CN106611402B - Image processing method and device - Google Patents
Image processing method and device Download PDFInfo
- Publication number
- CN106611402B CN106611402B CN201510697934.XA CN201510697934A CN106611402B CN 106611402 B CN106611402 B CN 106611402B CN 201510697934 A CN201510697934 A CN 201510697934A CN 106611402 B CN106611402 B CN 106611402B
- Authority
- CN
- China
- Prior art keywords
- image
- pixel
- mask
- original image
- brightness adjustment
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000003672 processing method Methods 0.000 title claims abstract description 27
- 239000011159 matrix material Substances 0.000 claims abstract description 49
- 230000009466 transformation Effects 0.000 claims abstract description 49
- 238000009499 grossing Methods 0.000 claims abstract description 32
- 238000000034 method Methods 0.000 claims description 44
- 238000003491 array Methods 0.000 claims description 3
- 238000005303 weighing Methods 0.000 claims 1
- 230000002087 whitening effect Effects 0.000 abstract description 17
- 230000000694 effects Effects 0.000 abstract description 14
- 230000015654 memory Effects 0.000 description 22
- 238000010586 diagram Methods 0.000 description 10
- 238000005516 engineering process Methods 0.000 description 10
- 238000006243 chemical reaction Methods 0.000 description 7
- 238000005282 brightening Methods 0.000 description 6
- 239000003086 colorant Substances 0.000 description 6
- 238000004891 communication Methods 0.000 description 6
- 230000002093 peripheral effect Effects 0.000 description 5
- 230000005540 biological transmission Effects 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000001514 detection method Methods 0.000 description 2
- 235000013399 edible fruits Nutrition 0.000 description 2
- 238000010295 mobile communication Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000003321 amplification Effects 0.000 description 1
- 230000003796 beauty Effects 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 239000007795 chemical reaction product Substances 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 230000003760 hair shine Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 238000003199 nucleic acid amplification method Methods 0.000 description 1
- 231100000289 photo-effect Toxicity 0.000 description 1
- 238000003825 pressing Methods 0.000 description 1
- 239000000047 product Substances 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/04—Context-preserving transformations, e.g. by using an importance map
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
Abstract
The present invention provides a kind of image processing method, comprising: obtains original image;Determine the specified region in the original image;For the specified Area generation mask code matrix;Grey scale transformation is carried out to the original image according to the mask code matrix;And edge-smoothing processing and whole equalization processing are carried out to the general image of the picture after progress grey scale transformation.The present invention also provides a kind of image processing apparatus.Above-mentioned image processing method and device can realize the colour of skin whitening effect of personage in photo and simple, convenient, handle photo for user, picture brings better experience effect.
Description
Technical field
The present invention relates to field of computer technology more particularly to a kind of image processing methods and device.
Background technique
End product with digital camera, mobile phone, tablet computer etc. with camera it is universal, the chance that people take pictures is got over
Come it is more, it is also more and more using the occasion of photo.Such as when being in the place that beautiful environment or just bought a novel clothes
When, it is desirable to by the place where oneself and wear the looks of new clothing and be shared with relatives and friends, whipped energy using mobile phone
It is taken a picture for oneself, and other people is shared with by social software, such as instant messaging product (QQ, wechat, Skype etc.).
But due to light, apparatus for making a video recording, shooting angle etc., photo effect after shooting, especially colour of skin portion
Point, it is often not fully up to expectations.Especially for people seeking beauty, if the colour of skin of personage is obscure in photo, shooting effect will be unsatisfied with,
Therefore, photo can be handled using softwares such as Photoshop before using photo, entire photo is highlighted, is made in photo
The colour of skin of personage bleaches.However, such method operation is more troublesome, learning cost is higher, and general user is difficult to grasp, Er Qie
When entire photo is highlighted, it is easy overexposure, so that the image in photo is seemed unnatural, reduces the whole table of photo instead
Existing effect.
Summary of the invention
In view of this, the present invention a kind of image processing method and device are provided, it can be achieved that in photo personage colour of skin whitening
Effect and simple, convenient handles photo for user, picture brings better experience effect.
A kind of image processing method provided in an embodiment of the present invention, comprising: obtain original image;Determine the original image
In specified region;For the specified Area generation mask code matrix;The original image is carried out according to the mask code matrix
Grey scale transformation;And the general image of the picture after progress grey scale transformation is carried out at edge-smoothing processing and whole equalization
Reason.
A kind of image processing apparatus provided in an embodiment of the present invention, comprising: picture obtains module, for obtaining original graph
Piece;Specified area determination module, for determining the specified region in the original image;Mask code matrix generation module is used for needle
To the specified Area generation mask code matrix;Grey scale transformation module, for according to the mask code matrix to the original image into
Row grey scale transformation;And disposed of in its entirety module, edge-smoothing is carried out for the general image to the picture after progress grey scale transformation
Processing and whole equalization processing.
Image processing method and device provided in an embodiment of the present invention, can be by ratio stretching conversion, to the finger in picture
Determine region, for example, the colour of skin carry out it is smooth highlight, avoid blooming, it can be achieved that the colour of skin whitening effect of personage in photo,
And it is simple, convenient, photo is handled for user, picture brings better experience effect.
For above and other objects, features and advantages of the invention can be clearer and more comprehensible, preferred embodiment is cited below particularly,
And cooperate institute's accompanying drawings, it is described in detail below.
Detailed description of the invention
Fig. 1 is one embodiment of terminal device applied by image processing method provided in an embodiment of the present invention and device
Structural block diagram.
Fig. 2 is the flow diagram for the image processing method that first embodiment of the invention provides.
Fig. 3 is the flow diagram of the major sub-steps of the step S14 in Fig. 2.
Fig. 4 is the flow diagram for the image processing method that second embodiment of the invention provides.
Fig. 5 is the flow diagram for the image processing method that third embodiment of the invention provides.
Fig. 6 is the structural block diagram for the image processing apparatus that fourth embodiment of the invention provides.
Fig. 7 is the structural block diagram for the image processing apparatus that fifth embodiment of the invention provides.
Fig. 8 is the structural block diagram for the image processing apparatus that sixth embodiment of the invention provides.
Specific embodiment
Further to illustrate that the present invention is the technical means and efficacy realizing predetermined goal of the invention and being taken, below in conjunction with
Attached drawing and preferred embodiment, to specific embodiment, structure, feature and its effect according to the present invention, detailed description is as follows.
Referring to FIG. 1, Fig. 1 is terminal device applied by image processing method provided in an embodiment of the present invention and device
The structural block diagram of one embodiment.Terminal device can be various electronic devices, as PC, laptop, tablet computer,
Mobile phone etc..As shown in Figure 1, terminal device includes memory 102, storage control 104, one or more (only shows one in figure
It is a) processor 106, Peripheral Interface 108, radio-frequency module 110, locating module 112, photographing module 114, audio-frequency module 116, display
Module 118 and key module 120.These components are mutually communicated by one or more communication bus/signal wire 122.
It is appreciated that structure shown in FIG. 1 is only to illustrate, terminal device may also include than shown in Fig. 1 more or more
Few component, or with the configuration different from shown in Fig. 1.Each component shown in Fig. 1 can use hardware, software or its group
It closes and realizes.
Wherein, memory 102 can be used for storing software program and module, such as the image processing method in the embodiment of the present invention
Method and the corresponding program instruction/module of device, processor 106 by the software program that is stored in memory 102 of operation and
Module, thereby executing various function application and data processing.
Memory 102 may include high speed random access memory, may also include nonvolatile memory, such as one or more magnetic
Property storage device, flash memory or other non-volatile solid state memories.In some instances, memory 102 can further comprise
The memory remotely located relative to processor 106, these remote memories can pass through network connection to terminal device.It is above-mentioned
The example of network includes but is not limited to internet, intranet, local area network, mobile radio communication and combinations thereof.Processor 106 with
And other possible components can carry out the access of memory 102 under the control of storage control 104.
Various input/output devices are couple processor 106 and memory 102 by Peripheral Interface 108.Processor 106
Various softwares, instruction in run memory 102 are to execute the various functions of terminal device and carry out data processing.
In some embodiments, Peripheral Interface 108, processor 106 and storage control 104 can be in one single chips
It realizes, in some other example, can also be realized respectively by independent chip.
Radio-frequency module 110 is used to receive and transmit electromagnetic wave, realizes the mutual conversion of electromagnetic wave and electric signal, thus with
Communication network or other equipment are communicated.Radio-frequency module 110 may include various existing for executing the electricity of these functions
Circuit component, for example, antenna, RF transceiver, digital signal processor, encryption/deciphering chip, subscriber identity module (SIM) card,
Memory etc..Radio-frequency module 110 can be communicated or be led to various networks such as internet, intranet, wireless network
Wireless network is crossed to be communicated with other equipment.Above-mentioned wireless network may include cellular telephone networks, WLAN or
Metropolitan Area Network (MAN).Various communication standards, agreement and technology can be used in above-mentioned wireless network, and including but not limited to the whole world is mobile logical
Letter system (Global System for Mobile Communication, GSM), enhanced mobile communication technology
(Enhanced Data GSM Environment, EDGE), Wideband CDMA Technology (wideband code division
Multiple access, W-CDMA), Code Division Multiple Access (Code division access, CDMA), time division multiple access technology
(time division multiple access, TDMA), bluetooth, adopting wireless fidelity technology (Wireless, Fidelity,
WiFi) (such as American Institute of Electrical and Electronics Engineers's standard IEEE 802.11a, IEEE 802.11b, IEEE802.11g and/
Or IEEE 802.11n), the networking telephone (Voice over internet protocal, VoIP), worldwide interoperability for microwave accesses
(Worldwide Interoperability for Microwave Access, Wi-Max), other be used for mail, Instant Messenger
The agreement and any other suitable communications protocol of news and short message, or even may include that those are not developed currently yet
Agreement.
Locating module 112 is used to obtain the current location of terminal device.The example of locating module 112 is including but not limited to complete
Ball global position system (GPS), the location technology based on WLAN or mobile radio communication.
Photographing module 114 is for shooting photo or video.The photo or video of shooting can store to memory 102
It is interior, and can be sent by radio-frequency module 110.
Audio-frequency module 116 provides a user audio interface, may include one or more microphones, one or more raises
Sound device and voicefrequency circuit.Voicefrequency circuit receives voice data from Peripheral Interface 108, and voice data is converted to power information,
Power information is transmitted to loudspeaker.Power information is converted to the sound wave that human ear can be heard by loudspeaker.Voicefrequency circuit is also from microphone
Place receive power information, convert electrical signals to voice data, and by data transmission in network telephony into Peripheral Interface 108 to carry out into one
The processing of step.Audio data can obtain from memory 102 or through radio-frequency module 110.In addition, audio data can also be with
It stores into memory 102 or is sent by radio-frequency module 110.In some instances, audio-frequency module 116 may also include
One earphone broadcasts hole, for providing audio interface to earphone or other equipment.
Display screen 118 provides an output interface between terminal device and user.Specifically, display screen 118 to
User shows video output, and the content of these videos output may include text, figure, video and any combination thereof.Some outputs
The result is that corresponding to some user interface objects.Further, display screen 118 can also provide between terminal device and user
One input interface, for receiving the input of user, such as the gesture operations such as click, sliding of user, so as to user interface pair
As the input to these users responds.Detection user input technology can be based on resistance-type, condenser type or other
Any possible touch control detection technology.The specific example of display screen 118 includes but is not limited to liquid crystal display or shines poly-
Close object display.
Key module 120 equally provides user's interface inputted to terminal device, and user can be by pressing difference
Key so that terminal device executes different functions.
Illustrate image processing method and device provided by the invention below in conjunction with specific embodiment.
First embodiment
First embodiment provides a kind of image processing method, and this method can be realized by terminal device shown in FIG. 1.Fig. 2
It show the flow chart of the above method.Referring to FIG. 2, the method for the present embodiment the following steps are included:
Step S11 obtains original image;
In this step, a user interface is provided by terminal device, the user interface is for showing picture and providing behaviour
Make interface.User can be obtained from the memory 102 of terminal device by the user interface to be thought original image to be processed and shows
Show in the user interface.
Step S12 determines the specified region in the original image;
In this step, user can be by the relevant operation button in the operation interface of user interface offer, for example is used for
The select button of image range to be treated is selected, to select to need processed range in original image, when user selects
After needing processed range, terminal device receives the range that user selects on the original image, which is described
Specified region.
It in other embodiments, can also be by the specified region in system automatic identification original image, if the specified region
It is set as the skin area of personage, system can be known automatically according to the method for the skin model pre-established or other automatic identifications
Specified region in other and determining original image.
Step S13, for specified Area generation mask (MASK) matrix;
In this step, mask code matrix is two bit arrays with sizes such as the images of original image, to indicate the original
Pixel in the image of beginning picture belongs to the probability in the specified region.For example, if determination is to belong to specified area in original image
The pixel in domain, then to element assignment 1 corresponding in mask code matrix;If determination is not the picture for belonging to specified region in original image
Element, then to element assignment 0 corresponding in mask code matrix;If the uncertain pixel for whether belonging to specified region, to mask code matrix
In corresponding element assignment 0.5, etc., and so on, it is corresponding to assign to belong to the probability in the specified region according to pixel
It is worth to element corresponding in mask code matrix.
Step S14 carries out grey scale transformation to the original image according to the mask code matrix;
In this step, user can pass through the relevant operation button in the operation interface of user interface offer, such as whitening
Button, to do whitening processing to specified region.
Referring to FIG. 3, Fig. 3 is the flow diagram of the major sub-steps of step S14.As shown in figure 3, step S14 includes
Following sub-step:
Sub-step S141 calculates the brightness of image map table of the original image to obtain the brightness adjustment ratio of pixel;
In this sub-step, it is calculated by the first equation r=i/255 and second party formula F [i]=(r) ^0.6
The brightness adjustment ratio, wherein i indicates the grayscale of the pixel of the image of the original image, and r indicates the original image
The normalized value of the grayscale of the pixel of image, F [i] are the brightness adjustment ratio.
Sub-step S142 is amplified according to grayscale of the brightness adjustment ratio to the pixel in the specified region.
In this sub-step, by third equation Gray [x, y]=Gray [x, y] (1-mask [x, y])+Gray [x,
Y] pixel gray level after brightness adjustment is calculated in * mask [x, y] * F [i], wherein after Gray [x, y] indicates brightness adjustment
Pixel gray level, x, y indicate that the coordinate of pixel, mask [x, y] indicate that pixel belongs to the probability in the specified region.Pass through the third
After equation calculates, the grayscale of the pixel in specified region is amplified, and the grayscale of the pixel except specified region is then
It is constant, it realizes to the ratio stretching conversion of image, the specified region in picture is highlighted.
Therefore, improve the colour of skin of personage in picture or photo by this method if user wishes, in selection skin ranges
It, can be by above-mentioned sub-step S141 and S142 to personage in picture or after passing through system automatic identification figure skin region
The colour of skin carry out brightness adjustment, so that the colour of skin is brightened.
Further, step S14 may also include that
Sub-step S143, to the image superposition designated color after brightness adjustment.
In this sub-step, with the corresponding RGB grayscale of the designated color to the pixel of the image after the brightness adjustment
Carry out the transformation of RGB channel, wherein pass through the 4th equation R=0.1* (mask [x, y]) * Rz+0.9* (1-mask [x, y]) *
R*Gray [x, y]/Rz, the 5th equation G=0.1* (mask [x, y]) * Gz+0.9* (1-mask [x, y]) * R*Gray [x, y]/
Gz and the 6th equation B=0.1* (mask [x, y]) * Bz+0.9* (1-mask [x, y]) * R*Gray [x, y]/Bz are folded
The RGB grayscale of the pixel of image after adding designated color, wherein mask [x, y] indicates that pixel belongs to the general of the specified region
Rate, Gray [x, y] indicate that the pixel gray level after brightness adjustment, Rz, Gz, Bz indicate the corresponding RGB grayscale of the designated color.
For example, if the colour of skin that user is not intended merely to personage in picture brightens, it is also desirable to which can add pink colour keeps skin aobvious
Must be more healthy lovely, then pink colour can be superimposed by the colour of skin that this method is personage in picture, it is preferable that pink colour is corresponding
RGB grayscale is respectively 255,204,204, even Rz=255, Gz=204, Bz=204, described value is updated to above-mentioned respectively
Four, the five, the 6th equations carry out the transformation of RGB channel with the pixel to the image after brightness adjustment, make personage in picture
The colour of skin further increases pink colour after brightening.
It is understood that can not only be superimposed pink colour by this method, other colors can also be superimposed, it is only necessary to change
Become the value of corresponding RGB grayscale Rz, Gz, the Bz of designated color.
Step S15 carries out edge-smoothing processing and whole equalization to the general image of the picture after progress grey scale transformation
Processing.
In this step, it after carrying out grey scale transformation to picture, needs further to carry out at edge-smoothing general image
Reason and whole equalization processing, so that entire image is more natural.
Wherein, Gaussian Blur can be used to general image to carry out edge-smoothing processing, such as the Gaussian Blur of 3*3.It is right
It carries out edge-smoothing treated image and carries out histogram equalization, improve the contrast of image, reduce because grey scale transformation is brought
Color it is uneven.
After being completed to image procossing, further user can be shown to by user interface and checked.
It can be seen that image processing method provided by through this embodiment, it can be by ratio stretching conversion, in picture
Specified region, such as the colour of skin carry out it is smooth highlight, avoid blooming.And while being highlighted to specified region,
It is also stackable to specify other colors, such as pink colour, increase the colour of skin by pink colour after brightening, so that the skin in picture after whitening
It is fair and tender, increase aesthetic feeling.Therefore, image processing method provided by the present embodiment can realize the colour of skin whitening effect of personage in photo
Fruit and simple, convenient handles photo for user, picture brings better experience effect.
Second embodiment
Second embodiment provides a kind of image processing method, and this method can equally be realized by terminal device shown in FIG. 1,
This method is similar to method provided by first embodiment.Fig. 4 show the flow chart of the above method.Referring to FIG. 4, this implementation
Example method the following steps are included:
Step S11 obtains original image;
Step S21 is decoded the original image;
In this step, after obtaining original image, which is decoded, generates original image information
Stream, such as the image data of rgb format.And after being decoded to original image, decoded picture is shown in user interface
In.
Step S12 determines the specified region in the original image;
Step S13, for the specified Area generation mask code matrix;
Step S14 carries out grey scale transformation to the original image according to the mask code matrix;
Step S15 carries out edge-smoothing processing and whole equalization to the general image of the picture after progress grey scale transformation
Processing;
Step S22 encodes the picture after equalization processing.
In this step, after completing to picture processing, to treated, picture is encoded, such as the figure such as generation JPEG
Piece format.
Further, the picture after coding is displayed in the user interface so that user checks.
The step S11 to step S15 of the method as provided by the present embodiment is corresponding with the method in first embodiment
Step is similar, and please further refer to first embodiment, details are not described herein.
Provided image processing method through this embodiment, can be by ratio stretching conversion, to the specified area in picture
Domain, for example, the colour of skin carry out it is smooth highlight, avoid blooming.And it is also stackable while being highlighted to specified region
Other colors, such as pink colour are specified, increases the colour of skin by pink colour after brightening, so that the skin in picture after whitening is fair and tender, is increased
Add aesthetic feeling.Therefore, image processing method provided by the present embodiment can realize the colour of skin whitening effect of personage in photo and grasp
Make simply, conveniently, handles photo for user, picture brings better experience effect, and can be decoded and compile as needed
Code, meets the picture processing requirement of different-format.
3rd embodiment
3rd embodiment provides a kind of image processing method, and this method can equally be realized by terminal device shown in FIG. 1,
This method is similar to method provided by first embodiment.Fig. 5 show the flow chart of the above method.Referring to FIG. 5, this implementation
Example method the following steps are included:
Step S31 receives user using the log-on message of the client of social platform;
In this step, installing terminal equipment have social platform client (such as instant communication software, as QQ, wechat,
Skype etc.), after user logs in the client, client receives the log-on message.
Step S11 obtains original image;
In this step, if user needs to send the picture to other users or shares in circle of friends, user can be in client
The input frame that the user interface at end provides obtains the original image, such as the photograph album from terminal device storage in the memory 102
The original image is obtained, or the photographing module 114 of the interface using terminal equipment of taking pictures provided according to client is taken pictures immediately
Obtain the original image.
Step S12 determines the specified region in the original image;
In this step, it if user is unsatisfied with picture effect, needs to handle picture, it can be by user circle of client
Face further provides for operation button, such as whitening button, selects to user.When user's selection carries out picture to handle it
Afterwards, client further provides for the select button of image range to be treated, selected to need in original image by user by
The range of processing, or directly by system identification region to be treated.
Step S13, for the specified Area generation mask code matrix;
Step S14 carries out grey scale transformation to the original image according to the mask code matrix;
Step S15 carries out edge-smoothing processing and whole equalization to the general image of the picture after progress grey scale transformation
Processing;
Step S32 sends the picture that processing is completed.
In this step, after completing equalization processing to picture, show that treated by the user interface of client
Picture is to user, and transmission handles the picture completed after receiving the transmission operation of user.
The step S11 to step S15 of the method as provided by the present embodiment is corresponding with the method in first embodiment
Step is similar, and please further refer to first embodiment, details are not described herein.
Provided image processing method through this embodiment, can be directly when using the client of social platform to picture
It is handled, realizes the colour of skin whitening effect of personage in photo, and simple, convenient, use social platform band for user
Carry out better experience effect.
Fourth embodiment
Fourth embodiment provides a kind of image processing apparatus, which can run on terminal device shown in FIG. 1, for real
Image processing method in existing above-described embodiment.As shown in fig. 6, described device includes that picture obtains module 401, specifies region true
Cover half block 402, mask code matrix generation module 403, grey scale transformation module 404 and disposed of in its entirety module 405.
Picture obtains module 401, for obtaining original image.Specifically, the user that user can be provided by terminal device
Interface is obtained module 401 and obtained from the memory 102 of terminal device using the picture thinks original image to be processed, this is original
Picture is shown in the user interface after obtaining by display module.
Specified area determination module 402, for determining the specified region in the original image.Wherein, specify region true
Cover half block 402 includes receiving unit 412, which is used to receive the range that user selects on the original image,
The range is the specified region.Specifically, the relevant operation in operation interface that user can be provided by user interface is pressed
Button, such as the select button for selecting image range to be treated, to select to need processed range in original image,
After user selects to need processed range, receiving unit 412 receives the range that user selects on the original image, should
Range is the specified region.
In other embodiments, which can further comprise automatic identification unit, certainly by this
It specified region in dynamic recognition unit automatic identification original image should be certainly if the specified region is set as the skin area of personage
Dynamic recognition unit can be according to the method automatic identification of the skin model pre-established or other automatic identifications and determining original graph
Specified region in piece.
Mask code matrix generation module 403, for being directed to the specified Area generation mask code matrix.Wherein, the mask code matrix
It is two bit arrays with sizes such as the images of original image, the pixel in image to indicate the original image belongs to described
The probability in specified region.For example, if determination is the pixel for belonging to specified region in original image, to corresponding in mask code matrix
Element assignment 1;If determination is not the pixel for belonging to specified region in original image, to element assignment corresponding in mask code matrix
0;If the uncertain pixel for whether belonging to specified region, to element assignment 0.5 corresponding in mask code matrix, etc., class according to this
It pushes away, the probability in the specified region is belonged to according to pixel to assign corresponding value to element corresponding in mask code matrix.
Grey scale transformation module 404, for carrying out grey scale transformation to the original image according to the mask code matrix.Wherein,
Grey scale transformation module 404 includes that brightness adjustment ratio acquisition unit 414, grayscale amplifying unit 424 and designated color superposition are single
Member 434.
Brightness adjustment ratio acquisition unit 414 is used to calculate the brightness of image map table of the original image to obtain pixel
Brightness adjustment ratio.Specifically, brightness adjustment ratio acquisition unit 414 passes through the first equation r=i/255 and second equation
The brightness adjustment ratio is calculated in formula F [i]=(r) ^0.6, wherein i indicates the pixel of the image of the original image
Grayscale, r indicate that the normalized value of the grayscale of the pixel of the image of the original image, F [i] are the brightness adjustment ratio.
Grayscale amplifying unit 424 be used for according to the brightness adjustment ratio to the grayscale of the pixel in the specified region into
Row amplification.Specifically, grayscale amplifying unit 424 by third equation Gray [x, y]=Gray [x, y] (1-mask [x, y])+
The pixel gray level after brightness adjustment is calculated in Gray [x, y] * mask [x, y] * F [i], wherein Gray [x, y] indicates brightness tune
Pixel gray level after whole, x, y indicate that the coordinate of pixel, mask [x, y] indicate that pixel belongs to the probability in the specified region.
If user wishes selecting skin ranges by the colour of skin of personage in present apparatus improvement picture perhaps photo or leading to
It crosses after system automatic identification figure skin region, brightness adjustment ratio acquisition unit 414 and grayscale amplifying unit can be passed through
The colour of skin of personage carries out brightness adjustment in 424 pairs of pictures, and the colour of skin is made to brighten.
Designated color superpositing unit 434 is used for the image superposition designated color after brightness adjustment.Specifically, designated color
Superpositing unit 434 carries out RGB channel with pixel of the corresponding RGB grayscale of the designated color to the image after the brightness adjustment
Transformation, wherein by the 4th equation R=0.1* (mask [x, y]) * Rz+0.9* (1-mask [x, y]) * R*Gray [x,
Y]/Rz, the 5th equation G=0.1* (mask [x, y]) * Gz+0.9* (1-mask [x, y]) * R*Gray [x, y]/Gz and
Six equation B=0.1* (mask [x, y]) * Bz+0.9* (1-mask [x, y]) * R*Gray [x, y]/Bz obtains being superimposed specified face
The RGB grayscale of the pixel of image after color, wherein mask [x, y] indicates that pixel belongs to the probability in the specified region, Gray
[x, y] indicates that the pixel gray level after brightness adjustment, Rz, Gz, Bz indicate the corresponding RGB grayscale of the designated color.
For example, if the colour of skin that user is not intended merely to personage in picture brightens, it is also desirable to which can add pink colour keeps skin aobvious
Must be more healthy lovely, then pink colour can be superimposed by the colour of skin that designated color superpositing unit 434 is personage in picture, preferably
Ground, the corresponding RGB grayscale of pink colour is respectively 255,204,204, even Rz=255, Gz=204, Bz=204, by described value point
It is not updated to the transformation that above-mentioned four, the five, the 6th equation carries out RGB channel with the pixel to the image after brightness adjustment,
The colour of skin of personage in picture is set to further increase pink colour after brightening.
It, can also be with it is understood that can not only be superimposed pink colour by the designated color superpositing unit 434 of the present apparatus
It is superimposed other colors, it is only necessary to change the value of corresponding RGB grayscale Rz, Gz, the Bz of designated color.
Disposed of in its entirety module 405 carries out edge-smoothing processing for the general image to the picture after progress grey scale transformation
And whole equalization processing, so that entire image is more natural.Wherein, disposed of in its entirety module 405 includes that edge-smoothing processing is single
Member 415 and equalization processing unit 425.Edge-smoothing processing unit 415 be used for the general image using Gaussian Blur come
Edge-smoothing processing is carried out, the Gaussian Blur of 3*3 is such as used.Equalization processing unit 425 is used for progress edge-smoothing processing
Image afterwards carries out histogram equalization, to improve the contrast of image, reduces because grey scale transformation bring color is uneven.
After being completed to image procossing, the device can by display module the user interface picture that shows that treated to
User checks.
It can be seen that image processing apparatus provided by through this embodiment, it can be by ratio stretching conversion, in picture
Specified region, such as the colour of skin carry out it is smooth highlight, avoid blooming.And while being highlighted to specified region,
It is also stackable to specify other colors, such as pink colour, increase the colour of skin by pink colour after brightening, so that the skin in picture after whitening
It is fair and tender, increase aesthetic feeling.Therefore, image processing apparatus provided by the present embodiment can realize the colour of skin whitening effect of personage in photo
Fruit and simple, convenient handles photo for user, picture brings better experience effect.
5th embodiment
5th embodiment provides a kind of image processing apparatus, which can run on terminal device shown in FIG. 1, for real
Image processing method in existing above-described embodiment, the device are similar to the device that fourth embodiment provides.As shown in fig. 7, described
Device include picture obtain module 401, decoder module 501, specified area determination module 402, mask code matrix generation module 403,
Grey scale transformation module 404, disposed of in its entirety module 405 and coding module 502.
Picture obtains module 401, for obtaining original image.
Decoder module 501, for being decoded to the original image.Specifically, module 401 is obtained in picture obtain original
After beginning picture, decoder module 501 is decoded the original image, generates original image information flow, such as the figure of rgb format
As data.After decoder module 501 is to original image decoding, which is shown decoded picture by display module
In user interface.
Specified area determination module 402, for determining the specified region in the original image.Wherein, specify region true
Cover half block 402 includes receiving unit 412, which is used to receive the range that user selects on the original image,
The range is the specified region.
In other embodiments, which can further comprise automatic identification unit, certainly by this
It specified region in dynamic recognition unit automatic identification original image should be certainly if the specified region is set as the skin area of personage
Dynamic recognition unit can be according to the method automatic identification of the skin model pre-established or other automatic identifications and determining original graph
Specified region in piece.
Mask code matrix generation module 403, for being directed to the specified Area generation mask code matrix.
Grey scale transformation module 404, for carrying out grey scale transformation to the original image according to the mask code matrix.Wherein,
Grey scale transformation module 404 includes that brightness adjustment ratio acquisition unit 414, grayscale amplifying unit 424 and designated color superposition are single
Member 434.Brightness adjustment ratio acquisition unit 414 is used to calculate the brightness of image map table of the original image to obtain pixel
Brightness adjustment ratio.Grayscale amplifying unit 424 is used for according to the brightness adjustment ratio to the pixel in the specified region
Grayscale amplifies.Designated color superpositing unit 434 is used for the image superposition designated color after brightness adjustment.
Disposed of in its entirety module 405 carries out edge-smoothing processing for the general image to the picture after progress grey scale transformation
And whole equalization processing, so that entire image is more natural.Wherein, disposed of in its entirety module 405 includes that edge-smoothing processing is single
Member 415 and equalization processing unit 425.Edge-smoothing processing unit 415 be used for the general image using Gaussian Blur come
Edge-smoothing processing is carried out, the Gaussian Blur of 3*3 is such as used.Equalization processing unit 425 is used for progress edge-smoothing processing
Image afterwards carries out histogram equalization, to improve the contrast of image, reduces because grey scale transformation bring color is uneven.
Coding module 502 generates the picture formats such as JPEG for encoding to the picture after equalization processing.
After being completed to image coding, the device can by display module the user interface picture that shows that treated to
User checks.
The device as provided by the present embodiment it is similar to the device in fourth embodiment, about other of the present embodiment
Particular content is please further refer to fourth embodiment, and details are not described herein.
Provided image processing apparatus through this embodiment, can be by ratio stretching conversion, to the specified area in picture
Domain, for example, the colour of skin carry out it is smooth highlight, avoid blooming.And it is also stackable while being highlighted to specified region
Other colors, such as pink colour are specified, increases the colour of skin by pink colour after brightening, so that the skin in picture after whitening is fair and tender, is increased
Add aesthetic feeling.Therefore, image processing apparatus provided by the present embodiment can realize the colour of skin whitening effect of personage in photo and grasp
Make simply, conveniently, handles photo for user, picture brings better experience effect, and can be decoded and compile as needed
Code, meets the picture processing requirement of different-format.
Sixth embodiment
Sixth embodiment provides a kind of image processing apparatus, which can run on terminal device shown in FIG. 1, for real
Image processing method in existing above-described embodiment, the device are similar to the device that fourth embodiment provides.As shown in figure 8, described
Device include login module 601, picture obtain module 401, specified area determination module 402, mask code matrix generation module 403,
Grey scale transformation module 404, disposed of in its entirety module 405 and sending module 602.
Login module 601, for receiving user using the log-on message of the client of social platform.In the present embodiment,
Installing terminal equipment has the client (such as instant communication software, such as QQ, wechat, Skype) of social platform, logs in user
After the client, client receives the log-on message by the login module 601.
Picture obtains module 401, for obtaining original image.In the present embodiment, if user needs to send the picture to it
His user shares in circle of friends, and the input frame that user can provide in the user interface of client obtains module by the picture
401 obtain the original image, for example obtain the original image, Huo Zhegen from the photograph album of terminal device storage in the memory 102
The photographing module 114 of the interface using terminal equipment of taking pictures provided according to client passes through the picture after taking pictures immediately and obtains module
401 obtain the original image.
Specified area determination module 402, for determining the specified region in the original image.Wherein, specify region true
Cover half block 402 includes receiving unit 412, which is used to receive the range that user selects on the original image,
The range is the specified region.In the present embodiment, it if user is unsatisfied with picture effect, needs to handle picture,
Operation button, such as whitening button can be further provided for by the user interface of client, selected to user.When user selects
After handling picture, client further provides for image range to be treated by specified area determination module 402
Select button, selected to need processed range in original image by user, or directly determine mould by specified region
402 automatic identification of block region to be treated.
In other embodiments, which can further comprise automatic identification unit, certainly by this
It specified region in dynamic recognition unit automatic identification original image should be certainly if the specified region is set as the skin area of personage
Dynamic recognition unit can be according to the method automatic identification of the skin model pre-established or other automatic identifications and determining original graph
Specified region in piece.
Mask code matrix generation module 403, for being directed to the specified Area generation mask code matrix.
Grey scale transformation module 404, for carrying out grey scale transformation to the original image according to the mask code matrix.Wherein,
Grey scale transformation module 404 includes that brightness adjustment ratio acquisition unit 414, grayscale amplifying unit 424 and designated color superposition are single
Member 434.Brightness adjustment ratio acquisition unit 414 is used to calculate the brightness of image map table of the original image to obtain pixel
Brightness adjustment ratio.Grayscale amplifying unit 424 is used for according to the brightness adjustment ratio to the pixel in the specified region
Grayscale amplifies.Designated color superpositing unit 434 is used for the image superposition designated color after brightness adjustment.
Disposed of in its entirety module 405 carries out edge-smoothing processing for the general image to the picture after progress grey scale transformation
And whole equalization processing, so that entire image is more natural.Wherein, disposed of in its entirety module 405 includes that edge-smoothing processing is single
Member 415 and equalization processing unit 425.Edge-smoothing processing unit 415 be used for the general image using Gaussian Blur come
Edge-smoothing processing is carried out, the Gaussian Blur of 3*3 is such as used.Equalization processing unit 425 is used for progress edge-smoothing processing
Image afterwards carries out histogram equalization, to improve the contrast of image, reduces because grey scale transformation bring color is uneven.
Sending module 602, the picture completed for sending processing.In the present embodiment, 425 pairs of equalization processing unit figures
After piece completes equalization processing, the device can by display module the user interface of the client picture that shows that treated to
User, and the picture that processing is completed is sent by sending module 602 after the transmission operation for receiving user.
The device as provided by the present embodiment it is similar to the device in fourth embodiment, about other of the present embodiment
Particular content is please further refer to fourth embodiment, and details are not described herein.
Provided image processing apparatus through this embodiment, can be directly when using the client of social platform to picture
It is handled, realizes the colour of skin whitening effect of personage in photo, and simple, convenient, use social platform band for user
Carry out better experience effect.
It should be noted that each embodiment in this specification is described in a progressive manner, each embodiment emphasis
What is illustrated is the difference from other embodiments, and the same or similar parts between the embodiments can be referred to each other.It is right
For device class embodiment, since it is basically similar to the method embodiment, so be described relatively simple, related place referring to
The part of embodiment of the method illustrates.
It should be noted that, in this document, relational terms such as first and second and the like are used merely to a reality
Body or operation are distinguished with another entity or operation, are deposited without necessarily requiring or implying between these entities or operation
In any actual relationship or order or sequence.Moreover, the terms "include", "comprise" or its any other variant are intended to
Non-exclusive inclusion, so that process, method, article or device including a series of elements are not only wanted including those
Element, but also including other elements that are not explicitly listed, or further include for this process, method, article or device
Intrinsic element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that
There is also other identical elements in process, method, article or device including element.
Those of ordinary skill in the art will appreciate that realizing that all or part of the steps of above-described embodiment can pass through hardware
It completes, relevant hardware can also be instructed to complete by program, program can store in a kind of computer-readable storage medium
In matter, storage medium mentioned above can be read-only memory, disk or CD etc..
More than, it is only presently preferred embodiments of the present invention, is not intended to limit the present invention in any form, although this
Invention has been disclosed in a preferred embodiment above, and however, it is not intended to limit the invention, any person skilled in the art,
It does not depart within the scope of technical solution of the present invention, is equal when the technology contents using the disclosure above are modified or are modified to
The equivalent embodiment of variation, but without departing from the technical solutions of the present invention, according to the technical essence of the invention to the above reality
Any simple modification, equivalent change and modification made by example are applied, all of which are still within the scope of the technical scheme of the invention.
Claims (17)
1. a kind of image processing method, which is characterized in that the described method includes:
Obtain original image;
Determine the specified region in the original image;
For the specified Area generation mask code matrix;The mask code matrix is two with sizes such as the images of the original image
Bit array, the pixel in image to indicate the original image belong to the probability in the specified region;Wherein, if the original
Determination is to belong to the pixel in the specified region in beginning picture, then to element assignment 1 corresponding in the mask code matrix;If described
Determination is not the pixel for belonging to the specified region in original image, then to element assignment 0 corresponding in the mask code matrix;If
The uncertain pixel for whether belonging to the specified region, then to element assignment 0.5 corresponding in the mask code matrix;
Grey scale transformation is carried out to the original image according to the mask code matrix;And
Edge-smoothing processing and whole equalization processing are carried out to the general image of the picture after progress grey scale transformation.
2. the method according to claim 1, wherein the specified region in the determination original image is wrapped
It includes:
The range that user selects on the original image is received, the range is the specified region.
3. the method according to claim 1, wherein the specified region includes personage in the original image
Skin area.
4. the method according to claim 1, wherein it is described according to the mask code matrix to the original image into
Row grey scale transformation includes:
The brightness of image map table of the original image is calculated to obtain the brightness adjustment ratio of pixel;And
It is amplified according to grayscale of the brightness adjustment ratio to the pixel in the specified region.
5. according to the method described in claim 4, it is characterized in that, passing through the first equation r=i/255 and second party formula F
The brightness adjustment ratio is calculated in [i]=(r) ^0.6, wherein i indicates the ash of the pixel of the image of the original image
Rank, r indicate that the normalized value of the grayscale of the pixel of the image of the original image, F [i] are the brightness adjustment ratio.
6. according to the method described in claim 5, it is characterized in that, it is described according to the brightness adjustment ratio to the specified area
The grayscale of pixel in domain, which amplifies, includes:
Pass through third equation Gray [x, y]=Gray [x, y] (1-mask [x, y])+Gray [x, y] * mask [x, y] * F [i]
Pixel gray level after brightness adjustment is calculated, wherein Gray [x, y] indicates that the pixel gray level after brightness adjustment, x, y indicate picture
The coordinate of element, mask [x, y] indicate that pixel belongs to the probability in the specified region.
7. according to the method described in claim 4, it is characterized in that, it is described according to the mask code matrix to the original image into
Row grey scale transformation further include:
To the image superposition designated color after brightness adjustment.
8. the method according to the description of claim 7 is characterized in that the image superposition designated color packet to after brightness adjustment
It includes:
The transformation of RGB channel is carried out to the pixel of the image after the brightness adjustment with the corresponding RGB grayscale of the designated color,
Wherein, pass through the 4th equation R=0.1* (mask [x, y]) * Rz+0.9* (1-mask [x, y]) * R*Gray [x, y]/Rz,
Five equation G=0.1* (mask [x, y]) * Gz+0.9* (1-mask [x, y]) * R*Gray [x, y]/Gz and the 6th equation B
=0.1* (mask [x, y]) * Bz+0.9* (1-mask [x, y]) * R*Gray [x, y]/Bz obtains the image after superposition designated color
Pixel RGB grayscale, wherein mask [x, y] indicates that pixel belongs to the probability in the specified region, and Gray [x, y] indicates bright
Pixel gray level adjusted is spent, Rz, Gz, Bz indicate the corresponding RGB grayscale of the designated color.
9. the method according to claim 1, wherein the general image of the picture after described pair of progress grey scale transformation
It carries out edge-smoothing processing and whole equalization processing includes:
Edge-smoothing processing is carried out using Gaussian Blur to the general image;And
Histogram equalization is carried out to edge-smoothing treated image is carried out.
10. a kind of image processing apparatus, which is characterized in that described device includes:
Picture obtains module, for obtaining original image;
Specified area determination module, for determining the specified region in the original image;
Mask code matrix generation module, for being directed to the specified Area generation mask code matrix;The mask code matrix is and the original
Two bit arrays of the sizes such as the image of beginning picture, the pixel in image to indicate the original image belong to the specified area
The probability in domain;Wherein, if determination is to belong to the pixel in the specified region in the original image, in the mask code matrix
Corresponding element assignment 1;If determination is not the pixel for belonging to the specified region in the original image, to the mask square
Corresponding element assignment 0 in battle array;If the uncertain pixel for whether belonging to the specified region, to corresponding in the mask code matrix
Element assignment 0.5;
Grey scale transformation module, for carrying out grey scale transformation to the original image according to the mask code matrix;And
Disposed of in its entirety module carries out edge-smoothing processing and entirety for the general image to the picture after progress grey scale transformation
Weighing apparatusization processing.
11. device according to claim 10, which is characterized in that the specified area determination module includes receiving unit,
The range selected on the original image for receiving user, the range are the specified region.
12. device according to claim 10, which is characterized in that the grey scale transformation module includes:
Brightness adjustment ratio acquisition unit, for calculating the brightness of image map table of the original image to obtain the brightness of pixel
Adjustment rate;And
Grayscale amplifying unit, for being put according to grayscale of the brightness adjustment ratio to the pixel in the specified region
Greatly.
13. device according to claim 12, which is characterized in that the brightness adjustment ratio acquisition unit passes through first party
The brightness adjustment ratio is calculated in formula r=i/255 and second party formula F [i]=(r) ^0.6, wherein described in i expression
The grayscale of the pixel of the image of original image, r indicate the normalized value of the grayscale of the pixel of the image of the original image, F [i]
The as described brightness adjustment ratio.
14. device according to claim 13, which is characterized in that the grayscale amplifying unit passes through third equation Gray
The picture after brightness adjustment is calculated in [x, y]=Gray [x, y] (1-mask [x, y])+Gray [x, y] * mask [x, y] * F [i]
Plain grayscale, wherein Gray [x, y] indicates that the pixel gray level after brightness adjustment, x, y indicate that the coordinate of pixel, mask [x, y] indicate
Pixel belongs to the probability in the specified region.
15. device according to claim 14, which is characterized in that the grey scale transformation module further includes designated color superposition
Unit, for the image superposition designated color after brightness adjustment.
16. device according to claim 15, which is characterized in that the designated color superpositing unit is with the designated color
Corresponding RGB grayscale carries out the transformation of RGB channel to the pixel of the image after the brightness adjustment, wherein passes through the 4th equation
Formula R=0.1* (mask [x, y]) * Rz+0.9* (1-mask [x, y]) * R*Gray [x, y]/Rz, the 5th equation G=0.1*
(mask [x, y]) * Gz+0.9* (1-mask [x, y]) * R*Gray [x, y]/Gz and the 6th equation B=0.1* (mask [x,
Y]) * Bz+0.9* (1-mask [x, y]) * R*Gray [x, y]/Bz obtain superposition designated color after image pixel RGB ash
Rank, wherein mask [x, y] indicates that pixel belongs to the probability in the specified region, and Gray [x, y] indicates the pixel after brightness adjustment
Grayscale, Rz, Gz, Bz indicate the corresponding RGB grayscale of the designated color.
17. device according to claim 10, which is characterized in that the disposed of in its entirety module includes:
Edge-smoothing processing unit, for carrying out edge-smoothing processing using Gaussian Blur to the general image;And
Equalization processing unit, for carrying out histogram equalization to carrying out edge-smoothing treated image.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510697934.XA CN106611402B (en) | 2015-10-23 | 2015-10-23 | Image processing method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510697934.XA CN106611402B (en) | 2015-10-23 | 2015-10-23 | Image processing method and device |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106611402A CN106611402A (en) | 2017-05-03 |
CN106611402B true CN106611402B (en) | 2019-06-14 |
Family
ID=58612997
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510697934.XA Active CN106611402B (en) | 2015-10-23 | 2015-10-23 | Image processing method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106611402B (en) |
Families Citing this family (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107464230B (en) * | 2017-08-23 | 2020-05-08 | 京东方科技集团股份有限公司 | Image processing method and device |
CN107705275B (en) * | 2017-09-08 | 2021-02-26 | 维沃移动通信有限公司 | Photographing method and mobile terminal |
CN107862658B (en) * | 2017-10-31 | 2020-09-22 | Oppo广东移动通信有限公司 | Image processing method, image processing device, computer-readable storage medium and electronic equipment |
CN109255306B (en) * | 2018-08-21 | 2022-03-25 | 广东工业大学 | Method, device and equipment for testing face detector and storage medium |
CN111127303A (en) * | 2018-11-01 | 2020-05-08 | Tcl集团股份有限公司 | Background blurring method and device, terminal equipment and computer readable storage medium |
CN111784611B (en) * | 2020-07-03 | 2023-11-03 | 厦门美图之家科技有限公司 | Portrait whitening method, device, electronic equipment and readable storage medium |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101051436A (en) * | 2006-04-03 | 2007-10-10 | 帆宣系统科技股份有限公司 | Method and device for regulating input image according to display system property |
CN101080026A (en) * | 2006-05-23 | 2007-11-28 | 普立尔科技股份有限公司 | Method for removing color deviation in the image generated because of high and low brightness |
CN101819162A (en) * | 2010-05-13 | 2010-09-01 | 山东大学 | Empty bottle wall defect detection method and device |
CN102135876A (en) * | 2010-01-21 | 2011-07-27 | 腾讯科技(深圳)有限公司 | Method and system for generating irregular skin |
CN102402279A (en) * | 2010-09-17 | 2012-04-04 | 腾讯科技(深圳)有限公司 | Human-computer interaction method and system based on gestures |
CN102567731A (en) * | 2011-12-06 | 2012-07-11 | 北京航空航天大学 | Extraction method for region of interest |
CN102663345A (en) * | 2012-03-07 | 2012-09-12 | 中盟智能科技(苏州)有限公司 | Method and apparatus for automatic identification of traffic lights |
CN102938054A (en) * | 2012-09-06 | 2013-02-20 | 北京工业大学 | Method for recognizing compressed-domain sensitive images based on visual attention models |
CN104581103A (en) * | 2013-10-21 | 2015-04-29 | 腾讯科技(深圳)有限公司 | Image processing method and device |
-
2015
- 2015-10-23 CN CN201510697934.XA patent/CN106611402B/en active Active
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101051436A (en) * | 2006-04-03 | 2007-10-10 | 帆宣系统科技股份有限公司 | Method and device for regulating input image according to display system property |
CN101080026A (en) * | 2006-05-23 | 2007-11-28 | 普立尔科技股份有限公司 | Method for removing color deviation in the image generated because of high and low brightness |
CN102135876A (en) * | 2010-01-21 | 2011-07-27 | 腾讯科技(深圳)有限公司 | Method and system for generating irregular skin |
CN101819162A (en) * | 2010-05-13 | 2010-09-01 | 山东大学 | Empty bottle wall defect detection method and device |
CN102402279A (en) * | 2010-09-17 | 2012-04-04 | 腾讯科技(深圳)有限公司 | Human-computer interaction method and system based on gestures |
CN102567731A (en) * | 2011-12-06 | 2012-07-11 | 北京航空航天大学 | Extraction method for region of interest |
CN102663345A (en) * | 2012-03-07 | 2012-09-12 | 中盟智能科技(苏州)有限公司 | Method and apparatus for automatic identification of traffic lights |
CN102938054A (en) * | 2012-09-06 | 2013-02-20 | 北京工业大学 | Method for recognizing compressed-domain sensitive images based on visual attention models |
CN104581103A (en) * | 2013-10-21 | 2015-04-29 | 腾讯科技(深圳)有限公司 | Image processing method and device |
Also Published As
Publication number | Publication date |
---|---|
CN106611402A (en) | 2017-05-03 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106611402B (en) | Image processing method and device | |
CN112714214B (en) | Content connection method, equipment, system, GUI and computer readable storage medium | |
WO2018228168A1 (en) | Image processing method and related product | |
KR101874895B1 (en) | Method for providing augmented reality and terminal supporting the same | |
CN106101743B (en) | Panoramic video recognition methods and device | |
CN105141568B (en) | Secured communication channel method for building up and system, client and server | |
CN107633499B (en) | Image processing method and related product | |
US10231067B2 (en) | Hearing aid adjustment via mobile device | |
US20160353173A1 (en) | Voice processing method and system for smart tvs | |
KR20160136337A (en) | Creating a realistic color for a virtual object in an augmented reality environment | |
WO2022142875A1 (en) | Image processing method and apparatus, electronic device, and storage medium | |
JP2010033342A (en) | Portable communication terminal and communication method | |
CN107644219B (en) | Face registration method and related product | |
CN114489533A (en) | Screen projection method and device, electronic equipment and computer readable storage medium | |
JP2018509663A (en) | Image type identification method, apparatus, program, and recording medium | |
US20180167515A1 (en) | Audio signal processing based on remote user control | |
CN108200421B (en) | White balance processing method, terminal and computer readable storage medium | |
WO2022148319A1 (en) | Video switching method and apparatus, storage medium, and device | |
KR20230015269A (en) | Apparatus and method for generating a picture frame based on images taken through a shooting room kiosk | |
CN111161176A (en) | Image processing method and device, storage medium and electronic equipment | |
CN108924647A (en) | Video editing method, video editing apparatus, terminal | |
CN108124515A (en) | Information broadcast method and device, service implementation method and device and access point | |
WO2023011386A1 (en) | Whitelist control method in beidou communication system and related device | |
EP4261739A1 (en) | Qr code generation method and related device | |
CN113923528B (en) | Screen sharing method, terminal 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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |