CN106033593A - Image processing equipment and image processing method - Google Patents
Image processing equipment and image processing method Download PDFInfo
- Publication number
- CN106033593A CN106033593A CN201510102800.9A CN201510102800A CN106033593A CN 106033593 A CN106033593 A CN 106033593A CN 201510102800 A CN201510102800 A CN 201510102800A CN 106033593 A CN106033593 A CN 106033593A
- Authority
- CN
- China
- Prior art keywords
- face
- region
- image
- roughness
- facial skin
- 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
- 238000012545 processing Methods 0.000 title claims abstract description 22
- 238000003672 processing method Methods 0.000 title claims abstract description 18
- 238000001914 filtration Methods 0.000 claims abstract description 12
- 230000001815 facial effect Effects 0.000 claims description 92
- 238000000034 method Methods 0.000 claims description 40
- 230000002401 inhibitory effect Effects 0.000 claims description 6
- 241000208340 Araliaceae Species 0.000 claims description 5
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 claims description 5
- 235000003140 Panax quinquefolius Nutrition 0.000 claims description 5
- 235000008434 ginseng Nutrition 0.000 claims description 5
- 238000009415 formwork Methods 0.000 claims 3
- 230000002087 whitening effect Effects 0.000 abstract 2
- 238000009499 grossing Methods 0.000 abstract 1
- 238000004590 computer program Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 210000000887 face Anatomy 0.000 description 3
- 239000007844 bleaching agent Substances 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 230000001413 cellular effect Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000037303 wrinkles Effects 0.000 description 2
- 206010013786 Dry skin Diseases 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 239000000654 additive Substances 0.000 description 1
- 230000000996 additive effect Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000013210 evaluation model Methods 0.000 description 1
- 230000003760 hair shine Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 230000035807 sensation Effects 0.000 description 1
Classifications
-
- G06T5/70—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30196—Human being; Person
- G06T2207/30201—Face
Abstract
The invention relates to image processing equipment which comprises the components of an image receiving module which is configured for receiving a to-be-processed image; a face area identification module which is configured for identifying a face area in the received image; a skin whitening module which is configured for processing pixels in the face area according to the brightness of a whole image and the brightness of the face area, thereby whitening the pixels in the face area; a face skin smoothing module which is configured for calculating face roughness of a face skin area in the face area and filtering the face skin area according to the face roughness; and an image output module which is configured for outputting the processed image. The invention further provides an image processing method. According to the image processing equipment and the image processing method, when a user wants to beautify the face skin in a picture, the face skin can be adaptively whitened according to the brightness of the face skin in the picture and the brightness of the whole picture, and furthermore the face skin can be adaptively smoothed according to the roughness of the face skin.
Description
Technical field
It relates to image processing techniques, more particularly, to a kind of to the face in image
Part carries out equipment and the method processed.
Background technology
Along with development and the development of multimedia equipment of multimedia technology, occur in that various application,
Facility is brought to the life of people.Such as, user is after photograph, it may be desirable to processes and shines
Sheet, then shares the photo after process with friend or household.
Such as, Chinese patent application CN201410042209.4 discloses a kind of based on without supervision
Optimum beautiful feature and the method for beautifying faces of depth evaluation model.The face beautified has not
Same type.
The most such as, Chinese patent application CN201410137069.9 discloses a kind of beautifying faces
Method, it pays close attention to the skin blemishes eliminated on face.
The most such as, Chinese patent application CN200810116057.2 discloses a kind of people's face skin
Beautification method, uses the projection vector of facial image.Projection vector may be used for reconstructing face figure
Picture, and do not include the HFS of facial image.
Additionally, korean patent application KR20070024140 proposes a kind of 3D face modeling it is
System and method, it considers individual for beautiful preference.
Chinese patent application CN201410042209.4 is focused mainly on beautifying of facial contours,
But facial skin is not beautified.
Chinese patent application CN201410137069.9 only processes skin blemishes, does not process
Other facial skin regions, and do not make whiteness of skin.
Chinese patent application CN200810116057.2 reconstructs facial image and does not include image
HFS, but this patent application does not make facial skin bleach.
Korean patent application KR20070024140 is focused mainly on the modeling of 3D face.
Generally, user may want to the facial skin beautifying in photo adaptively.
Summary of the invention
As it has been described above, existing image processing method, especially method for beautifying faces, have one
A little problems, it is difficult to self adaptation beautifies face, it is difficult to provide good Consumer's Experience.
Present disclosure proposes a kind of image processing equipment and method, it is possible to adaptively in photo
Facial skin beautify.
According to an aspect of this disclosure, it is proposed that a kind of image processing equipment, including:
Image receiver module, is configured to receive pending image；
Face area identification module, is configured to identify the human face region in the image received；
Whiteness of skin module, is configured to the brightness of the brightness according to whole image and human face region,
Pixel in human face region is processed so that the pixel in human face region bleaches；
Facial skin Leveling Block, the facial skin region being configured in calculating human face region
Face's roughness, and according to described face roughness, facial skin region is filtered；And
Image output module, is configured to the image after output processes,
Wherein, described whiteness of skin module is configured to calculate human face region according to below equation
In the gain gain of pixel:
Gain=cl*(gc+tg)
Wherein, gcIt is the gain constant factor, tg=exp (-bf*cl+ β-s), s=log (η+
gp), s is highlights inhibitive factor, β and η is steady state value, local contrast cl=gp/gt,
Wherein gpIt is the gray value of this pixel, gtIt it is the total ash in the k*k region centered by this pixel
Angle value, k is the constant specified.
Luminance factor bfIt is calculated as follows:
α is predetermined threshold value, CgIt is steady state value, x=gf*gf, y=gf*C2, t=(α-gf)/α,
C2It is steady state value, gfIt is the average gray value of human face region,
And
By the gray value of the pixel in human face region is multiplied with gain gain so that face district
Pixel in territory bleaches.
According to another aspect of the present disclosure, it is proposed that a kind of image processing method, including: image
Processing method, including:
Receive pending image；
Identify the human face region in the image received；
Brightness according to whole image and the brightness of human face region, enter the pixel in human face region
Row processes so that the pixel in human face region bleaches；
Face's roughness in the facial skin region in calculating human face region, and according to described face
Facial skin region is filtered by roughness, and
Image after output process,
Wherein, the gain gain of pixel in human face region is calculated according to below equation:
Gain=cl*(gc+tg)
Wherein, gcIt is the gain constant factor, tg=exp (-bf*cl+ β-s), s=log (η+
gp), s is highlights inhibitive factor, β and η is steady state value, local contrast cl=gp/gt,
Wherein gpIt is the gray value of this pixel, gtIt it is the total ash in the k*k region centered by this pixel
Angle value, k is the constant specified.
Luminance factor bfIt is calculated as follows:
α is predetermined threshold value, CgIt is steady state value, x=gf*gf, y=gf*C2, t=(α-gf)/α,
C2It is steady state value, gfIt is the average gray value of human face region,
And
By the gray value of the pixel in human face region is multiplied with gain gain so that face district
Pixel in territory bleaches.
According to the technical scheme of the disclosure, when user wants the facial skin in photo is carried out U.S.
During change, can make adaptively according to the brightness of facial skin in photo and the brightness of whole photo
Facial skin bleaches, and smooths facial skin adaptively according to the roughness of facial skin.
Accompanying drawing explanation
According to following description, the additional object of the present invention, feature and advantage will be more readily apparent from.
And, according to following explanation referring to the drawings, advantages of the present invention would is that it will be evident that accompanying drawing
In:
Fig. 1 shows the image processing equipment of the one or more embodiments according to the disclosure
Schematic block diagram.
Fig. 2 shows the image processing method of the one or more embodiments according to the disclosure
Flow chart.
Fig. 3 shows showing of the facial skin region according to one or more embodiments of the invention
It is intended to.
Detailed description of the invention
Referring to the drawings, example embodiment of this disclosure is described in detail.Retouch following
In stating, some specific embodiments are only used for describing purpose, and should not be construed and have the disclosure
Any restriction, and the example of the simply disclosure.It is mixed understanding of this disclosure may be caused to cause
When confusing, conventional structure or structure will be omitted.
Fig. 1 shows the image processing equipment of the one or more embodiments according to the disclosure
The schematic block diagram of 1000.As it can be seen, this image processing equipment 1000 includes: image-receptive
Module 1100, is configured to receive pending image；Face area identification module 1200, quilt
It is configured to identify the human face region in the image received；Whiteness of skin module 1300, is configured
For the brightness according to whole image and the brightness of human face region, the pixel in human face region is carried out
Process so that the pixel in human face region bleaches；Facial skin Leveling Block 1400, is configured
For calculating face's roughness in the facial skin region in human face region and thick according to described face
Facial skin region is filtered by rugosity, and image output module 1500, is configured to defeated
Go out the image after processing.
Wherein, described whiteness of skin module 1300 is configured to calculate face according to below equation
The gain gain of the pixel in region:
Gain=cl*(gc+tg)
Wherein, gcIt is the gain constant factor, tg=exp (-bf*cl+ β-s), s=log (η+
gp), s is highlights inhibitive factor, β and η is steady state value, local contrast cl=gp/gt,
Wherein gpIt is the gray value of this pixel, gtIt it is the total ash in the k*k region centered by this pixel
Angle value, k is the constant specified, such as, k=2,4,8 etc..
Luminance factor bfIt is calculated as follows:
α is predetermined threshold value, CgIt is steady state value, x=gf*gf, y=gf*C2, t=(α-gf)/α,
C2It is steady state value, gfIt is the average gray value of human face region, by calculating the picture in human face region
The average gray of element obtains.
By the gray value of the pixel in human face region is multiplied with gain gain so that face district
Pixel in territory bleaches.
According to embodiments of the invention, can bright according to the brightness of facial skin and whole image
Degree makes facial skin bleach adaptively.
In luminance factor bfCalculating in, C2, α and CgBeing all predetermined threshold value, its setting makes not
Same luminance factor gfCalculated bfValue is the most continuously.In the calculating of gain gain,
gc, β and η be all predetermined threshold value, its setting makes different gpCalculated gain gain falls
Enter suitable scope.
As example, g can be setcBeing 1.0, α is 0.3, CgIt is 1.0, C2Be 1.3, β and
η is respectively 0.001 and 0.0001.Certainly, other suitable values are also feasible.Such as,
{C2, α, Cg, gc, β, η } can be chosen as 1.3,0.5,0.8,1.2,0.002,0.00001} or
{ 1.2,0.4,0.9,1.25,0.005,0.00002}.
According to one or more embodiments, described face area identification module 1200 is configured to:
According to active shape model (ASM) or active appearance models (AAM) or other feasible methods,
Identify the human face region in the image received and the face in human face region, wherein, described people
Facial skin region in face region is the region in described human face region in addition to described face.
According to one or more embodiments, described facial skin Leveling Block 1400 can be configured to:
Use two groups of parameters that described facial skin region is filtered, to obtain two facial skin figures
Picture, calculate said two facial skin image difference, obtain difference image, the most often group parameter by
Gray value and pixel space size are constituted；And use the average gray value of difference image to estimate face
Portion's roughness.The average gray value of described difference image is the biggest, and described face roughness is the biggest.
According to one or more embodiments, described facial skin Leveling Block 1400 can be configured to:
Use two groups of parameters that described facial skin region is filtered, to obtain two facial skin figures
Picture, calculate said two facial skin image difference, obtain difference image, the most often group parameter by
Gray value and pixel space size are constituted；By fixed threshold dividing method, difference image is divided
For multiple zonules；Calculate area size and the average gray value of each zonule；According to each
The average gray value of zonule, calculates the zonule roughness of each zonule；And according to respectively
The area size of individual zonule, is weighted zonule roughness, to obtain face's roughness.
According to one or more embodiments, described face Leveling Block 1400 can be configured to: makes
Face's roughness is estimated by the size in described facial skin region.Described facial skin region is more
Greatly, described face roughness is the biggest.
Described facial skin Leveling Block 1400 is configured to: control according to described face roughness
The filtering degree that facial skin region is filtered by system.
As it has been described above, facial skin Leveling Block 1400 can use at least three kinds of methods to estimate
Face's roughness.Therefore, according to embodiments of the invention, can be according to facial skin roughness
Smooth facial skin adaptively.
Fig. 2 shows the image processing method of the one or more embodiments according to the disclosure
The flow chart of 2000.
As in figure 2 it is shown, the method starts from step S2100, in step S2100, receive
Pending image.Then in step S2200, the human face region in the image received is identified.
In step S2300, according to brightness and the brightness of human face region of whole image, to human face region
In pixel process so that the pixel in human face region bleaches.Then, in step S2400,
Face's roughness in the facial skin region in calculating human face region, and coarse according to described face
Facial skin region is filtered by degree.Finally, the figure after step S2500, output process
Picture,
Wherein, the gain gain of pixel in human face region is calculated according to below equation:
Gain=cl*(gc+tg)
Wherein, gcIt is the gain constant factor, tg=exp (-bf*cl+ β-s), s=log (η+
gp), s is highlights inhibitive factor, β and η is steady state value, local contrast cl=gp/gt,
Wherein gpIt is the gray value of this pixel, gtIt it is the total ash in the k*k region centered by this pixel
Angle value, k be the constant specified, such as k be 2,4 or 8.
Luminance factor bfIt is calculated as follows:
α is predetermined threshold value, CgIt is steady state value, x=gf*gf, y=gf*C2, t=(α-gf)/α,
C2It is steady state value, gfIt is the average gray value of human face region,
And
By the gray value of the pixel in human face region is multiplied with gain gain so that face district
Pixel in territory bleaches.
