CN107610042A - A kind of image beautification method and mobile terminal - Google Patents
A kind of image beautification method and mobile terminal Download PDFInfo
- Publication number
- CN107610042A CN107610042A CN201710730398.8A CN201710730398A CN107610042A CN 107610042 A CN107610042 A CN 107610042A CN 201710730398 A CN201710730398 A CN 201710730398A CN 107610042 A CN107610042 A CN 107610042A
- Authority
- CN
- China
- Prior art keywords
- image
- beautification
- model
- training
- self
- 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
Abstract
The invention provides a kind of image beautification method and mobile terminal, it is related to technical field of image processing.Methods described, including:Obtain the target image of user's input;Model is beautified by image landscaping treatment is carried out to the target image, described image beautification model is trained to obtain by training benchmark image of at least frame after self-defined beautification.The present invention carries out landscaping treatment according to the individual demand of user to image, can effectively improve the usage experience of user.
Description
Technical field
The present invention relates to technical field of image processing, more particularly to a kind of image beautification method and mobile terminal and calculating
Machine readable storage medium storing program for executing.
Background technology
Growing day by day with the self-timer demand of mobile terminal user, U.S. face camera has gradually formed a kind of trend.At present
Popular U.S. face camera is mainly clapped comprising mill skin, nti-freckle and whitening function, user using the U.S. face camera of mobile terminal on the market
According to when the result that can be more satisfied with by adjusting U.S. face dynamics.
But existing U.S. face algorithm is intended to be lifted the operability of the effect and U.S. face function after U.S. face, user uses beautiful
Change the image after algorithm process and lack differentiation and personalization.Some mobile terminal manufacturers although incorporated manual makeups function with
Individual demand of the user to U.S. face is made up, but needs user to manually adjust the image inputted each time, it is cumbersome
And inconvenience, Consumer's Experience are poor.
The content of the invention
Lack differentiation and personalization, and cumbersome and inconvenient, user to solve existing image beautification method
The problem of poor is experienced, the embodiment of the present invention provides a kind of image beautification method and mobile terminal.
In order to solve the above-mentioned technical problem, the present invention is realized in:A kind of image beautification method, including:
Obtain the target image of user's input;
When receiving self-defined beautification instruction, it is determined that the image beautification model of the corresponding self-defined beautification instruction;Institute
Image beautification model is stated to train to obtain by training benchmark image of at least frame after self-defined beautification;
Model is beautified by image landscaping treatment is carried out to the target image, described image beautifies model by an at least frame
Training benchmark image after self-defined beautification trains to obtain.
The embodiment of the present invention additionally provides a kind of mobile terminal, including:
Target image receiving module, for obtaining the target image of user's input;
Image beautifies model determining module, for when receiving self-defined beautification instruction, it is determined that corresponding described self-defined
The image beautification model of beautification instruction;Described image beautifies training benchmark image of the model by an at least frame after self-defined beautification
Training obtains;
Landscaping treatment module, landscaping treatment, described image are carried out to the target image for beautifying model by image
Beautification model is trained to obtain by training benchmark image of at least frame after self-defined beautification.
The embodiment of the present invention is additionally provided with a kind of mobile terminal, including:Memory, processor and it is stored in the storage
On device and the computer program that can run on the processor, the computer program are realized such as during the computing device
The step of above-mentioned image beautification method.
The embodiment of the present invention is additionally provided with a kind of computer-readable recording medium, on the computer-readable recording medium
Computer program is stored with, the computer program realizes image beautification method described above when being executed by processor the step of.
In embodiments of the present invention, the target image inputted by obtaining user;Model is beautified to the mesh by image
Logo image carries out landscaping treatment, and described image is beautified model and trained by training benchmark image of at least frame after self-defined beautification
Obtain.The embodiment of the present invention carries out landscaping treatment according to the individual demand of user to image, can effectively improve making for user
With experience.
Described above is only the general introduction of technical solution of the present invention, in order to better understand the technological means of the present invention,
And can be practiced according to the content of specification, and in order to allow above and other objects of the present invention, feature and advantage can
Become apparent, below especially exemplified by the embodiment of the present invention.
Brief description of the drawings
In order to illustrate the technical solution of the embodiments of the present invention more clearly, below by institute in the description to the embodiment of the present invention
The accompanying drawing needed to use is briefly described, it should be apparent that, drawings in the following description are only some implementations of the present invention
Example, for those of ordinary skill in the art, on the premise of not paying creative work, can also be obtained according to these accompanying drawings
Obtain other accompanying drawings.
Fig. 1 is a kind of step flow chart of image beautification method in the embodiment of the present invention one;
Fig. 2 is a kind of step flow chart of image beautification method in the embodiment of the present invention two;
The structural representation for the image beautification model that a kind of neural network model in Fig. 2A embodiment of the present invention two is formed;
Fig. 3 is a kind of structural representation of mobile terminal in the embodiment of the present invention three;
Fig. 4 is a kind of structural representation of mobile terminal in the embodiment of the present invention four;
Fig. 5 is a kind of block diagram of mobile terminal in the embodiment of the present invention five;
Fig. 6 is a kind of structural representation of mobile terminal in the embodiment of the present invention six.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete
Site preparation describes, it is clear that described embodiment is part of the embodiment of the present invention, rather than whole embodiments.It should be appreciated that
Specific embodiment described herein only to explain the present invention, is not intended to limit the present invention.Based on the implementation in the present invention
Example, the every other embodiment that those of ordinary skill in the art are obtained under the premise of creative work is not made, is belonged to
The scope of protection of the invention.
Embodiment one
A kind of image beautification method provided in an embodiment of the present invention is discussed in detail.
Reference picture 1, show a kind of step flow chart of image beautification method in the embodiment of the present invention.
Step 110, the target image of user's input is obtained.
Target image is that user needs to carry out the image of landscaping treatment, in actual applications, if user is needed to a certain
Target image carries out landscaping treatment, then then needs to input the target image.In embodiment itself, user can be by any
Available means input target image, and this embodiment of the present application is not limited.For example, user can locally deposit in mobile terminal
Selection is needed to carry out the target image of landscaping treatment in the image of storage, and the camera of mobile terminal can also be utilized to shoot and treated
Target image of landscaping treatment, etc..
Step 120, by image beautify model to the target image carry out landscaping treatment, described image beautify model by
Training benchmark image of at least frame after self-defined beautification trains to obtain.
In actual applications, user can be handled target image by selected existing automatic U.S. face, but from
The landscaping effect for moving U.S. face is fixed, possibly can not meet the individual demand of user, therefore in the embodiment of the present application, it is main
If solves the demand that user carries out personalized landscaping treatment to target image.User's difference can specifically be met with training in advance
The image beautification model of personalized beautification demand, and then model can be beautified by image and the target image is carried out at beautification
Reason.Image beautification model therein is trained to obtain by training benchmark image of at least frame after self-defined beautification.
