CN108174096A - Method, apparatus, terminal and the storage medium of acquisition parameters setting - Google Patents
Method, apparatus, terminal and the storage medium of acquisition parameters setting Download PDFInfo
- Publication number
- CN108174096A CN108174096A CN201711470123.1A CN201711470123A CN108174096A CN 108174096 A CN108174096 A CN 108174096A CN 201711470123 A CN201711470123 A CN 201711470123A CN 108174096 A CN108174096 A CN 108174096A
- Authority
- CN
- China
- Prior art keywords
- parameter
- acquisition parameters
- sample
- pose
- recommended models
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/62—Control of parameters via user interfaces
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/667—Camera operation mode switching, e.g. between still and video, sport and normal or high- and low-resolution modes
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Human Computer Interaction (AREA)
- Studio Devices (AREA)
Abstract
This application discloses a kind of acquisition parameters setting method, device, terminal and storage mediums, belong to field of computer technology.This method includes：It obtains the pose parameter of picture shooting assembly and is presently in the environmental parameter of environment；By the pose parameter and the environmental parameter input parameter recommended models, obtain recommending acquisition parameters；According to the recommendation acquisition parameters setting acquisition parameters；Wherein, the parameter recommended models are determined according to sample pose parameter, sample environment parameter and sample acquisition parameters.The application can solve the problems, such as the less efficient of terminal setting acquisition parameters；Custom is shot since the recommendation acquisition parameters that parameter recommended models are determined meet user, therefore, the probability adopted by user is higher, in this way, without user, acquisition parameters are voluntarily set, and can ensure the accuracy for the acquisition parameters that terminal is set automatically, the efficiency of terminal setting acquisition parameters can be improved.
Description
Technical field
The invention relates to field of computer technology, more particularly to a kind of acquisition parameters setting method, device, terminal
And storage medium.
Background technology
The terminal for being equipped with camera has shooting function.With the quality requirement for the image that user shoots camera
Higher and higher, terminal also has the function of that acquisition parameters are adjusted.Wherein, acquisition parameters refer to camera is being used to shoot
The parameter used during image.
At present, it is to the method that acquisition parameters are adjusted：Terminal shows the adjusting control of acquisition parameters, and reception acts on
The adjusting operation of control is adjusted, according to the corresponding acquisition parameters of adjusting operation setting.
However, above-mentioned regulative mode needs user's manual setting acquisition parameters, increase with the type of acquisition parameters, use
Family needs the number set also to increase therewith, sets the less efficient of acquisition parameters,
Invention content
Acquisition parameters setting method provided by the embodiments of the present application, device, terminal and storage medium can solve setting and clap
Take the photograph parameter it is less efficient the problem of.The technical solution is as follows：
In a first aspect, a kind of acquisition parameters setting method is provided, the method includes：
It obtains the pose parameter of picture shooting assembly and is presently in the environmental parameter of environment；
By the pose parameter and the environmental parameter input parameter recommended models, obtain recommending acquisition parameters；
According to the recommendation acquisition parameters setting acquisition parameters；
Wherein, the parameter recommended models are true according to sample pose parameter, sample environment parameter and sample acquisition parameters
Fixed；The sample acquisition parameters refer to actual photographed parameter when history shoots image；The sample pose parameter refer to
During the sample acquisition parameters shooting image, the pose parameter of the picture shooting assembly history；The sample pose parameter refer to
During the sample acquisition parameters shooting image, the environmental parameter of the picture shooting assembly history.
Second aspect, provides a kind of acquisition parameters setting device, and described device includes：
Parameter acquiring unit, for the environmental parameter for obtaining the pose parameter of picture shooting assembly He being presently in environment；
Parameter recommendation unit, for by the pose parameter and the environmental parameter input parameter recommended models, being pushed away
Recommend acquisition parameters；
Parameter set unit, for according to the recommendation acquisition parameters setting acquisition parameters；
Wherein, the parameter recommended models are true according to sample pose parameter, sample environment parameter and sample acquisition parameters
Fixed；The sample acquisition parameters refer to actual photographed parameter when history shoots image；The sample pose parameter refer to
During the sample acquisition parameters shooting image, the pose parameter of the picture shooting assembly history；The sample pose parameter refer to
During the sample acquisition parameters shooting image, the environmental parameter of the picture shooting assembly history.
The third aspect provides a kind of terminal, and the terminal includes processor, the memory being connected with the processor,
And the program instruction on the memory is stored in, the processor realizes that first aspect provides when performing described program instruction
Acquisition parameters setting method.
Fourth aspect, a kind of computer-readable medium are stored thereon with program instruction, and described program instruction is held by processor
The acquisition parameters setting method that first aspect provides is realized during row.
The advantageous effect that technical solution provided by the embodiments of the present application is brought includes：
By when shooting image, the attitude parameter of current shooting component and the environmental parameter of current environment being obtained, by this
Attitude parameter and environmental parameter input parameter recommended models；Since the parameter recommended models are to shoot image according to user's history
What rule determined, therefore, terminal can determine the recommendation for meeting the custom that user shoots image by the parameter recommended models
Acquisition parameters shoot custom since the recommendation acquisition parameters meet user, the probability adopted by user is higher, in this way, nothing
It needs user that acquisition parameters are voluntarily set, and can ensure the accuracy for the acquisition parameters that terminal is set automatically, terminal can be improved
The efficiency of acquisition parameters is set.
Description of the drawings
In order to illustrate more clearly of the technical solution in the embodiment of the present application, make required in being described below to embodiment
Attached drawing is briefly described, it should be apparent that, the accompanying drawings in the following description is only some embodiments of the present application, for
For those of ordinary skill in the art, without creative efforts, other are can also be obtained according to these attached drawings
Attached drawing.
Fig. 1 is the flow chart of acquisition parameters setting method that one exemplary embodiment of the application provides；
Fig. 2 is the schematic diagram of sample database that one exemplary embodiment of the application provides；
Fig. 3 is the schematic diagram that acquisition parameters are recommended in the acquisition that one exemplary embodiment of the application provides；
Fig. 4 is the schematic diagram that acquisition parameters are recommended in the acquisition that one exemplary embodiment of the application provides；
Fig. 5 is the schematic diagram of setting acquisition parameters that one exemplary embodiment of the application provides；
Fig. 6 is the block diagram of acquisition parameters setting device that the application one embodiment provides；
Fig. 7 is the block diagram for the terminal that the application one embodiment provides.
