is a passage colourity averages before adjustment, at‘It is the 3rd default colourity
Value, i.e., a passage chromatic values of the default skin landscaping effect with different colour of skin styles, at’Can be according to different colour of skin wind
Lattice are adjusted.
S1044, the difference for calculating the 4th default chromatic value and b passage colourity averages, and the 4th default chromatic value is led to b
The difference of road colourity average is with b passage chromatic value sums as b passages chromatic value after adjustment, and the 4th default chromatic value is to represent
B passage chromatic values with different colour of skin styles.It is embodied as:Wherein, b is the b before adjustment
Passage chromatic value, b ' is the b passage chromatic values after adjustment,It is the b passage colourity averages before adjustment, bt’It is the 4th default colourity
Value, i.e., the b passage chromatic values of the default skin landscaping effect with different colour of skin styles, bt‘Can be according to different colour of skin wind
Lattice are adjusted.
S1045, by each pixel in the skin area of pending image according to default colour of skin style adjust after brightness value and tune
Whole rear chromatic value changes the parameter that each pixel of skin area in rgb color space is generated to rgb color space.
Specifically, by the brightness value after adjustment and chromatic value L ', a ', b ' conversions to rgb color space, you can obtain waiting to locate
Each pixel is in the adjusting parameter of rgb color space in the skin area of reason image, and specific conversion method is prior art, herein not
Repeat again.
S1046, by the second preset algorithm the skin area in pending image is handled, obtained after skin beautification
Image, the second preset algorithm is:
IB(x, y)=I (x, y) (1-M (x, y))+I ' (x, y) M (x, y), wherein, IB(x, y) is after beautifying through skin
Image pixel parameter, I (x, y) be pending image in skin area pixel parameter, M (x, y) represent
The pixel value of pixel in skin mask, I ' (x, y) represents skin region in the rgb color space after brightness and colourity adjustment
The parameter of the pixel in domain, i.e., brightness and colourity after being adjusted according to default colour of skin style.
Image after being beautified by the second preset algorithm by pending image and through skin carries out fusion treatment, by this
After treatment effect, output image not only compared to pending image have beautification effect, and compared to beautifying through skin after
Image landscaping effect more can exist naturally, mitigating between the skin area after beautification and background area without landscaping treatment
Brightness/chroma inconsistence problems.
After being handled by the second preset algorithm the skin area in pending image, figure can also be further adjusted
The contrast of picture, the output effect of the image after optimization skin beautification.
The inventive method embodiment two, brightness and the color of skin area are adjusted by skin mask and default colour of skin style
Degree, can further be generated with the personalized landscaping treatment effect such as the pale colour of skin, the ruddy colour of skin, the wheat colour of skin, bronze colour of skin
Fruit image, improves Consumer's Experience.
Embodiment of the method three
Another specific embodiment of skin landscaping treatment method in image provided in an embodiment of the present invention, with reference to Fig. 3, figure
3 for the embodiment of the present invention image in skin landscaping treatment method another schematic flow sheet, specifically include:
By many character images under multiple different photoenvironments, skin area is identified, through chrominance space fitting of distribution
Afterwards, skin colorimetry model is generated.Pending image combination skin colorimetry model is subjected to skin detection, skin mask is generated, and
The skin area of pending image is determined by skin mask.Meanwhile, pending image is changed to Lab from RGB color degree space
Color space, and skin area is subjected to color transfer, i.e. brightness and colourity regulation, reconvert to rgb color space.Then,
By the image and artwork after conversion, image co-registration is carried out with reference to skin mask, finally degree adjustment by contrast, after generation landscaping treatment
Image.
Device embodiment one
A kind of specific embodiment of skin landscaping treatment device in image provided in an embodiment of the present invention, with being flowed shown in Fig. 1
Journey is corresponding, with reference to Fig. 4, and Fig. 4 is a kind of structural representation of skin landscaping treatment device in the image of the embodiment of the present invention, bag
Include:
Generation module 201, for according to skin colorimetry model, generating the skin mask of pending image, skin colourity mould
Type represents the corresponding relation of skin colourity and confidence level, and skin mask represents that each pixel is skin area in pending image
Confidence level;
Determining module 202, the pixel for confidence level in skin mask to be more than to predetermined threshold value is defined as pending image
Skin area;
First adjusting module 203, brightness and colourity for the skin area that adjusts pending image, generation skin beautification
Image afterwards so that the skin area of pending image reach needed for brightness and colourity.
Skin landscaping treatment device is used to realize skin landscaping treatment in image shown in Fig. 1 in the image that the present embodiment is provided
The technical scheme of method, its implementing principle and technical effect are similar, and here is omitted.
Wherein, landscaping treatment device also includes:
Acquisition module, for obtaining several skin colourity sample images, skin colourity sample image is determination skin area
Image;
Statistical module, the Colour result for counting skin area in several skin colourity sample images, obtains skin
Skin colorimetry model.
Wherein, generation module 201, are specifically included:
Acquisition submodule, the chromatic value of each pixel for obtaining pending image;
Submodule is searched, the corresponding confidence level of chromatic value for searching each pixel in skin colorimetry model will
Confidence level as each pixel pixel value;
Submodule is generated, for the pixel value according to each pixel, the skin mask of pending image is generated.
Wherein, the first adjusting module 203, is specifically included:
First transform subblock, for pending image to be changed to Lab color spaces;
First adjustment submodule, for adjusting the skin area of pending image by the first preset algorithm in Lab colors
The brightness of each pixel in space, obtains in the skin area of pending image brightness value after the adjustment of each pixel, so as to wait to locate
The brightness for managing each pixel in the skin area of image meets pre-set skin beautification brightness effects;
Second adjustment submodule, for adjusting the skin area of pending image in Lab colors sky by presetting chromatic value
Between in each pixel colourity, chromatic value after the adjustment of each pixel is obtained in the skin area of pending image, so that pending
The colourity of each pixel is migrated to default chromatic value in the skin area of image, and it is the fair-complexioned colourity of natural beauty to preset chromatic value
Value;
Second transform subblock, for by brightness value and adjustment after the adjustment of each pixel in the skin area of pending image
Chromatic value changes the parameter that each pixel of skin area in rgb color space is generated to rgb color space afterwards;
Submodule is handled, for being handled by the second preset algorithm the skin area in pending image, is obtained
Image after skin beautification, the second preset algorithm is:
IB(x, y)=I (x, y) (1-M (x, y))+I ' (x, y) M (x, y), wherein, IB(x, y) is after beautifying through skin
Image pixel parameter, I (x, y) be pending image in skin area pixel parameter, M (x, y) represent
The pixel value of pixel in skin mask, I ' (x, y) represents skin region in the rgb color space after brightness and colourity adjustment
The parameter of the pixel in domain.
Wherein, the second adjustment submodule, is specifically included:
First computing unit, a passage colourity averages and b passage colors for the skin area that calculates pending image respectively
Spend average;
Second computing unit, for calculating the first default chromatic value and the difference of a passage colourity averages, and first is preset
The difference of chromatic value and a passage colourity averages presets color with a passage chromatic value sums as a passages chromatic value after adjustment, first
Angle value is to represent with the fair-complexioned a passages chromatic value of natural beauty;
3rd computing unit, for calculating the second default chromatic value and the difference of b passage colourity averages, and second is preset
The difference of chromatic value and b passage colourity averages presets color with b passage chromatic value sums as b passages chromatic value after adjustment, second
Angle value is to represent with the fair-complexioned b passages chromatic value of natural beauty.
Skin landscaping treatment device is used to realize that the inventive method is implemented in the image that apparatus of the present invention embodiment one is provided
The landscaping treatment of skin landscaping treatment method in the image that example one is provided, its implementing principle and technical effect are similar, herein no longer
Repeat.
Device embodiment two
Another specific embodiment of skin landscaping treatment device in image provided in an embodiment of the present invention, and shown in Fig. 2
Flow is corresponding, with reference to Fig. 5, Fig. 5 for skin landscaping treatment device in the image of the embodiment of the present invention another structural representation
Figure, on the basis of device embodiment one, further comprises:
Second adjusting module 204, brightness and colourity for adjusting skin area according to different colour of skin styles, generation has
Image after the beautification of different colour of skin styles, different colour of skin styles are purported skin brightness and the combination of colourity, so that after beautification
Image reach default colour of skin style.
Skin landscaping treatment device is used to realize that the inventive method is implemented in the image that apparatus of the present invention embodiment two is provided
The landscaping treatment of skin landscaping treatment method in the image that example two is provided, its implementing principle and technical effect are similar, herein no longer
Repeat.
It should be noted that herein, such as first and second or the like relational terms are used merely to a reality
Body or operation make a distinction with another entity or operation, and not necessarily require or imply these entities or deposited between operating
In any this actual relation or order.Moreover, term " comprising ", "comprising" or its any other variant are intended to
Nonexcludability is included, so that process, method, article or equipment including a series of key elements not only will including those
Element, but also other key elements including being not expressly set out, or also include being this process, method, article or equipment
Intrinsic key element.In the absence of more restrictions, the key element limited by sentence "including a ...", it is not excluded that
Also there is other identical element in process, method, article or equipment including the key element.
Each embodiment in this specification is described by the way of related, identical similar portion between each embodiment
Divide mutually referring to what each embodiment was stressed is the difference with other embodiment.It is real especially for system
Apply for example, because it is substantially similar to embodiment of the method, so description is fairly simple, related part is referring to embodiment of the method
Part explanation.
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the scope of the present invention.It is all
Any modification, equivalent substitution and improvements made within the spirit and principles in the present invention etc., are all contained in protection scope of the present invention
It is interior.
Claims (12)
1. a kind of skin landscaping treatment method in image, it is characterised in that methods described includes:
According to skin colorimetry model, generate the skin mask of pending image, the skin colourity model table show skin colourity with
The corresponding relation of confidence level, the skin mask represents the confidence that each pixel in the pending image is skin area
Degree;
The pixel that confidence level in the skin mask is more than predetermined threshold value is defined as to the skin area of the pending image;
Adjust brightness and the colourity of the skin area of the pending image, the image after generation skin beautification so that described to treat
Processing image skin area reach needed for brightness and colourity.
2. skin landscaping treatment method in image according to claim 1, it is characterised in that described according to skin colourity mould
Before type, the skin mask for generating pending image, skin landscaping treatment method also includes in described image:
Several skin colourity sample images are obtained, the skin colourity sample image is the image for determining skin area;
The Colour result of skin area, obtains the skin colourity mould in several described skin colourity sample images of statistics
Type.
3. skin landscaping treatment method in image according to claim 1 or 2, it is characterised in that described according to skin-color
Model is spent, the skin mask of pending image is generated, including:
Obtain the chromatic value of each pixel of the pending image;
The corresponding confidence level of chromatic value of each pixel is searched in the skin colorimetry model, using the confidence level as every
The pixel value of one pixel;
According to the pixel value of each pixel, the skin mask of the pending image is generated.
4. skin landscaping treatment method in image according to claim 1 or 2, it is characterised in that treated described in the adjustment
Brightness and the colourity of the skin area of image are handled, the image after skin beautification is generated, including:
The pending image is changed to Lab color spaces;
The bright of each pixel of the skin area of the pending image in Lab color spaces is adjusted by the first preset algorithm
Degree, obtains in the skin area of the pending image brightness value after the adjustment of each pixel, so that the skin of the pending image
The brightness of each pixel meets pre-set skin beautification brightness effects in skin region;
The colourity of each pixel of the skin area of the pending image in Lab color spaces is adjusted by presetting chromatic value,
Chromatic value after the adjustment of each pixel is obtained in the skin area of the pending image, so that the skin region of the pending image
The colourity of each pixel is migrated to the default chromatic value in domain, and the default chromatic value is the fair-complexioned chromatic value of natural beauty;
Chromatic value after brightness value after the adjustment of each pixel in the skin area of the pending image and adjustment is changed to RGB color
The parameter of each pixel of skin area in color space, generation rgb color space;
The skin area in the pending image is handled by the second preset algorithm, the figure after skin beautification is obtained
Picture, second preset algorithm is:
IB(x, y)=I (x, y) (1-M (x, y))+I ' (x, y) M (x, y), wherein, IB(x, y) is the figure after beautifying through skin
The parameter of the pixel of picture, I (x, y) is the parameter of the pixel of the skin area in pending image, M (x, y) expression skins
The pixel value of pixel in mask, I ' (x, y) represents skin area in the rgb color space after brightness and colourity adjustment
The parameter of pixel, the parameter of the pixel is made up of brightness and colourity.
5. skin landscaping treatment method in image according to claim 4, it is characterised in that described by presetting chromatic value
The colourity of each pixel of the skin area of the pending image in Lab color spaces is adjusted, the pending image is obtained
Skin area in each pixel adjustment after chromatic value, including:
The a passage colourity averages and b passage colourity averages of the skin area of the pending image are calculated respectively;
The first default chromatic value and the difference of a passages colourity average are calculated, and chromatic value and a are preset by described first
The difference of passage colourity average is with a passage chromatic value sums as a passages chromatic value after adjustment, and the described first default chromatic value is used
To represent with the fair-complexioned a passages chromatic value of natural beauty;
The second default chromatic value and the difference of the b passages colourity average are calculated, and chromatic value and the b are preset by described second
The difference of passage colourity average is with b passage chromatic value sums as b passages chromatic value after adjustment, and the described second default chromatic value is used
To represent with the fair-complexioned b passages chromatic value of natural beauty.
6. skin landscaping treatment method in image according to claim 1 or 2, it is characterised in that described by the skin
Confidence level is defined as after the skin area of the pending image more than the pixel of predetermined threshold value in mask, skin in described image
Skin landscaping treatment method also includes:
Brightness and the colourity of the skin area are adjusted according to different colour of skin styles, after beautification of the generation with different colour of skin styles
Image, the different colour of skin styles be purported skin brightness and the combination of colourity so that the image after the beautification reach it is pre-
If colour of skin style.
7. skin landscaping treatment device in a kind of image, it is characterised in that described device includes:
Generation module, for according to skin colorimetry model, generating the skin mask of pending image, the skin colourity model table
Show the corresponding relation of skin colourity and confidence level, the skin mask represents that each pixel is skin in the pending image
The confidence level in region;
Determining module, the pixel for confidence level in the skin mask to be more than to predetermined threshold value is defined as the pending image
Skin area;
First adjusting module, brightness and colourity for the skin area that adjusts the pending image, after generation skin beautification
Image so that the skin area of the pending image reach needed for brightness and colourity.
8. skin landscaping treatment device in image according to claim 7, it is characterised in that the landscaping treatment device is also
Including:
Acquisition module, for obtaining several skin colourity sample images, the skin colourity sample image is determination skin area
Image;
Statistical module, the Colour result for counting skin area in several described skin colourity sample images, obtains institute
State skin colorimetry model.
9. skin landscaping treatment device in the image according to claim 7 or 8, it is characterised in that the generation module, tool
Body includes:
Acquisition submodule, the chromatic value of each pixel for obtaining the pending image;
Submodule is searched, the corresponding confidence level of chromatic value for searching each pixel in the skin colorimetry model will
The confidence level as each pixel pixel value;
Submodule is generated, for the pixel value according to each pixel, the skin mask of the pending image is generated.
10. skin landscaping treatment device in the image according to claim 7 or 8, it is characterised in that the first adjustment mould
Block, is specifically included:
First transform subblock, for the pending image to be changed to Lab color spaces;
First adjustment submodule, for adjusting the skin area of the pending image by the first preset algorithm in Lab colors
The brightness of each pixel in space, obtains in the skin area of the pending image brightness value after the adjustment of each pixel, so that
The brightness of each pixel meets pre-set skin beautification brightness effects in the skin area of the pending image;
Second adjustment submodule, for adjusting the skin area of the pending image in Lab colors sky by presetting chromatic value
Between in each pixel colourity, chromatic value after the adjustment of each pixel is obtained in the skin area of the pending image, so that institute
The colourity for stating each pixel in the skin area of pending image is migrated to the default chromatic value, and the default chromatic value is nature
U.S. fair-complexioned chromatic value;
Second transform subblock, for by brightness value and adjustment after the adjustment of each pixel in the skin area of the pending image
Chromatic value changes the parameter that each pixel of skin area in rgb color space is generated to rgb color space afterwards;
Submodule is handled, for being handled by the second preset algorithm the skin area in the pending image, is obtained
Image after skin beautification, second preset algorithm is:
IB(x, y)=I (x, y) (1-M (x, y))+I ' (x, y) M (x, y), wherein, IB(x, y) is the figure after beautifying through skin
The parameter of the pixel of picture, I (x, y) is the parameter of the pixel of the skin area in pending image, M (x, y) expression skins
The pixel value of pixel in mask, I ' (x, y) represents the rgb color space skin area that the second transform subblock is converted to
Pixel parameter, the parameter of the pixel is made up of brightness and colourity.
11. skin landscaping treatment device in image according to claim 10, it is characterised in that the second adjustment submodule
Block, is specifically included:
First computing unit, a passage colourity averages and b passage colors for the skin area that calculates the pending image respectively
Spend average;
Second computing unit, for calculating the first default chromatic value and the difference of a passages colourity average, and by described first
Default chromatic value and the difference and a passage chromatic value sums of a passages colourity average are used as a passages chromatic value after adjustment, institute
The first default chromatic value is stated to represent with the fair-complexioned a passages chromatic value of natural beauty;
3rd computing unit, for calculating the second default chromatic value and the difference of the b passages colourity average, and by described second
Default chromatic value and the difference and b passage chromatic value sums of the b passages colourity average are used as b passages chromatic value after adjustment, institute
The second default chromatic value is stated to represent with the fair-complexioned b passages chromatic value of natural beauty.
12. skin landscaping treatment device in the image according to claim 7 or 8, it is characterised in that the landscaping treatment dress
Put, further comprise:
Second adjusting module, brightness and colourity for adjusting the skin area according to different colour of skin styles, generation has not
With the image after the beautification of colour of skin style, the different colour of skin styles are purported skin brightness and the combination of colourity, so that described
Image after beautification reaches default colour of skin style.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710202767.6A CN107180415B (en) | 2017-03-30 | 2017-03-30 | Skin beautifying processing method and device in image |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710202767.6A CN107180415B (en) | 2017-03-30 | 2017-03-30 | Skin beautifying processing method and device in image |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107180415A true CN107180415A (en) | 2017-09-19 |
CN107180415B CN107180415B (en) | 2020-08-14 |
Family
ID=59830540
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710202767.6A Active CN107180415B (en) | 2017-03-30 | 2017-03-30 | Skin beautifying processing method and device in image |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107180415B (en) |
Cited By (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107862658A (en) * | 2017-10-31 | 2018-03-30 | 广东欧珀移动通信有限公司 | Image processing method, device, computer-readable recording medium and electronic equipment |
CN107945106A (en) * | 2017-11-30 | 2018-04-20 | 广东欧珀移动通信有限公司 | Image processing method, device, electronic equipment and computer-readable recording medium |
CN108040296A (en) * | 2017-12-25 | 2018-05-15 | 北京奇虎科技有限公司 | Live dress ornament based on the segmentation of adaptive tracing frame is dressed up method and device |
CN108495050A (en) * | 2018-06-15 | 2018-09-04 | Oppo广东移动通信有限公司 | Photographic method, device, terminal and computer readable storage medium |
CN109146815A (en) * | 2018-08-20 | 2019-01-04 | 深圳创维-Rgb电子有限公司 | Picture contrast method of adjustment, device and computer equipment |
CN109639960A (en) * | 2017-10-05 | 2019-04-16 | 卡西欧计算机株式会社 | Image processing apparatus, image processing method and recording medium |
CN111369470A (en) * | 2020-03-10 | 2020-07-03 | 昇显微电子(苏州)有限公司 | Image area tone adjusting method, device, storage medium and equipment |
CN111429536A (en) * | 2020-03-13 | 2020-07-17 | 深圳市雄帝科技股份有限公司 | Method, system and storage medium for toning complexion in image |
CN111583154A (en) * | 2020-05-12 | 2020-08-25 | Oppo广东移动通信有限公司 | Image processing method, skin beautifying model training method and related device |
CN111784635A (en) * | 2020-05-29 | 2020-10-16 | 北京工商大学 | Skin surface fluorescent point detection and evaluation method based on image color space |
CN112532891A (en) * | 2020-11-25 | 2021-03-19 | 维沃移动通信有限公司 | Photographing method and device |
CN112686965A (en) * | 2020-12-25 | 2021-04-20 | 百果园技术(新加坡)有限公司 | Skin color detection method, device, mobile terminal and storage medium |
CN114095656A (en) * | 2021-11-17 | 2022-02-25 | 维沃移动通信有限公司 | Image processing method and device and electronic equipment |
CN114565506A (en) * | 2022-01-17 | 2022-05-31 | 北京新氧科技有限公司 | Image color migration method, device, equipment and storage medium |
US11847778B2 (en) * | 2020-08-21 | 2023-12-19 | Apple Inc. | Image capture techniques personalized to individual subjects being imaged |
Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101964874A (en) * | 2009-07-23 | 2011-02-02 | 卡西欧计算机株式会社 | Image processing apparatus and image processing method |
CN102129575A (en) * | 2011-03-24 | 2011-07-20 | 成都四方信息技术有限公司 | Pornographic image analysis system based on color space skin color model |
CN103971344A (en) * | 2014-05-27 | 2014-08-06 | 广州商景网络科技有限公司 | Skin color error correction method and system for certificate images |
CN104050455A (en) * | 2014-06-24 | 2014-09-17 | 深圳先进技术研究院 | Skin color detection method and system |
CN104469138A (en) * | 2013-09-20 | 2015-03-25 | 卡西欧计算机株式会社 | Image Processing Apparatus, Image Processing Method And Recording Medium |
CN104767983A (en) * | 2015-03-19 | 2015-07-08 | 华为技术有限公司 | Picture processing method and device |
CN104881853A (en) * | 2015-05-28 | 2015-09-02 | 厦门美图之家科技有限公司 | Skin color rectification method and system based on color conceptualization |
CN105243371A (en) * | 2015-10-23 | 2016-01-13 | 厦门美图之家科技有限公司 | Human face beauty degree detection method and system and shooting terminal |
CN105608677A (en) * | 2015-12-28 | 2016-05-25 | 成都品果科技有限公司 | Image skin color beautifying method and system under any lighting conditions |
CN105913376A (en) * | 2016-04-14 | 2016-08-31 | 北京奇艺世纪科技有限公司 | Method and device for quick photo beautifying |
CN106101547A (en) * | 2016-07-06 | 2016-11-09 | 北京奇虎科技有限公司 | The processing method of a kind of view data, device and mobile terminal |
CN106375316A (en) * | 2016-08-31 | 2017-02-01 | 广州市百果园网络科技有限公司 | Video image processing method and device |
-
2017
- 2017-03-30 CN CN201710202767.6A patent/CN107180415B/en active Active
Patent Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101964874A (en) * | 2009-07-23 | 2011-02-02 | 卡西欧计算机株式会社 | Image processing apparatus and image processing method |
CN102129575A (en) * | 2011-03-24 | 2011-07-20 | 成都四方信息技术有限公司 | Pornographic image analysis system based on color space skin color model |
CN104469138A (en) * | 2013-09-20 | 2015-03-25 | 卡西欧计算机株式会社 | Image Processing Apparatus, Image Processing Method And Recording Medium |
CN103971344A (en) * | 2014-05-27 | 2014-08-06 | 广州商景网络科技有限公司 | Skin color error correction method and system for certificate images |
CN104050455A (en) * | 2014-06-24 | 2014-09-17 | 深圳先进技术研究院 | Skin color detection method and system |
CN104767983A (en) * | 2015-03-19 | 2015-07-08 | 华为技术有限公司 | Picture processing method and device |
CN104881853A (en) * | 2015-05-28 | 2015-09-02 | 厦门美图之家科技有限公司 | Skin color rectification method and system based on color conceptualization |
CN105243371A (en) * | 2015-10-23 | 2016-01-13 | 厦门美图之家科技有限公司 | Human face beauty degree detection method and system and shooting terminal |
CN105608677A (en) * | 2015-12-28 | 2016-05-25 | 成都品果科技有限公司 | Image skin color beautifying method and system under any lighting conditions |
CN105913376A (en) * | 2016-04-14 | 2016-08-31 | 北京奇艺世纪科技有限公司 | Method and device for quick photo beautifying |
CN106101547A (en) * | 2016-07-06 | 2016-11-09 | 北京奇虎科技有限公司 | The processing method of a kind of view data, device and mobile terminal |
CN106375316A (en) * | 2016-08-31 | 2017-02-01 | 广州市百果园网络科技有限公司 | Video image processing method and device |
Cited By (24)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109639960A (en) * | 2017-10-05 | 2019-04-16 | 卡西欧计算机株式会社 | Image processing apparatus, image processing method and recording medium |
CN109639960B (en) * | 2017-10-05 | 2020-12-29 | 卡西欧计算机株式会社 | Image processing apparatus, image processing method, and recording medium |
CN107862658A (en) * | 2017-10-31 | 2018-03-30 | 广东欧珀移动通信有限公司 | Image processing method, device, computer-readable recording medium and electronic equipment |
CN107945106A (en) * | 2017-11-30 | 2018-04-20 | 广东欧珀移动通信有限公司 | Image processing method, device, electronic equipment and computer-readable recording medium |
CN108040296B (en) * | 2017-12-25 | 2020-08-28 | 北京奇虎科技有限公司 | Live-broadcast dress decorating method and device based on self-adaptive tracking frame segmentation |
CN108040296A (en) * | 2017-12-25 | 2018-05-15 | 北京奇虎科技有限公司 | Live dress ornament based on the segmentation of adaptive tracing frame is dressed up method and device |
CN108495050A (en) * | 2018-06-15 | 2018-09-04 | Oppo广东移动通信有限公司 | Photographic method, device, terminal and computer readable storage medium |
CN111866394A (en) * | 2018-06-15 | 2020-10-30 | Oppo广东移动通信有限公司 | Photographing method, photographing device, terminal and computer-readable storage medium |
CN108495050B (en) * | 2018-06-15 | 2020-09-04 | Oppo广东移动通信有限公司 | Photographing method, photographing device, terminal and computer-readable storage medium |
CN109146815B (en) * | 2018-08-20 | 2022-08-30 | 深圳创维-Rgb电子有限公司 | Image contrast adjusting method and device and computer equipment |
CN109146815A (en) * | 2018-08-20 | 2019-01-04 | 深圳创维-Rgb电子有限公司 | Picture contrast method of adjustment, device and computer equipment |
CN111369470B (en) * | 2020-03-10 | 2024-05-31 | 昇显微电子(苏州)股份有限公司 | Image area tone adjustment method, device, storage medium and apparatus |
CN111369470A (en) * | 2020-03-10 | 2020-07-03 | 昇显微电子(苏州)有限公司 | Image area tone adjusting method, device, storage medium and equipment |
CN111429536A (en) * | 2020-03-13 | 2020-07-17 | 深圳市雄帝科技股份有限公司 | Method, system and storage medium for toning complexion in image |
CN111429536B (en) * | 2020-03-13 | 2023-12-19 | 深圳市雄帝科技股份有限公司 | Method, system and storage medium for toning skin color in image |
CN111583154B (en) * | 2020-05-12 | 2023-09-26 | Oppo广东移动通信有限公司 | Image processing method, skin beautifying model training method and related device |
CN111583154A (en) * | 2020-05-12 | 2020-08-25 | Oppo广东移动通信有限公司 | Image processing method, skin beautifying model training method and related device |
CN111784635B (en) * | 2020-05-29 | 2023-05-30 | 北京工商大学 | Skin surface fluorescent spot detection and evaluation method based on image color space |
CN111784635A (en) * | 2020-05-29 | 2020-10-16 | 北京工商大学 | Skin surface fluorescent point detection and evaluation method based on image color space |
US11847778B2 (en) * | 2020-08-21 | 2023-12-19 | Apple Inc. | Image capture techniques personalized to individual subjects being imaged |
CN112532891A (en) * | 2020-11-25 | 2021-03-19 | 维沃移动通信有限公司 | Photographing method and device |
CN112686965A (en) * | 2020-12-25 | 2021-04-20 | 百果园技术(新加坡)有限公司 | Skin color detection method, device, mobile terminal and storage medium |
CN114095656A (en) * | 2021-11-17 | 2022-02-25 | 维沃移动通信有限公司 | Image processing method and device and electronic equipment |
CN114565506A (en) * | 2022-01-17 | 2022-05-31 | 北京新氧科技有限公司 | Image color migration method, device, equipment and storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN107180415B (en) | 2020-08-14 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107180415A (en) | Skin landscaping treatment method and device in a kind of image | |
US11153547B1 (en) | Correlated illuminant estimations | |
CN110163810B (en) | Image processing method, device and terminal | |
CN110248450B (en) | Method and device for controlling light by combining people | |
CN104881853B (en) | A kind of colour of skin antidote and system based on color generalities | |
CN103581571B (en) | Video image matting method based on three elements of color | |
Störring et al. | Physics-based modelling of human skin colour under mixed illuminants | |
CN104574285B (en) | One kind dispels the black-eyed method of image automatically | |
CN110634169A (en) | Image processing apparatus and method | |
CN106878695A (en) | Method, device and computer equipment that white balance is processed | |
CN103108469B (en) | Method and device for controlling output light of illuminating device and illuminating system | |
US9460521B2 (en) | Digital image analysis | |
CN106326823B (en) | Method and system for obtaining head portrait in picture | |
CN106997584A (en) | A kind of haze weather image enchancing method | |
CN105608677A (en) | Image skin color beautifying method and system under any lighting conditions | |
CN106033529A (en) | Image processing method and electronic apparatus | |
CN109862389A (en) | A kind of method for processing video frequency, device, server and storage medium | |
CN108024105A (en) | Image color adjusting method, device, electronic equipment and storage medium | |
JPH0862741A (en) | Gradation correcting device | |
CN107623845B (en) | A kind of image processing method and device based on priori knowledge | |
CN105979236A (en) | Image quality adjustment method and device | |
CN107592517A (en) | A kind of method and device of colour of skin processing | |
CN108550124A (en) | A kind of illumination compensation and image enchancing method based on bionical helical | |
CN109064431B (en) | Picture brightness adjusting method, equipment and storage medium thereof | |
US20190347469A1 (en) | Method of improving image analysis |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |