CN106878695A - Method, device and computer equipment that white balance is processed - Google Patents
Method, device and computer equipment that white balance is processed Download PDFInfo
- Publication number
- CN106878695A CN106878695A CN201710077011.3A CN201710077011A CN106878695A CN 106878695 A CN106878695 A CN 106878695A CN 201710077011 A CN201710077011 A CN 201710077011A CN 106878695 A CN106878695 A CN 106878695A
- Authority
- CN
- China
- Prior art keywords
- white balance
- reference zone
- region
- human face
- face region
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N9/00—Details of colour television systems
- H04N9/64—Circuits for processing colour signals
- H04N9/73—Colour balance circuits, e.g. white balance circuits or colour temperature control
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30196—Human being; Person
- G06T2207/30201—Face
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Oral & Maxillofacial Surgery (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Human Computer Interaction (AREA)
- General Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- Signal Processing (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Processing (AREA)
- Color Image Communication Systems (AREA)
Abstract
Method, device and computer equipment the present invention relates to a kind for the treatment of of white balance.Methods described includes：Recognition of face is carried out to image, human face region and the background area in addition to the human face region is recognized；Reference zone is obtained from the human face region, wherein, the reference zone is the white portion in material object；White balance treatment is carried out to whole image according to the reference zone；Or, white balance treatment is carried out to the human face region according to the reference zone；White balance treatment is carried out to the region in addition to human face region according to the background area.The embodiment of the present invention can carry out white balance treatment to image according to particular reference region in image human face region, and then improve the degree of accuracy of white balance, lift Consumer's Experience.
Description
Technical field
The present invention relates to image processing techniques, the more particularly to method of white balance treatment, device and computer equipment.
Background technology
Colour temperature (Color Temperature) is the yardstick for representing that light source is photochromic, and unit is K (Kelvin).Human eye is in office
Being white is all differentiated to most bright object under what colour temperature.And the photo that camera is taken under different-colour shows as different colors,
As the photo under D65 light sources is partially blue, and the photo under A light is partially yellow.Indoor light source is often more complicated, whether incandescent lamp,
Fluorescence lamp color temperature is not very standard.So indoors shoot portrait frequently can lead to personage skin tone it is abnormal, partially
It is yellow or partially blue.
With the development of image processing techniques, requirement more and more higher of the people to image generally carries out the later stage excellent to image
Change so that picture obtains more preferable visual effect.AWB (Automatic White Balance, AWB) is used extensively
In the treatment of the portrait pictures comprising face.The essence of white balance (White Balance, WB) is to allow white object any
All shown as white under the light source of color.White balance makes the color of the image shot become seen by person by colour correction
Odd colors.From the photo referred to as original image that sensitive chip reads out, AWB color school is carried out to original image
Just, white balance effect is reached.
But in some scenarios, the effect of AWB still has differences with odd colors seen by person, meeting
There is the problem of color offset, Consumer's Experience is not good.
The content of the invention
The embodiment of the present invention provides a kind of method of white balance treatment, device and computer equipment, can be more accurate right
Image carries out white balance adjusting, improves user experience.
A kind of method of white balance treatment, including：
Recognition of face is carried out to image, human face region and the background area in addition to the human face region is recognized；
Reference zone is obtained from the human face region, wherein, the reference zone is the white portion in material object；
White balance treatment is carried out to whole image according to the reference zone；Or, according to the reference zone to described
Human face region carries out white balance treatment；The region in addition to human face region is carried out at white balance according to the background area
Reason.
A kind of device of white balance treatment, including：
Face recognition module, for recognizing human face region and the background area in addition to human face region；
Acquisition module, for obtaining reference zone in the human face region, wherein, during the reference zone is material object
White portion；
White balance processing module, for carrying out white balance treatment to whole image according to the reference zone；Or, according to
The reference zone human face region is carried out white balance treatment and according to the background area to it is described except human face region with
Outer region carries out white balance treatment.
A kind of computer equipment, including memory, processor and storage can run on a memory and on a processor
Computer program, following steps are realized during the computing device described program：
Recognition of face is carried out to image, human face region and the background area in addition to human face region is obtained；
Reference zone is obtained in the human face region, wherein, reference zone reflexes to the light of human eye described in material object
Ratio with blue, green, the red three kinds of coloured light in certain brightness and the light is identical；
White balance treatment is carried out to whole image according to the reference zone；Or, according to the reference zone to described
Human face region carries out white balance treatment；Background area is determined according to the human face region, the background area is except the face
Region beyond region；White balance treatment is carried out to the region in addition to human face region according to the background area.
, relative to traditional auto white balance method, the embodiment of the present invention can be according to figure for the method for above-mentioned white balance treatment
As particular reference region carries out white balance treatment to image in human face region, and then the degree of accuracy of white balance is improved, lift user
Experience.
Brief description of the drawings
Fig. 1 is the internal structure schematic diagram of terminal in one embodiment；
Fig. 2 is the flow chart of the method for white balance treatment in one embodiment；
Fig. 3 is the flow chart of the method for white balance treatment in another embodiment；
Fig. 4 be one embodiment in the human face region obtain reference zone flow chart；
Fig. 5 is to carry out the flow chart of white balance treatment to image according to the reference zone in one embodiment；
Fig. 6 is to carry out the flow chart of white balance treatment to image according to the background area in one embodiment；
Fig. 7 is the structural framing figure of the device of white balance treatment in one embodiment；
Fig. 8 is the structural framing figure of acquisition module in the device of white balance treatment in one embodiment；
Fig. 9 is the structural framing figure of white balance processing module in the device of white balance treatment in one embodiment；
Figure 10 is the flow chart of the step of being realized when one embodiment Computer device handler performs computer program.
Specific embodiment
In order to make the purpose , technical scheme and advantage of the present invention be clearer, it is right below in conjunction with drawings and Examples
The present invention is further elaborated.It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, and
It is not used in the restriction present invention.
