CN108810406A - Portrait light efficiency processing method, device, terminal and computer readable storage medium - Google Patents
Portrait light efficiency processing method, device, terminal and computer readable storage medium Download PDFInfo
- Publication number
- CN108810406A CN108810406A CN201810500747.1A CN201810500747A CN108810406A CN 108810406 A CN108810406 A CN 108810406A CN 201810500747 A CN201810500747 A CN 201810500747A CN 108810406 A CN108810406 A CN 108810406A
- Authority
- CN
- China
- Prior art keywords
- portrait
- light efficiency
- type
- model
- processing
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/80—Camera processing pipelines; Components thereof
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/70—Circuitry for compensating brightness variation in the scene
- H04N23/76—Circuitry for compensating brightness variation in the scene by influencing the image signals
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Image Processing (AREA)
Abstract
The invention relates to a kind of portrait light efficiency processing method, device, terminal and computer readable storage mediums.The above method, including：Pending image is obtained, determines the portrait area in the pending image；Identify the portrait type in the portrait area；It obtains light efficiency corresponding with the portrait type and handles model；Model is handled according to the light efficiency, and light efficiency processing is carried out to the portrait area.By the above method, the light efficiency processing model for adapting to the portrait type can be chosen according to different portrait types, makes one as having more expressive force, and simplify the process that user handles portrait light efficiency, improves user experience.
Description
Technical field
This application involves field of computer technology, more particularly to a kind of portrait light efficiency processing method, device, terminal and meter
Calculation machine readable storage medium storing program for executing.
Background technology
With the continuous development of Internet technology, the intelligence of mobile terminal brings great advantage to the user, such as
The pixel of camera function, mobile terminal is higher and higher, and effect of taking pictures even matches in excellence or beauty in Professional Photography instrument, and mobile terminal has
There is carrying and use upper convenience, therefore by mobile terminal take pictures and become amusement indispensable in people's life
Project.
Take pictures or image in the process of processing, it usually needs to image carry out light efficiency processing, to promote image
Appreciation effect.In traditional portrait light efficiency processing method, usually selected by user the type of light efficiency come for portrait add light efficiency, it is right
The parameter that image carries out light efficiency processing is fixed, and effect is more single, and traditional portrait light efficiency processing method shortage is directed to
Property, light efficiency effect is poor.
Invention content
A kind of portrait light efficiency processing method of the embodiment of the present application offer, device, terminal and computer readable storage medium, can
To increase the light efficiency for adapting to the portrait type for pending image according to different portrait types, make one as having more expressive force.
A kind of portrait light efficiency processing method, including：
Pending image is obtained, determines the portrait area of the pending image；
Identify the portrait type in the portrait area；
It obtains light efficiency corresponding with the portrait type and handles model；
Model is handled according to the light efficiency, and light efficiency processing is carried out to the portrait area.
A kind of portrait light efficiency processing unit, including：
Region identification module determines the portrait area in the pending image for obtaining pending image；
Type identification module, for identification the portrait type in the portrait area；
Model acquisition module handles model for obtaining light efficiency corresponding with the portrait type；
Light efficiency processing module carries out light efficiency processing for handling model according to the light efficiency to the portrait area.
A kind of terminal, including memory and processor are stored with computer program, the computer journey in the memory
When sequence is executed by the processor so that the processor realizes method as described above.
A kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer program
Method as described above is realized when being executed by processor.
Above-mentioned portrait light efficiency processing method, device, terminal and computer readable storage medium, by obtaining pending figure
Picture determines the portrait area in the pending image, identifies the portrait type in the portrait area, obtains and the portrait
The corresponding light efficiency of type handles model, and handle model according to the light efficiency carries out light efficiency processing, Neng Gougen to the portrait area
The light efficiency processing model for adapting to the portrait type is chosen according to different portrait types, is made one as having more expressive force, and simplify
The process that user handles portrait light efficiency improves user experience.
Description of the drawings
In order to illustrate the technical solutions in the embodiments of the present application or in the prior art more clearly, to embodiment or will show below
There is attached drawing needed in technology description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of application for those of ordinary skill in the art without creative efforts, can be with
Obtain other attached drawings according to these attached drawings.
Fig. 1 is the applied environment figure of portrait light efficiency processing method in one embodiment；
Fig. 2 is the internal structure schematic diagram of terminal in one embodiment；
Fig. 3 is the flow diagram of portrait light efficiency processing method in one embodiment；
Fig. 4 is the flow diagram of portrait light efficiency processing method in another embodiment；
Fig. 5 is the flow diagram of portrait light efficiency processing method in another embodiment；
Fig. 6 is the flow diagram of portrait light efficiency processing method in another embodiment；
Fig. 7 is the flow diagram of portrait light efficiency processing method in another embodiment；
Fig. 8 is the schematic diagram that light efficiency handles model in one embodiment；
Fig. 9 is the structure diagram of portrait light efficiency processing unit in one embodiment；
Figure 10 is the schematic diagram of image processing circuit in one embodiment.
Specific implementation mode
It is with reference to the accompanying drawings and embodiments, right in order to make the object, technical solution and advantage of the application be more clearly understood
The application is further elaborated.It should be appreciated that specific embodiment described herein is only used to explain the application, and
It is not used in restriction the application.
Unless otherwise defined, all of technologies and scientific terms used here by the article and belong to the technical field of the application
The normally understood meaning of technical staff is identical.The term used in the description of the present application is intended merely to description tool herein
The purpose of the embodiment of body, it is not intended that limitation the application.
Fig. 1 is the applied environment figure of portrait light efficiency processing method in one embodiment.With reference to as shown in Figure 1, terminal 110 can
Camera thereon is called to be shot, such as carrying out real time scan to the object 120 in environment obtains frame image, according to the frame figure
Image as generating shooting.Optionally, include the first camera module 112 and second camera module 124, root in the camera
Shooting is realized jointly according to first camera module 112 and second camera module 124.Terminal 110 is equipped with a variety of moulds of taking pictures
Formula, such as portrait mode of figure can shoot object 120 by enabling different screening-modes in shooting process, can
To obtain the image of different-effect.
Terminal 110 can be by the frame image or the image of generation, as pending image.It identifies in the pending image
Portrait area in photographed scene, and further identify the portrait type belonging to the portrait in the portrait area；Acquisition and portrait
The corresponding light efficiency of type handles model；Model is handled according to light efficiency, and light efficiency processing is carried out to portrait area.