According to one or more embodiments of the invention, identify the face district in the image received
The step in territory comprises the steps that according to active shape model (ASM) or active appearance models (AAM)
Or other feasible method, identify the human face region in the image received and five in human face region
Official.Wherein, the facial skin region in described human face region is except described in described human face region
Region outside face.So so that process only for the facial skin in human face region,
Image after the process obtained is more accurate.
Fig. 3 shows showing of the facial skin region according to one or more embodiments of the invention
It is intended to.As it can be seen, according to ASM or AAM or other known methods, reception can be identified
To image in human face region and the eyes of key component therein, i.e. people, nose and mouth
Bars etc., then, are used for estimating that face is coarse by region in addition to key component in human face region
Degree.As it is shown on figure 3, the region on figure mean camber line is human face region, hatched example areas is respectively
The nose of people and face, therefore, the part in addition to hatched example areas of the region on camber line is
Facial skin region.
According to one or more embodiments of the invention, calculate the facial skin district in human face region
The step of face's roughness in territory comprises the steps that described facial skin region is entered by two groups of parameters of use
Row filters, and to obtain two facial skin images, calculates the difference of said two facial skin image,
Obtaining difference image, the most often group parameter is made up of gray value and pixel space size；And use
The average gray value of difference image estimates face's roughness.The average gray value of described difference image is more
Greatly, described face roughness is the biggest.
In this application, the selection of two groups of parameters can be default to arrange in systems, from
Select without user.For example, it is possible to two groups of parameters of application can be respectively
(0.05,0.01) and (15.5,0.01).Time actually used, two groups of parameters are fixing.Use two groups of ginsengs
The roughness that number estimates is not necessarily consistent with the real roughness degree of people's sensation, it is only necessary to obtain
The different relative coarseness degree between real roughness degree is the most permissible.
According to one or more embodiments of the invention, calculate the facial skin district in human face region
The step of face's roughness in territory comprises the steps that described facial skin region is entered by two groups of parameters of use
Row filters, and to obtain two facial skin images, calculates the difference of said two facial skin image,
Obtaining difference image, the most often group parameter is made up of gray value and pixel space size；By fixing
Threshold segmentation method, is divided into multiple zonule by difference image；Calculate the region of each zonule
Size and average gray value；According to the average gray value of each zonule, calculate each zonule
Zonule roughness；And the area size according to each zonule, to zonule roughness
It is weighted, to obtain face's roughness.
Facial skin region is divided into zonule by the method, is then weighted zonule
Face's roughness to whole facial skin region.Compared with former approach, although amount of calculation
Slightly larger, but the most accurate face roughness can be obtained.For example, it is possible to by cheek region
Weighted value to be arranged with respect to the weighted value in other regions bigger so that can be preferably to face
Territory, buccal region smooths.The most such as, for circumference of eyes relative to other region wrinkles of face the most more
Many people, can be arranged with respect to the weighting in other regions by the weighted value in circumference of eyes region
It is worth bigger so that can preferably the wrinkle of face be smoothed.
According to one or more embodiments of the invention, calculate the facial skin district in human face region
The step of face's roughness in territory comprises the steps that the size using described facial skin region is estimated
Face's roughness.Described facial skin region is the biggest, and described face roughness is the biggest.The method
Compared to additive method, amount of calculation is minimum.
According to one or more embodiments of the invention, according to described face roughness to face's skin
The step that skin region carries out filtering includes: control facial skin according to described face roughness
Region carries out the filtering degree filtered.
According to one or more embodiments, directly can be controlled according to face's roughness by system
The filtering degree in facial skin region to be put on.According to other one or more embodiments, also
Can be selected filtering degree by user, the filtering degree then user selected is taken advantage of with face's roughness
The long-pending filtering degree as facial skin region to be put on, so that smooth image is both according to photograph
In sheet, the roughness of facial skin filters adaptively, also reflects the filtration that user needs
Degree.
Other of disclosure embodiment disclosed herein arrange the side including performing formerly to summarize
The software program of the steps and operations of method embodiment.More specifically, computer program be as
Under a kind of embodiment: there is computer-readable medium, on computer-readable medium coding have meter
Calculating machine program logic, when performing on the computing device, computer program logic provides relevant
Operation, thus technique scheme is provided.When holding at least one processor in the system of calculating
During row, computer program logic makes processor perform the operation (side described in disclosure embodiment
Method).This set of the disclosure is typically provided as arranging or encoding at such as light medium (such as
CD-ROM), the software on the computer-readable medium of floppy disk or hard disk etc., code and/or its
On his data structure or the most one or more ROM or RAM or PROM chip
Other media of firmware or microcode or special IC (ASIC) or one or more
Downloadable software image in module, shared data bank etc..Software or firmware or this configuration
May be installed on calculating equipment, so that the one or more processors in calculating equipment perform basis
Open technology described in embodiment.In conjunction with in such as one group of data communications equipment or other entities
The software process that calculating equipment carries out operating can also provide the equipment according to the disclosure.According to this
Multiple software process that disclosed equipment can also be distributed in multiple data communications equipment or
Transport on all software process run on one group of small, dedicated computer or single computer
Between all software process of row.