It is appreciated that term " first " used in the present invention, " second " etc. can be used to describe various elements herein,
But these elements should not be limited by these terms.These terms are only used for distinguishing first element and another element.Citing comes
Say, without departing from the scope of the invention, the first statistic unit can be referred to as the second statistic unit, and similarly,
Second statistic unit can be referred to as the first statistic unit.First statistic unit and the second statistic unit both statistic unit,
But it is not same statistic unit.
Fig. 1 is the internal structure schematic diagram of terminal in one embodiment.As shown in figure 1, the terminal is including total by system
The processor 101 of line connection, non-volatile memory medium 102, built-in storage 103, network interface 104, display screen 105, shooting
First 106, imageing sensor 107.Wherein, the non-volatile memory medium of terminal is stored with operating system, also including a kind of white flat
Weigh the device 108 for processing, and the device 108 of white balance treatment is used to realize a kind of white balancing treatment method.The processor 101 is used
Calculated and control ability in providing, support the operation of whole terminal.Can store computer in built-in storage 103 in terminal can
Reading instruction, when the computer-readable instruction is performed by the processor 101, may be such that the processor 101 is performed a kind of white flat
Weighing apparatus processing method.Network interface 104 is used to carry out network service with server, data access request of such as transmitting news to service
Device, news data that the reception server is returned etc..The display screen 105 of terminal can be that LCDs or electric ink show
Screen etc..The terminal can be mobile phone, panel computer, digital camera etc..It will be understood by those skilled in the art that shown in Fig. 1
Structure, only the block diagram of the part-structure related to application scheme, does not constitute and application scheme is applied thereon
Terminal restriction, specific terminal can include than more or less part shown in figure, or combine some parts, or
There are person different parts to arrange.
As shown in Fig. 2 in one embodiment, there is provided a kind of method of white balance treatment, the present embodiment is in this way
The terminal in above-mentioned Fig. 1 is applied to illustrate.The method specifically includes following steps：
Step 202, recognition of face is carried out to image, obtains human face region and the background area in addition to human face region.
Region division is carried out to pending image, human face region, image can be recognized by various face recognition algorithms
In region in addition to human face region be defined as background area.
Face identification method can be based on principal component analysis (principal component analysis, abbreviation PCA)
Face identification method, from the viewpoint of statistics, find the basic element of facial image distribution, i.e. facial image sample set covariance
The characteristic vector of matrix, facial image is approx characterized with this.These characteristic vectors are referred to as eigenface (Eigenface).Face
Recognition methods can also carry out Face Detection come locating human face by color analysis, and one is set up using the color characteristics of skin of face
Individual new color coordinates system, the positioning to face is realized by isolating the colour of skin from image.Face identification method can be with
It is deforming template class method, contouring head is approx represented with ellipse, by iteration refinement.Face identification method can also be to adopt
Use Adaboost algorithm.Preferably, dynamic thresholding can be used in Adaboost algorithm, the speed of recognition of face is further speeded up
Degree.Face recognition algorithms can also quickly recognize the algorithm of human face region using other, to face in the embodiment of the present invention
Recognizer is not especially limited.
Further, recognition of face is carried out to image, human face region and the background area in addition to human face region is obtained
Can include：Recognition of face is carried out to the image with face, the corresponding rectangle frame of face is determined；Face is extracted in rectangle frame
Profile；Using facial contour as the human face region, other regions in image are used as background area.Wherein, in rectangle frame
Extracting facial contour can be extracted using active shape model or active appearance models to facial contour.
Step 204, reference zone is obtained in the human face region, wherein, the reference zone is the white in material object
Region.
By the reference zone in face recognition algorithms locating human face region.Reference zone can be understood as in material object, people
White portion seen by eye, or can be understood as the white portion in the true man's face seen by eyes.Because white refers to
The light in human eye is reflexed to by blue, green, red three kinds of coloured light ratios are identical and anti-with the vision that certain brightness is formed
Should, the white in material object does not contain the brightness of hue component.Reference zone can be the white of the eye region of eyes, or tooth
Region.
Step 206, white balance treatment is carried out according to the reference zone to whole image.
RGB RGB vectors according to reference zone (white of the eye region or tooth regions) are carried out at white balance to whole image
Reason.
In one embodiment, with reference to Fig. 3, it is also possible to step 208 come instead of step 206.Step 208, according to described
Reference zone carries out white balance treatment to the human face region；According to the background area to the area in addition to human face region
Domain carries out white balance treatment.It is, the color vector according to the reference zone is carried out at white balance to the human face region
Reason；Meanwhile, the color vector according to the background area carries out white balance treatment to the region in addition to human face region.
AWB treatment, this hair are carried out to entire image relative to traditional color vector according to entire image
The method of white balance treatment in bright embodiment, by recognition of face, recognizes human face region and the background area in addition to human face region,
At the same time it can also orient reference zone in human face region, whole image is carried out according to specific reference zone automatic white
Balance Treatment, or AWB treatment is carried out to human face region according to specific reference zone, and according to background area
White balance treatment is carried out to going out the region outside human face region in entire image, and then improve the degree of accuracy of white balance, lift user
Experience.
In one embodiment, with reference to Fig. 4, step 204 obtains reference zone from the human face region, including：
Step 402, eye areas are positioned in the human face region.
After identifying human face region according to face identification method, the eyes in human face region are identified or position.
The identification of human eye has edge feature analytic approach, Hough transform method and deforming template method etc..The identification of human eye can also use intermediate value
After filtering and histogram equalizing method remove noise and illumination to the influence of image, image is done integral projection to narrow down to face
Ocular, try again horizontal integral projection in the eyebrow and eye regions for obtaining, and finds the upright position of two.Finally utilize
Human eye template carries out the matching degree highest part human eye area as to be positioned along the vertical direction.The embodiment of the present invention
In eye recognition method is not especially limited.
Step 404, white of the eye region is extracted from the eye areas and the white of the eye region is defined for reference zone.
Eye areas are positioned or recognized according to step 402.Eye areas include the white of the eye, pupil, part eyelid, from eyes area
White of the eye region is extracted in domain, and white of the eye region is defined as reference zone.
Under normal circumstances, the white of the eye of human eye is white.For from Color constitut, it is believed that white of the eye part is red green
The ratio of blue RGB color component is 1:1:1.White of the eye region is defined as reference zone, by reference zone RGB RGB color point
Amount is reduced to the color of the human eye white of the eye under normal circumstances, and then realizes carrying out human face region or view picture figure at automatic white flat place
Reason.
When extracting white of the eye region, the brightness histogram of eye areas is individually calculated, white of the eye area is positioned according to brightness histogram
Domain.
In one embodiment, white of the eye region is extracted from the eye areas and the white of the eye region is defined for reference area
The step of domain, specifically includes：
Obtain the brightness value of each pixel of the eye areas；Each pixel according to the eye areas it is bright
Angle value obtains the luminance mean value of the eye areas；White of the eye region is extracted, pixel brightness is more than brightness in choosing eye areas
The region of average is defined as white of the eye region, it is, the brightness of the pixel in the white of the eye region is more than luminance mean value.
In one embodiment, step 204, reference zone is obtained in the human face region, can also be：
In the human face region, position and extract tooth regions and define the tooth regions for reference zone.According to people
After face recognition method identifies human face region, the tooth in human face region is identified or positions.
Under normal circumstances, tooth is also white.For from Color constitut, it is believed that dental part RGB
The ratio of RGB color component is 1:1:1.Tooth regions are defined as reference zone, by reference zone RGB RGB color component
The color of the human eye white of the eye under normal circumstances is reduced to, and then realizes carrying out human face region or view picture figure automatic white flat treatment.
In one embodiment, by the method for recognition of face in image, while white of the eye region and tooth regions are identified,
Priority definition white of the eye region is reference zone, is that reference pair entire image or human face region are carried out at white balance with white of the eye region
Reason.In one embodiment, the weight of white of the eye region and tooth regions RGB RGB color vector can also be considered, it is fixed
Ocular prosthesis white region and tooth regions are reference zone, and then carry out white balance treatment to entire image or human face region.
In one embodiment, with reference to Fig. 5, step 206 is carried out at white balance according to the reference zone to whole image
Reason, including：
Step 502, the RGB RGB color component average or maximum of statistical-reference region all pixels point.
Lift the color component of reference zone all pixels point, the color of each pixel is blue by red Red, green Green
Blue tri- primary components are represented.RGB RGB color component to reference zone all pixels point is averaged, and is joined
The RGB RGB color component average in examination district domainOr, choose the red green of reference zone all pixels point
The maximum of blue RGB color component, obtains the RGB RGB color component maximum (R of reference zonemax、Gmax、Bmax)。
Step 504, according to the RGB RGB color component average or the school of the red R passages of maximum value calculation and blue channel B
Positive regulating factor.
The data of white balance treatment input are the bivector of (red, blue), and color on the basis of green is white flat without participating in
Weighing apparatus.
In an example, according to the corresponding RGB RGB color component average of reference zoneCalculate
The correction regulatory factor of red R passages and blue channel B.Wherein, red R channel correctings regulatory factor KRFor green channel components average divided by
The quotient of all red R channel components R of reference zone.Blue channel B correction regulatory factor KBIt is green channel components average divided by reference
The quotient of all blue channel B component B in region.
In an example, according to the corresponding RGB RGB color component maximum (R of reference zonemax、Gmax、Bmax) meter
Calculate the correction regulatory factor of red R passages and blue channel B.Wherein, red R channel correctings regulatory factor lRIt is green channel components maximum
Divided by the quotient of the red passage maximum of the reference zone.Blue channel B correction regulatory factor lBFor green channel components maximum is removed
With the quotient of the reference zone blue channel maximum.
Step 506, the correction regulatory factor according to the red R passages and blue channel B is carried out at white balance to whole image
Reason.
The red R passages and the correction regulatory factor of blue channel B that step 504 is calculated are brought into corresponding white balance treatment mould
In type, realization carries out white balance treatment to entire image or human face region, and realization quickly carries out white balance to human face region, improves
White balance efficiency.
In other embodiments, when white balance treatment is carried out to whole image according to the reference zone, at its white balance
Reason method can also be simple gray world algorithm (GW) and full perfection reflection algorithm (PR) Orthogonal Composite algorithm (QCGP), standard
The gray world algorithm (SDWGW) of difference weighting, luminance weighted gray world algorithm (LWGW), the standard deviation brightness/gray scale world calculate
Method (SDLWGW) and luminance weighted gray world algorithm and complete perfect reflection algorithm (PR) Orthogonal Composite algorithm (QCLWG P) etc.
Deng.
In one embodiment, step 208, white balance treatment is carried out according to the reference zone to the human face region；
White balance treatment is carried out to the region in addition to human face region according to the background area, including：
According to step 502 to step 506, after carrying out white balance treatment to human face region according to reference zone, further according to the back of the body
Scene area carries out white balance treatment to the region in addition to human face region.
Wherein, white balance treatment is carried out to the region in addition to human face region according to the background area, with reference to figure
6, including：
Step 602, counts the RGB RGB color component average or maximum of background area all pixels point.
Lift the color component of background area all pixels point, the color of each pixel is blue by red Red, green Green
Blue tri- primary components are represented.RGB RGB color component to background area all pixels point is averaged, and is joined
The RGB RGB color component average in examination district domainOr, choose the red green of background area all pixels point
The maximum of blue RGB color component, obtains the RGB RGB color component maximum (R of reference zonemax、Gmax、Bmax)。
Step 604, according to the RGB RGB color component average or the school of the red R passages of maximum value calculation and blue channel B
Positive regulating factor.