Specific embodiment
Purpose, technical scheme and advantage to make the application are clearer, below in conjunction with attached drawing to the application embodiment party
Formula is described in further detail.
First, to this application involves several nouns be introduced.
Parameter recommended models：It is a kind of recommendation for being used to determine picture shooting assembly according to the pose parameter and environmental parameter of input
The mathematical model of acquisition parameters.
Parameter recommended models are determined according to sample pose parameter, sample environment parameter and sample acquisition parameters.Wherein,
Sample acquisition parameters refer to actual photographed parameter when history shoots image；Sample pose parameter refers to clap with sample acquisition parameters
When taking the photograph image, the pose parameter of picture shooting assembly history；When sample pose parameter refers to shoot image with sample acquisition parameters, shooting
The environmental parameter of component history.
Wherein, sample pose parameter, sample environment parameter and sample acquisition parameters are stored in the sample database of terminal.Sample database
Including at least one set of sample, every group of sample includes collected sample pose parameter, sample environment parameter and sample shooting simultaneously
Parameter.
Optionally, pose parameter includes but not limited to：Vertical range and and reference object between rotation angle and ground
Between at least one of horizontal distance.
Rotation angle includes：The rotation of rotation angle and picture shooting assembly in the horizontal direction of picture shooting assembly in vertical direction
At least one of gyration.Optionally, rotation angle is collected by acceleration transducer；Alternatively, it is by adopting
The preview image collected carries out what image identified.Wherein, acceleration transducer can be arranged in picture shooting assembly；Alternatively,
The other positions mutually independent with picture shooting assembly of terminal are arranged on, the present embodiment is not construed as limiting this.
Optionally, the vertical range between ground is collected by acceleration transducer.Hanging down between ground
Straight distance refers to：Vertical range between acceleration transducer and ground.
Optionally, the horizontal distance between reference object is collected by range sensor.With reference object it
Between horizontal distance refer to：Horizontal distance between range sensor and reference object.
Optionally, environmental parameter includes but not limited to：Ambient light intensity, current time, current geographic position, reference object
Quantity, at least one of the scene characteristic of the characteristics of objects of reference object and photographed scene.
Ambient light intensity is collected by optical sensor；Geographical location is by global positioning system (Global
Positioning System, GPS) sensor is collected；The quantity of reference object, the characteristics of objects of reference object and shooting
The scene characteristic of scene identifies to obtain by carrying out image to preview image.
In the application, preview image refers to the image shown in the display screen of terminal before capturing the image.
It optionally, can also be by the pose parameter before by pose parameter and environmental parameter input parameter recommended models
And/or environmental parameter is converted into the data format of parameter recommended models support.
Such as：Current time is converted into the period belonging to the current time.Schematically, by 24 hours in one day
It was divided into one section every 10 minutes, then obtains 144 periods.At this point, when current time is converted i-th section, when i represents current
Between residing period be i-th of period, 1≤i≤144, i are integer.It is of course also possible to the time is divided otherwise
Section, the duration between the different periods may be the same or different, this implementation is not construed as limiting this.
For another example：Current geographic position is converted into the corresponding type in the geographical location.Schematically, 1 GT grand touring is represented
Type, 2 represent that the type of business, 3 represent residential building type etc..
For another example：The characteristics of objects of reference object is converted into feature vector.Schematically, feature vector includes n, and the
1 represent reference object whether be personage, the age of the 2nd expression personage, the 3rd expression personage gender etc..Wherein, n is
Positive integer.
For another example：The scene characteristic of photographed scene is converted into feature vector.Schematically, feature vector includes m, and the
1 represents whether photographed scene includes trees, whether the 2nd expression photographed scene includes lake, the 3rd expression photographed scene is
It is no including wall etc..Wherein, m is positive integer.
It is of course also possible to be converted otherwise to pose parameter and/or environmental parameter, the application does not make this
It limits.
Optionally, the form of the pose parameter of input parameter recommended models and environmental parameter is vector.
Optionally, parameter recommended models include but not limited to：K- means clustering algorithms, logistic regression (Logistic
Regression, LR) at least one of model and Bayes (Bayesian) model.
K- means clustering algorithms are a kind of algorithms that the data in some aspects with similitude are carried out to tissue typing.K
The process of means clustering algorithm includes：K object is randomly selected as initial cluster centre；Each object is calculated with each to gather
The cluster centre nearest apart from it is distributed to the object at the distance between class center, wherein, cluster centre and distribute to it
Object just represent a cluster.After all objects are all assigned, the cluster centre each clustered can be according in cluster
Existing object is recalculated, until not having (or less than or equal to i) object to be reassigned to different clusters；With/
Or, stop when there is no (or less than or equal to j) cluster centre to change again.Wherein, i and j is positive integer.Certainly, K-
The condition of the stopping cycle of means clustering algorithm may be other conditions, and the application is not construed as limiting this.
In the application, K- means clustering algorithms are used for sample pose parameter, sample environment parameter and sample acquisition parameters
Classify.
Logic Regression Models refer on the basis of linear regression, apply mechanically the model that a logical function is established.Optionally,
In the application, Logic Regression Models are used to classify to sample pose parameter, sample environment parameter and sample acquisition parameters.
Schematically, Logic Regression Models are represented by following mathematical model：
Wherein, x1、x2……xnIt is different types of status data；σ (z)=1/ (e-z)；θ1、θ2……θ2nIt is that logic is returned
Return the model parameter of model, θ0、θ1、θ2……θ2nCan be that developer is set or or according to sample pose
What parameter, sample environment parameter and sample acquisition parameters were trained.
Bayesian model is a kind of time series parameters recommended models using dynamic model as research object.Optionally, originally
In application, Bayesian model is used to predict the probability that group's message is paid close attention to by user.