It should be understood that strictly say, embodiment of the disclosure and can be implemented as on computer equipment
Software program, software and hardware or individually software and/or individually circuit.
It should be noted that, in the above description, the most in an illustrative manner, it is shown that these public affairs
The technical scheme opened, but it is not meant to that the disclosure is confined to above-mentioned steps and cellular construction.?
When possible, as required step and cellular construction can be adjusted and accept or reject.Cause
This, some step and unit not implement element necessary to the generic disclosure thought of the disclosure.
Therefore, technical characteristic necessary to the disclosure is limited solely by the generic disclosure being capable of the disclosure
The minimum requirements of thought, and do not limited by above instantiation.
So far already in connection with preferred embodiment, the disclosure is described.It should be understood that ability
Field technique personnel in the case of without departing from the spirit and scope of the disclosure, can carry out various its
Its change, replace and add.Therefore, the scope of the present disclosure is not limited to above-mentioned particular implementation
Example, and should be defined by the appended claims.
Claims (20)
1. an image processing equipment, including:
Image receiver module, is configured to receive pending image；
Face area identification module, is configured to identify the human face region in the image received；
Whiteness of skin module, is configured to the brightness of the brightness according to whole image and human face region,
Pixel in human face region is processed so that the pixel in human face region bleaches；
Facial skin Leveling Block, the facial skin region being configured in calculating human face region
Face's roughness, and according to described face roughness, facial skin region is filtered, and
Image output module, is configured to the image after output processes,
Wherein, described whiteness of skin module is configured to calculate human face region according to below equation
In the gain gain of pixel:
Gain=cl*(gc+tg)
Wherein, gcIt is the gain constant factor, tg=exp (-bf*cl+ β-s), s=log (η+
gp), s is highlights inhibitive factor, β and η is steady state value, local contrast cl=gp/gt,
Wherein gpIt is the gray value of this pixel, gtIt it is the total ash in the k*k region centered by this pixel
Angle value, k is the constant specified,
Luminance factor bfIt is calculated as follows:
α is predetermined threshold value, CgIt is steady state value, x=gf*gf, y=gf*C2, t=(α-gf)/α,
C2It is steady state value, gfIt is the average gray value of human face region,
And
By the gray value of the pixel in human face region is multiplied with gain gain so that face district
Pixel in territory bleaches.
Image processing equipment the most according to claim 1, wherein, described facial skin is put down
Sliding formwork block is configured to:
Use two groups of parameters that described facial skin region is filtered, to obtain Liang Ge face skin
Skin image, calculates the difference of said two facial skin image, obtains difference image, the most often organize ginseng
Number is made up of gray value and pixel space size；And
The average gray value using difference image estimates face's roughness.
Image processing equipment the most according to claim 2, wherein, putting down of described difference image
All gray values are the biggest, and described face roughness is the biggest.
Image processing equipment the most according to claim 1, wherein, described facial skin is put down
Sliding formwork block is configured to:
Use two groups of parameters that described facial skin region is filtered, to obtain Liang Ge face skin
Skin image, calculates the difference of said two facial skin image, obtains difference image, the most often organize ginseng
Number is made up of gray value and pixel space size；
By fixed threshold dividing method, difference image is divided into multiple zonule；
Calculate area size and the average gray value of each zonule；
According to the average gray value of each zonule, calculate the zonule roughness of each zonule；
And
According to the area size of each zonule, zonule roughness is weighted, to obtain
Face's roughness.
Image processing equipment the most according to claim 1, wherein, described facial skin is put down
Sliding formwork block is configured to:
Use the size in described facial skin region to estimate face's roughness.
Image processing equipment the most according to claim 5, wherein, described facial skin district
Territory is the biggest, and described face roughness is the biggest.
Image processing equipment the most according to claim 1, wherein said facial skin smooths
Module is configured to: control to filter facial skin region according to described face roughness
Filtering degree.
Image processing equipment the most according to claim 1, wherein, C2, α and CgArrange
Make different gfCalculated luminance factor bfValue is the most continuous, and gc, β and η arrange
Make different gpCalculated gain gain falls into suitable scope.
Image processing equipment the most according to claim 8, wherein, { C2, α, Cg, gc, β, η }
It is one below: { 1.3,0.3,1.0,1.0,0.001,0.0001}；
{ 1.3,0.5,0.8,1.2,0.002,0.00001}；{ 1.2,0.4,0.9,1.25,0.005,0.00002}.
Image processing equipment the most according to claim 1, wherein, described human face region
In facial skin region be region in addition to face in described human face region.
11. 1 kinds of image processing methods, including:
Receive pending image；
Identify the human face region in the image received；
Brightness according to whole image and the brightness of human face region, enter the pixel in human face region
Row processes so that the pixel in human face region bleaches；
Face's roughness in the facial skin region in calculating human face region, and according to described face
Facial skin region is filtered by roughness, and
Image after output process,
Wherein, the gain gain of pixel in human face region is calculated according to below equation:
Gain=cl*(gc+tg)
Wherein, gcIt is the gain constant factor, tg=exp (-bf*cl+ β-s), s=log (η+
gp), s is highlights inhibitive factor, β and η is steady state value, local contrast cl=gp/gt,
Wherein gpIt is the gray value of this pixel, gtIt it is the total ash in the k*k region centered by this pixel
Angle value, k is the constant specified,
Luminance factor bfIt is calculated as follows:
α is predetermined threshold value, CgIt is steady state value, x=gf*gf, y=gf*C2, t=(α-gf)/α,
C2It is steady state value, gfIt is the average gray value of human face region,
And
By the gray value of the pixel in human face region is multiplied with gain gain so that face district
Pixel in territory bleaches.
12. image processing methods according to claim 11, wherein, calculate human face region
In face's roughness in facial skin region include:
Use two groups of parameters that described facial skin region is filtered, to obtain Liang Ge face skin
Skin image, calculates the difference of said two facial skin image, obtains difference image, the most often organize ginseng
Number is made up of gray value and pixel space size；And
The average gray value using difference image estimates face's roughness.
13. image processing methods according to claim 12, wherein, described difference image
Average gray value is the biggest, and described face roughness is the biggest.
14. image processing methods according to claim 11, wherein, calculate human face region
In face's roughness in facial skin region include:
Use two groups of parameters that described facial skin region is filtered, to obtain Liang Ge face skin
Skin image, calculates the difference of said two facial skin image, obtains difference image, the most often organize ginseng
Number is made up of gray value and pixel space size；
By fixed threshold dividing method, difference image is divided into multiple zonule；
Calculate area size and the average gray value of each zonule；
According to the average gray value of each zonule, calculate the zonule roughness of each zonule；
And
According to the area size of each zonule, zonule roughness is weighted, to obtain
Face's roughness.
15. image processing methods according to claim 11, wherein, calculate human face region
In face's roughness in facial skin region include:
Use the size in described facial skin region to estimate face's roughness.
16. image processing methods according to claim 15, wherein, described facial skin
Region is the biggest, and described face roughness is the biggest.
17. image processing methods according to claim 11 are wherein thick according to described face
Rugosity carries out filtration to facial skin region and includes: control face according to described face roughness
Portion's skin area carries out the filtering degree filtered.
18. image processing methods according to claim 11, wherein, C2, α and CgIf
Put so that different gfCalculated luminance factor bfValue is the most continuous, and gc, β and η set
Put so that different gpCalculated gain gain falls into suitable scope.
19. image processing methods according to claim 18, wherein,
{C2, α, Cg, gc, β, η } be one below:
{ 1.3,0.3,1.0,1.0,0.001,0.0001}；{ 1.3,0.5,0.8,1.2,0.002,0.00001}；
{ 1.2,0.4,0.9,1.25,0.005,0.00002}；
20. image processing methods according to claim 11, wherein, described human face region
In facial skin region be region in addition to face in described human face region.
Priority Applications (3)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510102800.9A CN106033593A (en) | 2015-03-09 | 2015-03-09 | Image processing equipment and image processing method |
| PCT/CN2016/075789 WO2016141866A1 (en) | 2015-03-09 | 2016-03-07 | Image processing device and method |
| JP2017544939A JP6437664B2 (en) | 2015-03-09 | 2016-03-07 | Image processing apparatus and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510102800.9A CN106033593A (en) | 2015-03-09 | 2015-03-09 | Image processing equipment and image processing method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106033593A true CN106033593A (en) | 2016-10-19 |
Family
ID=56880009
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510102800.9A Pending CN106033593A (en) | 2015-03-09 | 2015-03-09 | Image processing equipment and image processing method |
Country Status (3)
| Country | Link |
|---|---|
| JP (1) | JP6437664B2 (en) |
| CN (1) | CN106033593A (en) |
| WO (1) | WO2016141866A1 (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107346544A (en) * | 2017-06-30 | 2017-11-14 | 联想(北京)有限公司 | A kind of image processing method and electronic equipment |
| CN107358601A (en) * | 2017-06-16 | 2017-11-17 | 广东欧珀移动通信有限公司 | Facial smoothness computational methods and device |
| CN107784175A (en) * | 2017-10-26 | 2018-03-09 | 深圳市雷鸟信息科技有限公司 | Light scanning control method and device and readable storage medium |
| CN107784629A (en) * | 2017-11-24 | 2018-03-09 | 努比亚技术有限公司 | Distant view photograph filter processing method and mobile terminal |
| CN108154483A (en) * | 2016-12-02 | 2018-06-12 | 卡西欧计算机株式会社 | Image Processing Apparatus, Image Processing Method And Recording Medium |
| CN108537155A (en) * | 2018-03-29 | 2018-09-14 | 广东欧珀移动通信有限公司 | Image processing method, device, electronic equipment and computer readable storage medium |
| CN108647600A (en) * | 2018-04-27 | 2018-10-12 | 深圳爱酷智能科技有限公司 | Face identification method, equipment and computer readable storage medium |
| CN109299632A (en) * | 2017-07-25 | 2019-02-01 | 上海中科顶信医学影像科技有限公司 | Skin detecting method, system, equipment and storage medium |
| CN111857512A (en) * | 2020-07-17 | 2020-10-30 | 维沃移动通信有限公司 | Image editing method and device and electronic equipment |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108428214B (en) * | 2017-02-13 | 2022-03-08 | 斑马智行网络(香港)有限公司 | Image processing method and device |
| CN107886469A (en) * | 2017-09-26 | 2018-04-06 | 北京潘达互娱科技有限公司 | A kind of image beautification method, device, electronic equipment and storage medium |
| CN108230331A (en) | 2017-09-30 | 2018-06-29 | 深圳市商汤科技有限公司 | Image processing method and device, electronic equipment, computer storage media |
| CN109685915B (en) * | 2018-12-11 | 2023-08-15 | 维沃移动通信有限公司 | Image processing method and device and mobile terminal |
| CN110944112A (en) * | 2019-11-22 | 2020-03-31 | 维沃移动通信有限公司 | Image processing method and electronic equipment |
| CN111507944B (en) * | 2020-03-31 | 2023-07-04 | 北京百度网讯科技有限公司 | Determination method and device for skin smoothness and electronic equipment |
| CN114219718A (en) * | 2020-09-04 | 2022-03-22 | 广州虎牙科技有限公司 | Skin processing method, live broadcast method, computer equipment and storage medium |
Family Cites Families (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP4182735B2 (en) * | 2002-11-28 | 2008-11-19 | ソニー株式会社 | Facial color correction method, facial color correction apparatus, and imaging device |
| JP2007036410A (en) * | 2005-07-25 | 2007-02-08 | Seiko Epson Corp | Image processing for making human skin in good condition |
| WO2010012448A2 (en) * | 2008-07-30 | 2010-02-04 | Fotonation Ireland Limited | Automatic face and skin beautification using face detection |
| JP2010244239A (en) * | 2009-04-03 | 2010-10-28 | Nikon Corp | Image processor, digital camera and program |
| JP4983962B2 (en) * | 2009-07-23 | 2012-07-25 | カシオ計算機株式会社 | Image processing apparatus, image processing method, and image processing program |
| CN103839250B (en) * | 2012-11-23 | 2017-03-01 | 诺基亚技术有限公司 | The method and apparatus processing for face-image |
| CN103268475A (en) * | 2013-05-10 | 2013-08-28 | 中科创达软件股份有限公司 | Skin beautifying method based on face and skin color detection |
| CN103455790B (en) * | 2013-06-24 | 2017-10-13 | 厦门美图网科技有限公司 | A kind of skin identification method based on complexion model |
| CN103927719B (en) * | 2014-04-04 | 2017-05-17 | 北京猎豹网络科技有限公司 | Picture processing method and device |
| CN104318262A (en) * | 2014-09-12 | 2015-01-28 | 上海明穆电子科技有限公司 | Method and system for replacing skin through human face photos |
-
2015
- 2015-03-09 CN CN201510102800.9A patent/CN106033593A/en active Pending
-
2016
- 2016-03-07 WO PCT/CN2016/075789 patent/WO2016141866A1/en active Application Filing
- 2016-03-07 JP JP2017544939A patent/JP6437664B2/en not_active Expired - Fee Related
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108154483A (en) * | 2016-12-02 | 2018-06-12 | 卡西欧计算机株式会社 | Image Processing Apparatus, Image Processing Method And Recording Medium |
| CN108154483B (en) * | 2016-12-02 | 2022-05-31 | 卡西欧计算机株式会社 | Image processing apparatus, image processing method, and recording medium |
| CN107358601B (en) * | 2017-06-16 | 2020-02-28 | Oppo广东移动通信有限公司 | Face smoothness calculation method and device |
| CN107358601A (en) * | 2017-06-16 | 2017-11-17 | 广东欧珀移动通信有限公司 | Facial smoothness computational methods and device |
| CN107346544A (en) * | 2017-06-30 | 2017-11-14 | 联想(北京)有限公司 | A kind of image processing method and electronic equipment |
| CN107346544B (en) * | 2017-06-30 | 2020-05-26 | 联想(北京)有限公司 | Image processing method and electronic equipment |
| CN109299632A (en) * | 2017-07-25 | 2019-02-01 | 上海中科顶信医学影像科技有限公司 | Skin detecting method, system, equipment and storage medium |
| CN107784175A (en) * | 2017-10-26 | 2018-03-09 | 深圳市雷鸟信息科技有限公司 | Light scanning control method and device and readable storage medium |
| CN107784175B (en) * | 2017-10-26 | 2021-11-09 | 深圳市雷鸟网络传媒有限公司 | Light scanning control method and device and readable storage medium |
| CN107784629B (en) * | 2017-11-24 | 2021-10-15 | 努比亚技术有限公司 | Panoramic photo filter processing method and mobile terminal |
| CN107784629A (en) * | 2017-11-24 | 2018-03-09 | 努比亚技术有限公司 | Distant view photograph filter processing method and mobile terminal |
| CN108537155A (en) * | 2018-03-29 | 2018-09-14 | 广东欧珀移动通信有限公司 | Image processing method, device, electronic equipment and computer readable storage medium |
| CN108537155B (en) * | 2018-03-29 | 2021-01-26 | Oppo广东移动通信有限公司 | Image processing method, image processing device, electronic equipment and computer readable storage medium |
| CN108647600A (en) * | 2018-04-27 | 2018-10-12 | 深圳爱酷智能科技有限公司 | Face identification method, equipment and computer readable storage medium |
| CN108647600B (en) * | 2018-04-27 | 2021-10-08 | 深圳爱酷智能科技有限公司 | Face recognition method, face recognition device and computer-readable storage medium |
| WO2022012657A1 (en) * | 2020-07-17 | 2022-01-20 | 维沃移动通信有限公司 | Image editing method and apparatus, and electronic device |
| CN111857512A (en) * | 2020-07-17 | 2020-10-30 | 维沃移动通信有限公司 | Image editing method and device and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2016141866A1 (en) | 2016-09-15 |
| JP6437664B2 (en) | 2018-12-12 |
| JP2018512651A (en) | 2018-05-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106033593A (en) | Image processing equipment and image processing method | |
| CN104811684B (en) | A kind of three-dimensional U.S. face method and device of image | |
| US9691136B2 (en) | Eye beautification under inaccurate localization | |
| US8681241B2 (en) | Automatic face and skin beautification using face detection | |
| CN105243371B (en) | A kind of detection method, system and the camera terminal of face U.S. face degree | |
| CN108447017A (en) | Face virtual face-lifting method and device | |
| CN106682632A (en) | Method and device for processing face images | |
| CN111031239B (en) | Image processing method and apparatus, electronic device, and computer-readable storage medium | |
| CN105578028A (en) | Photographing method and terminal | |
| CN108765264B (en) | Image beautifying method, device, equipment and storage medium | |
| CN109634320B (en) | Water outlet temperature adjusting platform | |
| CN103456032A (en) | Method and device for processing virtual fitting model images | |
| CN109255768A (en) | Image completion method, apparatus, terminal and computer readable storage medium | |
| Bacchuwar et al. | A jump patch-block match algorithm for multiple forgery detection | |
| CN109214996A (en) | A kind of image processing method and device | |
| CN106557729A (en) | For processing the apparatus and method of facial image | |
| KR20210092138A (en) | System and method for multi-frame contextual attention for multi-frame image and video processing using deep neural networks | |
| CN108346128B (en) | Method and device for beautifying and peeling | |
| CN107491714A (en) | Intelligent robot and its target object recognition methods and device | |
| GB2536715A (en) | Image processing method | |
| CN109003236B (en) | Self-adaptive buffing method and system based on separation of human face tone and light and shadow | |
| CN109646950B (en) | Image processing method and device applied to game scene and terminal | |
| CN114742725A (en) | Image processing method, image processing device, electronic equipment and storage medium | |
| Zachevsky et al. | Model-based color natural stochastic textures processing and classification | |
| Zachevsky et al. | Combining long-range dependencies with phase information in Natural Stochastic Texture enhancement |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20161019 |