Fig. 2 is the internal structure schematic diagram of terminal in one embodiment.As shown in Fig. 2, the terminal 110 includes passing through system
The processor of bus connection, memory, display screen and camera.Wherein, the processor is for providing calculating and control ability, branch
Support the operation of entire terminal 110.Memory for storing data, program etc., at least one computer program is stored on memory,
The computer program can be executed by processor, to realize the portrait light efficiency suitable for terminal 110 provided in the embodiment of the present application
Processing method.Memory may include that magnetic disc, CD, read-only memory (Read-Only Memory, ROM) etc. are non-volatile
Storage medium or random access memory (Random-Access-Memory, RAM) etc..For example, in one embodiment, depositing
Reservoir includes non-volatile memory medium and built-in storage.Non-volatile memory medium is stored with operating system and computer journey
Sequence.The computer program can be performed by processor, for a kind of realization portrait light efficiency that each embodiment is provided below
Processing method.Built-in storage provides the operation ring of cache for the operating system computer program in non-volatile memory medium
Border.Camera includes above-mentioned the first camera module and second camera module, is used equally for delta frame image.Display screen can
To be touch screen, for example be capacitance plate or touch screens, for showing the visual informations such as frame image or shooting image, can also by with
The touch operation of the display screen is acted in detection, generates corresponding instruction.The terminal 110 can be mobile phone, tablet computer,
(Point of Sales are sold mobile whole by PDA (Personal Digital Assistant, personal digital assistant), POS
End), vehicle-mounted computer, Wearable etc..
It will be understood by those skilled in the art that structure shown in Figure 2, is only tied with the relevant part of application scheme
The block diagram of structure, does not constitute the restriction for the terminal 110 being applied thereon to application scheme, and specific terminal 110 can wrap
It includes than more or fewer components as shown in the figure, either combine certain components or is arranged with different components.
As shown in figure 3, in one embodiment, a kind of portrait light efficiency processing method is provided, it can be according to different portrait classes
Type is that pending image increases the light efficiency for adapting to the portrait type, is made one as having more expressive force.The present embodiment is mainly in this way
Applied to being illustrated in terminal as shown in Figure 1,302~step 308 that this approach includes the following steps：
Step 302：Pending image is obtained, determines the portrait area in the pending image.
Wherein, pending image refers to the image for needing to carry out portrait light efficiency processing, can be that generation has been taken and stores
Image, can also be under screening-mode, frame image is obtained by camera real time scan.Optionally, terminal can be on display circle
Portrait light efficiency is arranged on face to switch, user can trigger portrait light efficiency switch, and selection carries out portrait light efficiency processing to pending image,
Wherein, the processing of portrait light efficiency refers to adding lighting effect for pending image, which can be different types of lamp
Light effect, such as the cloth light effect in studio can be simulated, polishing is carried out to the portrait in pending image, manufactures good light
Line effect.
Optionally, terminal is equipped with portrait light efficiency tupe, which is under terminal camera pattern
Optional mode, under the portrait light efficiency tupe terminal can automatically be image to be captured carry out portrait light efficiency processing.When logical
When crossing terminal and being shot, portrait light efficiency tupe is opened if detecting, generates light efficiency process instruction, light efficiency processing refers to
Order is used to indicate the pending image of terminal-pair and carries out portrait light efficiency processing.
Optionally, when pending image be generated and store image when, the image editor in terminal can be passed through
Post-processing is carried out to pending image, online editing can be carried out to the picture that terminal browses by image editor, such as
Picture editting interface is carried out after image edit mode on opening a terminal, can carry out portrait light efficiency processing to image.Work as reception
When handling request to the light efficiency acted on image editor, light efficiency process instruction is generated, which is used to indicate
The pending image of terminal-pair carries out portrait light efficiency processing.
Further, terminal can extract relevant characteristic from pending image, detection this feature data whether and
Portrait feature matches, if matching, further obtains region of the portrait detected in the pending image, which is
For portrait area.
Specifically, this feature data, which can include features, the terminals such as face, hair, clothes, human posture, can identify and wait for
Whether determine that the portrait area in pending image, terminal can extract the image of pending image in processing image comprising face
Feature, and characteristics of image is analyzed by preset portrait detection model, judge in pending image whether to include face.
Characteristics of image may include shape feature, space characteristics and edge feature etc., wherein shape feature refers to office in pending image
The shape in portion, space characteristics refer to the mutual spatial position or phase between the multiple regions split in pending image
To direction relations, edge feature refers to forming the boundary pixel etc. between two regions in pending image.Terminal can be with
Identify in pending image whether include hair feature, such as length, bang, hair style, the color etc. of identification hair, according to identification
To hair feature determine and determine the portrait area in pending image.Terminal can also be by identifying in pending image
The characteristics such as clothes material, clothing color determine portrait area, can also identify whether there is human posture, such as identification figure
Whether there are the features postures such as " scissors hand ", " OK gestures " as in, so that it is determined that the portrait area in pending image.
Optionally, portrait detection model can be the pre- decision model for first passing through machine learning structure, structure portrait detection
When model, a large amount of sample image can be obtained, includes portrait image and unmanned image in sample image, it can be according to each sample
Whether image is marked sample image comprising portrait, and using the sample image of label as the input of portrait detection model,
It is trained by machine learning, obtains portrait detection model.
Step 304：Identify the portrait type in the portrait area.
Wherein, terminal has preset a variety of portrait types, which can carry out clustering etc. according to preset image library and draw
Point, a variety of portrait types marked off.Image in the image library includes portrait, is gathered by the portrait to the image library
Class forms the portrait type belonging to the portrait type of preset quantity and the portrait in each image.It is every for being formed by
Kind portrait type calculates corresponding with the portrait type according to the portrait feature of the portrait in the image for belonging to the portrait type
Portrait feature.Optionally, which being weighted obtained from average computation for the portrait feature of affiliated portrait
Portrait feature.
Terminal can analyze the image in the portrait area in pending image, and the portrait to identify the portrait is special
The matching degree of sign and the portrait feature of each preset portrait type, and the highest portrait type of matching degree is chosen, as
Portrait type belonging to the portrait.
Further, terminal is also provided with portrait template characteristic, and portrait template characteristic is that the portrait in image carries out light efficiency
As the portrait feature of reference standard when processing.Can be different portrait types, different people according to Popular Aesthetics criteria classification
As type is corresponding with different portrait template characteristics.Portrait template characteristic and portrait feature are contained in portrait area and are preset respectively
One or more characteristic informations such as size, ratio, position, posture of a position on corresponding human body.Such as position Ke Bao
Include face, face, face, figure, hand, foot etc..Terminal can be carried out from the template of multiple and different portrait types signature analysis with
Extraction, to obtain the portrait template characteristic of different portrait types.
For example, portrait type may include the types such as soft and graceful type, sexy type, manly type, lovely type, artistic type, for
Each portrait type is provided with corresponding portrait template characteristic.When identifying the portrait feature in pending image and soft and graceful type
When the matching degree highest of portrait template characteristic, then it is assumed that the portrait type in the portrait area of pending image is soft and graceful type.