The data of white balance treatment input are the bivector of (red, blue), and color on the basis of green is white flat without participating in
Weighing apparatus.
In an example, according to the corresponding RGB RGB color component average of reference zoneCalculate
The correction regulatory factor of red R passages and blue channel B.Wherein, red R channel correctings regulatory factor KRFor green channel components average divided by
The quotient of all red R channel components R of reference zone.Blue channel B correction regulatory factor KBIt is green channel components average divided by reference
The quotient of all blue channel B component B in region.
In an example, according to the corresponding RGB RGB color component maximum (R of reference zonemax、Gmax、Bmax) meter
Calculate the correction regulatory factor of red R passages and blue channel B.Wherein, red R channel correctings regulatory factor lRIt is green channel components maximum
Divided by the quotient of the red passage maximum of the reference zone.Blue channel B correction regulatory factor lBFor green channel components maximum is removed
With the quotient of the reference zone blue channel maximum.
Step 606, the correction regulatory factor according to the red R passages and blue channel B carries out white flat to background area image
Weighing apparatus treatment.
The corresponding red R passages in background area and the correction regulatory factor of blue channel B that step 604 is calculated are brought into accordingly
White balance treatment model in, realization carries out white balance treatment to background area, realize it is quick in image in addition to human face region
Hair, environment carry out white balance, improve the degree of accuracy of white balance, reduce the difference of image and real scene, can be more accurate
True carries out white balance treatment, lifts Consumer's Experience.
Fig. 7 is the structured flowchart of the device of white balance treatment in one embodiment.As shown in figure 8, a kind of white balance treatment
Device, including：
Face recognition module 710, for recognizing human face region and the background area in addition to human face region；
Acquisition module 720, for obtaining reference zone in the human face region, wherein, the reference zone is material object
In white portion；
White balance processing module 730, for carrying out white balance treatment to whole image according to the reference zone；Or,
According to the reference zone human face region is carried out white balance treatment and according to the background area to described except face area
Region beyond domain carries out white balance treatment.
The device of above-mentioned white balance treatment, when white balance treatment is carried out to image, can be carried out to the face in image
Identification, recognizes human face region and the background area in addition to human face region.Reference zone, root are obtained in the human face region
White balance treatment is carried out to whole image according to the reference zone.Or, the human face region is entered according to the reference zone
The treatment of row white balance；White balance treatment is carried out to the region in addition to human face region according to the background area.The present invention
Embodiment carries out white balance treatment to image according to particular reference region in image human face region, and then improves the accurate of white balance
Degree, lifts Consumer's Experience.
In one embodiment, face recognition module 710 can carry out region division to pending image, can pass through
Various face recognition algorithms, recognize human face region, and the region in image in addition to human face region is defined as background area.Face is known
Other module 710 can be based on the recognition of face side of principal component analysis (principal component analysis, abbreviation PCA)
Method, from statistics viewpoint, find facial image distribution basic element, i.e., the feature of facial image sample set covariance matrix to
Amount, facial image is approx characterized with this.Face recognition module 710 can also carry out Face Detection to position by color analysis
Face, a new color coordinates system is set up using the color characteristics of skin of face, and the colour of skin is isolated come real by from image
Now to the positioning of face.Face recognition module 710 can also be deforming template class method, and head wheel is approx represented with ellipse
Exterior feature, by iteration refinement.Face recognition module 710 can also quickly recognize the algorithm of human face region, this hair using other
Face recognition algorithms are not especially limited in bright embodiment.
In one embodiment, acquisition module 720 can obtain reference zone from face recognition module 710.Reference area
Domain can be the white of the eye region of eyes, or tooth regions.Reference zone can be understood as in material object seen by human eye
White portion, or can be understood as the white portion in the true man's face seen by eyes.Because white refers to reflex to human eye
In light by blue, green, red three kinds of coloured light ratios are identical and vision response that formed with certain brightness, in material object
White does not contain the brightness of hue component.
In one embodiment, with reference to Fig. 8, the acquisition module 720 includes positioning unit 721 and extraction unit 723.Its
In, positioning unit 721, for eye areas or tooth regions in locating human face region.Extraction unit 723, for extracting
State white of the eye region in eye areas or for extracting the tooth regions.
By positioning unit 721 and extraction unit 723, eye areas or tooth regions can be recognized from human face region,
Reference zone can be extracted from eye areas or tooth regions by extraction unit 723 again, wherein, reference zone can be the white of the eye
Region, or tooth regions.
In one embodiment, acquisition module 720 also includes computing unit 725 and chooses unit 727.Wherein, calculate single
Unit 725, the luminance mean value of the eye areas is obtained for calculating the brightness value of each pixel of the eye areas.Choose
Unit 727, for choosing pixel of the eye areas brightness more than the luminance mean value, the collection of the pixel of selection is combined into the white of the eye
Region.
During the white of the eye is extracted, the brightness histogram of eye areas is calculated by computing unit 725.It is straight according to brightness
Fang Tu, obtains the luminance mean value of eye areas.By choosing unit 727, choose eye areas brightness and be more than the luminance mean value
Pixel, the collection of the pixel of selection is combined into white of the eye region.
In one embodiment, with reference to Fig. 9, the white balance processing module 730 includes the first statistic unit 731, first
Gain correction factor acquiring unit 732 and first corrects unit 733.Wherein, the first statistic unit 731, for statistical-reference area
The RGB RGB color component average or maximum of domain all pixels point.First gain correction factor acquiring unit 732, is used for
Correction regulation according to the reference zone RGB RGB color component average or the red R passages of maximum value calculation and blue channel B because
Son.First correction unit 733, for the correction regulatory factor according to the red R passages of the reference zone and blue channel B to whole figure
As carrying out white balance treatment.First correction unit 733 is according to the first gain correction factor acquiring unit 732, the reference area of acquisition
The correction regulatory factor of the corresponding red R passages in domain and blue channel B, realization is carried out at white balance to entire image or human face region
Reason, realizes quickly carrying out human face region white balance, improves white balance efficiency.
