CN109040729A - Image white balance correcting, device, storage medium and terminal - Google Patents
Image white balance correcting, device, storage medium and terminal Download PDFInfo
- Publication number
- CN109040729A CN109040729A CN201810934706.3A CN201810934706A CN109040729A CN 109040729 A CN109040729 A CN 109040729A CN 201810934706 A CN201810934706 A CN 201810934706A CN 109040729 A CN109040729 A CN 109040729A
- Authority
- CN
- China
- Prior art keywords
- light source
- white balance
- target
- image
- subgraph
- 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
- H04N9/00—Details of colour television systems
- H04N9/64—Circuits for processing colour signals
- H04N9/73—Colour balance circuits, e.g. white balance circuits or colour temperature control
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N9/00—Details of colour television systems
- H04N9/64—Circuits for processing colour signals
- H04N9/646—Circuits for processing colour signals for image enhancement, e.g. vertical detail restoration, cross-colour elimination, contour correction, chrominance trapping filters
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Color Television Image Signal Generators (AREA)
- Processing Of Color Television Signals (AREA)
Abstract
The embodiment of the present application discloses a kind of image white balance correcting, device, storage medium and terminal and obtains multiple target subgraphs this method comprises: being split first to target image；Secondly, obtaining the corresponding light source direction of each target sub-picture content；Again, light mixing scene whether there is according to the multiple target subgraph corresponding light source walking direction；Finally, carrying out white balance correction when there are light mixing scene according to the corresponding light source of the light mixing scene, can be improved image white balance correction effect under light mixing scene.
Description
Technical field
The invention relates to technical field of image processing more particularly to image white balance correcting, device, storages
Medium and terminal.
Background technique
With the continuous development of mobile terminal, almost every mobile terminal is configured with camera function, is based on camera function
It can take pictures.Mobile terminal is intended to the process of taking pictures of automation, can be exposed automatically according to photo environment and white
Balance correction.
But discovery in use, if there is light mixing scene there are when multiple and different direction light sources in shooting picture
When, then the photo white balance effect shot is poor.
Summary of the invention
The purpose of the embodiment of the present application is to provide a kind of image white balance correcting, device, storage medium and terminal, can
With the white balance correction effect under light mixing scene.
In a first aspect, the embodiment of the present application provides a kind of image white balance correcting, comprising:
Target image is split, multiple target subgraphs are obtained；
Obtain the corresponding light source direction of each target sub-picture content；
It whether there is light mixing scene according to the multiple target subgraph corresponding light source walking direction；
When there are light mixing scene, white balance correction is carried out according to the corresponding light source of the light mixing scene.
Second aspect, the embodiment of the present application provide a kind of image white balance correction device, comprising:
Divide module and obtains multiple target subgraphs for being split to target image；
Module is obtained, the corresponding light source direction of each target sub-picture content obtained for obtaining the segmentation module；
Judgment module, the multiple target subgraph corresponding light source walking direction for being obtained according to the acquisition module
With the presence or absence of light mixing scene；
White balance module, it is corresponding according to the light mixing scene for determining there are when light mixing scene when the judgment module
Light source carry out white balance correction.
The third aspect, the embodiment of the present application provide a kind of computer readable storage medium, are stored thereon with computer journey
Sequence realizes the image white balance correcting as shown in first aspect when the program is executed by processor.
Fourth aspect, the embodiment of the present application provide a kind of terminal, including memory, and processor and storage are on a memory
And the computer program that can be run in processor, the processor are realized as shown in first aspect when executing the computer program
Image white balance correcting.
The image white balance correction scheme provided in the embodiment of the present application, is first split target image, obtains more
A target subgraph；Secondly, obtaining the corresponding light source direction of each target sub-picture content；Again, according to the multiple target
Subgraph corresponding light source walking direction whether there is light mixing scene；Finally, when there are light mixing scene, according to the light mixing scene
Corresponding light source carries out white balance correction, can be improved image white balance correction effect under light mixing scene.
Detailed description of the invention
Fig. 1 is a kind of flow diagram of image white balance correcting provided by the embodiments of the present application；
Fig. 2 is the flow diagram of another image white balance correcting provided by the embodiments of the present application；
Fig. 3 is the flow diagram of another image white balance correcting provided by the embodiments of the present application；
Fig. 4 is the flow diagram of another image white balance correcting provided by the embodiments of the present application；
Fig. 5 is the flow diagram of another image white balance correcting provided by the embodiments of the present application；
Fig. 6 is the flow diagram of another image white balance correcting provided by the embodiments of the present application；
Fig. 7 is a kind of structural schematic diagram of image white balance correction device provided by the embodiments of the present application；
Fig. 8 is a kind of structural schematic diagram of mobile terminal provided by the embodiments of the present application.
Specific embodiment
Further illustrate the technical solution of the application below with reference to the accompanying drawings and specific embodiments.It is understood that
It is that specific embodiment described herein is used only for explaining the application, rather than the restriction to the application.It further needs exist for illustrating
, part relevant to the application is illustrated only for ease of description, in attached drawing rather than entire infrastructure.