In the embodiment of the present application, the type of image beautification model, structure etc. attribute information can exist according to demand
Before this step, or set according to demand before either step before this step, to this embodiment of the present application not
It is limited, and can also may be used for the attribute information of the image beautification model of different self-defined beautification schemes with identical
With difference, this embodiment of the present application is not also limited.
In the embodiment of the present application, user can treat beautifying picture according to the individual demand of itself and carry out personalized U.S.
Change, rather than treat beautifying picture using intrinsic beautification style and carry out landscaping treatment.For example, user can manually (or from
It is dynamic) increase treats the species of rouge, position and degree in beautifying picture, user can grind skin manually, decide in its sole discretion where need to grind skin,
Grind degree of skin, etc..
If for user in follow-up any once progress image beautification, it is beautiful with certain characteristic of historyization that it beautifies demand
Change consistent, then in order to avoid user's repetition is manually operated, in the embodiment of the present application, an at least frame can be utilized through self-defined
Training benchmark image after beautification train to obtain to should the image of self-defined beautification beautify model.So subsequently received right
Should self-defined beautification self-defined beautification instruction when, then can directly train to should self-defined beautification image it is beautiful
Change model and landscaping treatment is carried out to the image of input.
In addition, in actual applications, the individual demand beautified to image of user is not fixed yet, namely
User may treat that the personalized beautification demands of beautifying picture may be different at different moments, or for difference, then
In the embodiment of the present application, the user individual beautification demand of each different-style can be directed to, utilizes corresponding each personalized U.S.
Training benchmark image of at least frame for change demand after self-defined beautification corresponding with corresponding personalized beautification demand is trained
Image to corresponding each personalized beautification demand beautifies model.So now target image is entered by image beautification model
Before row landscaping treatment, can also first it be determined according to the self-defined beautification instruction received to instruction self-defined should be beautified
Image beautifies model.
For example, for image A and image B, individual demand of the user when beautifying to image A and B differs.It is false
It is located at when carrying out landscaping treatment to image A and have adjusted position and the degree of rouge manually, and image A is not ground manually
Skin, the image after landscaping treatment are image A ';And mill skin degree has been manually adjusted when carrying out landscaping treatment to image A, but simultaneously
Position and the degree of rouge are not adjusted, and the image after landscaping treatment is image B '.It can define and landscaping treatment is carried out to image A
Beautification scheme be self-defined beautification scheme 1, to image B carry out landscaping treatment beautification scheme be self-defined beautification scheme 2, that
User is subsequently quickly utilizing the target image of self-defined beautification scheme 1 or self-defined beautification scheme 2 to input for convenience
Carry out landscaping treatment, the training benchmark image that can be utilized respectively after the self-defined landscaping treatment of beautification scheme 1, for example, image
A ' training obtains an image beautification model 1 for self-defined beautification scheme 1, at through the self-defined beautification of beautification scheme 2
Training benchmark image after reason, for example, image B ' training obtains an image beautification model 2 for self-defined beautification scheme 2.
After the target image of user's input is obtained, if receiving the self-defined beautification instruction for self-defined beautification scheme 1,
Image beautification model 1 can be directly invoked landscaping treatment is carried out to the target image being currently received, hand is repeated without user
Dynamic operation.
In the embodiment of the present application, whether user autonomous control can be directed to the personalized beautification demand of itself according to demand
Training image beautifies model.For example, for foregoing self-defined beautification scheme 1 and self-defined beautification scheme 2, user can be with
Autonomous selection beautifies model just for the self-defined training image of beautification scheme 1 according to demand, or just for self-defined beautification side
The training image of case 2 beautifies model, or training image is beautiful for self-defined beautification scheme 1 and self-defined beautification scheme 2
Change model.Determined specifically, user can be set by whether preserving training benchmark image corresponding to each self-defined beautification scheme
Whether for corresponding self-defined beautification scheme training image beautification model, if for example, preserved in mobile terminal for making by oneself
The training benchmark image of adopted beautification scheme 2, for example, image B ', then it is beautiful can be then directed to the self-defined training image of beautification scheme 2
Change model;And if not preserving the training benchmark image for self-defined beautification scheme 1 in mobile terminal, then it will not be directed to certainly
Define the training image beautification model of beautification scheme 1.Or mobile terminal can be with automatic detection user to the self-defined of present image
Whether beautification operation matches with the image beautification model automatic beautifying functions that either mobile terminal camera carries trained, such as
Fruit mismatches then can beautify model for the self-defined operation training image that beautifies, and need not be directed to and be somebody's turn to do certainly if mismatching
Definition beautification operation training image beautification model.In the embodiment of the present application, can be confirmed whether using any available means pair
Each self-defined beautification scheme training image beautification model, is not limited to this embodiment of the present application.
Further, in the embodiment of the present application, user can be inputted self-defined beautification by any available means and be instructed,
This embodiment of the present application is not also limited.For example, obtain beautifying for the image of a certain self-defined beautification scheme in training
After model, then the selection control for the self-defined beautification scheme can be shown in display interface, if user triggers certain
The selection control of one self-defined beautification scheme, then refer to equivalent to the self-defined beautification that have input for the self-defined beautification scheme
Order, then can then be instructed according to the self-defined beautification received, it is determined that beautifying mould to the image that self-defined should beautify instruction
Type.
, then can be beautiful by the image after determining for the image beautification model for the target image being currently received
Change model and landscaping treatment is carried out to target image.
During being trained to image beautification model, image beautification model understanding and learning user input can be made
Training benchmark image whole style, the style of image can be summarised as roughly:The texture of image, integral color, light and shade pair
Than, the colour of skin of the smooth degree of the arrangement mode of pixel, figure skin, skin and contrast degree of personage and background etc..
Each parameter in image beautification model after training can characterize the whole style of training benchmark image, then after training
Image beautification model to target image carry out landscaping treatment, then can by train benchmark image whole style be mapped to target
In image, and then it is the beautifying picture close or consistent with training benchmark image style by target image landscaping treatment.
In embodiments of the present invention, the target image inputted by obtaining user;Model is beautified to the mesh by image
Logo image carries out landscaping treatment, and described image is beautified model and trained by training benchmark image of at least frame after self-defined beautification
Obtain.The embodiment of the present invention carries out landscaping treatment according to the individual demand of user to image, can effectively improve making for user
With experience.
Embodiment two
A kind of image beautification method provided in an embodiment of the present invention is discussed in detail.
Reference picture 2, show a kind of step flow chart of image beautification method in the embodiment of the present invention.
Step 210, the target image of user's input is obtained.
Step 220, the training benchmark image according to an at least frame after self-defined beautification, and with the training reference map
The original image training described image beautification model as corresponding to.
It has been observed that beautified using image before model carries out landscaping treatment to target image, it is necessary to which first training is corresponding
Image beautifies model.So then need according to training benchmark image of at least frame after self-defined beautification, and with the training
Original image training image corresponding to benchmark image beautifies model.Wherein, if according to training benchmark more than two frames or two frames
Image training image beautifies model, then personalized beautification scheme is corresponding to training benchmark image more than two frame or two frames
Consistent.
For example, benchmark image C ' and D ' is trained to train an image beautification model using two frames, it is assumed that the figure now trained
As beautification model correspond to self-defined beautification scheme 1 image beautification model, then training benchmark image C ' and D ' be all through
Image after the self-defined landscaping treatment of beautification scheme 1.
Alternatively, in the embodiment of the present application, the step 220 can further include:
Sub-step 221, obtains training benchmark image of at least frame after self-defined beautification, and with the training benchmark
Original image corresponding to image.
In order to be trained image beautification model, then need to obtain training benchmark of at least frame after self-defined beautification
Image, and original image corresponding with the training benchmark image.Original image therein is corresponding with training benchmark image
Non- landscaping treatment before image.In the embodiment of the present application, landscaping treatment can be carried out to original image manually in user to obtain
To after training benchmark image, that is, obtain the training benchmark image, and original image corresponding with the training benchmark image.When
Any get that so can also respectively before training trains the period of benchmark image and original image to obtain training
Benchmark image and original image, this embodiment of the present application is not limited.
Sub-step 222, the output using the training benchmark image as described image beautification model respectively, with the training
Input of the original image corresponding to benchmark image as described image beautification model, training described image beautification model.
So when training image beautifies model, then output of the benchmark image as image beautification model can be trained, together
When using original image corresponding to the training benchmark image as image beautify model input, training image beautification model.
If for example, obtaining training the benchmark image C ' and D ' for same self-defined beautification scheme 1, reference map is trained
Picture C ' corresponds to original image C, and training benchmark image D ' corresponds to original image D.So in the corresponding self-defined beautification side of training
, can be respectively to train benchmark image C ' to be used as input using original image C as output during the image beautification model of case 1;And
To train benchmark image D ' to be used as input training image beautification model using original image D as output.
Alternatively, in the embodiment of the present application, described image beautification model includes neural network model.
In the embodiment of the present application, image beautification model can be neural network model.Wherein corresponding different self-defined U.S.s
The number of plies of neural network model of change scheme etc. parameter can be consistent, it is possibility to have institute is different, to this embodiment of the present application not
It is limited.Moreover, the neural network model of corresponding different self-defined beautification schemes can be carried out before training according to demand
Personalization setting, is not also limited to this embodiment of the present application.
If Fig. 2A is the structural representation that a kind of image formed with neural network model beautifies model.Wherein, E is represented defeated
The energy damage threshold of the target image entered and training benchmark image " stylization ", E value are:
Wherein, Al, GlOriginal image corresponding to benchmark image and training benchmark image is respectively trained in l convolution
The convolution characteristic response of (conv, Convolution) layer, 4Nl 2Ml 2Represent normalization coefficient.
F in fig. 2l, PlThe convolution of the beautifying picture of output and the target image of input in l convolutional layers is represented respectively
Characteristic response.LcontentWhat is represented is the content loss function between the target image of input and the beautifying picture of output.Lstyle
What is represented is each convolutional layer energy damage threshold and value;ωlWhat is represented is the weight of l convolutional layers;LtotalFor LcontentWith
LstyleAnd value,What is represented is to ask inclined for the target image of input to content loss and energy loss and value
Derivative.Moreover, as shown in Figure 2 A, corresponding to original image, target image etc. corresponding to training benchmark image, training benchmark image
For the convolutional layer of input quantity, need to carry out pond (pool) processing between adjacent convolutional layer.
It can be seen that from Fig. 2A, training benchmark image input (input) image beautified into model, model is beautified to image
When being trained, image beautification model can be with the image style of learning training benchmark image.And beautiful using the image after training
When change model carries out landscaping treatment to the target image of input, image beautification model can obtain the content of target image, then
The image style learnt is mapped in target image, output obtains the beautifying picture after landscaping treatment.It is as can be seen that beautiful
It is consistent with target image to change the picture material of image, and image style is consistent with benchmark image.
Step 230, the test benchmark image according to an at least frame after self-defined beautification, and with the test benchmark figure
Whether the beautification success rate of original image detection described image beautification model meets that default beautification requires as corresponding to;It is if described
The beautification success rate of image beautification model is unsatisfactory for default beautification and required, then into step 220;If described image beautifies model
Beautification success rate meet that default beautification requires, then into step 240.
In the embodiment of the present application, cause to beautify using the image in order to avoid the training effect of image beautification model is bad
Image after model landscaping treatment can not meet that user requires, can also use after image beautifies model training and formally
Before, the beautification performance for beautifying model to image detects.Specifically can be according to an at least frame after self-defined beautification
Test benchmark image, and original image corresponding with the test benchmark image detection described image beautification model beautification into
Whether power meets that default beautification requires.Default beautification requirement therein can be according to demand or experience is preset right
This embodiment of the present application is not limited, and the default beautification requirement of corresponding different images beautification model can also may be used with identical
With different, this embodiment of the present application is not also limited.It can be to beautify mould using image after training to beautify success rate
Meet the frame number of user's requirement and the ratio of original image totalframes in the original image of type landscaping treatment.Test benchmark image
The training benchmark image for training image beautification model can be included, this embodiment of the present application is not limited.Moreover, test
The self-defined beautification scheme corresponding with image beautification model to be tested of self-defined beautification scheme corresponding to benchmark image is consistent
's.
For example, beautify model 1 for the image after a certain training, it is right using test benchmark image E ', F ', G ', H ' and I '
Image beautification model 1 carry out performance test, wherein original image corresponding to each test benchmark image be followed successively by original image E, F,
G, H and I.It should be noted that self-defined beautification scheme corresponding to test benchmark image E ', F ', G ', H ' and I ' and image beautify
Self-defined beautification scheme is consistent corresponding to model 1.In test process, image can be utilized to beautify model 1 respectively to original graph
As E, F, G, H and I progress landscaping treatment, obtained beautifying picture is followed successively by E ' ', F ' ', G ' ', H ' ' and I ' '.Assuming that through judging
Beautifying picture E ' ', G ' ' and I ' ' meet that beautification requires, then beautification success rate now is 3/5, i.e., 0.6.And if default U.S.
Change and require to be not less than 0.5 for beautification success rate, then then can confirm that image beautification model 1 now meets that default beautification will
Ask.
During actual test, the image that can be inputted with original image after training beautifies model, is utilized the image
Beautify model landscaping treatment after beautifying picture, then compare beautifying picture test benchmark image corresponding with original image it
Between similarity.In the embodiment of the present application, can be beautified by user's either person skilled subjective judgement using image
Whether the similarity between beautifying picture and test benchmark image after model landscaping treatment meets to require, if meeting to require
It can determine that image beautification model beautifies successfully to corresponding original image;A series of matching marks can certainly be preset
Standard, can be with if the beautifying picture and the test benchmark image that are beautified using image after model landscaping treatment meet matching standard
Determine that image beautification model beautifies successfully to corresponding original image;Etc., this embodiment of the present application is not limited.