Step 306：It obtains light efficiency corresponding with the portrait type and handles model.
Different light efficiency processing are carried out for different portrait types, portrait type is established in the present embodiment and handles model with light efficiency
Correspondence.It can also be optionally same portrait type that one of which portrait type, which corresponds to a kind of light efficiency processing model,
There is provided a variety of light efficiency tupes for selection by the user.
Further, the correspondence that model is handled according to pre-set portrait type and light efficiency, determines to currently waiting for
The light efficiency processing model that processing image should be chosen.Light efficiency processing model can be understood as the adjustment parameter to pending image, should
Parameter can be exposure, contrast, bloom, shade, level, saturation degree, colour temperature etc., by carrying out parameter tune to pending image
Section, to obtain that the image of more preferably expressive force can be obtained for different portrait types.
Specifically, when it is soft and graceful type to identify the portrait type in pending image, then according to suitable soft and graceful type personage
Lighting effect choose corresponding light efficiency and handle model；When it is sexy type to identify the portrait type in pending image, then
Corresponding light efficiency, which is chosen, according to the lighting effect of suitable sexy type personage handles model；It is understood that the present embodiment is not
Limit to the above-mentioned light efficiency processing model method of determination enumerated, can also determine that light efficiency handles mould according to other different portrait types
Type, such as manly type, lovely type, artistic type, the present embodiment will not enumerate explanation.
Step 308：Model is handled according to the light efficiency, and light efficiency processing is carried out to the portrait area.
Wherein, light efficiency includes but not limited to illumination type, intensity of illumination, illumination brightness, illumination color.The present embodiment according to
Determining light efficiency processing model carries out light efficiency processing to the portrait area of pending image.Specifically, light is carried out to portrait area
The mode of effect processing may include increasing different types of lighting effects, the center for highlighting portrait area, improving image
Brightness, increases cloth light effect etc. at the color for adjusting image.Light type can be profile light, light of stage, photographic studio lamp
Light, sheen etc., color can be warm tones, cool tone etc., and cloth light effect can be triangle light, negative and positive light, ring light etc..
Above-mentioned portrait light efficiency processing method determines the portrait area in the pending image by obtaining pending image
Domain identifies the portrait type in the portrait area, obtains light efficiency corresponding with the portrait type and handles model, according to described
Light efficiency handles model and carries out light efficiency processing to the portrait area, can be chosen according to different portrait types and adapt to the portrait type
Light efficiency handle model, make one, as having more expressive force, and to simplify the process that user handle portrait light efficiency, improvement user
Experience.
In one embodiment, as shown in figure 4, the portrait type namely step 304 identified in the portrait area
Including：
Step 402：The portrait feature of the portrait area is extracted, and the portrait feature and portrait template characteristic are carried out
Matching.
If it includes portrait that terminal, which detects in pending image, it may be determined that portrait area, the portrait for extracting portrait area are special
Sign, and portrait feature and pre-set portrait template characteristic are matched.Wherein portrait feature and portrait template characteristic packet
Including but be not limited to face characteristic, facial characteristics, body characteristics, face characteristic can include face feature, such as " three five, front yards ",
Arched eyebrows, peach blossom eye, apricot lips etc., face characteristic can also include shape of face feature, such as state's word face, oval face, round face etc.；
Facial characteristics can include facial expression, such as smile, laugh, sobbing, sad, serious, affability etc.；Body characteristics can include
Stature feature, such as sexy shaped form, inverted-triangular, golden ratio type etc..
Optionally, portrait feature can be by feature point group at characteristic point may include face shape, position and the figure of portrait
Profile etc..Portrait feature can be described with the coordinate value of each characteristic point, wherein the corresponding pixel of coordinate value available feature point
Position is indicated, such as the coordinate value of characteristic point is corresponding location of pixels X row Y row etc..
Terminal can be may include according to portrait feature recognition portrait type, portrait type soft and graceful type, sexy type, manly type,
Lovely type, artistic type etc..Terminal can build portrait template characteristic in advance, and it is special that terminal can analyze portrait by portrait template characteristic
Sign, obtains the portrait type of pending image.Mobile terminal can be according to including the portrait image of different portrait types as sample
This image portrays portrait template characteristic.The portrait type that terminal can include to every sample image is marked, for example, soft and graceful type
Type mark be 1, the type mark of sexy type is 2, and the type mark of manly type is 3 etc., and other modes progress can also be used
Label, however it is not limited to this.
Step 404：The portrait type belonging to the portrait in the portrait area is determined according to matching result.
Specifically, when portrait type is identified, terminal can by the portrait feature of extraction and portrait template characteristic into
Row comparison, and calculate the similarity of portrait feature and the portrait template characteristic of each portrait Type mapping.If portrait feature and people
As template characteristic similarity be more than similarity threshold, then terminal can determine pending image portrait type be and the portrait mould
The corresponding type of plate features.For example, the similarity of portrait feature portrait template characteristic corresponding with soft and graceful type is more than similarity threshold
Value 80% then can determine that portrait type is soft and graceful type.
Portrait light efficiency processing method provided in this embodiment, by extracting the portrait feature of the portrait area, and by institute
It states portrait feature and portrait template characteristic is matched, and then determine the portrait type belonging to the portrait in portrait area, it can
The recognition accuracy for improving portrait type can bring better portrait light efficiency processing effect by accurately identifying portrait type
Fruit.
In one embodiment, the portrait feature of the portrait area is extracted, and by the portrait feature and portrait template
Feature is matched namely step 402 can also include：It is obtained and the portrait in the pending image by emitting structural light
Corresponding three-dimensional portrait feature；When the three-dimensional actual information and the similarity of the three-dimensional reference position information are more than default threshold
When value, determine that the portrait feature matches with portrait template characteristic.
Wherein, which includes the three-dimensional reference position information of default organ, which includes
The three-dimensional actual position information of predetermined patterns.Terminal can be sent out during generating pending picture by calling camera
Penetrate structure light, with each pixel and the distance between the camera in the portrait area on identification shooting image, according to this away from
Three-dimensional portrait feature from the portrait that can be obtained in pending image.Wherein, the position showed relative to common picture
The two-dimentional portrait feature of size and the distance between each position etc., the three-dimensional portrait feature and portrait template characteristic are further
The three dimensional local information for containing each predetermined patterns of corresponding portrait, that is, include the three dimensional local information at each position.Such as
It can be reference with some reference plane, obtain each position point on portrait at a distance from the reference plane, can be obtained according to the distance
Thickness etc. to such as nose depth of beam, the depth of eye socket, body can embody the three dimensional local information at each position.It is optional
The structure light on ground, transmitting can be infrared structure light.When three-dimensional actual information and the similarity of three-dimensional reference position information are more than in advance
If when threshold value, determining that portrait feature matches with portrait template characteristic, and then determine the portrait of portrait area in pending image
Type.