It should be mentioned that some exemplary embodiments are described as before exemplary embodiment is discussed in greater detail
The processing or method described as flow chart.Although each step is described as the processing of sequence by flow chart, many of these
Step can be implemented concurrently, concomitantly or simultaneously.In addition, the sequence of each step can be rearranged.When its operation
The processing can be terminated when completion, it is also possible to have the additional step being not included in attached drawing.The processing can be with
Corresponding to method, function, regulation, subroutine, subprogram etc..
With the continuous development of mobile terminal, almost every mobile terminal is configured with camera function, is based on camera function
It can take pictures.Mobile terminal is intended to the process of taking pictures of automation, can be exposed automatically according to photo environment and white
Balance correction.But discovery in use, if there is light mixing scene there are when multiple and different direction light sources in shooting picture
When, then the photo white balance effect shot is poor, can not accurately reflect the main body colour temperature that is taken.In the embodiment of the present application
Light mixing scene include that there are the photographed scenes of the light source in multiple and different directions.The light that multiple light sources issue from different perspectives leads to
When being reflected into mould group of subject is crossed, it is not normal to will lead to collected light color temperature.Mobile terminal is automatic white at present
In equilibrium code, lack the mechanism identified to different light source directions, leads to not the light source for identifying different directions, Jin Erwu
Method carries out effective white balance processing to light mixing scene.
The embodiment of the present application provides a kind of image white balance correcting, can identify whether photographed scene is light mixing field
Scape can carry out white balance processing based on the light source in multiple light sources direction, improve light mixing field when photographed scene is light mixing scene
The white balance treatment effeciency of scape, makes white balance treated that image has more accurate colour temperature, improves resource utilization.Specifically
Scheme is as follows:
Fig. 1 is the flow diagram of image white balance correcting provided by the embodiments of the present application, and this method is for using
The case where the case where mobile terminal is taken pictures, especially light mixing scene is taken pictures, this method can be executed by mobile terminal, should
Mobile terminal can be smart phone, tablet computer, wearable device, laptop etc., and this method specifically includes following step
It is rapid:
Step 110 is split target image, obtains multiple target subgraphs.
Target image can be the photo that user takes pictures, or the preview image of preview phase.When user claps
It takes after obtaining a picture, to clap when mobile terminal carries out white balance processing or user's progress post-production to photo automatically
It is modified based on the picture taken.When user starts camera applications, camera applications real-time display camera in preview interface
The preview frame image got.When preview frame image meets user demand in preview interface, user clicks button progress of taking pictures
It takes pictures, obtains photo.Mobile terminal carries out white balance processing before showing preview screen, to preview screen, so that user is pre-
The stage of looking at can get the image of accurate colour temperature.The time is calculated in view of white balance processing can generate, can accordingly reduce preview
The frame per second of picture.
It can be according to fixed default divided area, such as with the fixed size segmentation object image of 50 pixel *, 50 pixel.Into
One step, if the partitioning scheme of fixed size can not be matched with target image, if there are a deficiencies for target image side
The subgraph of default divided area, then can ignore the subgraph.It can also be with according to fixed dividing number to target image memory
Segmentation, for example, target image is divided into 10*10, totally 100 target subgraphs.
Step 120 obtains the corresponding light source direction of each target sub-picture content.
In one implementation, there is directionality can be led to by the detection to light source and reflected light for the irradiation of light source
The light reflection case crossed in detection target subgraph determines light source direction.Illustratively, if at least two target subgraphs
Light source direction meet reflection law, then can determine reflective information according to target subgraph.Reflective information may include existing instead
Penetrate the corresponding relationship of at least two detection zones of relationship.
For example, when incandescent lamp is lighted, the objects such as desktop can be issued reflective for flashers such as incandescent lamps.Work as incandescent lamp
When extinguishing, the objects such as desktop do not shine.Therefore it can determine occur the inspection of pixel or brightness change in pairs according to pixel changing value
Survey region.Light source and its irradiation area can be determined based on the detection zone of brilliant synchrotron variation.
In another implementation, identification any one target can be realized by establishing default machine learning model
Light source direction in image, if output is the direction vector for indicating light source direction there are light source in target subgraph.If
Light source is not present in target subgraph, then exporting result can be 0 or default item etc..
Step 130 whether there is light mixing scene according to multiple target subgraph corresponding light source walking directions.
If there is multiple light sources direction, then it can determine there are light mixing scene, execute step 140.If only existing one
Light source direction, it is determined that light mixing scene is not present, executes step 150.
Step 140, when there are light mixing scene, white balance correction is carried out according to the corresponding light source of light mixing scene.
The corresponding light source of light mixing scene can be the corresponding whole light sources of target subgraph.Obtaining the multiple of light mixing scene
After light source, the reference color of white balance correction is determined according to the light intensity of multiple light sources.
Step 150, when be not present light mixing scene when, according to adjust to white plate carry out white balance processing.
It is available to environment colour temperature to adjust to white plate, white balance processing is carried out according to environment colour temperature.Optionally, with 3200K color
Blue, green, the red photosensitive balance being arranged under the conditions of temperature.When environment colour temperature is 3200K, video camera colour temperature filter is placed on
3200K, the available correct color rendition of scenery；When environment colour temperature is 5600K, video camera colour temperature filter is placed on
5600K, the available correct color rendition of scenery.When environment colour temperature above or below 3200K 1000K and 5600K or more 1000K model
In enclosing, the available human eye acceptable color rendition of white balance preparatory function is utilized.
Image white balance correcting provided by the embodiments of the present application, is first split target image, obtains multiple
Target subgraph.Secondly, obtaining the corresponding light source direction of each target sub-picture content.Again, according to multiple target subgraphs
Corresponding light source walking direction whether there is light mixing scene.Finally, when there are light mixing scene, according to the corresponding light source of light mixing scene
White balance correction is carried out, can be improved image white balance correction effect under light mixing scene.It at present can not be in recognition target image not
With the light source of light source direction, lead to target image entirety colour temperature judgement inaccuracy, white balance effect is poor.The application is implemented
Example can determine the light source of different light source directions based on the obtained target subgraph of segmentation, then according to the light source of different directions into
Row white balance correction, so can more high-quality reduction be taken scene colour temperature.
Fig. 2 is a kind of flow diagram of image white balance correcting provided by the embodiments of the present application, as to above-mentioned
The further explanation of embodiment, comprising:
Step 210 is split target image, obtains multiple target subgraphs.
Step 220 obtains the corresponding light source direction of each target sub-picture content.
Step 230 judges whether multiple adjacent corresponding light source directions of target subgraph are identical.
A key factor for judging whether there is light mixing scene is and one kind of multiple light sources with the presence or absence of multiple light sources
The form of expression is, the corresponding light source direction difference of multiple adjacent target subgraphs is identical.Pass through default machine learning model etc.
The light source direction of the available each target subgraph of algorithm.It is by comparing the light source direction between adjacent target subgraph
It is no identical, it may be determined whether there are different light sources.Further, when the angle of the light source direction between adjacent target subgraph
When difference is less than predetermined angle, it is possible to determine that the light source direction between adjacent target subgraph is identical.Predetermined angle is 5 degree 10
Degree.
If multiple adjacent corresponding light source directions of target subgraph are identical, 240 are thened follow the steps.If multiple adjacent
The corresponding light source direction of target subgraph it is not identical, then follow the steps 260.
If step 240, multiple adjacent corresponding light source directions of target subgraph be not identical, there are light mixing scenes.
Step 250, when there are light mixing scene, white balance correction is carried out according to the corresponding light source of light mixing scene.
If step 260, multiple adjacent corresponding light source directions of target subgraph are identical, light mixing scene is not present,
White balance processing is carried out according to plate is adjusted to white.
Image white balance correcting provided by the embodiments of the present application, can be based on the light source direction of adjacent target subgraph
Whether identical, in other words, whether the light source direction of adjacent target subgraph is significantly different, to determine whether there is multiple light sources,
And then more accurately determine light mixing scene, improve resource utilization.
Fig. 3 is a kind of flow diagram of image white balance correcting provided by the embodiments of the present application, as to above-mentioned
The further explanation of embodiment, comprising:
Step 310 is split target image, obtains multiple target subgraphs.
Step 320 obtains the corresponding light source direction of each target sub-picture content.
Step 330 whether there is light mixing scene according to multiple target subgraph corresponding light source walking directions.
Step 340, when there are light mixing scene, determine main light source according to the corresponding multiple light sources of multiple target subgraphs.
Optionally, light source intensity can be determined according to the brightness of target subgraph, based on the highest light source determination of light intensity
Light source.White balance correction is carried out according to the light source colour of main light source.
Further, the weight of each light source can also be determined according to light source intensity, the intensity of light source is higher, and weight is higher, according to
Each light source weight and each light source colour, obtain main light source color.White balance correction is carried out according to the light source colour of main light source.
Step 350 carries out white balance correction to target image according to main light source.
Step 360, when be not present light mixing scene when, according to adjust to white plate carry out white balance processing.
Image white balance correcting provided by the embodiments of the present application can determine main light source, and root from multiple light sources
White balance processing is carried out according to main light source, and then main light source color is determined more accurately, improves white balance treatment effeciency.
Fig. 4 is a kind of flow diagram of image white balance correcting provided by the embodiments of the present application, as to above-mentioned
The further explanation of embodiment, comprising:
Step 410 is split target image, obtains multiple target subgraphs.
Step 420 obtains the corresponding light source direction of each target sub-picture content.
Step 430 whether there is light mixing scene according to multiple target subgraph corresponding light source walking directions.
Step 440, when there are light mixing scene, obtain the corresponding multiple light sources direction of multiple target subgraphs.
After determining light mixing scene, the stronger multiple light sources direction of illumination can be filtered out according to intensity of illumination.Optionally,
Each light source colour is obtained, the light source that a light intensity is increased is chosen from similar light sources color.It is also possible that in read step 420 really
Fixed whole light sources direction.
Step 450, the corresponding target subgraph quantity of each light source direction of statistics.
The quantity with the target subgraph in same light source direction is counted, the corresponding target subgraph of each light source direction is obtained
As quantity.
Step 460 determines main light source according to the target subgraph quantity of statistics.
The corresponding light source direction of the highest target subgraph quantity of numerical value is determined as main light source.
Step 470 carries out white balance correction to target image according to main light source.
Step 480, when be not present light mixing scene when, according to adjust to white plate carry out white balance processing.
Image white balance correcting provided by the embodiments of the present application, can be highest by light source accounting from multiple light sources
Light source is determined as main light source, and then main light source color is determined more accurately, and improves white balance treatment effeciency.
Fig. 5 is a kind of flow diagram of image white balance correcting provided by the embodiments of the present application, as to above-mentioned
The further explanation of embodiment, comprising:
Step 510 obtains multiple study images with single light source, and study image is input to convolutional neural networks mould
In type, default machine learning model is obtained.
When obtaining the light source direction of each target subgraph, can be identified by default machine learning model.This is pre-
If machine learning model can be a convolutional neural networks model.Before the embodiment of the present application execution, pass through machine learning
Mode, convolutional neural networks model is trained, training sample can be the study image with single light source.By instruction
Experienced convolutional neural networks model, i.e., default machine learning model can identify the corresponding light source side of any one target subgraph
To.
Step 520 is split target image, obtains multiple target subgraphs.
Step 530, respectively by each target subgraph input value preset machine learning model, obtain each target subgraph
Corresponding light source direction.
Step 540 whether there is light mixing scene according to multiple target subgraph corresponding light source walking directions.
Step 550, when there are light mixing scene, white balance correction is carried out according to the corresponding light source of light mixing scene.
Step 560, when be not present light mixing scene when, according to adjust to white plate carry out white balance processing.
Image white balance correcting provided by the embodiments of the present application can have the study figure of single light source by inputting
Default machine learning model is obtained as training, and then avoids passing through the problem of fixed algorithm identification inaccuracy, improves light source direction
The ease for use of identification.
Fig. 6 is a kind of flow diagram of image white balance correcting provided by the embodiments of the present application, as to above-mentioned
The further explanation of embodiment, comprising:
Step 610, the input specification for obtaining default machine learning model.
If the input specification of default machine learning model is the image of fixed size, it is split to target image
Before, the input specification of default machine learning model is obtained, to be split according to input specification to target image.
Step 620 is split target image according to input specification, obtains multiple target subgraphs.
Step 630, respectively by each target subgraph input value preset machine learning model, obtain each target subgraph
Corresponding light source direction.
Step 640 whether there is light mixing scene according to multiple target subgraph corresponding light source walking directions.
Step 650, when there are light mixing scene, white balance correction is carried out according to the corresponding light source of light mixing scene.
Step 660, when be not present light mixing scene when, according to adjust to white plate carry out white balance processing.
Image white balance correcting provided by the embodiments of the present application can be advised according to the input of default machine learning model
Lattice divide target image, and then enable to preset the light source side that machine learning model identifies target subgraph faster
To raising treatment effeciency.
Fig. 7 is a kind of structural schematic diagram of image white balance correction device provided by the embodiments of the present application.As shown in fig. 7,
The device includes: segmentation module 710, obtains module 720, judgment module 730, white balance module 740 and study module 750.
Divide module 710 and obtains multiple target subgraphs for being split to target image；
Module 720 is obtained, the corresponding light source of each target sub-picture content obtained for obtaining the segmentation module 710
Direction；
Judgment module 730, the multiple target subgraph corresponding light source side for being obtained according to the acquisition module 720
To judging whether there is light mixing scene；
White balance module 740, for determining there are when light mixing scene, according to the light mixing field when the judgment module 730
The corresponding light source of scape carries out white balance correction.
Further, judgment module 730 is used for:
Judge whether multiple adjacent corresponding light source directions of target subgraph are identical；
If multiple adjacent corresponding light source directions of target subgraph are not identical, there are light mixing scenes.
Further, white balance module 740 is used for:
Main light source is determined according to the corresponding multiple light sources of the multiple target subgraph；
White balance correction is carried out to the target image according to the main light source.
Further, white balance module 740 determines main light source according to the corresponding multiple light sources of the multiple target subgraph,
Include:
Obtain the corresponding multiple light sources direction of the multiple target subgraph；
Count the corresponding target subgraph quantity of each light source direction；
Main light source is determined according to the target subgraph quantity of statistics.
Further, module 720 is obtained to be used for:
Each target subgraph input value is preset into machine learning model respectively, it is corresponding to obtain each target subgraph
Light source direction.
Further, further include study module 750, study module 750 is used for: respectively inputting each target subgraph
It is worth before default machine learning model, obtains multiple study images with single light source；
The study image is input in convolutional neural networks model, default machine learning model is obtained, to judge
Module 730 judges that multiple target subgraph corresponding light source directions are sentenced according to the default machine learning model that study module 750 obtains
It is disconnected to whether there is light mixing scene.
Further, module 720 is obtained to be used for:
Obtain the input specification of the default machine learning model；
The target image is split according to the input specification, obtains multiple target subgraphs.