Schematically, Bayesian model is represented by following mathematical model：
Wherein, A, B ... X are sample parameters, the sample parameter include the collected sample pose parameter of synchronization and
Sample environment.N (A) is that sample database includes the sum of sample parameter A, N (B) is that sample database includes the total of sample parameter B
Number ... N (X) is the sum that sample database includes sample parameter X.N is the group number of sample in sample database, and every group of sample includes same
When collected sample pose parameter, sample environment parameter and sample acquisition parameters.N (A, J) joins for sample in same group of sample
Total group number, the N (B, J) that number is A and sample acquisition parameters are J are that same group of sample parameter is B and sample acquisition parameters are the total of J
Group number ... N (X, J) is total group number that sample parameter is X in same group of sample and sample acquisition parameters are J.N (J) is sample database
Middle sample acquisition parameters are the number of J.
Certainly, parameter recommended models can also be other models, such as：Deep neural network (Deep Neural
Network, DNN) model, Recognition with Recurrent Neural Network (Recurrent Neural Networks, RNN) model, insertion
(embedding) model, gradient promote decision tree (Gradient Boosting Decision Tree, GBDT) model etc., this
Embodiment will not enumerate herein.
DNN models are a kind of deep learning frames.DNN models include input layer, at least one layer of hidden layer (or middle layer)
And output layer.Optionally, input layer, at least one layer of hidden layer (or middle layer) and output layer include at least one neuron,
Neuron is used to handle the data received.Optionally, the quantity of the neuron between different layers can be identical；Or
Person can also be different.
RNN models are a kind of neural networks with feedback arrangement.In RNN models, the output of neuron can be under
One timestamp is applied directly to itself, that is, input of the i-th layer of neuron at the m moment, in addition to (i-1) layer neuron this when
Outside the output at quarter, its own output at (m-1) moment is further included.
Embedding models are shown based on entity and relationship distribution vector table, by the relationship in each triple example
Regard the translation from entity head to entity tail as.Wherein, triple example includes main body, relationship, object, and triple example can be with table
It is shown as (main body, relationship, object)；Main body is entity head, and object is entity tail.Such as：The father of Xiao Ming is big bright, then passes through three
Tuple example is expressed as (Xiao Ming, father are big bright).
GBDT models are a kind of decision Tree algorithms of iteration, which is made of more decision trees, and the result of all trees is tired out
It adds up as final result.Each node of decision tree can obtain a predicted value, and by taking the age as an example, predicted value is belongs to
The average value at owner's age of age corresponding node.
Optionally, the executive agent of each step is terminal in the application；Picture shooting assembly is installed, alternatively, terminal in terminal
It is connected with the equipment for being equipped with picture shooting assembly by wired or wireless mode.Schematically, picture shooting assembly is camera.Terminal
Including but not limited to：Mobile phone, wearable device, camera, video camera, tablet computer, intelligent robot, smart home are set
At least one of standby, pocket computer on knee and desktop computer.In actual implementation, each step can be in the application
It is performed by the operating system in terminal；Alternatively, by the client executing of control picture shooting assembly, the application is not construed as limiting this.
Fig. 1 is the flow chart of the acquisition parameters setting method shown in the exemplary embodiment of the application.The shooting is joined
Number setting method includes following steps.
Step 101, it obtains the pose parameter of picture shooting assembly and is presently in the environmental parameter of environment.
Pose parameter includes but not limited to：Vertical range between rotation angle and ground and between reference object
At least one of horizontal distance.
Environmental parameter includes but not limited to：Ambient light intensity, current time, current geographic position, reference object quantity,
At least one of the characteristics of objects of reference object and the scene characteristic of photographed scene.
In one example, terminal obtains the pose parameter of picture shooting assembly and is presently in the environmental parameter of environment, including：
To picture shooting assembly, collected preview image is identified, and obtains reference object；When reference object is default reference object, obtain
Take pose parameter and environmental parameter.
Optionally, terminal is identified preview image by image recognition algorithm, obtains shooting image.Optionally, in advance
Image of looking at is collected frame image when picture shooting assembly maintains a certain pose constant.
Optionally, the reference object that shooting number is most in the image that reference object takes for history is preset.
In another example, when the operation duration of picture shooting assembly reaches preset duration, pose parameter and environment are obtained
Parameter.
Optionally, preset duration is default setting in terminal；Alternatively, preset duration is received by human-computer interaction interface
It arrives.Preset duration can be 1 second, 3 seconds, 5 seconds etc., and the present embodiment is not construed as limiting the numerical value of preset duration.
Optionally, after the operation duration of picture shooting assembly refers to that terminal calls picture shooting assembly, during the operation of the picture shooting assembly
It is long.
Step 102, it by pose parameter and environmental parameter input parameter recommended models, obtains recommending acquisition parameters.
Wherein, parameter recommended models are determined according to sample pose parameter, sample environment parameter and sample acquisition parameters；
Sample acquisition parameters refer to actual photographed parameter when history shoots image；Sample pose parameter refers to clap with sample acquisition parameters
When taking the photograph image, the pose parameter of picture shooting assembly history；When sample pose parameter refers to shoot image with sample acquisition parameters, shooting
The environmental parameter of component history.
Schematically, with reference to sample database shown in Fig. 2, in the sample database, belong to the sample pose parameter, sample of same a line
Environmental parameter and sample acquisition parameters are one group of sample.
Optionally, picture shooting assembly includes the picture shooting assembly for being set to terminal front end and the shooting group for being set to terminal rear end
Part；Alternatively, terminal includes one group of picture shooting assembly, this group of picture shooting assembly can both be arranged on terminal front end, can also be arranged on end
Hold rear end.At this point, parameter recommended models include the first parameter recommended models and the second parameter recommended models, when picture shooting assembly is set
When terminal front end, pose parameter and environmental parameter are inputted into the first parameter recommended models；After picture shooting assembly is set to terminal
During end, pose parameter and environmental parameter are inputted into the second parameter recommended models.
Wherein, the first parameter recommended models be use be set to terminal front end picture shooting assembly shoot image when, according to
What collected sample pose parameter, sample environment parameter and sample acquisition parameters determined；Second parameter recommended models are to make
Be set to terminal rear end picture shooting assembly shoot image when, according to collected sample pose parameter, sample environment parameter and
Sample acquisition parameters determine.
Certainly, picture shooting assembly is arranged on the front end of terminal still in rear end, and terminal can also be by collected pose
Parameter and environmental parameter input unified parameter recommended models, and the present embodiment is not construed as limiting this.
With reference to figure 3, by taking parameter recommended models are Logic Regression Models as an example, if pose parameter includes representing rotation angle
Parameter x1；Environmental parameter includes representing the parameter x of ambient light intensity2, represent photographed scene scene characteristic parameter x3And expression
The parameter x of the characteristics of objects of reference object4；Then by x1、x2、x3And x4Input logic regression model, at Logic Regression Models
After reason, obtain recommending acquisition parameters.
Optionally, the recommendation acquisition parameters of each Logic Regression Models output are one group of parameter.
Optionally, parameter recommended models can include multiple Logic Regression Models, and the output result of parameter recommended models is
The average value of the recommendation acquisition parameters of multiple Logic Regression Models outputs.
With reference to figure 4, by taking parameter recommended models are Bayesian model as an example, if pose parameter includes the ginseng for representing rotation angle
Number x1；Environmental parameter includes representing the parameter x of ambient light intensity2, represent photographed scene scene characteristic parameter x3It is clapped with expression
Take the photograph the parameter x of the characteristics of objects of object4；Then by x1、x2、x3And x4Bayesian model is inputted, after Bayesian model is handled, is obtained
Recommend acquisition parameters.
Optionally, each Bayesian model can obtain the probability that acquisition parameters is each recommended to be set in sample database, shellfish
The recommendation acquisition parameters that this model of leaf obtains can be the recommendation acquisition parameters of maximum probability.
Schematically, acquisition parameters is recommended to include：It is filter, special efficacy photo frame, special efficacy paster, Lens, aperture size, fast
At least one of door, exposure compensating, sensitivity and white balance.
Wherein, filter is used to filter the tone of natural light adjustment image.Special efficacy photo frame refers to be attached on image border
Figure layer.Special efficacy paster refers to be attached to the figure layer on a certain position of reference object, such as：Reference object is personage, special efficacy
Paster can be the figure layer that the shape on position is hair fastener overhead.Lens refer to camera lens for acquiring the model of image
It encloses.Aperture is used to control the thang-kng amount of camera lens.Shutter is used to control the effective exposure time of sensitive film.Exposure compensating is used to improve
Brightness of image.Sensitivity is used to adjust sensitivity level of the egative film to light.White balance is used to adjust three base of red, green, blue in display
White accuracy after mixture of colours generation.
Step 103, according to recommendation acquisition parameters setting acquisition parameters.
Optionally, terminal will recommend acquisition parameters to be directly disposed as acquisition parameters；Alternatively, terminal exports inquiry message, it should
Inquiry message, which is used to determine whether to use, recommends acquisition parameters as acquisition parameters；It is receiving according to inquiry message input really
When recognizing operation, acquisition parameters will be recommended to be set as acquisition parameters.
The type for recommending acquisition parameters is identical with the type for the acquisition parameters that terminal actually uses, schematically, shooting ginseng
Number includes：Filter, special efficacy photo frame, special efficacy paster, Lens, aperture size, shutter, exposure compensating, sensitivity and white balance
At least one of.
With reference to figure 5, terminal is obtained after recommending acquisition parameters, exports inquiry message 501, confirmation control is acted on receiving
During confirmation operation on 502, terminal will recommend acquisition parameters to be set as acquisition parameters.Optionally, if terminal is received according to inquiry
Ask the cancellation operation of information input, such as：The cancellation operation cancelled on control 503 is acted on, terminal is joined using the shooting of acquiescence
Number, alternatively, the acquisition parameters used when shooting image using the last time.
In conclusion acquisition parameters setting method provided in this embodiment, by when shooting image, obtaining current shooting
The attitude parameter of component and the environmental parameter of current environment, by the attitude parameter and environmental parameter input parameter recommended models；By
It is to determine that therefore, terminal can be pushed away by the parameter according to the rule of user's history shooting image in the parameter recommended models
It recommends model and determines the recommendation acquisition parameters for meeting the custom that user shoots image, clapped since the recommendation acquisition parameters meet user
Custom is taken the photograph, therefore, the probability adopted by user is higher, in this way, voluntarily setting acquisition parameters without user, and can ensure terminal
Automatically the accuracy of the acquisition parameters set can improve the efficiency of terminal setting acquisition parameters.
In addition, by when reference object is default reference object, pose parameter and environmental parameter are obtained；It is clapped due to default
It is to shoot the more reference object of number to take the photograph image, and the acquisition parameters and the default reference object for illustrating the setting of terminal history have
It closes, at this point, when reference object is default reference object, just obtains pose parameter and environmental parameter, carry out pushing away for acquisition parameters
It recommends, the accuracy that terminal recommends acquisition parameters can be improved.
In addition, due to picture shooting assembly sometimes be in the case that accidentally touch it is called, at this point, the operation duration of picture shooting assembly is led to
Often shorter, therefore, the present embodiment is by when the operation duration of picture shooting assembly reaches preset duration, then obtains pose parameter and ring
Border parameter, when avoiding picture shooting assembly by accidentally tactile calling, terminal still carries out acquisition parameters recommendation, wastes asking for terminal resource
Topic can save the resource of terminal.
In addition, the acquisition parameters that the picture shooting assembly due to terminal front end uses when shooting image may be with the bat of terminal rear end
It is different to take the photograph the acquisition parameters used during component shooting image, therefore, the present embodiment is shot by the picture shooting assembly in terminal front end
During image, attitude parameter and environmental parameter are inputted into the first parameter recommended models；Picture shooting assembly in terminal rear end shoots image
When, attitude parameter and environmental parameter are inputted into the second parameter recommended models so that terminal is established for the picture shooting assembly of different location
Different parameter recommended models can improve the accuracy that terminal recommends acquisition parameters.
Optionally, in the application, terminal can be updated parameter recommended models.At this point, it after step 203, obtains
Actual photographed parameter when taking with pose parameter and environmental parameter shooting image；Using pose parameter as sample pose parameter, incite somebody to action
Environmental parameter carries out parameter recommended models as sample environment parameter and using actual photographed parameter as sample acquisition parameters
Update, obtains updated parameter recommended models, and parameter recommended models are used to determine to recommend when carrying out image taking next time
Acquisition parameters.
Wherein, actual photographed parameter can recommend acquisition parameters；Or or on the basis for recommending acquisition parameters
It is upper to adjust obtained acquisition parameters.
Wherein, terminal according to sample pose parameter, sample environment parameter and sample acquisition parameters to parameter recommended models into
Row update, including following steps：
1st, by least one set of sample pose parameter, sample environment parameter input parameter recommended models, training result is obtained.
2nd, it determines to damage according to training result and the corresponding sample acquisition parameters of every group of sample pose parameter, sample environment parameter
Lose functional value.
Schematically, loss function is represented by following data models：
Cost(hθ(x(i)),y(i))=- y(i)loghθ(x(i))-(1-y(i))log(1-hθ(x(i))
Wherein, N is the group number of sample in sample database, and i is i-th group of sample.hθ(x)(i)It is parameter recommended models according to i-th
The training result that group sample pose parameter, sample environment parameter obtain, y(i)For i-th group of sample pose parameter, sample environment parameter
Corresponding i-th group of sample acquisition parameters.
3rd, the model parameter by gradient descent algorithm in loss function value undated parameter recommended models, is updated
Model parameter afterwards.
Schematically, gradient descent algorithm is represented by following mathematical models：
Wherein, J (θ) be loss function value, θjFor the weight of jth kind sample parameter, xj iFor in i-th group of sample parameter
J kind sample parameters.
Schematically, the process of the model parameter in the mathematical model undated parameter recommended models of gradient descent algorithm
It is represented by following formula：
Wherein, α is Learning Step, and α is constant, and the value of α can be terminal default setting；Or or user set
It puts.The present embodiment is not construed as limiting the value of α, schematically, α 0.5.
Optionally, { θ0、θ1、θ2……θ2nInitial value can be terminal default setting.
4th, detect whether the difference between the model parameter before updated model parameter and update is less than predetermined threshold value；
When the difference is less than predetermined threshold value, training terminates, the parameter recommended models after being trained；It is greater than or equal in the difference default
During threshold value, continue the training parameter recommended models since step 1.
In the present embodiment, by being carried out according to attitude parameter, environmental parameter and actual photographed parameter to parameter recommended models
Training；So that the parameter recommended models can adapt to the custom that user shoots image, it can improve and be pushed away by parameter recommended models
Recommend the accuracy of acquisition parameters.
Following is the application device embodiment, can be used for performing the application embodiment of the method.For the application device reality
The details not disclosed in example is applied, please refers to the application embodiment of the method.
Fig. 6 is please referred to, the acquisition parameters it illustrates the offer of the application one embodiment set the block diagram of device,
Acquisition parameters setting device can pass through the part for being implemented in combination with becoming acquisition parameters and setting equipment of software, hardware or both
Or all.The device can include：Parameter acquiring unit 610, parameter recommendation unit 620 and parameter set unit 630.
Parameter acquiring unit 610, for the environmental parameter for obtaining the pose parameter of picture shooting assembly He being presently in environment；
Parameter recommendation unit 620, for by the pose parameter and the environmental parameter input parameter recommended models, obtaining
Recommend acquisition parameters；
Parameter set unit 630, for according to the recommendation acquisition parameters setting acquisition parameters；
Wherein, the parameter recommended models are true according to sample pose parameter, sample environment parameter and sample acquisition parameters
Fixed；The sample acquisition parameters refer to actual photographed parameter when history shoots image；The sample pose parameter refer to
During the sample acquisition parameters shooting image, the pose parameter of the picture shooting assembly history；The sample pose parameter refer to
During the sample acquisition parameters shooting image, the environmental parameter of the picture shooting assembly history.
The pose parameter includes：Vertical range between rotation angle and ground and the level between reference object
At least one of distance；
The environmental parameter includes：Ambient light intensity, current time, current geographic position, the reference object quantity,
At least one of the characteristics of objects of the reference object and the scene characteristic of photographed scene.
Optionally, the parameter acquiring unit 610, is used for：
The collected preview image of the picture shooting assembly is identified, obtains reference object；
When the reference object is default reference object, the pose parameter and the environmental parameter are obtained.
Optionally, the parameter acquiring unit 610, is used for：
When the operation duration of the picture shooting assembly reaches preset duration, the pose parameter and environment ginseng are obtained
Number.
Optionally, the parameter recommended models include the first parameter recommended models and the second parameter recommended models, the ginseng
Number recommendation unit 620, is used for：
When the picture shooting assembly is set to terminal front end, by the pose parameter and environmental parameter input described the
One parameter recommended models, the first parameter recommended models are to use the picture shooting assembly shooting figure that is set to the terminal front end
During picture, determined according to collected sample pose parameter, sample environment parameter and sample acquisition parameters；
When the picture shooting assembly is set to terminal rear end, by the pose parameter and environmental parameter input described the
Two parameter recommended models, the second parameter recommended models are to use the picture shooting assembly shooting figure that is set to the terminal rear end
During picture, determined according to collected sample pose parameter, sample environment parameter and sample acquisition parameters.
Optionally, the acquisition parameters include：It is filter, special efficacy photo frame, special efficacy paster, Lens, aperture size, fast
At least one of door, exposure compensating, sensitivity and white balance.
Optionally, described device further includes：
Acquiring unit, actual photographed when shooting image for obtaining with the pose parameter and the environmental parameter are joined
Number；
Updating unit, for using the pose parameter as the sample pose parameter, using the environmental parameter as institute
State sample environment parameter and using the actual photographed parameter as the sample acquisition parameters, to the parameter recommended models into
Row update, obtains updated parameter recommended models, and the parameter recommended models are used for true when carrying out image taking next time
Surely recommend acquisition parameters.
Correlative detail refers to above method embodiment.
The application also provides a kind of computer-readable medium, is stored thereon with program instruction, and program instruction is held by processor
The acquisition parameters setting method that above-mentioned each embodiment of the method provides is realized during row.
Present invention also provides it is a kind of comprising instruction computer program product, when run on a computer so that
Computer performs the acquisition parameters setting method that above-mentioned each embodiment of the method provides.
With reference to figure 7, it illustrates the block diagrams of terminal that one exemplary embodiment of the application provides.In the application
Terminal can include it is one or more such as lower components：Processor 710 and memory 720.
Processor 710 can include one or more processing core.Processor 710 utilizes various interfaces and connection
Various pieces in entire terminal, by running or performing the instruction being stored in memory 720, program, code set or instruction
Collection and calling are stored in the data in memory 720, perform the various functions of terminal and processing data.Optionally, processor
710 may be used Digital Signal Processing (Digital Signal Processing, DSP), field programmable gate array
(Field-Programmable Gate Array, FPGA), programmable logic array (Programmable Logic
Array, PLA) at least one of example, in hardware realize.Processor 710 can integrating central processor (Central
Processing Unit, CPU) and one or more of modem etc. combination.Wherein, the main processing operation systems of CPU
System and application program etc.；Modem wirelessly communicates for handling.It is understood that above-mentioned modem can not also
It is integrated into processor 710, is realized separately through chip piece.
Optionally, above-mentioned each embodiment of the method carries under being realized when processor 710 performs the program instruction in memory 720
The acquisition parameters setting method of confession.
Memory 720 can include random access memory (Random Access Memory, RAM), can also include read-only
Memory (Read-Only Memory).Optionally, which includes non-transient computer-readable medium (non-
transitory computer-readable storage medium).Memory 720 can be used for store instruction, program, generation
Code, code set or instruction set.Memory 720 may include storing program area and storage data field, wherein, storing program area can store
Be used to implement operating system instruction, at least one function instruction, be used to implement the finger of above-mentioned each embodiment of the method
Enable etc.；Storage data field can be stored uses created data etc. according to terminal.
The structure of above-mentioned terminal is only illustrative, and in actual implementation, terminal can include more or fewer components,
Such as：Picture shooting assembly etc., the present embodiment is not construed as limiting this.
One of ordinary skill in the art will appreciate that hardware can be passed through by realizing all or part of step of above-described embodiment
It completes, relevant hardware can also be instructed to complete by program, the program can be stored in a kind of computer-readable
In storage medium, storage medium mentioned above can be read-only memory, disk or CD etc..
The foregoing is merely the preferred embodiment of the application, not to limit the application, it is all in spirit herein and
Within principle, any modification, equivalent replacement, improvement and so on should be included within the protection domain of the application.
Claims (10)
1. a kind of acquisition parameters setting method, which is characterized in that the method includes：
It obtains the pose parameter of picture shooting assembly and is presently in the environmental parameter of environment；
By the pose parameter and the environmental parameter input parameter recommended models, obtain recommending acquisition parameters；
According to the recommendation acquisition parameters setting acquisition parameters；
Wherein, the parameter recommended models are determined according to sample pose parameter, sample environment parameter and sample acquisition parameters；
The sample acquisition parameters refer to actual photographed parameter when history shoots image；The sample pose parameter refers to the sample
When this acquisition parameters shoots image, the pose parameter of the picture shooting assembly history；The sample pose parameter refers to the sample
When this acquisition parameters shoots image, the environmental parameter of the picture shooting assembly history.
2. according to the method described in claim 1, it is characterized in that,
The pose parameter includes：Vertical range between rotation angle and ground and the horizontal distance between reference object
At least one of；
The environmental parameter includes：Ambient light intensity, current time, current geographic position, the reference object quantity, described
At least one of the characteristics of objects of reference object and the scene characteristic of photographed scene.
3. according to the method described in claim 1, it is characterized in that, it is described obtain picture shooting assembly pose parameter and be presently in
The environmental parameter of environment, including：
The collected preview image of the picture shooting assembly is identified, obtains reference object；
When the reference object is default reference object, the pose parameter and the environmental parameter are obtained.
4. according to the method described in claim 1, it is characterized in that, it is described obtain picture shooting assembly pose parameter and be presently in
The environmental parameter of environment, including：
When the operation duration of the picture shooting assembly reaches preset duration, the pose parameter and the environmental parameter are obtained.
5. according to the method described in claim 1, it is characterized in that, the parameter recommended models include the first parameter recommended models
It is described by the pose parameter and the environmental parameter input parameter recommended models with the second parameter recommended models, recommended
Acquisition parameters, including：
When the picture shooting assembly is set to terminal front end, by the pose parameter and environmental parameter input first ginseng
Number recommended models, the first parameter recommended models are that the picture shooting assembly for being set to the terminal front end is being used to shoot image
When, it is determined according to collected sample pose parameter, sample environment parameter and sample acquisition parameters；
When the picture shooting assembly is set to terminal rear end, by the pose parameter and environmental parameter input second ginseng
Number recommended models, the second parameter recommended models are that the picture shooting assembly for being set to the terminal rear end is being used to shoot image
When, it is determined according to collected sample pose parameter, sample environment parameter and sample acquisition parameters.
6. according to the method described in claim 1, it is characterized in that, the acquisition parameters include：Filter, special efficacy photo frame, special efficacy
At least one of paster, Lens, aperture size, shutter, exposure compensating, sensitivity and white balance.
7. method according to any one of claims 1 to 6, which is characterized in that described according to the recommendation acquisition parameters setting
After acquisition parameters, further include：
Actual photographed parameter when obtaining with the pose parameter and environmental parameter shooting image；
Using the pose parameter as the sample pose parameter, using the environmental parameter as the sample environment parameter, simultaneously
Using the actual photographed parameter as the sample acquisition parameters, the parameter recommended models are updated, after obtaining update
Parameter recommended models, the parameter recommended models be used for next time carry out image taking when determine recommend acquisition parameters.
8. a kind of acquisition parameters set device, which is characterized in that described device includes：
Parameter acquiring unit, for the environmental parameter for obtaining the pose parameter of picture shooting assembly He being presently in environment；
Parameter recommendation unit, for by the pose parameter and the environmental parameter input parameter recommended models, obtaining recommending clapping
Take the photograph parameter；
Parameter set unit, for according to the recommendation acquisition parameters setting acquisition parameters；
Wherein, the parameter recommended models are determined according to sample pose parameter, sample environment parameter and sample acquisition parameters；
The sample acquisition parameters refer to actual photographed parameter when history shoots image；The sample pose parameter refers to the sample
When this acquisition parameters shoots image, the pose parameter of the picture shooting assembly history；The sample pose parameter refers to the sample
When this acquisition parameters shoots image, the environmental parameter of the picture shooting assembly history.
9. a kind of terminal, which is characterized in that the memory that the terminal includes processor, is connected with the processor, Yi Jicun
The program instruction on the memory is stored up, the processor is realized when performing described program instruction as claim 1 to 7 is any
The acquisition parameters setting method.
10. a kind of computer readable storage medium, which is characterized in that be stored thereon with program instruction, described program instruction is located
Manage the acquisition parameters setting method realized when device performs as described in claim 1 to 7 is any.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711470123.1A CN108174096A (en) | 2017-12-29 | 2017-12-29 | Method, apparatus, terminal and the storage medium of acquisition parameters setting |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711470123.1A CN108174096A (en) | 2017-12-29 | 2017-12-29 | Method, apparatus, terminal and the storage medium of acquisition parameters setting |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108174096A true CN108174096A (en) | 2018-06-15 |
Family
ID=62519869
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711470123.1A Pending CN108174096A (en) | 2017-12-29 | 2017-12-29 | Method, apparatus, terminal and the storage medium of acquisition parameters setting |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108174096A (en) |
Cited By (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109033276A (en) * | 2018-07-10 | 2018-12-18 | Oppo广东移动通信有限公司 | Sticker pushing method and device, storage medium and electronic equipment |
| CN109191229A (en) * | 2018-07-16 | 2019-01-11 | 三星电子（中国）研发中心 | Augmented reality ornament recommended method and device |
| CN109246364A (en) * | 2018-10-26 | 2019-01-18 | 华为技术有限公司 | Photographic device method of adjustment and relevant device |
| CN110278370A (en) * | 2019-06-21 | 2019-09-24 | 上海摩象网络科技有限公司 | Automatically generate method, apparatus, the electronic equipment of shooting controlling mechanism |
| CN110572582A (en) * | 2019-10-17 | 2019-12-13 | 北京小米智能科技有限公司 | Shooting parameter determining method and device and shooting data processing method and device |
| CN110741626A (en) * | 2018-10-31 | 2020-01-31 | 深圳市大疆创新科技有限公司 | Shooting control method, movable platform, control device and storage medium |
| CN111800569A (en) * | 2019-04-09 | 2020-10-20 | Oppo广东移动通信有限公司 | Photographing processing method and device, storage medium and electronic equipment |
| CN111801932A (en) * | 2018-08-31 | 2020-10-20 | 华为技术有限公司 | Image shooting method and device |
| CN111901475A (en) * | 2019-05-06 | 2020-11-06 | 苹果公司 | User interface for capturing and managing visual media |
| CN112154650A (en) * | 2019-08-13 | 2020-12-29 | 深圳市大疆创新科技有限公司 | Focusing control method and device for shooting device and unmanned aerial vehicle |
| CN112468729A (en) * | 2020-11-27 | 2021-03-09 | 广州富港生活智能科技有限公司 | Automatic photographing apparatus and control method thereof |
| CN112817563A (en) * | 2020-03-26 | 2021-05-18 | 腾讯科技（深圳）有限公司 | Target attribute configuration information determination method, computer device, and storage medium |
| US12101567B2 (en) | 2021-04-30 | 2024-09-24 | Apple Inc. | User interfaces for altering visual media |
| US12132981B2 (en) | 2016-06-12 | 2024-10-29 | Apple Inc. | User interface for camera effects |
| US12149831B2 (en) | 2015-04-23 | 2024-11-19 | Apple Inc. | Digital viewfinder user interface for multiple cameras |
| US12154218B2 (en) | 2018-09-11 | 2024-11-26 | Apple Inc. | User interfaces simulated depth effects |
| US12155925B2 (en) | 2020-09-25 | 2024-11-26 | Apple Inc. | User interfaces for media capture and management |
| US12170834B2 (en) | 2018-05-07 | 2024-12-17 | Apple Inc. | Creative camera |
| US12192617B2 (en) | 2019-05-06 | 2025-01-07 | Apple Inc. | User interfaces for capturing and managing visual media |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100045848A1 (en) * | 2008-08-22 | 2010-02-25 | Sanyo Electric Co., Ltd. | Electronic camera |
| CN102752506A (en) * | 2011-04-20 | 2012-10-24 | 宏达国际电子股份有限公司 | Handheld electronic device and automatic focusing method of photographic equipment in handheld electronic device |
| CN104679876A (en) * | 2015-03-11 | 2015-06-03 | 百度在线网络技术（北京）有限公司 | Photo shooting strategy recommendation device and method |
| CN106357983A (en) * | 2016-11-15 | 2017-01-25 | 上海传英信息技术有限公司 | Photographing parameter adjustment method and user terminal |
| CN107454331A (en) * | 2017-08-28 | 2017-12-08 | 维沃移动通信有限公司 | The switching method and mobile terminal of a kind of screening-mode |
-
2017
- 2017-12-29 CN CN201711470123.1A patent/CN108174096A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100045848A1 (en) * | 2008-08-22 | 2010-02-25 | Sanyo Electric Co., Ltd. | Electronic camera |
| CN102752506A (en) * | 2011-04-20 | 2012-10-24 | 宏达国际电子股份有限公司 | Handheld electronic device and automatic focusing method of photographic equipment in handheld electronic device |
| CN104679876A (en) * | 2015-03-11 | 2015-06-03 | 百度在线网络技术（北京）有限公司 | Photo shooting strategy recommendation device and method |
| CN106357983A (en) * | 2016-11-15 | 2017-01-25 | 上海传英信息技术有限公司 | Photographing parameter adjustment method and user terminal |
| CN107454331A (en) * | 2017-08-28 | 2017-12-08 | 维沃移动通信有限公司 | The switching method and mobile terminal of a kind of screening-mode |
Cited By (26)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US12149831B2 (en) | 2015-04-23 | 2024-11-19 | Apple Inc. | Digital viewfinder user interface for multiple cameras |
| US12132981B2 (en) | 2016-06-12 | 2024-10-29 | Apple Inc. | User interface for camera effects |
| US12170834B2 (en) | 2018-05-07 | 2024-12-17 | Apple Inc. | Creative camera |
| CN109033276A (en) * | 2018-07-10 | 2018-12-18 | Oppo广东移动通信有限公司 | Sticker pushing method and device, storage medium and electronic equipment |
| CN109191229A (en) * | 2018-07-16 | 2019-01-11 | 三星电子（中国）研发中心 | Augmented reality ornament recommended method and device |
| CN111801932A (en) * | 2018-08-31 | 2020-10-20 | 华为技术有限公司 | Image shooting method and device |
| US12154218B2 (en) | 2018-09-11 | 2024-11-26 | Apple Inc. | User interfaces simulated depth effects |
| CN109246364A (en) * | 2018-10-26 | 2019-01-18 | 华为技术有限公司 | Photographic device method of adjustment and relevant device |
| CN109246364B (en) * | 2018-10-26 | 2021-10-01 | 华为技术有限公司 | Camera device adjustment method and related equipment |
| US12177556B2 (en) | 2018-10-31 | 2024-12-24 | SZ DJI Technology Co., Ltd. | Photographing control method, mobile platform, control device, and storage medium |
| CN110741626A (en) * | 2018-10-31 | 2020-01-31 | 深圳市大疆创新科技有限公司 | Shooting control method, movable platform, control device and storage medium |
| CN110741626B (en) * | 2018-10-31 | 2022-05-27 | 深圳市大疆创新科技有限公司 | Shooting control method, movable platform, control device and storage medium |
| CN114827474A (en) * | 2018-10-31 | 2022-07-29 | 深圳市大疆创新科技有限公司 | Shooting control method, movable platform, control device and storage medium |
| CN111800569A (en) * | 2019-04-09 | 2020-10-20 | Oppo广东移动通信有限公司 | Photographing processing method and device, storage medium and electronic equipment |
| CN111800569B (en) * | 2019-04-09 | 2022-02-22 | Oppo广东移动通信有限公司 | Photographing processing method and device, storage medium and electronic equipment |
| CN111901475A (en) * | 2019-05-06 | 2020-11-06 | 苹果公司 | User interface for capturing and managing visual media |
| US12192617B2 (en) | 2019-05-06 | 2025-01-07 | Apple Inc. | User interfaces for capturing and managing visual media |
| CN110278370A (en) * | 2019-06-21 | 2019-09-24 | 上海摩象网络科技有限公司 | Automatically generate method, apparatus, the electronic equipment of shooting controlling mechanism |
| CN112154650A (en) * | 2019-08-13 | 2020-12-29 | 深圳市大疆创新科技有限公司 | Focusing control method and device for shooting device and unmanned aerial vehicle |
| CN110572582B (en) * | 2019-10-17 | 2022-04-08 | 北京小米智能科技有限公司 | Shooting parameter determining method and device and shooting data processing method and device |
| CN110572582A (en) * | 2019-10-17 | 2019-12-13 | 北京小米智能科技有限公司 | Shooting parameter determining method and device and shooting data processing method and device |
| CN112817563A (en) * | 2020-03-26 | 2021-05-18 | 腾讯科技（深圳）有限公司 | Target attribute configuration information determination method, computer device, and storage medium |
| CN112817563B (en) * | 2020-03-26 | 2023-09-29 | 腾讯科技（深圳）有限公司 | Target attribute configuration information determining method, computer device, and storage medium |
| US12155925B2 (en) | 2020-09-25 | 2024-11-26 | Apple Inc. | User interfaces for media capture and management |
| CN112468729A (en) * | 2020-11-27 | 2021-03-09 | 广州富港生活智能科技有限公司 | Automatic photographing apparatus and control method thereof |
| US12101567B2 (en) | 2021-04-30 | 2024-09-24 | Apple Inc. | User interfaces for altering visual media |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108174096A (en) | Method, apparatus, terminal and the storage medium of acquisition parameters setting | |
| WO2021169723A1 (en) | Image recognition method and apparatus, electronic device, and storage medium | |
| US11158090B2 (en) | Enhanced video shot matching using generative adversarial networks | |
| CN107995428B (en) | Image processing method, image processing device, storage medium and mobile terminal | |
| CN108780389A (en) | Image retrieval for computing device | |
| WO2019120016A1 (en) | Image processing method and apparatus, storage medium, and electronic device | |
| CN108664651B (en) | Pattern recommendation method, device and storage medium | |
| CN112580400B (en) | Image optimization method and electronic device | |
| CN108513060A (en) | Use the electronic equipment of the image pickup method and support this method of external electronic device | |
| CN115049057B (en) | Model deployment method and device, electronic equipment and storage medium | |
| CN108198130B (en) | Image processing method, image processing device, storage medium and electronic equipment | |
| CN109101931A (en) | Scene recognition method, scene recognition device and terminal equipment | |
| CN109086742A (en) | scene recognition method, scene recognition device and mobile terminal | |
| CN110390705A (en) | A method and device for generating virtual images | |
| CN106815803B (en) | Picture processing method and device | |
| CN112036492B (en) | Sample set processing method, device, equipment and storage medium | |
| JP2020507159A (en) | Picture push method, mobile terminal and storage medium | |
| US20240169687A1 (en) | Model training method, scene recognition method, and related device | |
| CN111798811B (en) | Method, device, storage medium and electronic device for adjusting screen backlight brightness | |
| CN108198162A (en) | Photo processing method, mobile terminal, server, system, storage medium | |
| CN110309339A (en) | Picture tag generation method and device, terminal and storage medium | |
| CN112052759A (en) | Living body detection method and device | |
| CN107832848B (en) | Application management method and device, storage medium and electronic equipment | |
| WO2022115840A1 (en) | Transfer learning for sound event classification | |
| CN115546010B (en) | Image processing method and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180615 |