In one embodiment, as shown in figure 5, the portrait light efficiency processing method further includes the step that portrait template characteristic generates
Suddenly, including：
Step 502：For each portrait type, corresponding reference picture set is obtained.
In the present embodiment, reference picture set refers to the set of the reference picture for training portrait template characteristic.Each
Include multiple reference pictures in reference picture set.For each reference picture set, establish the reference picture set with
The relationship of one of which portrait type.Reference picture set corresponding with a certain portrait type, in reference picture in include
Portrait type belong to a certain portrait type.For each portrait type, terminal can according to the correspondence pre-established,
Obtain corresponding reference picture set.
Step 504：Obtain the portrait fixed reference feature in each reference picture in reference picture set.
The portrait type of portrait in reference picture is marked as the people corresponding to the reference picture set belonging to the image
As type.Portrait in reference picture is the portrait for meeting Popular Aesthetics standard chosen in advance, for example can be the portrait of star.
Portrait fixed reference feature may include embodying size, color, position and the depth at each position on portrait etc. it is one such or
The characteristic of much information.
Step 506：Portrait template characteristic corresponding with portrait type is generated according to portrait fixed reference feature.
It, can be by each portrait for indicating same area with reference to special according to the portrait fixed reference feature of each portrait type of acquisition
Sign carries out averaging operation, to calculate the portrait template characteristic of corresponding portrait type.Optionally, it can pre-set for portrait
The training pattern of template characteristic is trained by importing the portrait template characteristic of identical portrait type in the training pattern,
To generate portrait template characteristic.
In the present embodiment, portrait template characteristic is generated by the above method, can further improve the standard of portrait template characteristic
True property.
In one embodiment, as shown in fig. 6, described handle model to portrait area progress light according to the light efficiency
Effect processing namely step 308 include：
Step 602：Obtain adjustable range and adjustment parameter to light efficiency under determining light efficiency processing model.
Wherein adjustable range can be understood as the processing region selected in pending image, which can pass through
Presetted pixel point is chosen to be determined, or the aberration by analyzing pixel region marks off different zones, then chooses needs
The pixel region of processing is as processing region.Optionally, the processing region can also be construct in advance with specific shape
Region, such as border circular areas, elliptic region, Delta Region, annular region etc..Adjustment parameter may include light exposure, white balance,
Contrast, bloom, shade, level, saturation degree, colour temperature etc..Different light efficiency processing model correspondences are preset with different adjusting models
It encloses and adjustment parameter.Optionally, light efficiency processing model can also include light efficiency simulation algorithm, be to wait locating by light efficiency simulation algorithm
It manages image and increases simulation light efficiency.
Step 604：Lighting effect is added to the pending image according to the adjustable range and adjustment parameter
Processing.
Post-processing is carried out to pending image by default adjustment parameter, can be that image adds light efficiency, light efficiency includes
But it is not limited to illumination type, intensity of illumination, illumination brightness, illumination color.
For example, increasing sexy type portrait the light efficiency that can fully show personage's stature effect, then when portrait type is property
When sense type, the parameters such as color, exposure, the contrast of image are adjusted according to adjustable range and adjustment parameter, increase light for image
It concentrates, light efficiency with distinct contrast, color is full, so that light efficiency is focused in personage's main body, achieve the effect that prominent personage's main body.Again
Such as when it is soft and graceful type to identify the portrait type in pending image, the illumination that soft light is added to pending image is imitated
Fruit.For another example when it is manly type to identify the portrait type in pending image, the light of clearance light is added to pending image
According to effect, to achieve the effect that prominent character contour.It is understood that the present embodiment does not limit at the above-mentioned light efficiency enumerated
Effect after reason.
Portrait light efficiency processing method provided in this embodiment adds light according to different types of portrait to pending image
Effect can have the special feature that the light efficiency of corresponding addition different-effect in conjunction with different types of portrait, promoted the expressive force of portrait with
Appeal.
In one embodiment, as shown in fig. 7, light efficiency processing model can be dimensional gaussian distribution function, according to described
Light efficiency handles model and carries out light efficiency processing to the portrait area, further includes：
Step 702：Obtain blast position.
Terminal can obtain blast position, and blast position may refer to highlight center to the progress blast processing of pending image
Position, blast position can be considered as the highest position of light effects intensity of addition.Centered on blast position, to blast position
Setting the intensity of the light effects of surrounding addition can continuously decrease.Optionally, blast position can be the pre-set fixation of terminal
Point.For example, blast position can be the central point of pending image.Terminal can obtain the length and width of pending image,
And the central point of pending image is determined according to length and width, the position of the central point of pending image can be in width
Between value and length median.If the width of pending image is W, length L, then (L/2, W/2) can be used in the position of central point
It indicates.Blast position can also be other pre-set fixed points, be not limited to that.
Optionally, blast position can be the center of portrait area in pending image.Terminal determines portrait area
Afterwards, the center of portrait area can be obtained, and using the center as blast position.Blast position can also be portrait area
The privileged site in domain, for example, can be using the human face region of portrait as blast position.After terminal determines portrait area, people can extract
As the characteristic point in region, characteristic point can be used for describing face characteristic, facial characteristics, the body characteristics etc. of portrait area.Terminal can
Human face region is determined according to characteristic point, and chooses the central point of human face region, using the central point of human face region as blast position.
The privileged site chosen in portrait area is blast position, and the light effects of pending image addition can be made more preferable.
Optionally, blast position can also be that the position of user oneself selection, user can pass through the pending image of touch-control
Any position, to the blast position needed for selection.Terminal can receive the touch control operation of user, and according to the touch control operation of reception
Position of touch is obtained, it can be using the position of touch as blast position.User can select blast position according to actual demand, meet not
With the demand of user, the light effects of addition are can effectively improve.It is to be appreciated that blast position can also be used other modes into
Row obtains, and is not limited in above-mentioned several ways.
Step 704：The distribution center of model is handled according to light efficiency described in the blast location determination, and according to the light efficiency
Brightness enhancing coefficient in processing model determines distribution range.
In the present embodiment, light efficiency processing model is dimensional gaussian distribution function, and terminal can be according to blast location determination light
The distribution center of effect processing model, and coefficient is enhanced according to brightness and determines distribution range.The distribution center that light efficiency handles model can
For determining that light efficiency handles the position of model, terminal can handle the distribution center of model using blast position as light efficiency, in distribution
The heart can be highest point in dimensional gaussian distribution function.The distribution range of light efficiency processing model can be used for describing dimensional gaussian distribution
The shape of function.When brightness enhancing coefficient is bigger, the shape that light efficiency handles model can more " tall and thin ", when brightness enhancing coefficient is got over
Hour, the shape that light efficiency handles model can more " slight of stature ".