In one embodiment, the white balance processing module 730 also includes the second statistic unit 736, the second gain school
Positive divisor acquiring unit 737 and second corrects unit 738.Wherein, the second statistic unit 736, owns for counting background area
The RGB RGB color component average or maximum of pixel.Second gain correction factor acquiring unit 737, for according to institute
State the correction regulation of the corresponding RGB RGB color component average in background area or the red R passages of maximum value calculation and blue channel B because
Son.Second correction unit 738, for the correction regulatory factor pair according to the corresponding red R passages in the background area and blue channel B
Background area image carries out white balance treatment.Second correction unit 738 is obtained according to the second gain correction factor acquiring unit 737
The red R passages in background area and blue channel B correction regulatory factor, white balance treatment is carried out to background area, it is quick right to realize
Hair, environment in image in addition to human face region carry out white balance, improve the degree of accuracy of white balance, reduce image with true field
The difference of scape, can more accurately carry out white balance treatment, lift Consumer's Experience.
The division of modules is only used for for example, in other embodiments in the device of above-mentioned white balance treatment, can
The device of white balance treatment is divided into different modules as required, with complete the device that above-mentioned white balance is processed whole or
Partial function.
Figure 10 is the flow chart of the step of being realized when one embodiment Computer device handler performs computer program.
As shown in Figure 10, a kind of computer equipment, including memory, processor and storage can run on a memory and on a processor
Computer program (instruction), realize following steps during computing device program：
Step 1002, recognition of face is carried out to image, obtains human face region and the background area in addition to human face region.
Region division is carried out to pending image, human face region, image can be recognized by various face recognition algorithms
In region in addition to human face region be defined as background area.
Face identification method can be based on principal component analysis (principal component analysis, abbreviation PCA)
Face identification method, from the viewpoint of statistics, find the basic element of facial image distribution, i.e. facial image sample set covariance
The characteristic vector of matrix, facial image is approx characterized with this.These characteristic vectors are referred to as eigenface (Eigenface).Face
Recognition methods can also carry out Face Detection come locating human face by color analysis, and one is set up using the color characteristics of skin of face
Individual new color coordinates system, the positioning to face is realized by isolating the colour of skin from image.Face identification method can be with
It is deforming template class method, contouring head is approx represented with ellipse, by iteration refinement.Face identification method can also be to adopt
Use Adaboost algorithm.Preferably, dynamic thresholding can be used in Adaboost algorithm, the speed of recognition of face is further speeded up
Degree.Face recognition algorithms can also quickly recognize the algorithm of human face region using other, to face in the embodiment of the present invention
Recognizer is not especially limited.
Further, recognition of face is carried out to image, human face region and the background area in addition to human face region is obtained
Can include：Recognition of face is carried out to the image with face, the corresponding rectangle frame of face is determined；Face is extracted in rectangle frame
Profile；Using facial contour as the human face region, other regions in image are used as background area.Wherein, in rectangle frame
Extracting facial contour can be extracted using active shape model or active appearance models to facial contour.
Step 1004, reference zone is obtained in the human face region, wherein, the reference zone in material object is reflexed to
The light of human eye has the ratio of blue, green, the red three kinds of coloured light in certain brightness and the light identical.
By the reference zone in face recognition algorithms locating human face region.Reference zone can be the white of the eye area of eyes
Domain, or tooth regions.Reference zone can be understood as the white portion seen by human eye in material object, or can be understood as
The white portion in true man's face seen by eyes.Because white refers to reflex to light in human eye due to blue, green, red three
Kind of coloured light ratio is identical and vision response that formed with certain brightness, and the white in material object does not contain the bright of hue component
Degree.
Step 1006, white balance treatment is carried out according to the reference zone to whole image.Or according to the reference zone
White balance treatment is carried out to the human face region；The region in addition to human face region is carried out according to the background area white
Balance Treatment.
RGB RGB vectors according to reference zone (white of the eye region or tooth regions) are carried out at white balance to whole image
Reason.Or, the color vector according to the reference zone carries out white balance treatment to the human face region；Meanwhile, according to described
The color vector of background area carries out white balance treatment to the region in addition to human face region.
Processor, by recognition of face, recognizes human face region and except face in configuration processor in above computer equipment
Background area outside region, at the same time it can also orient reference zone in human face region, according to specific reference zone to whole
Individual image carries out AWB treatment, or carries out AWB treatment to human face region according to specific reference zone,
And white balance treatment is carried out to going out the region outside human face region in entire image according to background area, and then improve white balance
The degree of accuracy, lifts Consumer's Experience.
One of ordinary skill in the art will appreciate that all or part of flow in realizing above-described embodiment method, can be
The hardware of correlation is instructed to complete by computer program, described program can be stored in a non-volatile computer and can read
In storage medium, the program is upon execution, it may include such as the flow of the embodiment of above-mentioned each method.Wherein, described storage is situated between
Matter can be magnetic disc, CD, read-only memory (Read-Only Memory, ROM) etc..
Embodiment described above only expresses several embodiments of the invention, and its description is more specific and detailed, but simultaneously
Therefore the limitation to the scope of the claims of the present invention can not be interpreted as.It should be pointed out that for one of ordinary skill in the art
For, without departing from the inventive concept of the premise, various modifications and improvements can be made, these belong to guarantor of the invention
Shield scope.Therefore, the protection domain of patent of the present invention should be determined by the appended claims.
Claims (13)
1. a kind of method that white balance is processed, it is characterised in that including：
Recognition of face is carried out to image, human face region and the background area in addition to the human face region is recognized；
Reference zone is obtained from the human face region, wherein, the reference zone is the white portion in material object；
White balance treatment is carried out to whole image according to the reference zone；Or, according to the reference zone to the face
Region carries out white balance treatment；White balance treatment is carried out to the region in addition to human face region according to the background area.