So, require, can continue to the figure if the beautification success rate of image beautification model is unsatisfactory for default beautification
As beautification model is trained, training benchmark image that also can be according to an at least frame after self-defined beautification, and with institute
State original image training described image beautification model corresponding to training benchmark image.Made by oneself corresponding to training benchmark image now
Adopted beautification scheme need also exist for it is consistent with the corresponding self-defined beautification scheme of image beautification model, and in order that through this instruction
The performance of image beautification model after white silk beautifies this training process of model to the image relative to that can have been lifted before
The training benchmark image utilized needs the training benchmark with being utilized for the history training process of same image beautification model
Image is different.
And if the beautification success rate of described image beautification model meets that default beautification requires, then illustrate that now the image is beautiful
The performance for changing model meets requirement, can be to image progress landscaping treatment, then can then enter self-defined when receiving
During beautification instruction, it is determined that the step of image beautification model of the corresponding self-defined beautification instruction.Now, if receive from
Definition beautification instruction is that the self-defined beautification for beautifying model for the image instructs, then can then determine it is now to utilize the figure
As beautification model carries out landscaping treatment to target image.
Step 240, by image beautify model to the target image carry out landscaping treatment, described image beautify model by
Training benchmark image of at least frame after self-defined beautification trains to obtain.
In embodiments of the present invention, the target image inputted by obtaining user;Model is beautified to the mesh by image
Logo image carries out landscaping treatment, and described image is beautified model and trained by training benchmark image of at least frame after self-defined beautification
Obtain.It can realize and automatic landscaping treatment is carried out to image according to the individual demand of user, making for user can be effectively improved
With experience.
Moreover, in embodiments of the present invention, training benchmark image of at least frame after self-defined beautification can also be obtained,
And original image corresponding with the training benchmark image;Mould is beautified as described image using the training benchmark image respectively
The output of type, beautify the input of model as described image using original image corresponding to the training benchmark image, described in training
Image beautifies model.Also, can also according to test benchmark image of at least frame after self-defined beautification, and with the survey
Whether the beautification success rate of original image detection described image beautification model meets that default beautification requires corresponding to examination benchmark image;
Require, enter according to an at least frame through self-defined if the beautification success rate of described image beautification model is unsatisfactory for default beautification
Training benchmark image after beautification, and original image training described image beautification model corresponding with the training benchmark image
The step of;If the beautification success rate of described image beautification model meets that default beautification requires, image beautification mould is entered through
Type carries out landscaping treatment to the target image, and described image beautifies training base of the model by an at least frame after self-defined beautification
The step of quasi- image trains to obtain.So as to further improve the beautification performance of image beautification model, user is further improved
Usage experience.
In addition, in embodiments of the present invention, image beautification model includes neural network model.Equally can further it improve
Image beautifies the performance of model, makes it easier to the beautification demand for meeting user.
Embodiment three
A kind of mobile terminal provided in an embodiment of the present invention is discussed in detail.
Reference picture 3, show a kind of structural representation of mobile terminal in the embodiment of the present invention.
The mobile terminal 300 of the embodiment of the present invention includes:Target image receiving module 310 and landscaping treatment module 320.
Be discussed in detail separately below each module function and each module between interactive relation.
Target image receiving module 310, for obtaining the target image of user's input;
Landscaping treatment module 320, landscaping treatment, the figure are carried out to the target image for beautifying model by image
As beautification model is trained to obtain by training benchmark image of at least frame after self-defined beautification.
In embodiments of the present invention, the target image inputted by obtaining user;Model is beautified to the mesh by image
Logo image carries out landscaping treatment, and described image is beautified model and trained by training benchmark image of at least frame after self-defined beautification
Obtain.The embodiment of the present invention carries out landscaping treatment according to the individual demand of user to image, can effectively improve making for user
With experience.
Example IV
A kind of mobile terminal provided in an embodiment of the present invention is discussed in detail.
Reference picture 4, show a kind of structural representation of mobile terminal in the embodiment of the present invention.
The mobile terminal 400 of the embodiment of the present invention includes:Target image receiving module 410, image beautification model training mould
Block 420, performance test module 430 and landscaping treatment module 440.
Be discussed in detail separately below each module function and each module between interactive relation.
Target image receiving module 410, for obtaining the target image of user's input;
Image beautifies model training module 420, for according to training benchmark image of at least frame after self-defined beautification,
And original image training described image beautification model corresponding with the training benchmark image.
Alternatively, in embodiment is applied, described image beautification model training module 420, can further include:
Training sample acquisition submodule, for obtaining training benchmark image of at least frame after self-defined beautification, and
Original image corresponding with the training benchmark image.
Model training submodule, for beautifying the output of model using the training benchmark image as described image respectively,
The input of described image beautification model, training described image beautification mould are used as using original image corresponding to the training benchmark image
Type.
Performance test module 430, for according to test benchmark image of at least frame after self-defined beautification, and with institute
Whether the beautification success rate for stating original image detection described image beautification model corresponding to test benchmark image meets default beautification
It is required that;Required if the beautification success rate of described image beautification model is unsatisfactory for default beautification, into image beautification model instruction
Practice module 420;If the beautification success rate of described image beautification model meets that default beautification requires, into landscaping treatment module
440。
Landscaping treatment module 440, landscaping treatment, the figure are carried out to the target image for beautifying model by image
As beautification model is trained to obtain by training benchmark image of at least frame after self-defined beautification.
In embodiments of the present invention, the target image inputted by obtaining user;Model is beautified to the mesh by image
Logo image carries out landscaping treatment, and described image is beautified model and trained by training benchmark image of at least frame after self-defined beautification
Obtain.It can realize and automatic landscaping treatment is carried out to image according to the individual demand of user, making for user can be effectively improved
With experience.
Moreover, in embodiments of the present invention, training benchmark image of at least frame after self-defined beautification can also be obtained,
And original image corresponding with the training benchmark image;Mould is beautified as described image using the training benchmark image respectively
The output of type, beautify the input of model as described image using original image corresponding to the training benchmark image, described in training
Image beautifies model.Also, can also according to test benchmark image of at least frame after self-defined beautification, and with the survey
Whether the beautification success rate of original image detection described image beautification model meets that default beautification requires corresponding to examination benchmark image;
Require, enter according to an at least frame through self-defined if the beautification success rate of described image beautification model is unsatisfactory for default beautification
Training benchmark image after beautification, and original image training described image beautification model corresponding with the training benchmark image
The step of;If the beautification success rate of described image beautification model meets that default beautification requires, image beautification mould is entered through
Type carries out landscaping treatment to the target image, and described image beautifies training base of the model by an at least frame after self-defined beautification
The step of quasi- image trains to obtain.So as to further improve the beautification performance of image beautification model, user is further improved
Usage experience.
In addition, in embodiments of the present invention, image beautification model includes neural network model.Equally can further it improve
Image beautifies the performance of model, makes it easier to the beautification demand for meeting user.
Mobile terminal provided in an embodiment of the present invention can realize that mobile terminal is realized in Fig. 1 to Fig. 2 embodiment of the method
Each process, to avoid repeating, repeat no more here.
Embodiment five
A kind of mobile terminal provided in an embodiment of the present invention is discussed in detail.
Reference picture 5, show a kind of block diagram of mobile terminal in the embodiment of the present invention.
Mobile terminal 500 shown in Fig. 5 includes:At least one processor 501, memory 502, at least one network interface
504 and user interface 503.Each component in mobile terminal 500 is coupled by bus system 505.It is understood that bus
System 505 is used to realize the connection communication between these components.Bus system 505 is in addition to including data/address bus, in addition to electricity
Source bus, controlling bus and status signal bus in addition.But for the sake of clear explanation, various buses are all designated as always in Figure 5
Linear system system 505.
Wherein, user interface 503 can include display, keyboard or pointing device (for example, mouse, trace ball
(trackball), touch-sensitive plate or touch-screen etc..
It is appreciated that the memory 502 in the embodiment of the present invention can be volatile memory or nonvolatile memory,
Or it may include both volatibility and nonvolatile memory.Wherein, nonvolatile memory can be read-only storage (Read-
Only Memory, ROM), programmable read only memory (Programmable ROM, PROM), the read-only storage of erasable programmable
Device (Erasable PROM, EPROM), Electrically Erasable Read Only Memory (Electrically EPROM, EEPROM) or
Flash memory.Volatile memory can be random access memory (Random Access Memory, RAM), and it is used as outside high
Speed caching.By exemplary but be not restricted explanation, the RAM of many forms can use, such as static RAM
(Static RAM, SRAM), dynamic random access memory (Dynamic RAM, DRAM), Synchronous Dynamic Random Access Memory
(Synchronous DRAM, SDRAM), double data speed synchronous dynamic RAM (Double Data Rate
SDRAM, DDRSDRAM), enhanced Synchronous Dynamic Random Access Memory (Enhanced SDRAM, ESDRAM), synchronized links
Dynamic random access memory (Synch Link DRAM, SLDRAM) and direct rambus random access memory (Direct
Rambus RAM, DRRAM).The embodiment of the present invention description system and method memory 502 be intended to including but not limited to these
With the memory of any other suitable type.
In some embodiments, memory 502 stores following element, can perform module or data structure, or
Their subset of person, or their superset:Operating system 5021 and application program 5022.
Wherein, operating system 5021, comprising various system programs, such as ccf layer, core library layer, driving layer etc., it is used for
Realize various basic businesses and the hardware based task of processing.Application program 5022, include various application programs, such as media
Player (Media Player), browser (Browser) etc., for realizing various applied business.Realize the embodiment of the present invention
The program of method may be embodied in application program 5022.
In embodiments of the present invention, by calling program or the instruction of the storage of memory 502, specifically, can be application
The program stored in program 5022 or instruction, processor 501 are used for the target image for obtaining user's input;Mould is beautified by image
Type carries out landscaping treatment to the target image, and described image beautifies training base of the model by an at least frame after self-defined beautification
Quasi- image trains to obtain.
The method that the embodiments of the present invention disclose can apply in processor 501, or be realized by processor 501.
Processor 501 is probably a kind of IC chip, has the disposal ability of signal.In implementation process, the above method it is each
Step can be completed by the integrated logic circuit of the hardware in processor 501 or the instruction of software form.Above-mentioned processing
Device 501 can be general processor, digital signal processor (Digital Signal Processor, DSP), special integrated electricity
Road (Application Specific Integrated Circuit, ASIC), ready-made programmable gate array (Field
Programmable Gate Array, FPGA) either other PLDs, discrete gate or transistor logic,
Discrete hardware components.It can realize or perform disclosed each method, step and the logic diagram in the embodiment of the present invention.It is general
Processor can be microprocessor or the processor can also be any conventional processor etc..With reference to institute of the embodiment of the present invention
The step of disclosed method, can be embodied directly in hardware decoding processor and perform completion, or with the hardware in decoding processor
And software module combination performs completion.Software module can be located at random access memory, flash memory, read-only storage, may be programmed read-only
In the ripe storage medium in this area such as memory or electrically erasable programmable memory, register.The storage medium is located at
Memory 502, processor 501 read the information in memory 502, with reference to the step of its hardware completion above method.
It is understood that the embodiment of the present invention description these embodiments can use hardware, software, firmware, middleware,
Microcode or its combination are realized.Realized for hardware, processing unit can be realized in one or more application specific integrated circuits
(Application Specific Integrated Circuits, ASIC), digital signal processor (Digital Signal
Processing, DSP), digital signal processing appts (DSP Device, DSPD), programmable logic device (Programmable
Logic Device, PLD), field programmable gate array (Field-Programmable Gate Array, FPGA), general place
Manage in device, controller, microcontroller, microprocessor, other electronic units for performing herein described function or its combination.
For software realize, can by perform the module (such as process, function etc.) of function described in the embodiment of the present invention come
Realize the technology described in the embodiment of the present invention.Software code is storable in memory and passes through computing device.Memory can
To realize within a processor or outside processor.
Alternatively, it is additionally operable to as another embodiment, processor 501:According to an at least frame after self-defined beautification
Train benchmark image, and original image training described image beautification model corresponding with the training benchmark image.
Alternatively, it is additionally operable to as another embodiment, processor 501:An at least frame is obtained after self-defined beautification
Train benchmark image, and original image corresponding with the training benchmark image;Respectively using it is described training benchmark image as
Described image beautifies the output of model, and described image beautification model is used as using original image corresponding to the training benchmark image
Input, training described image beautification model.
Alternatively, processor 501 is additionally operable to:According to test benchmark image of at least frame after self-defined beautification, and
Whether the beautification success rate of original image detection described image beautification model corresponding with the test benchmark image meets to preset
Beautification requires;Require, enter according at least one if the beautification success rate of described image beautification model is unsatisfactory for default beautification
Training benchmark image of the frame after self-defined beautification, and original image corresponding with the training benchmark image train the figure
As the step of beautification model;If the beautification success rate of described image beautification model meets that default beautification requires, enter through
Image beautifies model and landscaping treatment is carried out to the target image, and described image beautifies model by an at least frame through self-defined beautification
The step of training benchmark image afterwards trains to obtain.
Alternatively, processor 501 is additionally operable to:Described image beautification model includes neural network model.
Mobile terminal 500 can realize each process that mobile terminal is realized in previous embodiment, to avoid repeating, here
Repeat no more.
Embodiment six
Fig. 6 is the structural representation of the mobile terminal of another embodiment of the present invention.Specifically, the mobile terminal in Fig. 6
Can be mobile phone, tablet personal computer, personal digital assistant (Personal Digital Assistant, PDA) or vehicle-mounted computer
Deng.
Mobile terminal in Fig. 6 includes radio frequency (Radio Frequency, RF) circuit 610, memory 620, input block
630th, display unit 640, processor 660, voicefrequency circuit 670, WiFi (Wireless Fidelity) modules 680 and power supply
690。
Wherein, input block 630 can be used for the numeral or character information for receiving user's input, and generation and mobile terminal
User set and function control it is relevant signal input.Specifically, in the embodiment of the present invention, the input block 630 can be with
Including contact panel 631.Contact panel 631, also referred to as touch-screen, collect touch operation (ratio of the user on or near it
Such as user uses the operation of finger, any suitable object of stylus or annex on contact panel 631), and according to setting in advance
Fixed formula drives corresponding attachment means.Optionally, contact panel 631 may include touch detecting apparatus and touch controller two
Individual part.Wherein, the touch orientation of touch detecting apparatus detection user, and the signal that touch operation is brought is detected, signal is passed
Give touch controller;Touch controller receives touch information from touch detecting apparatus, and is converted into contact coordinate, then
Give the processor 660, and the order sent of reception processing device 660 and can be performed.Furthermore, it is possible to using resistance-type, electricity
The polytypes such as appearance formula, infrared ray and surface acoustic wave realize contact panel 631.Except contact panel 631, input block 630
Can also include other input equipments 632, other input equipments 632 can include but is not limited to physical keyboard, function key (such as
Volume control button, switch key etc.), trace ball, mouse, the one or more in action bars etc..
Wherein, display unit 640 can be used for display by the information of user's input or be supplied to information and the movement of user
The various menu interfaces of terminal.Display unit 640 may include display panel 641, optionally, can use LCD or organic light emission
The forms such as diode (Organic Light-Emitting Diode, OLED) configure display panel 641.
It should be noted that contact panel 631 can cover display panel 641, touch display screen is formed, when the touch display screen is examined
After measuring the touch operation on or near it, processor 660 is sent to determine the type of touch event, is followed by subsequent processing device
660 provide corresponding visual output according to the type of touch event in touch display screen.
Touch display screen includes Application Program Interface viewing area and conventional control viewing area.The Application Program Interface viewing area
And arrangement mode of the conventional control viewing area does not limit, can be arranged above and below, left-right situs etc. can distinguish two it is aobvious
Show the arrangement mode in area.The Application Program Interface viewing area is displayed for the interface of application program.Each interface can be with
The interface element such as the icon comprising at least one application program and/or widget desktop controls.The Application Program Interface viewing area
It can also be the empty interface not comprising any content.The conventional control viewing area is used to show the higher control of utilization rate, for example,
Application icons such as settings button, interface numbering, scroll bar, phone directory icon etc..
Wherein, processor 660 is the control centre of mobile terminal, utilizes each of various interfaces and connection whole mobile phone
Individual part, by running or performing the software program and/or module that are stored in first memory 621, and call and be stored in
Data in second memory 622, the various functions and processing data of mobile terminal are performed, it is overall so as to be carried out to mobile terminal
Monitoring.Optionally, processor 660 may include one or more processing units.
In embodiments of the present invention, by call store the first memory 621 in software program and/or module and/
Or the data in the second memory 622, processor 660 are used for the target image for obtaining user's input;Mould is beautified by image
Type carries out landscaping treatment to the target image, and described image beautifies training base of the model by an at least frame after self-defined beautification
Quasi- image trains to obtain.
Alternatively, it is additionally operable to as another embodiment, processor 660:According to an at least frame after self-defined beautification
Train benchmark image, and original image training described image beautification model corresponding with the training benchmark image.
Alternatively, it is additionally operable to as another embodiment, processor 660:An at least frame is obtained after self-defined beautification
Train benchmark image, and original image corresponding with the training benchmark image;Respectively using it is described training benchmark image as
Described image beautifies the output of model, and described image beautification model is used as using original image corresponding to the training benchmark image
Input, training described image beautification model.
Alternatively, processor 660 is additionally operable to:According to test benchmark image of at least frame after self-defined beautification, and
Whether the beautification success rate of original image detection described image beautification model corresponding with the test benchmark image meets to preset
Beautification requires;Require, enter according at least one if the beautification success rate of described image beautification model is unsatisfactory for default beautification
Training benchmark image of the frame after self-defined beautification, and original image corresponding with the training benchmark image train the figure
As the step of beautification model;If the beautification success rate of described image beautification model meets that default beautification requires, enter through
Image beautifies model and landscaping treatment is carried out to the target image, and described image beautifies model by an at least frame through self-defined beautification
The step of training benchmark image afterwards trains to obtain.
Alternatively, processor 660 is additionally operable to:Described image beautification model includes neural network model.
It can be seen that in embodiments of the present invention, the target image inputted by obtaining user;Refer to when receiving self-defined beautification
When making, it is determined that the image beautification model of the corresponding self-defined beautification instruction;Described image is beautified model and passed through certainly by an at least frame
Training benchmark image after definition beautification trains to obtain;Model is beautified by image landscaping treatment is carried out to the target image,
Described image beautification model is trained to obtain by training benchmark image of at least frame after self-defined beautification.Can realize according to
The individual demand at family carries out automatic landscaping treatment to image, can effectively improve the usage experience of user.
Moreover, in embodiments of the present invention, training benchmark image of at least frame after self-defined beautification can also be obtained,
And original image corresponding with the training benchmark image;Mould is beautified as described image using the training benchmark image respectively
The output of type, beautify the input of model as described image using original image corresponding to the training benchmark image, described in training
Image beautifies model.Also, can also according to test benchmark image of at least frame after self-defined beautification, and with the survey
Whether the beautification success rate of original image detection described image beautification model meets that default beautification requires corresponding to examination benchmark image;
Require, enter according to an at least frame through self-defined if the beautification success rate of described image beautification model is unsatisfactory for default beautification
Training benchmark image after beautification, and original image training described image beautification model corresponding with the training benchmark image
The step of;If the beautification success rate of described image beautification model meets that default beautification requires, image beautification mould is entered through
Type carries out landscaping treatment to the target image, and described image beautifies training base of the model by an at least frame after self-defined beautification
The step of quasi- image trains to obtain.So as to further improve the beautification performance of image beautification model, user is further improved
Usage experience.
In addition, in embodiments of the present invention, image beautification model includes neural network model.Equally can further it improve
Image beautifies the performance of model, makes it easier to the beautification demand for meeting user.
The embodiment of the present invention additionally provides a kind of mobile terminal, including:Memory, processor and storage are on a memory simultaneously
The computer program that can be run on a processor, the computer program realize that above-mentioned image beautification method is real when being executed by processor
Each process of example is applied, and identical technique effect can be reached, to avoid repeating, is repeated no more here.
The embodiment of the present invention additionally provides a kind of computer-readable recording medium, is stored with computer-readable recording medium
Computer program, each process of above-mentioned image beautification method embodiment, and energy are realized when computer program is executed by processor
Reach identical technique effect, to avoid repeating, repeat no more here.Wherein, described computer-readable recording medium, such as only
Read memory (Read-Only Memory, abbreviation ROM), random access memory (Random Access Memory, abbreviation
RAM), magnetic disc or CD etc..
Those of ordinary skill in the art it is to be appreciated that with reference to disclosed in the embodiment of the present invention embodiment description it is each
The unit and algorithm steps of example, it can be realized with the combination of electronic hardware or computer software and electronic hardware.These
Function is performed with hardware or software mode actually, application-specific and design constraint depending on technical scheme.Specialty
Technical staff can realize described function using distinct methods to each specific application, but this realization should not
Think beyond the scope of this invention.
It is apparent to those skilled in the art that for convenience and simplicity of description, the system of foregoing description,
The specific work process of device and unit, the corresponding process in preceding method embodiment is may be referred to, will not be repeated here.
In embodiment provided herein, it should be understood that disclosed apparatus and method, others can be passed through
Mode is realized.For example, device embodiment described above is only schematical, for example, the division of the unit, is only
A kind of division of logic function, can there is an other dividing mode when actually realizing, for example, multiple units or component can combine or
Person is desirably integrated into another system, or some features can be ignored, or does not perform.Another, shown or discussed is mutual
Between coupling or direct-coupling or communication connection can be INDIRECT COUPLING or communication link by some interfaces, device or unit
Connect, can be electrical, mechanical or other forms.
The unit illustrated as separating component can be or may not be physically separate, show as unit
The part shown can be or may not be physical location, you can with positioned at a place, or can also be distributed to multiple
On NE.Some or all of unit therein can be selected to realize the mesh of this embodiment scheme according to the actual needs
's.
In addition, each functional unit in each embodiment of the present invention can be integrated in a processing unit, can also
That unit is individually physically present, can also two or more units it is integrated in a unit.
If the function is realized in the form of SFU software functional unit and is used as independent production marketing or in use, can be with
It is stored in a computer read/write memory medium.Based on such understanding, technical scheme is substantially in other words
The part to be contributed to prior art or the part of the technical scheme can be embodied in the form of software product, the meter
Calculation machine software product is stored in a storage medium, including some instructions are causing a computer equipment (can be
People's computer, server, or network equipment etc.) perform all or part of step of each embodiment methods described of the present invention.
And foregoing storage medium includes:USB flash disk, mobile hard disk, ROM, RAM, magnetic disc or CD etc. are various can be with store program codes
Medium.
The foregoing is only a specific embodiment of the invention, but protection scope of the present invention is not limited thereto, any
Those familiar with the art the invention discloses technical scope in, change or replacement can be readily occurred in, should all be contained
Cover within protection scope of the present invention.Therefore, protection scope of the present invention should be defined by scope of the claims.
Claims (12)
1. a kind of image beautification method, methods described is applied to mobile terminal, it is characterised in that including:
Obtain the target image of user's input;
Model is beautified by image landscaping treatment is carried out to the target image, described image is beautified model and passed through certainly by an at least frame
Training benchmark image after definition beautification trains to obtain.
2. according to the method for claim 1, it is characterised in that model is beautified to the target image by image described
Landscaping treatment is carried out, described image beautification model trains what is obtained by training benchmark image of at least frame after self-defined beautification
Before step, in addition to:
According to training benchmark image of at least frame after self-defined beautification, and it is corresponding original with the training benchmark image
Image training described image beautification model.
3. according to the method for claim 2, it is characterised in that training of the basis at least frame after self-defined beautification
Benchmark image, and the step of original image training described image beautification model corresponding with the training benchmark image, including:
Training benchmark image of at least frame after self-defined beautification is obtained, and it is corresponding original with the training benchmark image
Image;
Output using the training benchmark image as described image beautification model respectively, with corresponding to the training benchmark image
Input of the original image as described image beautification model, training described image beautification model.
4. according to the method for claim 2, it is characterised in that in instruction of the basis at least frame after self-defined beautification
Practice benchmark image, and with the step of the training benchmark image corresponding original image training described image beautification model it
Afterwards, in addition to:
According to test benchmark image of at least frame after self-defined beautification, and it is corresponding original with the test benchmark image
Whether the beautification success rate of image detection described image beautification model meets that default beautification requires;
Required if the beautification success rate of described image beautification model is unsatisfactory for default beautify, enter and passed through certainly according to an at least frame
Training benchmark image after definition beautification, and original image training described image beautification corresponding with the training benchmark image
The step of model;
If the beautification success rate of described image beautification model meets that default beautification requires, image beautification model pair is entered through
The target image carries out the step of landscaping treatment.
5. according to the method described in claim any one of 1-4, it is characterised in that described image beautification model includes neutral net
Model.
A kind of 6. mobile terminal, it is characterised in that including:
Target image receiving module, for obtaining the target image of user's input;
Landscaping treatment module, landscaping treatment, described image beautification are carried out to the target image for beautifying model by image
Model is trained to obtain by training benchmark image of at least frame after self-defined beautification.
7. mobile terminal according to claim 6, it is characterised in that also include:
Image beautifies model training module, for the training benchmark image according to an at least frame after self-defined beautification, Yi Jiyu
Original image training described image beautification model corresponding to the training benchmark image.
8. mobile terminal according to claim 7, it is characterised in that described image beautifies model training module, including:
Training sample acquisition submodule, for obtaining training benchmark image of at least frame after self-defined beautification, and with institute
State original image corresponding to training benchmark image;
Model training submodule, for the output using the training benchmark image as described image beautification model respectively, with institute
State input of the original image as described image beautification model corresponding to training benchmark image, training described image beautification model.
9. mobile terminal according to claim 7, it is characterised in that also include:
Performance test module, for according to test benchmark image of at least frame after self-defined beautification, and with the test
Whether the beautification success rate of original image detection described image beautification model meets that default beautification requires corresponding to benchmark image;Such as
The beautification success rate of fruit described image beautification model is unsatisfactory for default beautification and required, then beautifies model training module into image;
If the beautification success rate of described image beautification model meets that default beautification requires, beautify model determining module into image.
10. according to the mobile terminal described in claim any one of 6-9, it is characterised in that described image beautification model includes god
Through network model.
A kind of 11. mobile terminal, it is characterised in that including:Memory, processor and it is stored on the memory and can be in institute
The computer program run on processor is stated, the computer program is realized such as claim 1 to 5 during the computing device
Any one of image beautification method the step of.
12. a kind of computer-readable recording medium, it is characterised in that be stored with computer on the computer-readable recording medium
Program, the image beautification method as any one of claim 1 to 5 is realized when the computer program is executed by processor
The step of.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710730398.8A CN107610042B (en) | 2017-08-23 | 2017-08-23 | A kind of image beautification method and mobile terminal |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710730398.8A CN107610042B (en) | 2017-08-23 | 2017-08-23 | A kind of image beautification method and mobile terminal |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107610042A true CN107610042A (en) | 2018-01-19 |
CN107610042B CN107610042B (en) | 2019-06-07 |
Family
ID=61065826
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710730398.8A Active CN107610042B (en) | 2017-08-23 | 2017-08-23 | A kind of image beautification method and mobile terminal |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107610042B (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110543276A (en) * | 2019-08-30 | 2019-12-06 | 维沃移动通信有限公司 | Picture screening method and terminal equipment thereof |
CN110968235A (en) * | 2018-09-28 | 2020-04-07 | 上海寒武纪信息科技有限公司 | Signal processing device and related product |
CN110968285A (en) * | 2018-09-28 | 2020-04-07 | 上海寒武纪信息科技有限公司 | Signal processing device and related product |
CN111553854A (en) * | 2020-04-21 | 2020-08-18 | 维沃移动通信有限公司 | Image processing method and electronic equipment |
CN113222841A (en) * | 2021-05-08 | 2021-08-06 | 北京字跳网络技术有限公司 | Image processing method, device, equipment and medium |
US11703939B2 (en) | 2018-09-28 | 2023-07-18 | Shanghai Cambricon Information Technology Co., Ltd | Signal processing device and related products |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7626743B2 (en) * | 2001-12-11 | 2009-12-01 | Minolta Co., Ltd. | Image processing apparatus, image processing method and image processing program for rendering pixels transparent in circumscribed areas |
CN102609895A (en) * | 2012-01-31 | 2012-07-25 | 华为终端有限公司 | Image processing method and terminal equipment |
US20130064430A1 (en) * | 2010-05-26 | 2013-03-14 | Nec Corporation | Image processing device, image processing method, and image processing program |
CN106657793A (en) * | 2017-01-11 | 2017-05-10 | 维沃移动通信有限公司 | Image processing method and mobile terminal |
CN106780298A (en) * | 2016-11-30 | 2017-05-31 | 努比亚技术有限公司 | The processing method and processing device of picture |
CN106846281A (en) * | 2017-03-09 | 2017-06-13 | 广州四三九九信息科技有限公司 | image beautification method and terminal device |
CN107025629A (en) * | 2017-04-27 | 2017-08-08 | 维沃移动通信有限公司 | A kind of image processing method and mobile terminal |
-
2017
- 2017-08-23 CN CN201710730398.8A patent/CN107610042B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7626743B2 (en) * | 2001-12-11 | 2009-12-01 | Minolta Co., Ltd. | Image processing apparatus, image processing method and image processing program for rendering pixels transparent in circumscribed areas |
US20130064430A1 (en) * | 2010-05-26 | 2013-03-14 | Nec Corporation | Image processing device, image processing method, and image processing program |
CN102609895A (en) * | 2012-01-31 | 2012-07-25 | 华为终端有限公司 | Image processing method and terminal equipment |
CN106780298A (en) * | 2016-11-30 | 2017-05-31 | 努比亚技术有限公司 | The processing method and processing device of picture |
CN106657793A (en) * | 2017-01-11 | 2017-05-10 | 维沃移动通信有限公司 | Image processing method and mobile terminal |
CN106846281A (en) * | 2017-03-09 | 2017-06-13 | 广州四三九九信息科技有限公司 | image beautification method and terminal device |
CN107025629A (en) * | 2017-04-27 | 2017-08-08 | 维沃移动通信有限公司 | A kind of image processing method and mobile terminal |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110968235A (en) * | 2018-09-28 | 2020-04-07 | 上海寒武纪信息科技有限公司 | Signal processing device and related product |
CN110968285A (en) * | 2018-09-28 | 2020-04-07 | 上海寒武纪信息科技有限公司 | Signal processing device and related product |
CN110968235B (en) * | 2018-09-28 | 2022-02-22 | 上海寒武纪信息科技有限公司 | Signal processing device and related product |
US11703939B2 (en) | 2018-09-28 | 2023-07-18 | Shanghai Cambricon Information Technology Co., Ltd | Signal processing device and related products |
CN110543276A (en) * | 2019-08-30 | 2019-12-06 | 维沃移动通信有限公司 | Picture screening method and terminal equipment thereof |
CN110543276B (en) * | 2019-08-30 | 2021-04-02 | 维沃移动通信有限公司 | Picture screening method and terminal equipment thereof |
CN111553854A (en) * | 2020-04-21 | 2020-08-18 | 维沃移动通信有限公司 | Image processing method and electronic equipment |
CN113222841A (en) * | 2021-05-08 | 2021-08-06 | 北京字跳网络技术有限公司 | Image processing method, device, equipment and medium |
WO2022237633A1 (en) * | 2021-05-08 | 2022-11-17 | 北京字跳网络技术有限公司 | Image processing method, apparatus, and device, and storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN107610042B (en) | 2019-06-07 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107610042A (en) | A kind of image beautification method and mobile terminal | |
CN107025629A (en) | A kind of image processing method and mobile terminal | |
CN106657793A (en) | Image processing method and mobile terminal | |
CN107678641A (en) | A kind of method and mobile terminal into target display interface | |
CN107492067B (en) | A kind of image beautification method and mobile terminal | |
CN107147852A (en) | Image capturing method, mobile terminal and computer-readable recording medium | |
CN107464206A (en) | A kind of watermark adding method and mobile terminal | |
CN107368150A (en) | A kind of photographic method and mobile terminal | |
CN106777329A (en) | The processing method and mobile terminal of a kind of image information | |
CN107527034A (en) | A kind of face contour method of adjustment and mobile terminal | |
CN107492079A (en) | A kind of image mill skin method and mobile terminal | |
CN107222675A (en) | The photographic method and mobile terminal of a kind of mobile terminal | |
CN106791393A (en) | A kind of image pickup method and mobile terminal | |
CN106919318A (en) | The method and terminal of a kind of picture processing | |
CN106791438A (en) | A kind of photographic method and mobile terminal | |
CN107800868A (en) | A kind of method for displaying image and mobile terminal | |
CN107392933A (en) | A kind of method and mobile terminal of image segmentation | |
CN107798228A (en) | A kind of face identification method and mobile terminal | |
CN106954027A (en) | The method and mobile terminal of a kind of image taking | |
CN107404577A (en) | A kind of image processing method, mobile terminal and computer-readable recording medium | |
CN107358111A (en) | A kind of method for secret protection and mobile terminal | |
CN107172346A (en) | A kind of weakening method and mobile terminal | |
CN106952235A (en) | A kind of image processing method and mobile terminal | |
CN107277411A (en) | A kind of video recording method and mobile terminal | |
CN106855744B (en) | A kind of screen display method and mobile 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 |