In one embodiment, the dimensional gaussian distribution function of light efficiency processing model can use formula (1) to indicate：
Wherein, z indicates the pixel in pending image；P (z) indicates brightness enhancing when pixel carries out blast processing
Amplitude；D is standard deviation, and brightness enhancing coefficient can influence the size of d, and when brightness enhancing coefficient is bigger, d can be smaller, brightness enhancing
Coefficient is got over hour, and d can be bigger；μ indicates the distribution center of light efficiency processing model, and optionally, distribution center can be the blast obtained
Position.In light efficiency handles model, it is in the pixel of pending image different location, corresponding brightness enhancing amplitude is different,
Pixel closer range distribution center μ, brightness enhance stronger, the remoter range distribution center μ pixel of amplitude, brightness enhancing
Amplitude is smaller.
Step 706：Dimensional gaussian distribution function is built according to the distribution center and distribution range.
Terminal can build dimensional gaussian distribution function according to determining distribution center and distribution range, and according to the two of structure
It ties up gauss of distribution function and blast processing is carried out to pending image.
Fig. 8 is the schematic diagram that light efficiency handles model in one embodiment.As shown in figure 8, light efficiency processing model is that two dimension is high
This distribution function, two edge distributions of the dimensional gaussian distribution function are all the forms of One-Dimensional Normal distribution.In light efficiency processing
In model, x-axis and y-axis can be used for indicating that position coordinates of the pixel in pending image, z-axis can be used for indicating pixel
Brightness enhances amplitude.Distribution center 402 is the pixel that position coordinates are (x0, y0), and terminal can obtain blast position, and will increase
As distribution center 402, distribution center 402 is the brightness enhancing maximum point of amplitude in light efficiency processing model for bright position.Brightness increases
Strong coefficient can be used for influencing the distribution range of light efficiency processing model, and brightness enhancing coefficient is bigger, and light efficiency handles pixel in model
Brightness enhancing amplitude it is bigger, pixel improve brightness it is larger；Brightness enhancing coefficient is smaller, and light efficiency handles pixel in model
Brightness enhancing amplitude it is smaller, pixel improve brightness it is smaller.
Step 708：The place of lighting effect is added according to pending image described in the dimensional gaussian distribution function pair
Reason.
Terminal can according to dimensional gaussian distribution function calculate pixel brightness enhance amplitude, and by brightness enhancing amplitude with
The original brightness value of pixel is multiplied, and can be calculated blast treated brightness value.Terminal can be according to the brightness being calculated
Value carries out blast processing to pixel, and light effects are added in pending image.
In the present embodiment, the place of light effects can be added by the pending image of dimensional gaussian distribution function pair
The brightness enhancing amplitude of reason, the pixel of different location is different, image can be made to have better light effects so that the light of addition
Line effect is more true, natural.
It should be understood that although each step in the flow chart of Fig. 3-7 is shown successively according to the instruction of arrow,
These steps are not that the inevitable sequence indicated according to arrow executes successively.Unless expressly stating otherwise herein, these steps
Execution there is no stringent sequences to limit, these steps can execute in other order.Moreover, at least one in Fig. 3-7
Part steps may include that either these sub-steps of multiple stages or stage are not necessarily in synchronization to multiple sub-steps
Completion is executed, but can be executed at different times, the execution sequence in these sub-steps or stage is also not necessarily successively
It carries out, but can either the sub-step of other steps or at least part in stage be in turn or alternately with other steps
It executes.
As shown in figure 9, in one embodiment, providing a kind of portrait light efficiency processing unit, which includes：Region recognition
Module 910, type identification module 920, model acquisition module 930 and light efficiency processing module 940.
Region identification module 910 determines the portrait area in the pending image for obtaining pending image.
Type identification module 920, for identification the portrait type in the portrait area.
Model acquisition module 930 handles model for obtaining light efficiency corresponding with the portrait type.
Light efficiency processing module 940 carries out light efficiency processing for handling model according to the light efficiency to the portrait area.
Above-mentioned portrait light efficiency processing unit obtains pending image by region identification module 910, determines described pending
Portrait area in image, type identification module 920 identify the portrait type in the portrait area, model acquisition module 930
It obtains light efficiency corresponding with the portrait type and handles model, light efficiency processing module 940 handles model to institute according to the light efficiency
It states portrait area and carries out light efficiency processing, the light efficiency processing model for adapting to the portrait type can be chosen according to different portrait types,
It makes one as having more expressive force, and simplifies the process that user handles portrait light efficiency, improve user experience.
In one embodiment, type identification module 920 is additionally operable to extract the portrait feature of the portrait area, and by institute
It states portrait feature and portrait template characteristic is matched；The people belonging to the portrait in the portrait area is determined according to matching result
As type.
In one embodiment, type identification module 920 is additionally operable to obtain and the pending figure by emitting structural light
The corresponding three-dimensional portrait feature of portrait as in；The three-dimensional portrait feature includes the three-dimensional actual position information of predetermined patterns；
When the three-dimensional actual information and the similarity of the three-dimensional reference position information are more than predetermined threshold value, determine that the portrait is special
Sign matches with portrait template characteristic.
In one embodiment, model acquisition module 930 is additionally operable to obtain under determining light efficiency processing model to light efficiency
Adjustable range and adjustment parameter；Lighting effect is added to the pending image according to the adjustable range and adjustment parameter
Processing.
In one embodiment, model acquisition module 930 is additionally operable to obtain blast position；According to the blast location determination
The distribution center of the light efficiency processing model, and the brightness enhancing coefficient in model is handled according to the light efficiency and determines distribution range
Degree；Dimensional gaussian distribution function is built according to the distribution center and distribution range；According to the dimensional gaussian distribution function pair
The pending image is added the processing of lighting effect.
In one embodiment, which further includes template generation module, for being directed to each portrait
Type obtains corresponding reference picture set；Obtain personage's reference in each reference picture in the reference picture set
Feature；Portrait template characteristic corresponding with the portrait type is generated according to personage's fixed reference feature.
The division of modules is only used for for example, in other embodiments in above-mentioned portrait light efficiency processing unit, can
Signal processing apparatus is divided into different modules as required, to complete all or part of above-mentioned portrait light efficiency processing unit
Function.
Specific about portrait light efficiency processing unit limits the limit that may refer to above for portrait light efficiency processing method
Fixed, details are not described herein.Modules in above-mentioned portrait light efficiency processing unit can fully or partially through software, hardware and its
It combines to realize.Above-mentioned each module can be embedded in or in the form of hardware independently of in the processor in terminal, can also be with software
Form is stored in the memory in terminal, and the corresponding operation of the above modules is executed in order to which processor calls.
The realization of modules in the portrait light efficiency processing unit provided in the embodiment of the present application can be computer program
Form.The computer program can be run in terminal or server.The program module that the computer program is constituted is storable in
On the memory of terminal or server.When the computer program is executed by processor, realize described in the embodiment of the present application
The step of portrait light efficiency processing method.
The embodiment of the present application also provides a kind of computer readable storage mediums.One or more is executable comprising computer
The non-volatile computer readable storage medium storing program for executing of instruction, when the computer executable instructions are executed by one or more processors
When so that the processor executes the portrait light efficiency processing method as described in the various embodiments described above.
The embodiment of the present application also provides a kind of computer program products.A kind of computer program product including instruction,
When run on a computer so that computer executes the portrait light efficiency processing method described in the various embodiments described above.
The embodiment of the present application also provides a kind of terminal device.The terminal device includes image processing circuit, image procossing
Circuit can utilize hardware and or software component to realize, it may include define ISP (Image Signal Processing, image
Signal processing) pipeline various processing units.Figure 10 is the schematic diagram of image processing circuit in one embodiment.Such as Figure 10 institutes
Show, for purposes of illustration only, only showing the various aspects with the relevant image processing techniques of the embodiment of the present application.
As shown in Figure 10, image processing circuit includes ISP processors 1040 and control logic device 1050.Imaging device 1010
The image data of capture is handled by ISP processors 1040 first, and ISP processors 1040 analyze image data can with capture
Image statistics for determining and/or imaging device 1010 one or more control parameters.Imaging device 1010 can wrap
Include the camera with one or more lens 1012 and imaging sensor 1014.Imaging sensor 1014 may include colour filter
Array (such as Bayer filters), imaging sensor 1014 can obtain the light captured with each imaging pixel of imaging sensor 1014
Intensity and wavelength information, and the one group of raw image data that can be handled by ISP processors 1040 is provided.1020 (such as top of sensor
Spiral shell instrument) parameter (such as stabilization parameter) of the image procossing of acquisition can be supplied to ISP processing based on 1020 interface type of sensor
Device 1040.1020 interface of sensor can utilize SMIA, and (Standard Mobile Imaging Architecture, standard are moved
Dynamic Imager Architecture) interface, other serial or parallel camera interfaces or above-mentioned interface combination.
In addition, raw image data can be also sent to sensor 1020 by imaging sensor 1014, sensor 1020 can base
It is supplied to ISP processors 1040 or sensor 1020 by original graph raw image data in 1020 interface type of sensor
As in data storage to video memory 1030.
ISP processors 1040 handle raw image data pixel by pixel in various formats.For example, each image pixel can
Bit depth with 8,10,12 or 14 bits, ISP processors 1040 can carry out raw image data at one or more images
Reason operation, statistical information of the collection about image data.Wherein, image processing operations can be by identical or different bit depth precision
It carries out.
ISP processors 1040 can also receive image data from video memory 1030.For example, 1020 interface of sensor will be former
Beginning image data is sent to video memory 1030, and the raw image data in video memory 1030 is available to ISP processing
Device 1040 is for processing.Video memory 1030 can be only in a part, storage device or electronic equipment for memory device
Vertical private memory, and may include DMA (Direct Memory Access, direct direct memory access (DMA)) feature.
1014 interface of imaging sensor is come from when receiving or from 1020 interface of sensor or from video memory
When 1030 raw image data, ISP processors 1040 can carry out one or more image processing operations, such as time-domain filtering.Place
Image data after reason can be transmitted to video memory 1030, to carry out other processing before shown.ISP processors
1040 can also from video memory 1030 receive processing data, to the processing data progress original domain in and RGB and YCbCr
Image real time transfer in color space.Image data that treated may be output to display 1080, for user viewing and/or
It is further processed by graphics engine or GPU (Graphics Processing Unit, graphics processor).In addition, ISP processors
1040 output also can be transmitted to video memory 1030, and display 1080 can read picture number from video memory 1030
According to.In one embodiment, video memory 1030 can be configured as realizing one or more frame buffers.In addition, ISP processing
The output of device 1040 can be transmitted to encoder/decoder 1070, so as to encoding/decoding image data.The image data of coding can
It is saved, and is decompressed before being shown in 1080 equipment of display.
ISP processors 1040 handle image data the step of include：VFE (Video Front are carried out to image data
End, video front) it handles and CPP (Camera Post Processing, camera post-processing) processing.To image data
VFE processing may include the contrast for correcting image data or brightness, change the illumination conditions data recorded in a digital manner, to figure
As data compensate processing (such as white balance, automatic growth control, γ correction etc.), image data is filtered.
The CPP processing of image data may include zooming in and out image, preview frame and record frame are provided to each path.Wherein, CPP
Different codecs can be used to handle preview frame and record frame.Treated the image data of ISP processors 1040 is transmittable
To light efficiency processing module 1060, to carry out light efficiency processing to image before shown.Light efficiency processing module 1060 is to image
The processing of data light efficiency may include：Fine day light efficiency, cloudy light efficiency, natural light, studio's light, stage light applications, rim(ming) light etc..Wherein, light efficiency
Processing module 1060 can be CPU (Central Processing Unit, central processing unit), GPU or association's processing in mobile terminal
Device etc..Treated that data can be transmitted to encoder/decoder 1070, so as to encoding/decoding image for light efficiency processing module 1060
Data.The image data of coding can be saved, and be decompressed before being shown in 1080 equipment of display.Wherein, at light efficiency
Reason module 1060 may be additionally located between encoder/decoder 1070 and display 1080, i.e., light efficiency processing module 1060 is to having become
The image of picture carries out light efficiency processing.Above-mentioned encoder/decoder 1070 can be CPU, GPU or coprocessor etc. in mobile terminal.
The statistical data that ISP processors 1040 determine, which can be transmitted, gives control logic device Unit 1050.For example, statistical data can
It is passed including the images such as automatic exposure, automatic white balance, automatic focusing, flicker detection, black level compensation, 1012 shadow correction of lens
1014 statistical information of sensor.Control logic device 1050 may include the processor for executing one or more routines (such as firmware) and/or
Microcontroller, one or more routines can determine the control parameter and ISP of imaging device 1010 according to the statistical data of reception
The control parameter of processor 1040.For example, the control parameter of imaging device 1010 may include 1020 control parameter of sensor (such as
Gain, spectrum assignment the time of integration), camera flash control parameter, 1012 control parameter of lens (such as focus or zoom use
Focal length) or these parameters combination.ISP control parameters may include for automatic white balance and color adjustment (for example, at RGB
During reason) 1012 shadow correction parameter of gain level and color correction matrix and lens.
