CN106296617A - The processing method and processing device of facial image - Google Patents
The processing method and processing device of facial image Download PDFInfo
- Publication number
- CN106296617A CN106296617A CN201610700384.7A CN201610700384A CN106296617A CN 106296617 A CN106296617 A CN 106296617A CN 201610700384 A CN201610700384 A CN 201610700384A CN 106296617 A CN106296617 A CN 106296617A
- Authority
- CN
- China
- Prior art keywords
- pixel
- facial image
- pixel value
- highlight area
- skin color
- 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
- 230000001815 facial effect Effects 0.000 title claims abstract description 132
- 238000012545 processing Methods 0.000 title claims abstract description 29
- 238000003672 processing method Methods 0.000 title claims abstract description 28
- 230000008439 repair process Effects 0.000 claims abstract description 65
- 238000005457 optimization Methods 0.000 claims abstract description 60
- 238000013386 optimize process Methods 0.000 claims abstract description 19
- 238000000034 method Methods 0.000 claims description 75
- 230000008569 process Effects 0.000 claims description 65
- 239000000284 extract Substances 0.000 claims description 10
- 238000000605 extraction Methods 0.000 claims description 10
- 238000006243 chemical reaction Methods 0.000 claims description 7
- 230000000694 effects Effects 0.000 abstract description 12
- 230000000875 corresponding effect Effects 0.000 description 20
- 230000006870 function Effects 0.000 description 14
- 230000006854 communication Effects 0.000 description 9
- 238000004891 communication Methods 0.000 description 8
- 238000003860 storage Methods 0.000 description 7
- 230000008859 change Effects 0.000 description 4
- 230000000295 complement effect Effects 0.000 description 4
- 238000001514 detection method Methods 0.000 description 4
- 235000000391 Lepidium draba Nutrition 0.000 description 2
- 230000009471 action Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000000205 computational method Methods 0.000 description 2
- 238000004590 computer program Methods 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000005484 gravity Effects 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 230000007774 longterm Effects 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000007704 transition Effects 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000002146 bilateral effect Effects 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 238000005314 correlation function Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000012856 packing Methods 0.000 description 1
- 238000009527 percussion Methods 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000013139 quantization Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000010897 surface acoustic wave method Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G06T5/77—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30196—Human being; Person
- G06T2207/30201—Face
Abstract
The invention discloses the processing method and processing device of a kind of facial image, this processing method comprises the following steps: obtaining the highlight area of facial image, described highlight area includes multiple boundary pixel point；The pixel value of the pixel that skin color probability is maximum in acquisition predeterminable area, wherein said predeterminable area is the region of boundary pixel point preset value described in distance one；The pixel value of the pixel according to described skin color probability maximum is optimized process to the pixel value of described boundary pixel point, to obtain the optimization pixel value of described boundary pixel point；Obtain according to described optimization pixel value and corresponding with described highlight area initially repair figure；According to described initial repairing figure, described highlight area is carried out repair process.The present invention has the repairing effect beneficially improving facial image.
Description
Technical field
The invention belongs to communication technical field, particularly relate to the processing method and processing device of a kind of facial image.
Background technology
In shooting process, owing to face is more oily or due to reasons such as light, the photo that can cause shooting out
Some region of face can present the effect of Gao Guang, affects user and normally watches photo, causes bad Consumer's Experience.
The method that there is a lot of middle Gao Guang removing facial image in prior art, but, its Gao Guang extracted
Region is frequently not very accurate, especially highlight area and the pixel of the intersection of normal region extraction the most no
Accurately, cause the repairing figure effect being subsequently generated poor, do not reach predetermined demand with the matching degree of artwork.
Therefore, how to improve in face image processing the technical problem of the degree of accuracy of extraction for highlight area, need
Urgently have been resolved.
Summary of the invention
The embodiment of the present invention provides the processing method and processing device of a kind of facial image, to solve in existing face image processing
For the technical problem that the degree of accuracy of the extraction of highlight area is the highest.
The embodiment of the present invention provides the processing method of a kind of facial image, comprises the following steps:
Obtaining the highlight area of facial image, described highlight area includes multiple boundary pixel point；
The pixel value of the pixel that skin color probability is maximum in acquisition predeterminable area, wherein said predeterminable area is distance one institute
State the region of boundary pixel point preset value；
The pixel value of described boundary pixel point is optimized by the pixel value of the pixel according to described skin color probability maximum
Process, to obtain the optimization pixel value of described boundary pixel point；
Obtain according to described optimization pixel value and corresponding with described highlight area initially repair figure；
According to described initial repairing figure, described highlight area is carried out repair process.
The embodiment of the present invention additionally provides the processing means of a kind of facial image, including:
First acquisition module, for obtaining the highlight area of facial image, described highlight area includes multiple boundary pixel
Point；
Second acquisition module, in obtaining predeterminable area, the pixel value of the pixel that skin color probability is maximum, wherein said
Predeterminable area is the region of boundary pixel point preset value described in distance one；
Optimize module, for the pixel value of the pixel maximum according to the described skin color probability picture to described boundary pixel point
Element value is optimized process, to obtain the optimization pixel value of described boundary pixel point；
3rd acquisition module, for obtaining the initial repairing corresponding with described highlight area according to described optimization pixel value
Figure；
Repair module, for carrying out repair process according to described initial repairing figure to described highlight area.
The embodiment of the present invention is by obtaining the highlight area of facial image；The picture that in acquisition predeterminable area, skin color probability is maximum
The pixel value of vegetarian refreshments, wherein said predeterminable area is the region of boundary pixel point preset value described in distance one；According to the described colour of skin
The pixel value of the pixel of maximum probability is optimized process to the pixel value of described boundary pixel point, to obtain described border picture
The optimization pixel value of vegetarian refreshments；Obtain according to described optimization pixel value and corresponding with described highlight area initially repair figure；According to institute
State initial repairing figure and described highlight area is carried out repair process, thus complete facial image is removed the operation of Gao Guang, and
And owing to, during extracting highlight area, have employed the pixel value of the maximum pixel of skin color probability to described boundary pixel
The pixel value of point is optimized process so that the boundary pixel point of highlight area is closer to the pixel value of normal region, has
It is beneficial to improve the degree of accuracy that highlight area is extracted so that initially repair figure and this facial image according to what this optimization pixel value generated
Normal region more agree with, be conducive to improve remove Gao Guang repairing effect.
Accompanying drawing explanation
For the technical scheme being illustrated more clearly that in the embodiment of the present invention, in embodiment being described below required for make
Accompanying drawing be briefly described, it should be apparent that, below describe in accompanying drawing be only some embodiments of the present invention, for
From the point of view of those skilled in the art, on the premise of not paying creative work, it is also possible to obtain the attached of other according to these accompanying drawings
Figure.
Fig. 1 is the flow chart of the processing method of the facial image that the embodiment of the present invention provides；
Fig. 2 is another flow chart of the processing method of the facial image that the embodiment of the present invention provides；
Fig. 3 is the structural representation of the processing means of the facial image that the embodiment of the present invention provides；
Fig. 4 is the structural representation of the first acquisition module of the processing means of the facial image that the embodiment of the present invention provides；
Fig. 5 is the structural representation of the repair module of the processing means of the facial image that the embodiment of the present invention provides；
Fig. 6 is the structural representation of a kind of terminal that the embodiment of the present invention provides.
Detailed description of the invention
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
Describe, it is clear that described embodiment is only a part of embodiment of the present invention rather than whole embodiments wholely.Based on
Embodiment in the present invention, the every other enforcement that those skilled in the art are obtained under not making creative work premise
Example, broadly falls into the scope of protection of the invention.
The present invention provides the processing method and processing device of a kind of facial image.
Wherein, the processing means of this facial image can integrated in the terminal, such as mobile phone, panel computer etc., also
Can integrated in the server.Such as, user uses mobile phone to have taken one and is then stored in photograph album from taking pictures, mobile phone from
Get this auto heterodyne in this photograph album and shine into row repair process.First, first will obtain this from photograph album and certainly take pictures, then to from this certainly
Take pictures and extract highlight area, then the pixel value of the boundary pixel point of this highlight area is optimized, obtain optimizing pixel
Value；Obtain corresponding with highlight area initially repair figure, finally according to initial repairing figure to highlight area according to optimizing pixel value
Carry out repair process；Thus complete this from the reparation of the removal Gao Guang taken pictures.
It is described in detail individually below.It should be noted that, the sequence number of following example is not as the most suitable to embodiment
The restriction of sequence.
Embodiment one,
In the present embodiment, it is provided that the processing method of a kind of facial image, comprise the following steps: obtain the height of facial image
Light region, described highlight area includes multiple boundary pixel point；The picture of the pixel that skin color probability is maximum in acquisition predeterminable area
Element value, wherein said predeterminable area is the region of boundary pixel point preset value described in distance one；Maximum according to described skin color probability
The pixel value of pixel the pixel value of described boundary pixel point is optimized process, to obtain the excellent of described boundary pixel point
Change pixel value；Obtain according to described optimization pixel value and corresponding with described highlight area initially repair figure；Initially repair according to described
Complement carries out repair process to described highlight area.
As it is shown in figure 1, with mobile terminal as subject of implementation in the present embodiment, the processing method of this facial image includes following
Step:
S101, the highlight area of acquisition facial image, described highlight area includes multiple boundary pixel point；
Wherein, the plurality of boundary pixel point forms the border of this highlight area.In specific implementation process, can be according to people
The face image luminance component L in HSV (Hue, Saturation, Value) space and saturation component V realize extracting for
The extraction of highlight area.Certainly, it is not limited to this, it would however also be possible to employ other extraction algorithm, extracts from this facial image
Go out highlight area.
S102, obtain the pixel value of the pixel that skin color probability is maximum in predeterminable area, wherein said predeterminable area be away from
From the region of boundary pixel point preset value described in.
Wherein, skin color probability is the probability that this pixel belongs to skin area.
In specific implementation process, first, calculate each pixel of facial image according to skin color detection algorithm to belong to
The skin color probability P of face skin area.Wherein, this skin color detection algorithm is algorithm, and it is mainly by detecting this pixel
Pixel value, belongs to the skin color probability P of face skin area calculating this pixel.
Then, obtain the skin color probability P of each pixel in the predeterminable area of each boundary pixel point respectively, and therefrom
Filter out the skin color probability P of the maximum pixel of skin color probability.Wherein, this predeterminable area is pre-apart from corresponding boundary pixel point
If the region of value, specifically, in the present embodiment, this predeterminable area is the predetermined neighborhood of this boundary pixel point.
The pixel value of described boundary pixel point is carried out by S103, pixel value according to the maximum pixel of described skin color probability
Optimization processes, to obtain the optimization pixel value of described boundary pixel point.
Wherein, the mode that the pixel value of described boundary pixel point is optimized process can have multiple, for example, it is possible to such as
Under:
In specific implementation process, if the skin color probability of the pixel of described skin color probability maximum is less than the first preset value,
Then using the pixel value of described boundary pixel point as the optimization pixel value of described boundary pixel point.If described skin color probability maximum
The skin color probability of pixel is more than or equal to the first preset value, then using the pixel value of the maximum pixel of described skin color probability as
The optimization pixel value of described boundary pixel point.Wherein, this first preset value can be configured according to the demand of reality application, than
As, this first preset value can be 0.7.
S104, obtain according to described optimization pixel value and corresponding with described highlight area initially repair figure.
In specific implementation process, the optimization pixel value to all boundary pixel point is used to carry out bilinearity difference process, from
And supplemented by the pixel value of each pixel in the region within border complete, and then obtain this initial repairing figure.
S105, according to described initial repairing figure, described highlight area is carried out repair process.
In specific implementation process, directly this initial repairing figure can be carried out with the artwork of facial image mixing and superpose place
Reason, that is to say the highlight area going to replace artwork with this initial repairing figure, thus completes repair process.Can also take to optimize and calculate
Method is optimized process to this initial repairing figure, and the repairing figure after using optimization to process the most again carries out mixing and superposes place with artwork
Reason, thus complete repair process.
From the foregoing, it will be observed that the processing method of the facial image of the present embodiment offer is by obtaining the highlight area of facial image,
Described highlight area includes multiple boundary pixel point；The pixel value of the pixel that skin color probability is maximum in acquisition predeterminable area, its
Described in predeterminable area be the region of boundary pixel point preset value described in distance one；According to the pixel that described skin color probability is maximum
Pixel value the pixel value of described boundary pixel point is optimized process, to obtain the optimization pixel of described boundary pixel point
Value；Obtain according to described optimization pixel value and corresponding with described highlight area initially repair figure；Right according to described initial repairing figure
Described highlight area carries out repair process, thus completes to remove facial image the operation of Gao Guang, and owing to extracting height
During light region, the pixel value of described boundary pixel point is carried out by the pixel value that have employed the maximum pixel of skin color probability
Optimization processes so that the boundary pixel point of highlight area is closer to the pixel value of normal region so that according to this optimization picture
The initial repairing figure that element value generates more agrees with the normal region of this facial image, is conducive to improving the reparation effect removing Gao Guang
Really.
Embodiment two,
In the present embodiment, it is provided that the processing method of a kind of facial image, comprise the following steps: obtain the height of facial image
Light region, described highlight area includes multiple boundary pixel point；The picture of the pixel that skin color probability is maximum in acquisition predeterminable area
Element value, wherein said predeterminable area is the region of boundary pixel point preset value described in distance one；Maximum according to described skin color probability
The pixel value of pixel the pixel value of described boundary pixel point is optimized process, to obtain the excellent of described boundary pixel point
Change pixel value；Obtain according to described optimization pixel value and corresponding with described highlight area initially repair figure；Initially repair according to described
Complement carries out repair process to described highlight area.
As in figure 2 it is shown, with subject of implementation for mobile terminal as subject of implementation, the processing method of this facial image includes following
Step:
S201, the highlight area of acquisition facial image, described highlight area includes multiple boundary pixel point；
Wherein, the plurality of boundary pixel point forms the border of this highlight area.Can be according to facial image in HSV space
Luminance component L and saturation component V realizes extracting the extraction for highlight area.Certainly, it is not limited to this, it is also possible to
Use existing extraction algorithm, from this facial image, extract highlight area.
In specific implementation process, this step S201 includes following sub-step:
S2011, obtain pending facial image.
Such as, mobile terminal can obtain the facial image of pending device from local photograph album or network.
Wherein, depending on the form of this pending facial image can be according to the demand of reality application, such as, this is pending
Facial image be RGB (red, green, blue) coloured image.
S2012, this facial image is carried out place to go noise processed.
In order to reduce noise spot, impact, the facial image that reply obtains are removed noise processed.
Wherein, the mode removing noise processed can have multiple, such as, in the present embodiment, can use bilateral filtering
Device carries out denoising to facial image.
S2013, this facial image is carried out top cap conversion process.
Exist in specific implementation process, use the conversion of white top cap to increase image highlight area and the contrast of non-highlight area
Degree, in order to the extraction operation of follow-up highlight area.
S2014, this facial image is transformed into HSV space, to obtain the bright of each pixel of this facial image respectively
Degree component L and saturation component S.
Owing to facial image is not easy to analyze its brightness and saturation, therefore, in this reality in the data of RGB color space
Execute in example select facial image by RGB color space be transformed into HSV space be analyzed process.
S2015, obtain the plurality of pixel according to the luminance component L and saturation component S of each described pixel
Average M of luminance component L1And variance V1, average M of saturation component S2And variance V2。
Wherein, the present embodiment uses the luminance component L and saturation component S of this facial image are carried out rectangular histogram system
Meter, thus calculate average and the variance of the luminance component of all pixels of this facial image, the average of luminance component respectively
And variance.
S2016, average M according to the luminance component of the plurality of pixel1And variance V1, the plurality of pixel
Average M of saturation component2And variance V2, the luminance component L of each described pixel and saturation component S, extract institute
State the highlight area of facial image.
Wherein, in specific implementation process, first according to formula S T=M2-1.5V2Calculate saturation threshold value ST, Yi Jigen
Luminance threshold LT is calculated according to formula LT=M 1+V1.Then, according to formula Q=(L/S)/(LT/ST), this pixel is calculated
Belong to the probability Q-value of highlight area.When this Q-value is more than 1, it is judged that this pixel is the pixel of highlight area, when this Q-value
During less than or equal to 1, it is judged that this pixel is the pixel of non-highlight area, thus extract of this facial image or each
Individual highlight area.
S202, obtain the pixel value of the pixel that skin color probability is maximum in predeterminable area, wherein, described predeterminable area be away from
From the region of boundary pixel point preset value described in；
In specific implementation process, first, calculating each pixel of facial image according to skin color detection algorithm is people
The skin color probability P of face skin.Wherein, this skin color detection algorithm is mainly by detecting the pixel value of this pixel, to draw
One this pixel belongs to the skin color probability P of people's face skin.
Then, obtain the skin color probability PP of each pixel in the predeterminable area of each boundary pixel point respectively, and from
In filter out the skin color probability PP of the maximum pixel of skin color probability.Wherein, the boundary pixel that during this predeterminable area, distance is corresponding
The region of some preset value, specifically, in the present embodiment, this predeterminable area is the predetermined neighborhood of this boundary pixel point.
The pixel value of described boundary pixel point is carried out by S203, pixel value according to the maximum pixel of described skin color probability
Optimization processes, to obtain the optimization pixel value of described boundary pixel point.
In specific implementation process, if the skin color probability of the pixel of described skin color probability maximum is less than the first preset value,
Then using the pixel value of described boundary pixel point as the optimization pixel value of described boundary pixel point；If described skin color probability maximum
The skin color probability of pixel is more than or equal to the first preset value, then using the pixel value of the maximum pixel of described skin color probability as
The optimization pixel value of described boundary pixel point.Can be configured according to the demand of reality application, such as, this first preset value is
0.7。
S204, obtain according to described optimization pixel value and corresponding with described highlight area initially repair figure.
In specific implementation process, the optimization pixel value to all boundary pixel point is used to carry out bilinearity difference process, from
And supplemented by the pixel value of each pixel in the region within border complete, and then obtain this initial repairing figure.
S205, according to described initial repairing figure, described highlight area is carried out repair process.
Wherein it is possible to take optimized algorithm that this initial repairing figure is optimized process, after using optimization to process the most again
Repairing figure carry out mixing overlap-add procedure with artwork, thus complete repair process.
Wherein, in specific implementation process, this step S205 includes following sub-step:
S2051, initial repair figure according to the pixel value of the pixel in preset range around described highlight area to described
Do Gaussian Blur to process, to obtain smooth repairing figure.Wherein, around this highlight area, preset range may refer to apart from this Gao Guang
In the range of the pixel of the boundary pixel point predetermined number in region, such as 100 or 200 pixels.This Gaussian Blur
Processing and use Gaussian distribution formula to process, its concrete principle does not repeats.This initial repairing figure is carried out Gaussian Blur process
So that the transition of the smooth pixel repaired around figure and highlight area is more smooth, be conducive to raising that highlight area is repaiied
The effect mended.
S2052, the texture information of acquisition facial image.Wherein, in specific implementation process, the texture information of this facial image
The second dervative using this facial image carrys out quantization means, and it uses formula Δ2F (x, y)=δ2f/δx2+δ2f/δy2Obtain, its
In, x and y represents abscissa and the vertical coordinate of corresponding pixel points respectively, and f represents the pixel value of this pixel.
S2053, according to described texture information, described smooth repairing figure is carried out texture overlap-add procedure, repair obtaining target
Figure.In specific implementation process, the computational methods of employing are that smooth repairing figure is multiplied by the second dervative Δ of this facial image2F (x,
Y), this target repairing figure can i.e. be obtained.
S2054, according to described target repairing figure, described highlight area is carried out repair process.In specific implementation process, will
This target repairing figure carries out mixing and superposes with this artwork, that is to say to use and goes this target repairing figure to replace the specular in artwork
Territory, the facial image after i.e. can being repaired.
From the foregoing, it will be observed that the processing method of the facial image of the present embodiment offer is by obtaining the highlight area of facial image,
Described highlight area includes multiple boundary pixel point；The pixel value of the pixel that skin color probability is maximum in acquisition predeterminable area, its
Described in predeterminable area be the region of boundary pixel point preset value described in distance one；According to the pixel that described skin color probability is maximum
Pixel value the pixel value of described boundary pixel point is optimized process, to obtain the optimization pixel of described boundary pixel point
Value；Obtain according to described optimization pixel value and corresponding with described highlight area initially repair figure；Right according to described initial repairing figure
Described highlight area carries out repair process, thus completes to remove facial image the operation of Gao Guang, and owing to extracting height
During light region, the pixel value of described boundary pixel point is carried out by the pixel value that have employed the maximum pixel of skin color probability
Optimization processes so that the boundary pixel point of highlight area is closer to the pixel value of normal region so that according to this optimization picture
The initial repairing figure that element value generates more agrees with the normal region of this facial image, is conducive to improving follow-up removal Gao Guang's
Repairing effect；Further, owing to this initial repairing figure to be carried out successively Gaussian Blur process and texture overlap-add operation,
Thus obtaining target repairing figure, this target repairs figure relative to initial figure of repairing closer to the truth of facial image, has
It is beneficial to improve repairing effect further.
Embodiment three,
In order to preferably realize said method, present invention also offers the processing means of a kind of facial image, such as Fig. 3 institute
Showing, the processing means of this facial image includes: first acquisition module the 301, second acquisition module 302, optimization module the 303, the 3rd
Acquisition module 304 and repair module 305.
Wherein, this first acquisition module 301 is for obtaining the highlight area of facial image, and described highlight area includes multiple
Boundary pixel point.
Wherein, as shown in Figure 4, this first acquisition module 301 includes:
Acquiring unit 3011, for obtaining pending facial image, this pending facial image is RGB color figure
Picture.Wherein, this pending facial image can be that this mobile terminal obtains pending device from local photograph album or network
Facial image.
Denoising unit 3012, for carrying out place to go noise processed to this facial image.In order to reduce noise spot to impact, must
The facial image obtained must be removed noise processed.In the present embodiment, use two-sided filter that facial image is carried out denoising
Process.
Top cap converter unit 3013, for carrying out top cap conversion process to this facial image.Specifically, top cap converter unit
The conversion of white top cap is used to increase image highlight area and the contrast of non-highlight area, in order to carrying of follow-up highlight area
Extract operation.
Converting unit 3014, for being transformed into HSV space by this facial image, to obtain each of this facial image respectively
The luminance component L and saturation component S of pixel.Owing to facial image is not easy to analyze it in the data of RGB color space
Brightness and saturation, therefore, select that facial image RGB color space is transformed into HSV space in the present embodiment and carry out point
Analysis processes.
Computing unit 3015, obtains described many for the luminance component L and saturation component S according to each described pixel
Average M of the luminance component L of individual pixel1And variance V1, average M of saturation component S2And variance V2.Wherein, this reality
Execute example uses and the luminance component L and saturation component S of this facial image are carried out statistics with histogram, thus calculate respectively
The average of the luminance component of all pixels of this facial image and variance, the average of luminance component and variance.
Extraction unit 3016, for average M of the luminance component according to the plurality of pixel1And variance V1, described many
Average M of the saturation component of individual pixel2And variance V2, the luminance component L of each described pixel and saturation component
S, extracts the highlight area of described facial image.Wherein, in specific implementation process, first according to formula S T=M2-1.5V2Meter
Calculate saturation threshold value ST, and according to formula LT=M1+V1Calculate luminance threshold LT.Then, according to formula Q=(L/S)/
(LT/ST), calculate this pixel and belong to the probability Q-value of highlight area.When this Q-value is more than 1, it is judged that this pixel is high
The pixel in light region, when this Q-value is less than or equal to 1, it is judged that this pixel is the pixel of non-highlight area, thus extracts
Go out the highlight area of this facial image.
This second acquisition module 302 pixel value of the pixel that skin color probability is maximum in obtaining predeterminable area, wherein
Described predeterminable area is the region of boundary pixel point preset value described in distance one.
This optimization module 303 is used for the pixel value of the pixel maximum according to described skin color probability to described boundary pixel point
Pixel value be optimized process, to obtain the optimization pixel value of described boundary pixel point.Wherein, if described skin color probability is maximum
The skin color probability of pixel less than the first preset value, then using the pixel value of described boundary pixel point as described boundary pixel point
Optimization pixel value.If the skin color probability of the pixel that described skin color probability is maximum is more than or equal to the first preset value, then with institute
State the pixel value optimization pixel value as described boundary pixel point of the maximum pixel of skin color probability.Wherein, this first preset
Value can be 0.7.
3rd acquisition module 304 is for obtaining initially repair corresponding with described highlight area according to described optimization pixel value
Complement.Specifically, the 3rd acquisition module 304 uses the optimization pixel value to all boundary pixel point to carry out at bilinearity difference
Reason, thus the pixel value of each pixel in the region within border is supplemented complete, and then obtain this initial repairing figure.
Repair module 305 is for carrying out repair process according to described initial repairing figure to described highlight area.Wherein, such as figure
Shown in 5, this repair module 305 includes:
Gauss processing unit 3051, for the pixel value pair according to the pixel in preset range around described highlight area
Described initial repairing figure does Gaussian Blur and processes, to obtain smooth repairing figure.Wherein, around this highlight area, preset range is permissible
Refer in the range of the pixel of the boundary pixel point predetermined number of this highlight area, such as 100 or 200 pixels
Point.This Gaussian Blur processes and uses Gaussian distribution formula to process, and its concrete principle does not repeats.This initial repairing figure is carried out
So that the transition of the smooth pixel repaired around figure and highlight area is more smooth, beneficially after Gaussian Blur processes
Improve the effect that highlight area is repaired.
Texture information acquiring unit 3052, for obtaining the texture information of facial image.Wherein, in specific implementation process,
The texture information of this facial image uses the second dervative of this facial image to quantify, and it uses formula Δ2F (x, y)=δ2f/δ
x2+δ2f/δy2Obtaining, wherein, x and y represents abscissa and the vertical coordinate of corresponding pixel points respectively, and f represents the pixel of this pixel
Value.
Superpositing unit 3053, for described smooth repairing figure being carried out texture overlap-add procedure according to described texture information, with
Obtain target and repair figure.In specific implementation process, the computational methods of employing are that smooth repairing figure is multiplied by the two of this facial image
Order derivative Δ2(x y), i.e. can obtain this target repairing figure to f.
Repair unit 3054, for described highlight area being carried out repair process according to described target repairing figure.
From the foregoing, it will be observed that processing means first acquisition module of the facial image of the present embodiment offer is by obtaining facial image
Highlight area, described highlight area includes multiple boundary pixel point；Second acquisition module obtains skin color probability in predeterminable area
The pixel value of maximum pixel, wherein said predeterminable area is the region of boundary pixel point preset value described in distance one；Optimize
Module is optimized process according to the pixel value of the pixel of described skin color probability maximum to the pixel value of described boundary pixel point,
To obtain the optimization pixel value of described boundary pixel point；3rd acquisition module obtains and described Gao Guang according to described optimization pixel value
What region was corresponding initially repairs figure；Repair module carries out repair process according to described initial repairing figure to described highlight area, from
And complete facial image is removed the operation of Gao Guang, and owing to extracting during highlight area, the 3rd acquisition module
The pixel value that have employed the maximum pixel of skin color probability is optimized process to the pixel value of described boundary pixel point so that high
The boundary pixel point in light region is closer to the pixel value of normal region so that initially repair according to what this optimization pixel value generated
Complement more agrees with the normal region of this facial image, is conducive to improving the repairing effect of follow-up removal Gao Guang；Further
Ground, processes and texture overlap-add operation owing to repair module has carried out Gaussian Blur successively to this initial repairing figure, thus obtains
Target repairs figure, and this target repairs figure relative to initial figure of repairing closer to the truth of facial image, is conducive to into one
Step improves repairing effect.
The embodiment of the present invention provides, such as computer, panel computer, the mobile phone with touch function etc., this people
The processing means of face image belongs to same design, at this facial image with the processing method of the facial image in foregoing embodiments
Can run the either method provided in the processing method embodiment of this facial image in processing means, it is detailed that it implements process
Seeing the processing method embodiment of this facial image, here is omitted.
Embodiment four,
Accordingly, the embodiment of the present invention also provides for a kind of terminal, as shown in Figure 6, this terminal can include radio frequency (RF,
Radio Frequency) circuit 601, include the memorizer 602 of one or more computer-readable recording mediums, defeated
Enter unit 603, display unit 604, sensor 605, voicefrequency circuit 606, Wireless Fidelity (WiFi, Wireless Fidelity)
Module 607, include one or more than one processes the parts such as the processor 608 of core and power supply 609.This area skill
Art personnel are appreciated that the terminal structure shown in Fig. 6 is not intended that the restriction to terminal, can include more more or more than diagram
Few parts, or combine some parts, or different parts are arranged.Wherein:
RF circuit 601 can be used for receiving and sending messages or in communication process, the reception of signal and transmission, especially, by base station
After downlink information receives, transfer to one or more than one processor 608 processes；It addition, be sent to relating to up data
Base station.Generally, RF circuit 601 includes but not limited to antenna, at least one amplifier, tuner, one or more agitator, use
Family identity module (SIM, SubscriberIdentity Module) card, transceiver, bonder, low-noise amplifier (LNA,
LowNoiseAmplifier), duplexer etc..Additionally, RF circuit 601 can also be by radio communication and network and other equipment
Communication.Described radio communication can use arbitrary communication standard or agreement, include but not limited to global system for mobile communications (GSM,
Global System ofMobile communication), general packet radio service (GPRS, General Packet
Radio Service), CDMA (CDMA, Code Division Multiple Access), WCDMA
(WCDMA, Wideband Code Division MultipleAccess), Long Term Evolution (LTE, Long Term
Evolution), Email, Short Message Service (SMS, Short Messaging Service) etc..
Memorizer 602 can be used for storing software program and module, and processor 608 is stored in memorizer 602 by operation
Software program and module, thus perform various function application and data process.Memorizer 602 can mainly include storing journey
Sequence district and storage data field, wherein, storage program area can store the application program (ratio needed for operating system, at least one function
Such as sound-playing function, image player function etc.) etc.；Storage data field can store the data that the use according to terminal is created
(such as voice data, phone directory etc.) etc..Additionally, memorizer 602 can include high-speed random access memory, it is also possible to include
Nonvolatile memory, for example, at least one disk memory, flush memory device or other volatile solid-state parts.Phase
Ying Di, memorizer 602 can also include Memory Controller, to provide processor 608 and input block 603 to memorizer 602
Access.
Input block 603 can be used for receiving numeral or the character information of input, and produces and user setup and function
Control relevant keyboard, mouse, action bars, optics or the input of trace ball signal.Specifically, a specific embodiment
In, input block 603 can include Touch sensitive surface and other input equipments.Touch sensitive surface, also referred to as touches display screen or touches
Control plate, can collect user thereon or neighbouring touch operation (such as user use any applicable object such as finger, stylus or
Adnexa operation on Touch sensitive surface or near Touch sensitive surface), and connect dress accordingly according to formula set in advance driving
Put.Optionally, Touch sensitive surface can include touch detecting apparatus and two parts of touch controller.Wherein, touch detecting apparatus inspection
Survey the touch orientation of user, and detect the signal that touch operation brings, transmit a signal to touch controller；Touch controller from
Receive touch information on touch detecting apparatus, and be converted into contact coordinate, then give processor 608, and can reception process
Order that device 608 is sent also is performed.Furthermore, it is possible to use resistance-type, condenser type, infrared ray and surface acoustic wave etc. multiple
Type realizes Touch sensitive surface.Except Touch sensitive surface, input block 603 can also include other input equipments.Specifically, other are defeated
Enter equipment and can include but not limited to physical keyboard, function key (such as volume control button, switch key etc.), trace ball, Mus
One or more in mark, action bars etc..
Display unit 604 can be used for the various of the information that inputted by user of display or the information being supplied to user and terminal
Graphical user interface, these graphical user interface can be made up of figure, text, icon, video and its combination in any.Display
Unit 604 can include display floater, optionally, can use liquid crystal display (LCD, Liquid Crystal Display),
The forms such as Organic Light Emitting Diode (OLED, Organic Light-Emitting Diode) configure display floater.Further
, Touch sensitive surface can cover display floater, when Touch sensitive surface detects thereon or after neighbouring touch operation, sends process to
Device 608, to determine the type of touch event, provides corresponding with preprocessor 608 according to the type of touch event on a display panel
Visual output.Although in figure 6, Touch sensitive surface and display floater are to realize input and input as two independent parts
Function, but in some embodiments it is possible to by integrated to Touch sensitive surface and display floater and realize input and output function.
Terminal may also include at least one sensor 605, such as optical sensor, motion sensor and other sensors.
Specifically, optical sensor can include ambient light sensor and proximity transducer, and wherein, ambient light sensor can be according to ambient light
Light and shade regulate the brightness of display floater, proximity transducer can cut out display floater and/or the back of the body when terminal moves in one's ear
Light.As the one of motion sensor, Gravity accelerometer can detect (generally three axles) acceleration in all directions
Size, can detect that size and the direction of gravity time static, can be used for identify mobile phone attitude application (such as horizontal/vertical screen switching,
Dependent game, magnetometer pose calibrating), Vibration identification correlation function (such as pedometer, percussion) etc.；Can also configure as terminal
Gyroscope, barometer, drimeter, thermometer, other sensors such as infrared ray sensor, do not repeat them here.
Voicefrequency circuit 606, speaker, microphone can provide the audio interface between user and terminal.Voicefrequency circuit 606 can
The signal of telecommunication after the voice data conversion that will receive, is transferred to speaker, speaker be converted to acoustical signal output；Another
Aspect, the acoustical signal of collection is converted to the signal of telecommunication by microphone, voicefrequency circuit 606 be converted to voice data after receiving, then
After voice data output processor 608 is processed, through RF circuit 601 to be sent to such as another terminal, or by voice data
Output is to memorizer 602 to process further.Voicefrequency circuit 606 is also possible that earphone jack, with provide peripheral hardware earphone with
The communication of terminal.
WiFi belongs to short range wireless transmission technology, and terminal can help user's transceiver electronics postal by WiFi module 607
Part, browsing webpage and access streaming video etc., it has provided the user wireless broadband internet and has accessed.Although Fig. 6 shows
WiFi module 607, but it is understood that, it is also not belonging to must be configured into of terminal, can not change as required completely
Omit in the scope of the essence becoming invention.
Processor 608 is the control centre of terminal, utilizes various interface and the various piece of the whole mobile phone of connection, logical
Cross operation or perform to be stored in the software program in memorizer 602 and/or module, and calling and be stored in memorizer 602
Data, perform the various functions of terminal and process data, thus mobile phone is carried out integral monitoring.Optionally, processor 608 can wrap
Include one or more process core；Preferably, processor 608 can integrated application processor and modem processor, wherein, should
Mainly process operating system, user interface and application program etc. with processor, modem processor mainly processes radio communication.
It is understood that above-mentioned modem processor can not also be integrated in processor 608.
Terminal also includes the power supply 609 (such as battery) powered to all parts, it is preferred that power supply can pass through power supply pipe
Reason system is logically contiguous with processor 608, thus realizes management charging, electric discharge and power managed by power-supply management system
Etc. function.Power supply 609 can also include one or more direct current or alternating current power supply, recharging system, power failure inspection
Slowdown monitoring circuit, power supply changeover device or the random component such as inverter, power supply status indicator.
Although not shown, terminal can also include photographic head, bluetooth module etc., does not repeats them here.Specifically in this enforcement
In example, the processor 608 in terminal can be according to following instruction, by corresponding for the process of one or more application program
Executable file is loaded in memorizer 602, and is run storage application program in the memory 602 by processor 608, from
And realize various function:
Obtaining the highlight area of facial image, described highlight area includes multiple boundary pixel point；
The pixel value of the pixel that skin color probability is maximum in acquisition predeterminable area, wherein said predeterminable area is distance one institute
State the region of boundary pixel point preset value；
The pixel value of described boundary pixel point is optimized by the pixel value of the pixel according to described skin color probability maximum
Process, to obtain the optimization pixel value of described boundary pixel point；
Obtain according to described optimization pixel value and corresponding with described highlight area initially repair figure；According to described initial repairing
Figure carries out repair process to described highlight area.
From the foregoing, it will be observed that this terminal runs storage application program in the memory 602 by processor 608, thus realize
Obtaining the highlight area of facial image, described highlight area includes multiple boundary pixel point；Obtain skin color probability in predeterminable area
The pixel value of maximum pixel, wherein said predeterminable area is the region of boundary pixel point preset value described in distance one；According to
The pixel value of the pixel that described skin color probability is maximum is optimized process to the pixel value of described boundary pixel point, to obtain
State the optimization pixel value of boundary pixel point；The initial repairing corresponding with described highlight area is obtained according to described optimization pixel value
Figure；According to described initial repairing figure, described highlight area is carried out repair process；And then complete the highlight area to facial image
Reparation；Owing to, during extracting highlight area, have employed the pixel value of the maximum pixel of skin color probability to described limit
The pixel value of boundary's pixel is optimized process so that the boundary pixel point of highlight area is closer to the pixel of normal region
Value so that the initial repairing figure generated according to this optimization pixel value more agrees with the normal region of this facial image, is conducive to
Improve the repairing effect of follow-up removal Gao Guang.It should be noted that for the processing method of facial image of the present invention, ability
Territory common test personnel are appreciated that all or part of flow process of the processing method realizing this facial image of the embodiment of the present invention, are
Can be completed by the hardware that computer program controls to be correlated with, this computer program can be stored in an embodied on computer readable and deposit
In storage media, as being stored in the memorizer of terminal, and performed, in the process of implementation by least one processor in this terminal
The flow process of the embodiment of the display packing such as this navigation information can be included.Wherein, the storage medium being somebody's turn to do can be magnetic disc, CD, only
Read memorizer (ROM, Read Only Memory), random access memory (RAM, Random Access Memory) etc..
For the processing means of the facial image of the embodiment of the present invention, its each functional module can be integrated in a process
In chip, it is also possible to be that modules is individually physically present, it is also possible to two or more modules are integrated in a module.
Above-mentioned integrated module both can realize to use the form of hardware, it would however also be possible to employ the form of software function module realizes.This collection
If the module become is using the form realization of software function module and as independent production marketing or use, it is also possible to be stored in
In one computer read/write memory medium, this storage medium is such as read only memory, disk or CD etc..
The processing method and processing device of a kind of facial image provided the embodiment of the present invention above is described in detail,
Principle and the embodiment of the present invention are set forth by specific case used herein, and the explanation of above example is simply used
In helping to understand method and the core concept thereof of the present invention；Simultaneously for those skilled in the art, according to the think of of the present invention
Thinking, the most all will change, in sum, it is right that this specification content should not be construed as
The restriction of the present invention.
Claims (12)
1. the processing method of a facial image, it is characterised in that comprise the following steps:
Obtaining the highlight area of facial image, described highlight area includes multiple boundary pixel point；
The pixel value of the pixel that skin color probability is maximum in acquisition predeterminable area, wherein, described predeterminable area is described in distance one
The region of boundary pixel point preset value；
The pixel value of the pixel according to described skin color probability maximum is optimized process to the pixel value of described boundary pixel point,
To obtain the optimization pixel value of described boundary pixel point；
Obtain according to described optimization pixel value and corresponding with described highlight area initially repair figure；
According to described initial repairing figure, described highlight area is carried out repair process.
The processing method of facial image the most according to claim 1, it is characterised in that described according to described skin color probability
The pixel value of big pixel is optimized process to the pixel value of described boundary pixel point, to obtain described boundary pixel point
The step optimizing pixel value includes:
If the skin color probability of the pixel that described skin color probability is maximum is less than the first preset value, then with the picture of described boundary pixel point
Element value is as the optimization pixel value of described boundary pixel point；
If the skin color probability of the pixel that described skin color probability is maximum is more than or equal to the first preset value, then with described skin color probability
The pixel value of maximum pixel is as the optimization pixel value of described boundary pixel point.
The processing method of facial image the most according to claim 1, it is characterised in that described according to described optimization pixel value
The step obtaining the initial repairing figure corresponding with described highlight area includes:
The optimization pixel value of the plurality of boundary pixel point is made bilinear interpolation process, corresponding with described highlight area to obtain
Initially repair figure.
The processing method of facial image the most according to claim 1, it is characterised in that described according to described initial repairing figure
The step that described highlight area carries out repair process includes:
Described initial repairing figure is done Gaussian Blur by the pixel value according to the pixel in preset range around described highlight area
Process, to obtain smooth repairing figure；
Obtain the texture information of described facial image；
According to described texture information, described smooth repairing figure is carried out texture overlap-add procedure, to obtain target repairing figure；
According to described target repairing figure, described highlight area is carried out repair process.
5. according to the processing method of the facial image described in any one of Claims 1-4, it is characterised in that described acquisition face
The step of the highlight area of image includes:
The luminance component of each pixel according to facial image and saturation component obtain each pixel of facial image
The average of luminance component and variance, the average of saturation component and variance；
Average according to described luminance component and variance, the average of described saturation component and variance, each described pixel
The luminance component of point and saturation component, extract the highlight area of described facial image.
6. according to the processing method of the facial image described in any one of Claims 1-4, it is characterised in that described acquisition face
Before the step of the highlight area of image further comprising the steps of:
Described facial image is carried out top cap conversion process to strengthen the contrast of described facial image.
7. the processing means of a facial image, it is characterised in that including:
First acquisition module, for obtaining the highlight area of facial image, described highlight area includes multiple boundary pixel point；
Second acquisition module, the pixel value of the pixel that skin color probability is maximum in obtaining predeterminable area, wherein, described default
Region is the region of boundary pixel point preset value described in distance one；
Optimize module, for the pixel value of the pixel maximum according to the described skin color probability pixel value to described boundary pixel point
It is optimized process, to obtain the optimization pixel value of described boundary pixel point；
3rd acquisition module, corresponding with described highlight area initially repairs figure for obtaining according to described optimization pixel value；
Repair module, for carrying out repair process according to described initial repairing figure to described highlight area.
The processing means of facial image the most according to claim 7, it is characterised in that described optimization module specifically for:
If the skin color probability of the pixel that described skin color probability is maximum is less than the first preset value, then with the picture of described boundary pixel point
Element value is as the optimization pixel value of described boundary pixel point；
If the skin color probability of the pixel that described skin color probability is maximum is more than or equal to the first preset value, then with described skin color probability
The pixel value of maximum pixel is as the optimization pixel value of described boundary pixel point.
The processing means of facial image the most according to claim 7, it is characterised in that described 3rd acquisition module is specifically used
In:
The optimization pixel value of the plurality of described boundary pixel point is made bilinear interpolation process, to obtain and described highlight area
Corresponding initially repairs figure.
The processing means of facial image the most according to claim 7, it is characterised in that described repair module includes:
Gauss processing unit, for according to the pixel value of the pixel in preset range around described highlight area to described initially
Repairing figure does Gaussian Blur and processes, to obtain smooth repairing figure；
Texture information acquiring unit, for obtaining the texture information of described facial image；
Superpositing unit, for carrying out texture overlap-add procedure, to obtain target according to described texture information to described smooth repairing figure
Repair figure；
Repair unit, for described highlight area being carried out repair process according to described target repairing figure.
11. according to the processing means of the facial image described in any one of claim 7-10, it is characterised in that described first obtains
Module, including:
Computing unit, luminance component and saturation component for each pixel according to facial image obtain facial image
The average of the luminance component of each pixel and variance, the average of saturation component and variance；
Extraction unit, for according to the average of described luminance component and variance, the average of described saturation component and variance,
The luminance component of each described pixel and saturation component, extract the highlight area of described facial image.
12. according to the processing means of the facial image described in any one of claim 7-10, it is characterised in that described first obtains
Module, also includes:
Top cap converter unit, for carrying out top cap conversion process to strengthen the contrast of described facial image to described facial image
Degree.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610700384.7A CN106296617B (en) | 2016-08-22 | 2016-08-22 | The processing method and processing device of facial image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610700384.7A CN106296617B (en) | 2016-08-22 | 2016-08-22 | The processing method and processing device of facial image |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106296617A true CN106296617A (en) | 2017-01-04 |
| CN106296617B CN106296617B (en) | 2019-03-05 |
Family
ID=57661083
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610700384.7A Active CN106296617B (en) | 2016-08-22 | 2016-08-22 | The processing method and processing device of facial image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106296617B (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107038715A (en) * | 2017-03-21 | 2017-08-11 | 腾讯科技（深圳）有限公司 | A kind of image processing method and device |
| CN107194374A (en) * | 2017-06-16 | 2017-09-22 | 广东欧珀移动通信有限公司 | Human face region goes glossy method, device and terminal |
| CN107392859A (en) * | 2017-06-16 | 2017-11-24 | 广东欧珀移动通信有限公司 | Removing method, device and the terminal of highlight area |
| CN107610059A (en) * | 2017-08-28 | 2018-01-19 | 维沃移动通信有限公司 | A kind of image processing method and mobile terminal |
| CN108122212A (en) * | 2017-12-21 | 2018-06-05 | 北京小米移动软件有限公司 | Image repair method and device |
| CN108346128A (en) * | 2018-01-08 | 2018-07-31 | 北京美摄网络科技有限公司 | A kind of method and apparatus of U.S.'s face mill skin |
| CN108665421A (en) * | 2017-03-31 | 2018-10-16 | 北京旷视科技有限公司 | The high light component removal device of facial image and method, storage medium product |
| CN109344752A (en) * | 2018-09-20 | 2019-02-15 | 北京字节跳动网络技术有限公司 | Method and apparatus for handling mouth image |
| CN110069974A (en) * | 2018-12-21 | 2019-07-30 | 北京字节跳动网络技术有限公司 | Bloom image processing method, device and electronic equipment |
| CN111241934A (en) * | 2019-12-30 | 2020-06-05 | 成都品果科技有限公司 | Method and device for acquiring photophobic region in face image |
| CN113221618A (en) * | 2021-01-28 | 2021-08-06 | 深圳市雄帝科技股份有限公司 | Method, system and storage medium for removing highlight of face image |
| CN115965735A (en) * | 2022-12-22 | 2023-04-14 | 百度时代网络技术（北京）有限公司 | Texture map generation method and device |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA2460179A1 (en) * | 2001-09-14 | 2003-03-27 | Pixology Limited | Image processing to remove red-eye features |
| US20080085249A1 (en) * | 2006-10-06 | 2008-04-10 | L'oreal | Artificial hair color removal compositions and methods |
| CN102301694A (en) * | 2009-11-18 | 2011-12-28 | 松下电器产业株式会社 | Image processing method, and image processing device |
| CN102693532A (en) * | 2011-02-25 | 2012-09-26 | 微软公司 | Automatic localized adjustment of image shadows and highlights |
| CN102722872A (en) * | 2012-05-30 | 2012-10-10 | 山东神思电子技术股份有限公司 | Method for eliminating local highlight blooming of digital image |
| KR20120113005A (en) * | 2011-04-04 | 2012-10-12 | 주식회사 매크로그래프 | Estimation method of skin reflectance properties and data processing device |
| US20120288192A1 (en) * | 2011-05-13 | 2012-11-15 | Wolfgang Heidrich | Color highlight reconstruction |
| CN103020579A (en) * | 2011-09-22 | 2013-04-03 | 上海银晨智能识别科技有限公司 | Face recognition method and system, and removing method and device for glasses frame in face image |
| CN103337088A (en) * | 2013-07-10 | 2013-10-02 | 北京航空航天大学 | Human face image light and shadow editing method based on edge preserving |
| CN103985098A (en) * | 2014-05-27 | 2014-08-13 | 广州商景网络科技有限公司 | Method and system for removing highlight of certificate image |
| CN105023249A (en) * | 2015-06-26 | 2015-11-04 | 清华大学深圳研究生院 | Highlight image restoration method and device based on optical field |
| CN105719234A (en) * | 2016-01-26 | 2016-06-29 | 厦门美图之家科技有限公司 | Automatic gloss removing method and system for face area and shooting terminal |
| CN105741249A (en) * | 2016-02-03 | 2016-07-06 | 哈尔滨理工大学 | Highlight removal method for high reflective surface |
-
2016
- 2016-08-22 CN CN201610700384.7A patent/CN106296617B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA2460179A1 (en) * | 2001-09-14 | 2003-03-27 | Pixology Limited | Image processing to remove red-eye features |
| US20080085249A1 (en) * | 2006-10-06 | 2008-04-10 | L'oreal | Artificial hair color removal compositions and methods |
| CN102301694A (en) * | 2009-11-18 | 2011-12-28 | 松下电器产业株式会社 | Image processing method, and image processing device |
| CN102693532A (en) * | 2011-02-25 | 2012-09-26 | 微软公司 | Automatic localized adjustment of image shadows and highlights |
| KR20120113005A (en) * | 2011-04-04 | 2012-10-12 | 주식회사 매크로그래프 | Estimation method of skin reflectance properties and data processing device |
| US20120288192A1 (en) * | 2011-05-13 | 2012-11-15 | Wolfgang Heidrich | Color highlight reconstruction |
| CN103020579A (en) * | 2011-09-22 | 2013-04-03 | 上海银晨智能识别科技有限公司 | Face recognition method and system, and removing method and device for glasses frame in face image |
| CN102722872A (en) * | 2012-05-30 | 2012-10-10 | 山东神思电子技术股份有限公司 | Method for eliminating local highlight blooming of digital image |
| CN103337088A (en) * | 2013-07-10 | 2013-10-02 | 北京航空航天大学 | Human face image light and shadow editing method based on edge preserving |
| CN103985098A (en) * | 2014-05-27 | 2014-08-13 | 广州商景网络科技有限公司 | Method and system for removing highlight of certificate image |
| CN105023249A (en) * | 2015-06-26 | 2015-11-04 | 清华大学深圳研究生院 | Highlight image restoration method and device based on optical field |
| CN105719234A (en) * | 2016-01-26 | 2016-06-29 | 厦门美图之家科技有限公司 | Automatic gloss removing method and system for face area and shooting terminal |
| CN105741249A (en) * | 2016-02-03 | 2016-07-06 | 哈尔滨理工大学 | Highlight removal method for high reflective surface |
Non-Patent Citations (3)
| Title |
|---|
| PING TAN ET AL.: "Highlight Removal by Illumination-Constrained Inpainting", 《PROCEEDINGS OF THE NINTH IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION》 * |
| 周伟等: "实时单幅图片高光去除算法", 《计算机工程与应用》 * |
| 陈锻生等: "彩色图像啊人脸高光区域的自动检测与校正方法", 《软件学报》 * |
Cited By (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107038715B (en) * | 2017-03-21 | 2022-03-08 | 腾讯科技（深圳）有限公司 | Image processing method and device |
| CN107038715A (en) * | 2017-03-21 | 2017-08-11 | 腾讯科技（深圳）有限公司 | A kind of image processing method and device |
| CN108665421A (en) * | 2017-03-31 | 2018-10-16 | 北京旷视科技有限公司 | The high light component removal device of facial image and method, storage medium product |
| CN107392859B (en) * | 2017-06-16 | 2020-08-04 | Oppo广东移动通信有限公司 | Method and device for eliminating highlight area and terminal |
| CN107194374A (en) * | 2017-06-16 | 2017-09-22 | 广东欧珀移动通信有限公司 | Human face region goes glossy method, device and terminal |
| CN107392859A (en) * | 2017-06-16 | 2017-11-24 | 广东欧珀移动通信有限公司 | Removing method, device and the terminal of highlight area |
| CN107610059A (en) * | 2017-08-28 | 2018-01-19 | 维沃移动通信有限公司 | A kind of image processing method and mobile terminal |
| CN107610059B (en) * | 2017-08-28 | 2020-10-16 | 维沃移动通信有限公司 | Image processing method and mobile terminal |
| CN108122212A (en) * | 2017-12-21 | 2018-06-05 | 北京小米移动软件有限公司 | Image repair method and device |
| CN108346128B (en) * | 2018-01-08 | 2021-11-23 | 北京美摄网络科技有限公司 | Method and device for beautifying and peeling |
| CN108346128A (en) * | 2018-01-08 | 2018-07-31 | 北京美摄网络科技有限公司 | A kind of method and apparatus of U.S.'s face mill skin |
| CN109344752B (en) * | 2018-09-20 | 2019-12-10 | 北京字节跳动网络技术有限公司 | Method and apparatus for processing mouth image |
| CN109344752A (en) * | 2018-09-20 | 2019-02-15 | 北京字节跳动网络技术有限公司 | Method and apparatus for handling mouth image |
| CN110069974A (en) * | 2018-12-21 | 2019-07-30 | 北京字节跳动网络技术有限公司 | Bloom image processing method, device and electronic equipment |
| CN110069974B (en) * | 2018-12-21 | 2021-09-17 | 北京字节跳动网络技术有限公司 | Highlight image processing method and device and electronic equipment |
| CN111241934A (en) * | 2019-12-30 | 2020-06-05 | 成都品果科技有限公司 | Method and device for acquiring photophobic region in face image |
| CN113221618A (en) * | 2021-01-28 | 2021-08-06 | 深圳市雄帝科技股份有限公司 | Method, system and storage medium for removing highlight of face image |
| CN113221618B (en) * | 2021-01-28 | 2023-10-17 | 深圳市雄帝科技股份有限公司 | Face image highlight removing method, system and storage medium thereof |
| CN115965735A (en) * | 2022-12-22 | 2023-04-14 | 百度时代网络技术（北京）有限公司 | Texture map generation method and device |
| CN115965735B (en) * | 2022-12-22 | 2023-12-05 | 百度时代网络技术（北京）有限公司 | Texture map generation method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106296617B (en) | 2019-03-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106296617A (en) | The processing method and processing device of facial image | |
| CN103871051B (en) | Image processing method, device and electronic equipment | |
| CN108875451B (en) | Method, device, storage medium and program product for positioning image | |
| CN106778440B (en) | Two-dimensional code identification method and device | |
| CN104134230B (en) | A kind of image processing method, device and computer equipment | |
| CN104135609B (en) | Auxiliary photo-taking method, apparatus and terminal | |
| US10915750B2 (en) | Method and device for searching stripe set | |
| CN105828068A (en) | Method and device for carrying out occlusion detection on camera and terminal device | |
| CN104133832B (en) | The recognition methods of pirate application and device | |
| CN104717125B (en) | Graphic code store method and device | |
| CN104463105A (en) | Guide board recognizing method and device | |
| CN110796157A (en) | Image difference identification method and device and storage medium | |
| CN106296634B (en) | A kind of method and apparatus detecting similar image | |
| CN106156711A (en) | The localization method of line of text and device | |
| CN105447819A (en) | Picture processing method and apparatus | |
| CN106203254A (en) | A kind of adjustment is taken pictures the method and device in direction | |
| CN106204552A (en) | The detection method of a kind of video source and device | |
| CN104134043B (en) | Content is hidden, separates method, device and the terminal hidden | |
| CN111986250A (en) | Object volume measuring method, device, measuring equipment and storage medium | |
| CN108269220A (en) | Method and device for positioning digital watermark | |
| US10795456B2 (en) | Method, device and terminal for determining effectiveness of stripe set | |
| CN110363785A (en) | A kind of super frame detection method and device of text | |
| CN103869977B (en) | Method for displaying image, device and electronics | |
| CN105898561A (en) | Video image processing method and video image processing device | |
| CN104574452A (en) | Generating method and device for window background |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | 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 | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20210927 Address after: 518057 Tencent Building, No. 1 High-tech Zone, Nanshan District, Shenzhen City, Guangdong Province, 35 floors Patentee after: TENCENT TECHNOLOGY (SHENZHEN) Co.,Ltd. Patentee after: TENCENT CLOUD COMPUTING (BEIJING) Co.,Ltd. Address before: 2, 518000, East 403 room, SEG science and Technology Park, Zhenxing Road, Shenzhen, Guangdong, Futian District Patentee before: TENCENT TECHNOLOGY (SHENZHEN) Co.,Ltd. |