2. the method that white balance according to claim 1 is processed, it is characterised in that described to be obtained from the human face region
Reference zone, including：
Eye areas are positioned in the human face region；
White of the eye region is extracted from the eye areas and the white of the eye region is defined for reference zone.
3. the method that white balance according to claim 2 is processed, it is characterised in that extract the white of the eye from the eye areas
Region simultaneously defines the white of the eye region for reference zone, including：
Obtain the brightness value of each pixel of the eye areas；
The brightness value of each pixel according to the eye areas obtains the luminance mean value of the eye areas；
White of the eye region is extracted, the brightness of the pixel in the white of the eye region is more than the luminance mean value.
4. the method that white balance according to claim 1 is processed, it is characterised in that according to the reference zone to whole figure
As carrying out white balance treatment, including：
Count the RGB RGB color component average or maximum of the reference zone all pixels point；
Correction according to the reference zone RGB RGB color component average or the red R passages of maximum value calculation and blue channel B is adjusted
The section factor；
Correction regulatory factor according to the red R passages of the reference zone and blue channel B carries out white balance treatment to whole image.
5. the method that white balance according to claim 4 is processed, it is characterised in that the red R passages of calculating and blue channel B
Correction regulatory factor, including：
The green channel components average is respectively divided by all red R channel components of the reference zone, blue channel B component to deserved
To red R passages, the correction regulatory factor of blue channel B；Or
The green channel components maximum is respectively divided by the red passage maximum of the reference zone, blue channel maximum to deserved
To red R passages, the correction regulatory factor of blue channel B.
6. the method for white balance according to claim 1 treatment, it is characterised in that it is described according to the background area to removing
Region beyond human face region carries out white balance treatment, including：
Count the RGB RGB color component average or maximum of the background area all pixels point；
Correction according to the background area RGB RGB color component average or the red R passages of maximum value calculation and blue channel B is adjusted
The section factor；
The correction regulatory factor of red R passages and blue channel B is carried out at white balance to background area image according to background area
Reason.
7. the method that white balance according to claim 1 is processed, it is characterised in that described to be obtained in the human face region
Reference zone, including：
In the human face region, position and extract tooth regions and define the tooth regions for reference zone.
8. the device that a kind of white balance is processed, it is characterised in that including：
Face recognition module, for recognizing human face region and the background area in addition to human face region；
Acquisition module, for obtaining reference zone in the human face region, wherein, the reference zone is the white in material object
Region；
White balance processing module, for carrying out white balance treatment to whole image according to the reference zone；Or, according to described
Reference zone the human face region is carried out white balance treatment and according to the background area to described in addition to human face region
Region carries out white balance treatment.
9. the device that white balance according to claim 8 is processed, it is characterised in that the acquisition module includes：
Positioning unit, for eye areas or tooth regions in locating human face region；
Extraction unit, for extracting the white of the eye region in the eye areas or for extracting the tooth regions.
10. the device that white balance according to claim 8 is processed, it is characterised in that the acquisition module also includes：
Computing unit, the brightness of the brightness value acquisition eye areas of each pixel for calculating the eye areas is equal
Value；
Unit is chosen, for choosing pixel of the eye areas brightness more than the luminance mean value, the set of the pixel of selection
It is white of the eye region.
The device of 11. white balance treatment according to claim 9, it is characterised in that the processing module includes：
First statistic unit, for the RGB RGB color component average or maximum of statistical-reference region all pixels point；
First gain correction factor acquiring unit, for the RGB RGB color component average according to the reference zone or most
Big value calculates the correction regulatory factor of red R passages and blue channel B；
First correction unit, for according to the correction regulatory factor of the red R passages of the reference zone and blue channel B to whole image
Carry out white balance treatment.
The device of 12. white balance treatment according to claim 8, it is characterised in that the processing module also includes：
Second statistic unit, RGB RGB color component average or maximum for counting background area all pixels point；
Second gain correction factor acquiring unit, for according to the background area RGB RGB color component average or maximum
Value calculates the correction regulatory factor of red R passages and blue channel B；
Second correction unit, for according to the correction regulatory factor of the red R passages in the background area and blue channel B to background area
Image carries out white balance treatment.
A kind of 13. computer equipments, including memory, processor and the meter that store on a memory and can run on a processor
Calculation machine program, following steps are realized during the computing device described program：
Recognition of face is carried out to image, human face region and the background area in addition to human face region is obtained；
Reference zone is obtained in the human face region, wherein, the light that reference zone described in material object reflexes to human eye has
The ratio of blue, green, the red three kinds of coloured light in certain brightness and the light is identical；
White balance treatment is carried out to whole image according to the reference zone；Or, according to the reference zone to the face
Region carries out white balance treatment；Background area is determined according to the human face region, the background area is except the human face region
Region in addition；White balance treatment is carried out to the region in addition to human face region according to the background area.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710077011.3A CN106878695A (en) | 2017-02-13 | 2017-02-13 | Method, device and computer equipment that white balance is processed |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710077011.3A CN106878695A (en) | 2017-02-13 | 2017-02-13 | Method, device and computer equipment that white balance is processed |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106878695A true CN106878695A (en) | 2017-06-20 |
Family
ID=59166111
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710077011.3A Pending CN106878695A (en) | 2017-02-13 | 2017-02-13 | Method, device and computer equipment that white balance is processed |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106878695A (en) |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107277481A (en) * | 2017-07-14 | 2017-10-20 | 维沃移动通信有限公司 | A kind of image processing method and mobile terminal |
| CN107483906A (en) * | 2017-07-25 | 2017-12-15 | 广东欧珀移动通信有限公司 | White balancing treatment method, device and the terminal device of image |
| CN107635124A (en) * | 2017-10-31 | 2018-01-26 | 广东欧珀移动通信有限公司 | White balancing treatment method, device and the equipment of face shooting |
| CN107690065A (en) * | 2017-07-31 | 2018-02-13 | 努比亚技术有限公司 | A kind of white balance correcting, device and computer-readable recording medium |
| CN107730446A (en) * | 2017-10-31 | 2018-02-23 | 广东欧珀移动通信有限公司 | Image processing method, device, computer equipment and computer-readable recording medium |
| CN107995418A (en) * | 2017-11-21 | 2018-05-04 | 维沃移动通信有限公司 | A kind of image pickup method, device and mobile terminal |
| CN108024107A (en) * | 2017-12-06 | 2018-05-11 | 广东欧珀移动通信有限公司 | Image processing method, device, electronic equipment and computer-readable recording medium |
| CN108182667A (en) * | 2017-12-29 | 2018-06-19 | 努比亚技术有限公司 | A kind of image optimization method, terminal and computer readable storage medium |
| CN108376404A (en) * | 2018-02-11 | 2018-08-07 | 广东欧珀移动通信有限公司 | Image processing method and device, electronic equipment, storage medium |
| CN108960382A (en) * | 2018-05-07 | 2018-12-07 | 广东数相智能科技有限公司 | A kind of colour barcode and its color calibration method |
| CN109495731A (en) * | 2017-09-13 | 2019-03-19 | 三星电子株式会社 | Auto white balance method is used for by what image-signal processor executed |
| CN109561291A (en) * | 2018-10-23 | 2019-04-02 | Oppo广东移动通信有限公司 | Color temperature compensating method, device, storage medium and mobile terminal |
| CN109753899A (en) * | 2018-12-21 | 2019-05-14 | 普联技术有限公司 | A kind of face identification method, system and equipment |
| CN110570476A (en) * | 2018-06-06 | 2019-12-13 | 英属开曼群岛商玩美股份有限公司 | System, method and storage medium for execution on computing device |
| CN111754906A (en) * | 2020-06-30 | 2020-10-09 | 上海天马微电子有限公司 | Method for detecting brightness uniformity of curved surface display screen |
| CN114143526A (en) * | 2021-11-19 | 2022-03-04 | 昆山丘钛光电科技有限公司 | Image processing method and device, terminal equipment and readable storage medium |
| CN115118947A (en) * | 2021-03-23 | 2022-09-27 | 北京小米移动软件有限公司 | Image processing method and device, electronic equipment and storage medium |
| CN116915964A (en) * | 2023-09-13 | 2023-10-20 | 北京智芯微电子科技有限公司 | Gray world white balance correction method, device, equipment, chip and storage medium |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1885952A (en) * | 2005-06-20 | 2006-12-27 | 佳能株式会社 | Image sensing apparatus and image processing method |
| JP2008182368A (en) * | 2007-01-23 | 2008-08-07 | Funai Electric Co Ltd | Imaging device |
| JP2008182369A (en) * | 2007-01-23 | 2008-08-07 | Funai Electric Co Ltd | Imaging device |
| CN101272505A (en) * | 2007-03-19 | 2008-09-24 | 株式会社理光 | Pick-up device and pick-up method |
| CN101527860A (en) * | 2008-03-04 | 2009-09-09 | 佳能株式会社 | White balance control apparatus, control method therefor, and image sensing apparatus |
| CN101753815A (en) * | 2008-12-03 | 2010-06-23 | 索尼株式会社 | Imaging apparatus |
| CN103686114A (en) * | 2012-09-10 | 2014-03-26 | 索尼公司 | Image processing apparatus, method, and program |
| CN105187810A (en) * | 2014-11-11 | 2015-12-23 | 怀效宁 | Automatic white balance method based on face color features and electronic media device |
| CN105282530A (en) * | 2014-05-28 | 2016-01-27 | 深圳中兴力维技术有限公司 | Method and device for implementing automatic white balance based on background modeling |
| CN106331661A (en) * | 2015-06-25 | 2017-01-11 | 西安中兴新软件有限责任公司 | White balance processing method and device |
-
2017
- 2017-02-13 CN CN201710077011.3A patent/CN106878695A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1885952A (en) * | 2005-06-20 | 2006-12-27 | 佳能株式会社 | Image sensing apparatus and image processing method |
| JP2008182368A (en) * | 2007-01-23 | 2008-08-07 | Funai Electric Co Ltd | Imaging device |
| JP2008182369A (en) * | 2007-01-23 | 2008-08-07 | Funai Electric Co Ltd | Imaging device |
| CN101272505A (en) * | 2007-03-19 | 2008-09-24 | 株式会社理光 | Pick-up device and pick-up method |
| CN101527860A (en) * | 2008-03-04 | 2009-09-09 | 佳能株式会社 | White balance control apparatus, control method therefor, and image sensing apparatus |
| CN101753815A (en) * | 2008-12-03 | 2010-06-23 | 索尼株式会社 | Imaging apparatus |
| CN103686114A (en) * | 2012-09-10 | 2014-03-26 | 索尼公司 | Image processing apparatus, method, and program |
| CN105282530A (en) * | 2014-05-28 | 2016-01-27 | 深圳中兴力维技术有限公司 | Method and device for implementing automatic white balance based on background modeling |
| CN105187810A (en) * | 2014-11-11 | 2015-12-23 | 怀效宁 | Automatic white balance method based on face color features and electronic media device |
| CN106331661A (en) * | 2015-06-25 | 2017-01-11 | 西安中兴新软件有限责任公司 | White balance processing method and device |
Cited By (27)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107277481A (en) * | 2017-07-14 | 2017-10-20 | 维沃移动通信有限公司 | A kind of image processing method and mobile terminal |
| CN107483906A (en) * | 2017-07-25 | 2017-12-15 | 广东欧珀移动通信有限公司 | White balancing treatment method, device and the terminal device of image |
| US11277595B2 (en) | 2017-07-25 | 2022-03-15 | Guangdong Oppo Mobile Telecommunications Corp., Ltd. | White balance method for image and terminal device |
| CN107483906B (en) * | 2017-07-25 | 2019-03-19 | Oppo广东移动通信有限公司 | White balancing treatment method, device and the terminal device of image |
| CN107690065A (en) * | 2017-07-31 | 2018-02-13 | 努比亚技术有限公司 | A kind of white balance correcting, device and computer-readable recording medium |
| CN109495731A (en) * | 2017-09-13 | 2019-03-19 | 三星电子株式会社 | Auto white balance method is used for by what image-signal processor executed |
| CN109495731B (en) * | 2017-09-13 | 2022-06-17 | 三星电子株式会社 | Method for automatic white balance executed by image signal processor |
| US11503262B2 (en) | 2017-09-13 | 2022-11-15 | Samsung Electronics Co., Ltd. | Image processing method and device for auto white balance |
| CN107730446A (en) * | 2017-10-31 | 2018-02-23 | 广东欧珀移动通信有限公司 | Image processing method, device, computer equipment and computer-readable recording medium |
| CN107635124A (en) * | 2017-10-31 | 2018-01-26 | 广东欧珀移动通信有限公司 | White balancing treatment method, device and the equipment of face shooting |
| CN107730446B (en) * | 2017-10-31 | 2022-02-18 | Oppo广东移动通信有限公司 | Image processing method, image processing device, computer equipment and computer readable storage medium |
| CN107995418A (en) * | 2017-11-21 | 2018-05-04 | 维沃移动通信有限公司 | A kind of image pickup method, device and mobile terminal |
| CN108024107A (en) * | 2017-12-06 | 2018-05-11 | 广东欧珀移动通信有限公司 | Image processing method, device, electronic equipment and computer-readable recording medium |
| CN108182667A (en) * | 2017-12-29 | 2018-06-19 | 努比亚技术有限公司 | A kind of image optimization method, terminal and computer readable storage medium |
| CN108182667B (en) * | 2017-12-29 | 2020-07-17 | 珠海大横琴科技发展有限公司 | Image optimization method, terminal and computer readable storage medium |
| CN108376404A (en) * | 2018-02-11 | 2018-08-07 | 广东欧珀移动通信有限公司 | Image processing method and device, electronic equipment, storage medium |
| CN108960382A (en) * | 2018-05-07 | 2018-12-07 | 广东数相智能科技有限公司 | A kind of colour barcode and its color calibration method |
| CN110570476A (en) * | 2018-06-06 | 2019-12-13 | 英属开曼群岛商玩美股份有限公司 | System, method and storage medium for execution on computing device |
| CN109561291A (en) * | 2018-10-23 | 2019-04-02 | Oppo广东移动通信有限公司 | Color temperature compensating method, device, storage medium and mobile terminal |
| CN109753899A (en) * | 2018-12-21 | 2019-05-14 | 普联技术有限公司 | A kind of face identification method, system and equipment |
| CN111754906A (en) * | 2020-06-30 | 2020-10-09 | 上海天马微电子有限公司 | Method for detecting brightness uniformity of curved surface display screen |
| CN111754906B (en) * | 2020-06-30 | 2022-09-27 | 上海天马微电子有限公司 | Method for detecting brightness uniformity of curved surface display screen |
| CN115118947A (en) * | 2021-03-23 | 2022-09-27 | 北京小米移动软件有限公司 | Image processing method and device, electronic equipment and storage medium |
| CN115118947B (en) * | 2021-03-23 | 2023-11-24 | 北京小米移动软件有限公司 | Image processing method and device, electronic equipment and storage medium |
| CN114143526A (en) * | 2021-11-19 | 2022-03-04 | 昆山丘钛光电科技有限公司 | Image processing method and device, terminal equipment and readable storage medium |
| CN116915964A (en) * | 2023-09-13 | 2023-10-20 | 北京智芯微电子科技有限公司 | Gray world white balance correction method, device, equipment, chip and storage medium |
| CN116915964B (en) * | 2023-09-13 | 2024-01-23 | 北京智芯微电子科技有限公司 | Gray world white balance correction method, device, equipment, chip and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106878695A (en) | Method, device and computer equipment that white balance is processed | |
| US20210329208A1 (en) | Illuminant estimation referencing facial color features | |
| US10304166B2 (en) | Eye beautification under inaccurate localization | |
| EP3338217B1 (en) | Feature detection and masking in images based on color distributions | |
| US8331666B2 (en) | Automatic red eye artifact reduction for images | |
| US8675960B2 (en) | Detecting skin tone in images | |
| CN105139404B (en) | A kind of the license camera and shooting quality detection method of detectable shooting quality | |
| CN107730445A (en) | Image processing method, device, storage medium and electronic equipment | |
| CN112784773B (en) | Image processing method and device, storage medium and terminal | |
| CN105894458A (en) | Processing method and device of image with human face | |
| CN106326823B (en) | Method and system for obtaining head portrait in picture | |
| JP3018914B2 (en) | Gradation correction device | |
| US20100008567A1 (en) | Pupil color correction device and program | |
| CN107368806A (en) | Image correction method, device, computer-readable recording medium and computer equipment | |
| CN108022207A (en) | Image processing method, device, storage medium and electronic equipment | |
| CN107454345A (en) | White balancing treatment method, device and the terminal device of image | |
| US20090290048A1 (en) | Pupil color correction device and program | |
| CN106331661A (en) | White balance processing method and device | |
| CN107295324A (en) | White balancing treatment method, device and terminal device | |
| CN107845076A (en) | Image processing method, device, computer-readable recording medium and computer equipment | |
| CN112581564B (en) | Image generation method and device, electronic equipment and storage medium | |
| US8270715B2 (en) | Method for correcting red-eye | |
| TW202101385A (en) | Skin tone image gamut weight detecting method and device thereof | |
| CN113610723B (en) | Image processing method and related device | |
| CN115937919A (en) | Method, device and equipment for identifying makeup color and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170620 |