Image white balance correction device provided by the embodiments of the present application, first segmentation module 710 divide target image
It cuts, obtains multiple target subgraphs；Secondly, obtaining module 720 obtains the corresponding light source direction of each target sub-picture content；Again
Secondary, judgment module 730 whether there is light mixing scene according to the multiple target subgraph corresponding light source walking direction；Finally, working as
There are when light mixing scene, white balance module 740 carries out white balance correction according to the corresponding light source of the light mixing scene, can be improved
Image white balance correction effect under light mixing scene.At present can not in recognition target image different light source directions light source, lead to mesh
The problems such as logo image entirety colour temperature judgement inaccuracy, white balance effect is poor.The mesh that the embodiment of the present application can be obtained based on segmentation
Mark subgraph determines the light source of different light source directions, then carries out white balance correction according to the light source of different directions, and then can
More high-quality reduction is taken scene colour temperature.
Method provided by the aforementioned all embodiments of the application can be performed in above-mentioned apparatus, and it is corresponding to have the execution above method
Functional module and beneficial effect.The not technical detail of detailed description in the present embodiment, reference can be made to the aforementioned all implementations of the application
Method provided by example.
Fig. 8 is a kind of structural schematic diagram of terminal device provided by the embodiments of the present application.As shown in figure 8, the terminal can be with
Include: shell (not shown), memory 801, central processing unit (Central Processing Unit, CPU) 802 (again
Claim processor, hereinafter referred to as CPU), the computer program, the circuit that are stored on memory 801 and can be run on processor 802
Plate (not shown) and power circuit (not shown).The circuit board is placed in the space interior that the shell surrounds；
The CPU802 and the memory 801 are arranged on the circuit board；The power circuit, for for each of the terminal
Circuit or device power supply；The memory 801, for storing executable program code；The CPU802 described in reading by depositing
The executable program code stored in reservoir 801 runs program corresponding with the executable program code.
The terminal further include: Peripheral Interface 803, RF (Radio Frequency, radio frequency) circuit 805, voicefrequency circuit
806, loudspeaker 811, power management chip 808, input/output (I/O) subsystem 809, touch screen 812, other input/controls
Equipment 810 and outside port 804, these components are communicated by one or more communication bus or signal wire 807.
It should be understood that graphic terminal 800 is only an example of terminal, and terminal device 800 can be with
With than shown in the drawings more or less component, two or more components can be combined, or can have
Different component configurations.Various parts shown in the drawings can include one or more signal processings and/or dedicated integrated
It is realized in the combination of hardware, software or hardware and software including circuit.
Just provided in this embodiment below to be described in detail for a kind of terminal device, the terminal device is with intelligent hand
For machine.
Memory 801, the memory 801 can be accessed by CPU802, Peripheral Interface 803 etc., and the memory 801 can
It can also include nonvolatile memory to include high-speed random access memory, such as one or more disk memory,
Flush memory device or other volatile solid-state parts.
The peripheral hardware that outputs and inputs of equipment can be connected to CPU802 and deposited by Peripheral Interface 803, the Peripheral Interface 803
Reservoir 801.
I/O subsystem 809, the I/O subsystem 809 can be by the input/output peripherals in equipment, such as touch screen 812
With other input/control devicess 810, it is connected to Peripheral Interface 803.I/O subsystem 809 may include 8091 He of display controller
For controlling one or more input controllers 8092 of other input/control devicess 810.Wherein, one or more input controls
Device 8092 processed receives electric signal from other input/control devicess 810 or sends electric signal to other input/control devicess 810,
Other input/control devicess 810 may include physical button (push button, rocker buttons etc.), dial, slide switch, behaviour
Vertical pole clicks idler wheel.It is worth noting that input controller 8092 can with it is following any one connect: keyboard, infrared port,
The indicating equipment of USB interface and such as mouse.
Wherein, according to the working principle of touch screen and transmission information medium classification, touch screen 812 can for resistance-type,
Capacitor induction type, infrared-type or surface acoustic wave type.Classify according to mounting means, touch screen 812 can be with are as follows: external hanging type, built-in
Formula or monoblock type.Classify according to technical principle, touch screen 812 can be with are as follows: vector pressure sensing technology touch screen, resistive technologies touching
Touch screen, capacitance technology touch screen, infrared technology touch screen or surface acoustic wave technique touch screen.
Touch screen 812, the touch screen 812 are the input interface and output interface between user terminal and user, can
It is shown to user depending on output, visual output may include figure, text, icon, video etc..Optionally, touch screen 812 is by user
The electric signal (electric signal of such as contact surface) triggered on touch screen curtain, is sent to processor 802.
Display controller 8091 in I/O subsystem 809 receives electric signal from touch screen 812 or sends out to touch screen 812
Electric signals.Touch screen 812 detects the contact on touch screen, and the contact that display controller 8091 will test is converted to and is shown
The interaction of user interface object on touch screen 812, i.e. realization human-computer interaction, the user interface being shown on touch screen 812
Object can be the icon of running game, the icon for being networked to corresponding network etc..It is worth noting that equipment can also include light
Mouse, light mouse are the extensions for the touch sensitive surface for not showing the touch sensitive surface visually exported, or formed by touch screen.
RF circuit 805 is mainly used for establishing the communication of intelligent sound box Yu wireless network (i.e. network side), realizes intelligent sound box
Data receiver and transmission with wireless network.Such as transmitting-receiving short message, Email etc..
Voicefrequency circuit 806 is mainly used for receiving audio data from Peripheral Interface 803, which is converted to telecommunications
Number, and the electric signal is sent to loudspeaker 811.
Loudspeaker 811 is reduced to for intelligent sound box to be passed through RF circuit 805 from the received voice signal of wireless network
Sound simultaneously plays the sound to user.
Power management chip 808, the hardware for being connected by CPU802, I/O subsystem and Peripheral Interface are powered
And power management.
In the present embodiment, central processing unit 802 is used for:
Target image is split, multiple target subgraphs are obtained；
Obtain the corresponding light source direction of each target sub-picture content；
It whether there is light mixing scene according to the multiple target subgraph corresponding light source walking direction；
When there are light mixing scene, white balance correction is carried out according to the corresponding light source of the light mixing scene.
It is further, described that light mixing scene whether there is according to the multiple target subgraph corresponding light source walking direction,
Include:
Judge whether multiple adjacent corresponding light source directions of target subgraph are identical；
If multiple adjacent corresponding light source directions of target subgraph are not identical, there are light mixing scenes.
It is further, described that white balance correction is carried out according to the corresponding light source of the light mixing scene, comprising:
Main light source is determined according to the corresponding multiple light sources of the multiple target subgraph；
White balance correction is carried out to the target image according to the main light source.
It is further, described to determine main light source according to the corresponding multiple light sources of the multiple target subgraph, comprising:
Obtain the corresponding multiple light sources direction of the multiple target subgraph；
Count the corresponding target subgraph quantity of each light source direction；
Main light source is determined according to the target subgraph quantity of statistics.
It is further, described to obtain the corresponding light source direction of each target sub-picture content, comprising:
Each target subgraph input value is preset into machine learning model respectively, it is corresponding to obtain each target subgraph
Light source direction.
Further, before each target subgraph input value is preset machine learning model respectively, further includes:
Obtain multiple study images with single light source；
The study image is input in convolutional neural networks model, default machine learning model is obtained.
Further, described that target image is split, obtain multiple target subgraphs, comprising:
Obtain the input specification of the default machine learning model；
The target image is split according to the input specification, obtains multiple target subgraphs.
The embodiment of the present application also provides a kind of storage medium comprising terminal device executable instruction, and the terminal device can
It executes instruction when being executed by terminal device processor for executing a kind of image white balance correcting, this method comprises:
Target image is split, multiple target subgraphs are obtained；
Obtain the corresponding light source direction of each target sub-picture content；
It whether there is light mixing scene according to the multiple target subgraph corresponding light source walking direction；
When there are light mixing scene, white balance correction is carried out according to the corresponding light source of the light mixing scene.
It is further, described that light mixing scene whether there is according to the multiple target subgraph corresponding light source walking direction,
Include:
Judge whether multiple adjacent corresponding light source directions of target subgraph are identical；
If multiple adjacent corresponding light source directions of target subgraph are not identical, there are light mixing scenes.
It is further, described that white balance correction is carried out according to the corresponding light source of the light mixing scene, comprising:
Main light source is determined according to the corresponding multiple light sources of the multiple target subgraph；
White balance correction is carried out to the target image according to the main light source.
It is further, described to determine main light source according to the corresponding multiple light sources of the multiple target subgraph, comprising:
Obtain the corresponding multiple light sources direction of the multiple target subgraph；
Count the corresponding target subgraph quantity of each light source direction；
Main light source is determined according to the target subgraph quantity of statistics.
It is further, described to obtain the corresponding light source direction of each target sub-picture content, comprising:
Each target subgraph input value is preset into machine learning model respectively, it is corresponding to obtain each target subgraph
Light source direction.
Further, before each target subgraph input value is preset machine learning model respectively, further includes:
Obtain multiple study images with single light source；
The study image is input in convolutional neural networks model, default machine learning model is obtained.
Further, described that target image is split, obtain multiple target subgraphs, comprising:
Obtain the input specification of the default machine learning model；
The target image is split according to the input specification, obtains multiple target subgraphs.
The computer storage medium of the embodiment of the present application, can be using any of one or more computer-readable media
Combination.Computer-readable medium can be computer-readable signal media or computer readable storage medium.It is computer-readable
Storage medium for example may be-but not limited to-the system of electricity, magnetic, optical, electromagnetic, infrared ray or semiconductor, device or
Device, or any above combination.The more specific example (non exhaustive list) of computer readable storage medium includes: tool
There are electrical connection, the portable computer diskette, hard disk, random access memory (RAM), read-only memory of one or more conducting wires
(ROM), erasable programmable read only memory (EPROM or flash memory), optical fiber, portable compact disc read-only memory (CD-
ROM), light storage device, magnetic memory device or above-mentioned any appropriate combination.In this document, computer-readable storage
Medium can be any tangible medium for including or store program, which can be commanded execution system, device or device
Using or it is in connection.
Computer-readable signal media may include in a base band or as carrier wave a part propagate data-signal,
Wherein carry computer-readable program code.The data-signal of this propagation can take various forms, including but unlimited
In electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal media can also be that computer can
Any computer-readable medium other than storage medium is read, which can send, propagates or transmit and be used for
By the use of instruction execution system, device or device or program in connection.
The program code for including on computer-readable medium can transmit with any suitable medium, including --- but it is unlimited
In wireless, electric wire, optical cable, RF etc. or above-mentioned any appropriate combination.
Can with one or more programming languages or combinations thereof come write for execute the application operation computer
Program code, programming language include object oriented program language-such as Java, Smalltalk, C++, are also wrapped
Include conventional procedural programming language-such as " C " language or similar programming language.Program code can be complete
Ground executes on the user computer, partly executes on the user computer, executing as an independent software package, partially existing
Part executes on the remote computer or executes on a remote computer or server completely on subscriber computer.It is being related to
In the situation of remote computer, remote computer can pass through the network of any kind --- including local area network (LAN) or wide area
Net (WAN)-be connected to subscriber computer, or, it may be connected to outer computer (such as utilize ISP
To be connected by internet).
Certainly, a kind of storage medium comprising computer executable instructions, computer provided by the embodiment of the present application
The image white balance correction operation that executable instruction is not limited to the described above, can also be performed the application any embodiment and is provided
Image white balance correcting in relevant operation.
Note that above are only the preferred embodiment and institute's application technology principle of the application.It will be appreciated by those skilled in the art that
The application is not limited to specific embodiment described here, be able to carry out for a person skilled in the art it is various it is apparent variation,
The protection scope readjusted and substituted without departing from the application.Therefore, although being carried out by above embodiments to the application
It is described in further detail, but the application is not limited only to above embodiments, in the case where not departing from the application design, also
It may include more other equivalent embodiments, and scope of the present application is determined by the scope of the appended claims.
Claims (10)
1. a kind of image white balance correcting characterized by comprising
Target image is split, multiple target subgraphs are obtained；
Obtain the corresponding light source direction of each target sub-picture content；
It whether there is light mixing scene according to the multiple target subgraph corresponding light source walking direction；
When there are light mixing scene, white balance correction is carried out according to the corresponding light source of the light mixing scene.
2. image white balance correcting according to claim 1, which is characterized in that described according to the multiple target
Image corresponding light source walking direction whether there is light mixing scene, comprising:
Judge whether multiple adjacent corresponding light source directions of target subgraph are identical；
If multiple adjacent corresponding light source directions of target subgraph are not identical, there are light mixing scenes.
3. image white balance correcting according to claim 1, which is characterized in that described according to the light mixing scene pair
The light source answered carries out white balance correction, comprising:
Main light source is determined according to the corresponding multiple light sources of the multiple target subgraph；
White balance correction is carried out to the target image according to the main light source.
4. image white balance correcting according to claim 3, which is characterized in that described according to the multiple target
The corresponding multiple light sources of image determine main light source, comprising:
Obtain the corresponding multiple light sources direction of the multiple target subgraph；
Count the corresponding target subgraph quantity of each light source direction；
Main light source is determined according to the target subgraph quantity of statistics.
5. image white balance correcting according to claim 1, which is characterized in that described to obtain each target subgraph
The corresponding light source direction of content, comprising:
Each target subgraph input value is preset into machine learning model respectively, obtains the corresponding light of each target subgraph
Source direction.
6. image white balance correcting according to claim 5, which is characterized in that respectively by each target subgraph
Input value is preset before machine learning model, further includes:
Obtain multiple study images with single light source；
The study image is input in convolutional neural networks model, default machine learning model is obtained.
7. image white balance correcting according to claim 5, which is characterized in that described to divide target image
It cuts, obtains multiple target subgraphs, comprising:
Obtain the input specification of the default machine learning model；
The target image is split according to the input specification, obtains multiple target subgraphs.
8. a kind of image white balance correction device characterized by comprising
Divide module and obtains multiple target subgraphs for being split to target image；
Module is obtained, the corresponding light source direction of each target sub-picture content obtained for obtaining the segmentation module；
Judgment module, whether the multiple target subgraph corresponding light source walking direction for being obtained according to the acquisition module
There are light mixing scenes；
White balance module, for determining there are when light mixing scene, according to the corresponding light of the light mixing scene when the judgment module
Source carries out white balance correction.
9. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the program is held by processor
It is realized when row such as any described image white balance correcting in claim 1-7.
10. a kind of terminal, including memory, processor and storage are on a memory and can be in the computer journey of processor operation
Sequence, which is characterized in that the processor realizes that image as claimed in claim 1 is white when executing the computer program
Method for correcting balance.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810934706.3A CN109040729B (en) | 2018-08-16 | 2018-08-16 | Image white balance correction method and device, storage medium and terminal |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810934706.3A CN109040729B (en) | 2018-08-16 | 2018-08-16 | Image white balance correction method and device, storage medium and terminal |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109040729A true CN109040729A (en) | 2018-12-18 |
| CN109040729B CN109040729B (en) | 2020-04-07 |
Family
ID=64631682
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810934706.3A Active CN109040729B (en) | 2018-08-16 | 2018-08-16 | Image white balance correction method and device, storage medium and terminal |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109040729B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110647930A (en) * | 2019-09-20 | 2020-01-03 | 北京达佳互联信息技术有限公司 | Image processing method and device and electronic equipment |
| CN112561810A (en) * | 2020-12-07 | 2021-03-26 | 西安诺瓦星云科技股份有限公司 | Display screen light-mixing removing method and device, storage medium and processor |
| CN112634182A (en) * | 2020-12-18 | 2021-04-09 | 平安普惠企业管理有限公司 | Image correction method, device and equipment based on light field and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101046847A (en) * | 2007-04-29 | 2007-10-03 | 中山大学 | Human face light alignment method based on secondary multiple light mould |
| US20110007181A1 (en) * | 2005-05-16 | 2011-01-13 | Sony Corporation | Image processing apparatus, method, program and image pickup apparatus |
| CN106651795A (en) * | 2016-12-03 | 2017-05-10 | 北京联合大学 | Method of using illumination estimation to correct image color |
| CN107464244A (en) * | 2017-03-09 | 2017-12-12 | 广东顺德中山大学卡内基梅隆大学国际联合研究院 | A kind of image irradiation method of estimation based on neutral net |
| CN107682685A (en) * | 2017-10-30 | 2018-02-09 | 广东欧珀移动通信有限公司 | White balancing treatment method and device, electronic installation and computer-readable recording medium |
| CN108401148A (en) * | 2017-02-06 | 2018-08-14 | 联发科技股份有限公司 | Method for executing automatic white balance to image |
-
2018
- 2018-08-16 CN CN201810934706.3A patent/CN109040729B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110007181A1 (en) * | 2005-05-16 | 2011-01-13 | Sony Corporation | Image processing apparatus, method, program and image pickup apparatus |
| CN101046847A (en) * | 2007-04-29 | 2007-10-03 | 中山大学 | Human face light alignment method based on secondary multiple light mould |
| CN106651795A (en) * | 2016-12-03 | 2017-05-10 | 北京联合大学 | Method of using illumination estimation to correct image color |
| CN108401148A (en) * | 2017-02-06 | 2018-08-14 | 联发科技股份有限公司 | Method for executing automatic white balance to image |
| CN107464244A (en) * | 2017-03-09 | 2017-12-12 | 广东顺德中山大学卡内基梅隆大学国际联合研究院 | A kind of image irradiation method of estimation based on neutral net |
| CN107682685A (en) * | 2017-10-30 | 2018-02-09 | 广东欧珀移动通信有限公司 | White balancing treatment method and device, electronic installation and computer-readable recording medium |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110647930A (en) * | 2019-09-20 | 2020-01-03 | 北京达佳互联信息技术有限公司 | Image processing method and device and electronic equipment |
| CN112561810A (en) * | 2020-12-07 | 2021-03-26 | 西安诺瓦星云科技股份有限公司 | Display screen light-mixing removing method and device, storage medium and processor |
| CN112561810B (en) * | 2020-12-07 | 2023-09-08 | 西安诺瓦星云科技股份有限公司 | Light-mixing removing method and device for display screen, storage medium and processor |
| CN112634182A (en) * | 2020-12-18 | 2021-04-09 | 平安普惠企业管理有限公司 | Image correction method, device and equipment based on light field and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109040729B (en) | 2020-04-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109191410B (en) | Face image fusion method and device and storage medium | |
| EP2958316B1 (en) | Electronic device using composition information of picture and shooting method using the same | |
| US20180041724A1 (en) | Electronic device having camera module, and image processing method for electronic device | |
| CN104869320A (en) | Electronic device and control method of the same | |
| CN109413563A (en) | The sound effect treatment method and Related product of video | |
| CN108881875A (en) | Image white balancing treatment method, device, storage medium and terminal | |
| CN109327691B (en) | Image shooting method and device, storage medium and mobile terminal | |
| CN108668086A (en) | Atomatic focusing method, device, storage medium and terminal | |
| CN109040729A (en) | Image white balance correcting, device, storage medium and terminal | |
| CN109639896A (en) | Block object detecting method, device, storage medium and mobile terminal | |
| KR102206877B1 (en) | Method and apparatus for displaying biometric information | |
| CN108650457A (en) | Automatic photographing method, device, storage medium and mobile terminal | |
| CN107484231A (en) | Screen parameter method of adjustment, device, terminal and computer-readable recording medium | |
| CN109040524A (en) | Artifact eliminating method, device, storage medium and terminal | |
| CN109101931A (en) | A kind of scene recognition method, scene Recognition device and terminal device | |
| CN109120864B (en) | Light supplement processing method and device, storage medium and mobile terminal | |
| CN109348206A (en) | Image white balancing treatment method, device, storage medium and mobile terminal | |
| CN111092748A (en) | Alarm rule setting method, device, equipment and storage medium for Internet of things equipment | |
| CN108021905A (en) | image processing method, device, terminal device and storage medium | |
| CN106815803B (en) | Picture processing method and device | |
| WO2022140887A1 (en) | Image processing method and apparatus | |
| CN108665510A (en) | Rendering intent, device, storage medium and the terminal of continuous shooting image | |
| CN112116690A (en) | Video special effect generation method and device and terminal | |
| CN109561291A (en) | Color temperature compensating method, device, storage medium and mobile terminal | |
| CN104270564A (en) | Terminal |
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 |