Portrait light efficiency processing method as described above can be realized with image processing techniques in Figure 10.Pass through the portrait light efficiency
Processing method can choose the light efficiency processing model for adapting to the portrait type according to different portrait types, make one as having more table
Existing power, and the process that user handles portrait light efficiency is simplified, improve user experience.
Used in this application may include to any reference of memory, storage, database or other media is non-volatile
And/or volatile memory.Suitable nonvolatile memory may include read-only memory (ROM), programming ROM (PROM),
Electrically programmable ROM (EPROM), electrically erasable ROM (EEPROM) or flash memory.Volatile memory may include arbitrary access
Memory (RAM), it is used as external cache.By way of illustration and not limitation, RAM is available in many forms, such as
It is static RAM (SRAM), dynamic ram (DRAM), synchronous dram (SDRAM), double data rate sdram (DDR SDRAM), enhanced
SDRAM (ESDRAM), synchronization link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM
(RDRAM), direct memory bus dynamic ram (DRDRAM) and memory bus dynamic ram (RDRAM).
The several embodiments of the application above described embodiment only expresses, the description thereof is more specific and detailed, but simultaneously
Cannot the limitation to the application the scope of the claims therefore be interpreted as.It should be pointed out that for those of ordinary skill in the art
For, under the premise of not departing from the application design, various modifications and improvements can be made, these belong to the guarantor of the application
Protect range.Therefore, the protection domain of the application patent should be determined by the appended claims.
Claims (10)
1. a kind of portrait light efficiency processing method, which is characterized in that including：
Pending image is obtained, determines the portrait area of the pending image；
Identify the portrait type in the portrait area；
It obtains light efficiency corresponding with the portrait type and handles model；
Model is handled according to the light efficiency, and light efficiency processing is carried out to the portrait area.
2. according to the method described in claim 1, it is characterized in that, the portrait type identified in the portrait area, packet
It includes：
The portrait feature of the portrait area is extracted, and the portrait feature and portrait template characteristic are matched；Wherein institute
It includes at least one of face characteristic, facial characteristics, body characteristics to state portrait feature and portrait template characteristic；
The portrait type belonging to the portrait in the portrait area is determined according to matching result.
3. according to the method described in claim 2, it is characterized in that, the portrait template characteristic includes the three-dimensional ginseng of default organ
Examine location information；
The portrait feature of the extraction portrait area, and the portrait feature and portrait template characteristic are matched, it wraps
It includes：
Obtain three-dimensional portrait feature corresponding with the portrait in the pending image；The three-dimensional portrait feature includes default portion
The actual position information of position；
When the similarity of the actual position information and the three-dimensional reference position information is more than predetermined threshold value, the people is determined
As feature and portrait template characteristic match.
4. according to the method described in claim 1, it is characterized in that, being obtained at light efficiency corresponding with the portrait type described
Before managing model, further include：
Establish the correspondence of portrait type and light efficiency processing model.
5. according to the method described in claim 1, it is characterized in that, described handle model to the portrait area according to the light efficiency
Domain carries out light efficiency processing, including：
Obtain adjustable range and adjustment parameter to light efficiency under determining light efficiency processing model；
The processing of lighting effect is added to the pending image according to the adjustable range and adjustment parameter；Wherein, institute
It includes at least one of illumination type, intensity of illumination, illumination brightness, illumination color to state lighting effect.
6. according to the method described in claim 1, it is characterized in that, described handle model to the portrait area according to the light efficiency
Domain carries out light efficiency processing, further includes：
Obtain blast position；
The distribution center of model is handled according to light efficiency described in the blast location determination, and is handled in model according to the light efficiency
Brightness enhancing coefficient determines distribution range；
Dimensional gaussian distribution function is built according to the distribution center and distribution range；
The processing of lighting effect is added according to pending image described in the dimensional gaussian distribution function pair.
7. method according to any one of claim 1 to 6, which is characterized in that the method further includes：
For each portrait type, corresponding reference picture set is obtained；
Obtain personage's fixed reference feature in each reference picture in the reference picture set；
Portrait template characteristic corresponding with the portrait type is generated according to personage's fixed reference feature.
8. a kind of portrait light efficiency processing unit, which is characterized in that including：
Region identification module determines the portrait area in the pending image for obtaining pending image；
Type identification module, for identification the portrait type in the portrait area；
Model acquisition module handles model for obtaining light efficiency corresponding with the portrait type；
Light efficiency processing module carries out light efficiency processing for handling model according to the light efficiency to the portrait area.
9. a kind of terminal, including memory and processor, computer program, the computer program are stored in the memory
When being executed by the processor so that the processor is realized such as the step of any one of claim 1 to 7 the method.
10. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer program
It is realized when being executed by processor such as the step of any one of claim 1 to 7 the method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810500747.1A CN108810406B (en) | 2018-05-23 | 2018-05-23 | Portrait light effect processing method, device, terminal and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810500747.1A CN108810406B (en) | 2018-05-23 | 2018-05-23 | Portrait light effect processing method, device, terminal and computer readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108810406A true CN108810406A (en) | 2018-11-13 |
| CN108810406B CN108810406B (en) | 2021-03-02 |
Family
ID=64091445
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810500747.1A Expired - Fee Related CN108810406B (en) | 2018-05-23 | 2018-05-23 | Portrait light effect processing method, device, terminal and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108810406B (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109584149A (en) * | 2018-11-28 | 2019-04-05 | 东软集团股份有限公司 | Image processing method, device, equipment and computer readable storage medium |
| CN111198962A (en) * | 2018-11-19 | 2020-05-26 | 纳博特斯克有限公司 | Information processing apparatus, system, method, similarity judging method, and medium |
| CN111476304A (en) * | 2020-04-10 | 2020-07-31 | 国网冀北电力有限公司承德供电公司 | Image data processing method and device |
| CN113489901A (en) * | 2021-06-30 | 2021-10-08 | 维沃移动通信（杭州）有限公司 | Shooting method and device thereof |
| CN113993250A (en) * | 2021-12-24 | 2022-01-28 | 深圳市奥新科技有限公司 | Stage lighting control method, device, equipment and storage medium |
| CN115705614A (en) * | 2021-08-05 | 2023-02-17 | 北京小米移动软件有限公司 | Image processing method, image processing device, electronic equipment and storage medium |
| WO2023055817A1 (en) * | 2021-09-30 | 2023-04-06 | Snap Inc. | Customized image reprocessing system |
| US11770621B2 (en) | 2021-09-30 | 2023-09-26 | Snap Inc. | Customized image reprocessing system using a machine learning model |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101308572A (en) * | 2008-06-24 | 2008-11-19 | 北京中星微电子有限公司 | Luminous effect processing method and apparatus |
| CN103841324A (en) * | 2014-02-20 | 2014-06-04 | 小米科技有限责任公司 | Shooting processing method and device and terminal device |
| JP2014206566A (en) * | 2013-04-10 | 2014-10-30 | 株式会社ハートス | Image processing light-emission control system, light-emitting display image processing program, and image light-emitting display method |
| CN105513007A (en) * | 2015-12-11 | 2016-04-20 | 惠州Tcl移动通信有限公司 | Mobile terminal based photographing beautifying method and system, and mobile terminal |
| CN107197171A (en) * | 2017-06-22 | 2017-09-22 | 西南大学 | A kind of digital photographing processing method for adding intelligence software light source |
| CN107730445A (en) * | 2017-10-31 | 2018-02-23 | 广东欧珀移动通信有限公司 | Image processing method, device, storage medium and electronic equipment |
| CN107742274A (en) * | 2017-10-31 | 2018-02-27 | 广东欧珀移动通信有限公司 | Image processing method, device, computer-readable recording medium and electronic equipment |
| CN107995418A (en) * | 2017-11-21 | 2018-05-04 | 维沃移动通信有限公司 | A kind of image pickup method, device and mobile terminal |
-
2018
- 2018-05-23 CN CN201810500747.1A patent/CN108810406B/en not_active Expired - Fee Related
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101308572A (en) * | 2008-06-24 | 2008-11-19 | 北京中星微电子有限公司 | Luminous effect processing method and apparatus |
| JP2014206566A (en) * | 2013-04-10 | 2014-10-30 | 株式会社ハートス | Image processing light-emission control system, light-emitting display image processing program, and image light-emitting display method |
| CN103841324A (en) * | 2014-02-20 | 2014-06-04 | 小米科技有限责任公司 | Shooting processing method and device and terminal device |
| CN105513007A (en) * | 2015-12-11 | 2016-04-20 | 惠州Tcl移动通信有限公司 | Mobile terminal based photographing beautifying method and system, and mobile terminal |
| CN107197171A (en) * | 2017-06-22 | 2017-09-22 | 西南大学 | A kind of digital photographing processing method for adding intelligence software light source |
| CN107730445A (en) * | 2017-10-31 | 2018-02-23 | 广东欧珀移动通信有限公司 | Image processing method, device, storage medium and electronic equipment |
| CN107742274A (en) * | 2017-10-31 | 2018-02-27 | 广东欧珀移动通信有限公司 | Image processing method, device, computer-readable recording medium and electronic equipment |
| CN107995418A (en) * | 2017-11-21 | 2018-05-04 | 维沃移动通信有限公司 | A kind of image pickup method, device and mobile terminal |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111198962A (en) * | 2018-11-19 | 2020-05-26 | 纳博特斯克有限公司 | Information processing apparatus, system, method, similarity judging method, and medium |
| CN109584149A (en) * | 2018-11-28 | 2019-04-05 | 东软集团股份有限公司 | Image processing method, device, equipment and computer readable storage medium |
| CN109584149B (en) * | 2018-11-28 | 2023-03-07 | 东软集团股份有限公司 | Image processing method, device, equipment and computer readable storage medium |
| CN111476304A (en) * | 2020-04-10 | 2020-07-31 | 国网冀北电力有限公司承德供电公司 | Image data processing method and device |
| CN111476304B (en) * | 2020-04-10 | 2023-09-05 | 国网冀北电力有限公司承德供电公司 | Image data processing method and device |
| CN113489901A (en) * | 2021-06-30 | 2021-10-08 | 维沃移动通信（杭州）有限公司 | Shooting method and device thereof |
| CN113489901B (en) * | 2021-06-30 | 2023-04-28 | 维沃移动通信（杭州）有限公司 | Shooting method and device thereof |
| CN115705614A (en) * | 2021-08-05 | 2023-02-17 | 北京小米移动软件有限公司 | Image processing method, image processing device, electronic equipment and storage medium |
| WO2023055817A1 (en) * | 2021-09-30 | 2023-04-06 | Snap Inc. | Customized image reprocessing system |
| US11770621B2 (en) | 2021-09-30 | 2023-09-26 | Snap Inc. | Customized image reprocessing system using a machine learning model |
| CN113993250A (en) * | 2021-12-24 | 2022-01-28 | 深圳市奥新科技有限公司 | Stage lighting control method, device, equipment and storage medium |
| CN113993250B (en) * | 2021-12-24 | 2022-03-15 | 深圳市奥新科技有限公司 | Stage lighting control method, device, equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108810406B (en) | 2021-03-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108810406A (en) | Portrait light efficiency processing method, device, terminal and computer readable storage medium | |
| CN108846807A (en) | Light efficiency processing method, device, terminal and computer readable storage medium | |
| CN108537749B (en) | Image processing method, image processing device, mobile terminal and computer readable storage medium | |
| CN105608447B (en) | To the detection method of human body face smile expression depth convolutional neural networks | |
| CN107730445A (en) | Image processing method, device, storage medium and electronic equipment | |
| CN110149482A (en) | Focusing method, device, electronic equipment and computer readable storage medium | |
| CN107705248A (en) | Image processing method, device, electronic equipment and computer-readable recording medium | |
| CN107818305A (en) | Image processing method, device, electronic equipment and computer-readable recording medium | |
| CN108537155A (en) | Image processing method, device, electronic equipment and computer readable storage medium | |
| CN107808136A (en) | Image processing method, device, readable storage medium storing program for executing and computer equipment | |
| CN110111418A (en) | Create the method, apparatus and electronic equipment of facial model | |
| CN103945104B (en) | Information processing method and electronic equipment | |
| CN107886484A (en) | U.S. face method, apparatus, computer-readable recording medium and electronic equipment | |
| CN109690617A (en) | System and method for digital vanity mirror | |
| CN110334635A (en) | Main body method for tracing, device, electronic equipment and computer readable storage medium | |
| CN107766831A (en) | Image processing method, device, mobile terminal and computer-readable recording medium | |
| CN108810413A (en) | Image processing method and device, electronic equipment, computer readable storage medium | |
| CN108540716A (en) | Image processing method, device, electronic equipment and computer readable storage medium | |
| CN109886153B (en) | Real-time face detection method based on deep convolutional neural network | |
| CN108022207A (en) | Image processing method, device, storage medium and electronic equipment | |
| CN110300264A (en) | Image processing method, device, mobile terminal and storage medium | |
| CN108093174A (en) | Patterning process, device and the photographing device of photographing device | |
| CN108022206A (en) | Image processing method, device, electronic equipment and computer-readable recording medium | |
| CN108632512A (en) | Image processing method, device, electronic equipment and computer readable storage medium | |
| CN109242794A (en) | Image processing method, device, electronic equipment and computer readable 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 | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20210302 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |