CN109147007A - Paster loading method, device, terminal and computer readable storage medium - Google Patents
Paster loading method, device, terminal and computer readable storage medium Download PDFInfo
- Publication number
- CN109147007A CN109147007A CN201810867377.5A CN201810867377A CN109147007A CN 109147007 A CN109147007 A CN 109147007A CN 201810867377 A CN201810867377 A CN 201810867377A CN 109147007 A CN109147007 A CN 109147007A
- Authority
- CN
- China
- Prior art keywords
- paster
- sub
- image
- goal
- processed
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T11/00—2D [Two Dimensional] image generation
- G06T11/60—Editing figures and text; Combining figures or text
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
The application belongs to technical field of image processing more particularly to a kind of paster loading method, device, terminal and computer readable storage medium, wherein the paster loading method includes: to obtain image to be processed；Detect one or more sub-goal objects of the target object for including in the image to be processed and target object attachment；The characteristic information of each sub-goal object is extracted, and the corresponding paster inquiry instruction of each sub-goal object is generated according to the characteristic information；The corresponding paster of each sub-goal object is obtained according to the paster inquiry instruction, and the paster is loaded onto the image to be processed on corresponding sub-goal object；Enhance the expression effect of paster.
Description
Technical field
The application belongs to technical field of image processing more particularly to a kind of paster loading method, device, terminal and computer
Readable storage medium storing program for executing.
Background technique
With the development of shooting technology, people can carry out U.S. face, filter using to image by various take pictures
Or increase the processing of paster.
The general fixation material that can use pre-production of processing for increase paster to image is synthesized in image in fact
It is existing, however, this processing mode is possible to that same paster can be made to be used in different images, paster processing is caused to occur thousand
Same phenomenon reduces the expression effect of paster.
Summary of the invention
The embodiment of the present application provides a kind of paster loading method, device, terminal and computer readable storage medium, can solve
The technical issues of certainly same paster is used in different images, reduces paster expression effect.
The embodiment of the present application first aspect provides a kind of paster loading method, comprising:
Obtain image to be processed；
Detect one or more of the target object for including in the image to be processed and target object attachment
Target object；
The characteristic information of each sub-goal object is extracted, and each sub-goal object is generated according to the characteristic information and is corresponded to
Paster inquiry instruction；
The corresponding paster of each sub-goal object is obtained according to the paster inquiry instruction, and the paster is loaded onto institute
It states in image to be processed on corresponding sub-goal object.
The embodiment of the present application second aspect provides a kind of paster loading device, comprising:
Acquiring unit, for obtaining image to be processed；
Detection unit, for detecting the target object for including in the image to be processed and target object attachment
One or more sub-goal objects；
Generation unit generates each for extracting the characteristic information of each sub-goal object, and according to the characteristic information
The corresponding paster inquiry instruction of sub-goal object；
Loading unit, for obtaining the corresponding paster of each sub-goal object according to the paster inquiry instruction, and by institute
Paster is stated to be loaded onto the image to be processed on corresponding sub-goal object.
The embodiment of the present application third aspect provides a kind of terminal, including memory, processor and storage are in memory
And the computer program that can be run on a processor, when processor executes computer program the step of the realization above method.
The embodiment of the present application fourth aspect provides a kind of computer readable storage medium, computer-readable recording medium storage
The step of having computer program, the above method is realized when computer program is executed by processor.
In the embodiment of the present application, by detecting the target object for including in the image to be processed and the target pair
As one or more sub-goal objects of attachment, then the characteristic information of each sub-goal object is extracted, generates and carry the feature
The corresponding paster inquiry instruction of each sub-goal object of information, to inquire to obtain every height according to the paster inquiry instruction
The corresponding paster of target object, and the paster is loaded onto the image to be processed on corresponding sub-goal object, it completes
Paster processing to one or more sub-goal objects in image to be processed；Since the application increases on sub-goal object
Paster is inquired according to the characteristic information of sub-goal object, is not the paster of pre-production, therefore can be to avoid same
One paster is used in different images, and there is a situation where influence paster expression effect.
Detailed description of the invention
Technical solution in ord to more clearly illustrate embodiments of the present application, below will be to needed in the embodiment attached
Figure is briefly described, it should be understood that the following drawings illustrates only some embodiments of the application, therefore is not construed as pair
The restriction of range for those of ordinary skill in the art without creative efforts, can also be according to this
A little attached drawings obtain other relevant attached drawings.
Fig. 1 is a kind of implementation process schematic diagram of paster loading method provided by the embodiments of the present application；
Fig. 2 is a kind of specific implementation flow schematic diagram of paster loading method step 103 provided by the embodiments of the present application；
Fig. 3 is paster load interface schematic diagram provided by the embodiments of the present application；
Fig. 4 is the paster load interface signal provided by the embodiments of the present application for being loaded with price paster and purchase link paster
Figure；
Fig. 5 is a kind of specific implementation flow schematic diagram of paster loading method step 104 provided by the embodiments of the present application；
Fig. 6 is the paster load interface schematic diagram provided by the embodiments of the present application for being loaded with paster label；
Fig. 7 is the structural schematic diagram of paster loading device provided by the embodiments of the present application；
Fig. 8 is the structural schematic diagram of terminal provided by the embodiments of the present application.
Specific embodiment
It is with reference to the accompanying drawings and embodiments, right in order to which the objects, technical solutions and advantages of the application are more clearly understood
The application is further elaborated.It should be appreciated that specific embodiment described herein is only used to explain the application, and
It is not used in restriction the application.Meanwhile in the description of the present application, term " first ", " second " etc. are only used for distinguishing description, without
It can be interpreted as indication or suggestion relative importance.
It should be appreciated that ought use in this specification and in the appended claims, term " includes " instruction is described special
Sign, entirety, step, operation, the presence of element and/or component, but be not precluded one or more of the other feature, entirety, step,
Operation, the presence or addition of element, component and/or its set.
It is also understood that mesh of the term used in this present specification merely for the sake of description specific embodiment
And be not intended to limit the application.As present specification and it is used in the attached claims, unless on
Other situations are hereafter clearly indicated, otherwise " one " of singular, "one" and "the" are intended to include plural form.
It will be further appreciated that the term "and/or" used in present specification and the appended claims is
Refer to any combination and all possible combinations of one or more of associated item listed, and including these combinations.
As used in this specification and in the appended claims, term " if " can be according to context quilt
Be construed to " when ... " or " once " or " in response to determination " or " in response to detecting ".Similarly, phrase " if it is determined that " or
" if detecting [described condition or event] " can be interpreted to mean according to context " once it is determined that " or " in response to true
It is fixed " or " once detecting [described condition or event] " or " in response to detecting [described condition or event] ".
In order to illustrate the above-mentioned technical solution of the application, the following is a description of specific embodiments.
The mode for usually carrying out paster processing to image is synthesized in image in fact using the fixation material of pre-production
It is existing, for example, obtaining the paster of user's selection when taking pictures preview, the paster that user selects then is placed on camera and is obtained
Picture corresponding position；Alternatively, the paster that user selects to be placed on to the corresponding position of photo after the completion of taking pictures.However,
The displaying of these materials generally also rests on single machine or some Face datections, and material is relatively fixed, can not be according to increasing
The attribute for sticking on the target object of paper produces personalized paster.
For example, above-mentioned paster processing generally at most only will do it Face datection, so when the target object of shooting is human body
The corresponding position that the good paster of the pre-production that user selects is increased to face afterwards, for example, " cap " that pre-production is good
Paster, " glasses " paster or " blush " paster are added to the corresponding position of face；Without further to being attached on the person
The objects such as clothes, cap, shoes, ornaments, mobile phone detect, it is even more impossible to provide the paster for being able to reflect the object attribute, this
Kind paster processing mode is possible to that same paster can be made to be used in different images, causes paster processing to occur machine-made
Phenomenon reduces the expression effect of paster, and people can not usually obtain any intellectual relevant to object from paster
Content.
In the embodiment of the present application, by detecting the target object for including in the image to be processed and the target pair
As one or more sub-goal objects of attachment, then the characteristic information of each sub-goal object is extracted, generates and carry the feature
The corresponding paster inquiry instruction of each sub-goal object of information, to inquire to obtain every height according to the paster inquiry instruction
The corresponding paster of target object, and the paster is loaded onto the image to be processed on corresponding sub-goal object, it completes
Paster processing to one or more sub-goal objects in image to be processed；Since the application increases on sub-goal object
Paster is inquired according to the characteristic information of sub-goal object, is not the paster of pre-production, therefore can be to avoid same
One paster is used in different images, and there is a situation where influencing paster expression effect, the expression effect of paster is enhanced, no
It will use family and see machine-made paster, realize the beneficial effect for loading different pasters according to different sub-goal objects
Fruit, and the paster of multiple sub-goal objects can be loaded simultaneously.
A kind of implementation process schematic diagram of paster loading method provided by the embodiments of the present application as shown in figure 1, this method
Applied to terminal, can be executed by the paster loading device configured in terminal, suitable for the situation of paster expression effect need to be improved,
Including step 101 to step 104.
Step 101, image to be processed is obtained.
Wherein, above-mentioned terminal includes that smart phone, tablet computer, learning machine etc. are set configured with the terminal of paster loading device
It is standby.Also, the application such as application of taking pictures, browser, wechat can be installed on above-mentioned terminal device.
In some embodiments of the application, above-mentioned acquisition image to be processed be can be during acquisition camera preview
Preview frame image；Wherein, when preview frame image refers to application of taking pictures in preview state, camera acquires external optical signals and generates
Frame image.The data that camera acquires external optical signals output every time are known as frame data, and user opens taking pictures in terminal and answers
With rear, into preview mode, terminal is shown to obtain above-mentioned preview frame by obtaining the frame data of camera acquisition back
Image.
In some embodiments of the application, above-mentioned acquisition image to be processed can also be acquisition by taking pictures using bat
The image taken the photograph, alternatively, can be through the received image of other applications, for example, other received by wechat application
The image that wechat contact person sends；Alternatively, the image downloaded from internet by browser application；Also, it is above-mentioned to be processed
Image can be photograph image, be also possible to video image, be not construed as limiting herein to the source and form of image to be processed.
Step 102, one for detecting the target object for including in above-mentioned image to be processed and the attachment of above-mentioned target object
Or multiple sub-goal objects.
It is attached by detecting the target object for including in image to be processed and above-mentioned target object in the embodiment of the present application
One or more sub-goal objects, obtain the object for needing to carry out paster processing in image to be processed, that is, each sub-goal
Object.
That is, identifying that one of effect of target object in image to be processed obtains for setting in the embodiment of the present application
The acquisition range of sub-goal object, the i.e. range of paster process object are taken, disposably to paste to multiple sub-goal objects
When paper loads, more targetedly it can reduce the calculation amount of paster processing.
In the embodiment of the present application, by the one or more target objects for including in detection image to be processed, and each
One or more sub-goal objects of target object attachment, obtain one that needs to carry out paster processing in image to be processed or more
A object, that is, one or more sub-goal objects.It is relatively simple to solve current paster object, can only to wherein some or
Certain target object carries out paster processing, for example, face, clothes, and paster processing can not be carried out to multiple sub-goal objects
The technical issues of.
Wherein, target object refers to the object that main body is occupied in above-mentioned image to be processed, for example, above-mentioned image to be processed is
When character image, then the target object is human body, and when above-mentioned image to be processed is indoor decorative image, then the target object is pendulum
If the cabinet of article, sofa, wall, desk etc. occupy the object of main body.It should be noted that the mesh in above-mentioned image to be processed
It is either one or more to mark object, for example, then the target object can when in image to be processed including multiple personages
Think multiple human bodies.
Above-mentioned sub-goal object refers to the object for needing to load paster being attached on target object.
It, can be by algorithm of target detection to the target in above-mentioned image to be processed in some embodiments of the application
Object and the target sub-object being attached on target object are detected, and common algorithm of target detection has local binary patterns
(Local Binary Pattern, LBP) algorithm, orientation Gradient Features combination supporting vector machine model and convolutional neural networks
(Convolutional Neural Network, CNN) model etc..Wherein, compared to other algorithm of target detection, convolutional Neural
Network model may be implemented that therefore, trained convolutional Neural net can be selected to the more accurate quickly detection of target object
One or more sub-goal objects of target object and target object attachment in the above-mentioned image to be processed of network model inspection.
It is above-mentioned using the target object in the above-mentioned image to be processed of trained convolutional neural networks model inspection before,
Need first to obtain trained convolutional neural networks model.The trained convolutional neural networks model is according to each sample graph
The training of testing result corresponding to picture and each sample image obtains, wherein detection knot corresponding to each sample image
One or more sub-goals pair of the fruit to all target objects and the target object attachment for indicating to include in the sample image
As.
Optionally, the training step of above-mentioned convolutional neural networks model may include: to obtain sample image and sample graph
As corresponding testing result；Above-mentioned sample image is detected using convolutional neural networks model, is adjusted according to testing result
The parameter of above-mentioned convolutional neural networks model, until above-mentioned convolutional neural networks model adjusted can detecte out above-mentioned sample
All target objects in image, or detect one of target object in above-mentioned sample image and target object attachment
Or the accuracy rate of multiple sub-goal objects is greater than preset value, then using the convolutional neural networks model adjusted as trained
Convolutional neural networks model.Wherein, the parameter of above-mentioned convolutional neural networks model may include every in convolutional neural networks model
The weight of a convolutional layer, deviation, regression function coefficient, can also include of learning rate, the number of iterations, every layer of neuron
Number etc..
It should be noted that being herein only that the detection method of above-mentioned target object is illustrated, it is not expressed as
Limitation to the application protection scope, other methods that target object detection may be implemented are equally applicable in the application, herein,
It will not enumerate.
Step 103, the characteristic information of each sub-goal object is extracted, and each sub-goal is generated according to features described above information
The corresponding paster inquiry instruction of object.
After detecting each sub-goal object, need to extract the characteristic information of each sub-goal object, so as to basis
Features described above information generates the corresponding paster inquiry instruction of each sub-goal object, and is obtained according to the paster inquiry instruction each
The corresponding paster of sub-goal object.
Wherein, features described above information can be the geometry characteristic information of sub-goal object, or to utilize LBP algorithm
The LBP feature of extraction, or for using scale invariant feature conversion (Scale-invariant feature transform,
SIFT) the SIFT feature that algorithm extracts, is different from other sub-goal objects for above-mentioned sub-goal object by features described above information,
To generate the corresponding paster inquiry instruction of each sub-goal object according to features described above information, the paster inquiry instruction is for looking into
Ask paster corresponding with each sub-goal object.
Step 104, the corresponding paster of each sub-goal object is obtained according to paster inquiry instruction, and by paster be loaded onto
It handles in image on corresponding sub-goal object.
It is above-mentioned to can be according to the corresponding paster of each sub-goal object of paster inquiry instruction acquisition in the embodiment of the present application
Local data base is inquired according to paster inquiry instruction and obtains the corresponding paster of each sub-goal object, or to be inquired according to paster
Instructions query third-party server obtains the corresponding paster of each sub-goal object, so as to the paster that will acquire be loaded onto it is to be processed
In image on corresponding sub-goal object.
Optionally, above-mentioned that the corresponding paster of each sub-goal object is obtained according to paster inquiry instruction, comprising: by above-mentioned patch
Paper inquiry instruction is sent to server；Receive each sub-goal object pair that server is inquired according to above-mentioned paster inquiry instruction
The paster answered.
For example, the paster inquiry instruction for carrying sub-goal characteristics of objects information is sent to server, server is received
After the paster inquiry instruction, the pre-stored characteristic information of server is searched using the characteristic information that the paster inquiry instruction carries
With the corresponding relationship list of paster information, the corresponding paster of sub-goal object with this feature information is obtained.
In the embodiment of the present application, adhered to by detecting the target object for including in image to be processed and target object
One or more sub-goal objects, then the characteristic information of each sub-goal object is extracted, it generates and carries the every of features described above information
The corresponding paster inquiry instruction of a sub- target object, to inquire to obtain each sub-goal object according to above-mentioned paster inquiry instruction
Corresponding paster, and above-mentioned paster is loaded onto above-mentioned image to be processed on corresponding sub-goal object, it completes to be processed
The paster of one or more sub-goal objects in image is handled；Since the paster that the application increases on sub-goal object is root
It is inquired according to the characteristic information of sub-goal object, is not the paster of pre-production, therefore can be to avoid same paster quilt
It uses in different images, and there is a situation where influence paster expression effect.
Optionally, as shown in Fig. 2, in above-mentioned steps 103, the corresponding patch of each sub-goal object is generated according to characteristic information
Paper inquiry instruction may include: step 201 to step 202.
Step 201, the paster type that user chooses is obtained；Above-mentioned paster type includes price paster, brand paster, purchase
Link the subject description paster of paster and target object；
Step 202, the corresponding paster of each sub-goal object is generated according to features described above information and above-mentioned paster type
Inquiry instruction.
That is, above-mentioned paster inquiry instruction also carries useful in addition to carrying the corresponding characteristic information of sub-goal object
The paster type of family selection.
For example, as shown in figure 3, then detecting the mesh for including in image to be processed when above-mentioned image to be processed is character image
Mark one or more sub-goal objects of object and target object attachment, comprising: detect the target for including in image to be processed
Human body and one or more sub-goal objects of target body attachment.Wherein, above-mentioned multiple sub-goal objects can be the person
On the attachment such as clothes, cap, shoes, trousers, knapsack, glasses, necklace, ear pendant, ring, bracelet, mobile phone, wrist-watch on the person
Sub-goal object.
Since the sub-goal object of target object attachment is more, and each sub-goal object has its corresponding a variety of category
Property information, therefore, to above-mentioned character image carry out paster processing when, firstly, it is necessary to obtain user paster load interface 31
On the paster type chosen, generate each sub-goal object pair further according to the characteristic information of the paster type and sub-goal object
The paster inquiry instruction answered.
For example, as shown in figure 4, if user is price paster 41 and buys in the paster type that paster load interface is chosen
When linking paster 42, then generates and carry the corresponding characteristic information of each sub-goal object, price paster type and purchase link patch
The paster inquiry instruction of sheet type, and when inquiring the corresponding price of sub-goal object and purchase link, with price paster 41 '
It is loaded on the corresponding sub-goal object of above-mentioned character image with the form of purchase link paster 42 '.
Optionally, above-mentioned that paster is loaded onto corresponding specific item in above-mentioned image to be processed as shown in figure 5, in step 104
It marks on object, comprising: step 501 to step 502.
In step 501, if paster quantity is greater than preset threshold, the corresponding paster label of above-mentioned paster is loaded onto above-mentioned
In image to be processed on corresponding sub-goal object；
In step 502, when receiving the instruction of paster mark triggers, above-mentioned paster mark triggers are instructed into corresponding paster
It is loaded onto above-mentioned image to be processed on corresponding sub-goal object；Above-mentioned paster mark triggers instruction clicks above-mentioned patch by user
Paper mark triggers.
Above-mentioned preset threshold can be numerical value set by user, or the numerical value being arranged when default setting.
In the embodiment of the present application, by the way that when paster quantity is greater than preset threshold, the corresponding paster of above-mentioned paster is marked
It is loaded onto above-mentioned image to be processed on corresponding sub-goal object, rather than paster is loaded directly into above-mentioned image to be processed
In corresponding sub-goal object so that image to be processed will not be blocked by paster, only when user clicks above-mentioned paster label,
Just corresponding paster is instructed to be loaded onto above-mentioned image to be processed on corresponding sub-goal object, just above-mentioned paster mark triggers
Image to be processed can be preferably checked in user.
As shown in fig. 6, above-mentioned paster label can be the point of different colours or the small circle of different colours, for referring to
Show different types of paster, for example, paster label 61 is used to indicate price paster, paster label 62 is used to indicate purchase link patch
Paper.
Optionally, above-mentioned acquisition image to be processed, comprising: obtain the preview frame image during camera preview；Correspondingly,
The one or more sub-goal objects for target object and the target object attachment for including in above-mentioned detection image to be processed, packet
It includes: during camera preview, treating reference object and carry out structure light detection, and depth of field detection is combined to obtain in object to be captured
Target object and above-mentioned target object on one or more sub-goal objects for adhering to, obtain wrapping in above-mentioned preview frame image
The one or more sub-goal objects adhered on the target object and above-mentioned target object contained.
In the embodiment of the present application, by obtaining preview frame image, and in camera preview mistake when camera take pictures preview
Cheng Zhong treats reference object and carries out structure light detection, in combination with depth of field detection obtain the target object in object to be captured with
And the one or more sub-goal objects adhered on above-mentioned target object, obtain the target object for including in above-mentioned preview frame image
And the one or more sub-goal objects adhered on above-mentioned target object, so as to the sub-goal pair in above-mentioned preview frame image
As carrying out paster loading processing.
For example, when user on the way encounters the more unique people of a clothing matching, using it as pair of shooting preview
As, then information such as available brand, subject description and price of dress ornament arranged in pairs or groups with it, and load exists in the form of paster
It is for reference on preview frame image, so that user can be arranged in pairs or groups with real-time capture to good-looking clothes.
Wherein, structure light detection includes the detection methods such as Moire fringe detection method, Stereo Vision.Specifically, not
Your jail-bar detection approach uses two groups of gratings, a key light grid, and a benchmark grating detects contour surface by benchmark grating
Key light grid, and calculate according to striped rule the contoured surface type of object；Have the characteristics that measurement accuracy is higher.And stereoscopic vision
Method then utilizes imaging device from the two images of different position acquisition testees, by calculating the position between image corresponding points
Deviation obtains the three-dimensional geometric information of object, does not influence vulnerable to factors such as the object planes such as material color property and bias lights.
In the embodiment of the present application, the target object and above-mentioned target object in structure light detection object to be captured are being utilized
While one or more sub-goal objects of upper attachment, also by combining depth of field detection to obtain the target pair in object to be captured
As and above-mentioned target object on one or more sub-goal objects for adhering to, can effectively exclude not to be attached to target object
Object so that the testing result of sub-goal object is more accurate.
For example, the same depth of field will be in target object, and there is the object of intersection as above-mentioned specific item with target object
Mark object.
Optionally, it is above-mentioned above-mentioned paster is loaded onto above-mentioned image to be processed on corresponding sub-goal object after, also
It include: the image file that the image to be processed for completing paster load is saved as to Exif file format.
Wherein, Exif is a kind of image file format, when storing image data, can be inserted with photo in data header and clap
Information is taken the photograph, for example, the various shooting conditions such as aperture, shutter, white balance, ISO, focal length, date-time and camera brand, type
Number, color coding, shooting when the information such as the sound recorded and GPS geo-location system data, thumbnail.
In the embodiment of the present application, by the image that the image to be processed for completing paster load is saved as to Exif file format
File, so that the paster information completed in the image to be processed of paster load can be also saved, for example, linking paster to purchase
In include purchase link saved, so as to subsequent user links paster by the purchase clicked in image to be processed can chain
It is connected to corresponding purchase webpage.
It should be noted that for the various method embodiments described above, for simple description, therefore, it is stated as a series of
Combination of actions, but those skilled in the art should understand that, the present invention is not limited by the sequence of acts described because
According to the present invention, some steps may be performed in other sequences or simultaneously.
Fig. 7 shows a kind of structural schematic diagram of paster loading device 700 provided by the embodiments of the present application, including obtains single
Member 701, detection unit 702, generation unit 703 and loading unit 704.
Acquiring unit 701, for obtaining image to be processed；
Detection unit 702, it is attached for detecting the target object for including in above-mentioned image to be processed and above-mentioned target object
One or more sub-goal objects；
Generation unit 703 generates often for extracting the characteristic information of each sub-goal object, and according to features described above information
The corresponding paster inquiry instruction of a sub- target object；
Loading unit 704, for obtaining the corresponding paster of each sub-goal object according to above-mentioned paster inquiry instruction, and will
Above-mentioned paster is loaded onto above-mentioned image to be processed on corresponding sub-goal object.
In some embodiments of the application, above-mentioned generation unit 703 is specifically used for: obtaining the paster class that user chooses
Type；Above-mentioned paster type includes the subject description paster of price paster, brand paster, purchase link paster and target object；
The corresponding paster inquiry instruction of each sub-goal object is generated according to features described above information and above-mentioned paster type.
In some embodiments of the application, above-mentioned loading unit 704, if being specifically used for paster quantity is greater than default threshold
The corresponding paster label of above-mentioned paster is then loaded onto above-mentioned image to be processed on corresponding sub-goal object by value；It is receiving
To when the instruction of paster mark triggers, corresponding paster is instructed to be loaded onto above-mentioned paster mark triggers right in above-mentioned image to be processed
On the sub-goal object answered；Above-mentioned paster mark triggers instruction clicks above-mentioned paster mark triggers by user.
In some embodiments of the application, above-mentioned acquiring unit 701, during acquisition camera preview
Preview frame image.
Correspondingly, above-mentioned detection unit 702 is specifically used for, during camera preview, treats reference object and carry out structure
Light detection, and combine depth of field detection obtain one adhered on target object and above-mentioned target object in object to be captured or
Multiple sub-goal objects obtain one adhered on the target object and above-mentioned target object that include in above-mentioned preview frame image
Or multiple sub-goal objects.
Correspondingly, above-mentioned detection unit 702 also particularly useful for, detect the target body for including in above-mentioned image to be processed,
And one or more sub-goal objects of above-mentioned target body attachment.
Optionally, above-mentioned generation unit 703 is specifically used for, and above-mentioned paster inquiry instruction is sent to server；Receive clothes
The corresponding paster of each sub-goal object that business device is inquired according to above-mentioned paster inquiry instruction.
Optionally, above-mentioned paster loading device further includes storage unit, is specifically used for, above-mentioned above-mentioned paster to be loaded onto
In image to be processed on corresponding sub-goal object after, will complete paster load image to be processed save as Exif tray
The image file of formula.
It should be noted that for convenience and simplicity of description, the specific works mistake of the paster loading device 700 of foregoing description
Journey, can be with reference to the corresponding process of method described in above-mentioned Fig. 1 to Fig. 6, and details are not described herein.
As shown in figure 8, the application provides a kind of terminal for realizing above-mentioned paster loading method, which can be shifting
Dynamic terminal, the mobile terminal can be the terminals such as smart phone, tablet computer, PC (PC), learning machine, comprising: one
Or multiple input equipments 83 (one is only shown in Fig. 8) and one or more output equipment 84 (one is only shown in Fig. 8).Processing
Device 81, memory 82, input equipment 83 and output equipment 84 are connected by bus 85.
It should be appreciated that in the embodiment of the present application, alleged processor 81 can be central processing unit (Central
Processing Unit, CPU), which can also be other general processors, digital signal processor (Digital
Signal Processor, DSP), specific integrated circuit (Application Specific Integrated Circuit,
ASIC), field programmable gate array (Field-Programmable Gate Array, FPGA) or other programmable logic
Device, discrete gate or transistor logic, discrete hardware components etc..General processor can be microprocessor or this at
Reason device is also possible to any conventional processor etc..
Input equipment 83 may include that dummy keyboard, Trackpad, fingerprint adopt sensor (for acquiring the finger print information of user
With the directional information of fingerprint), microphone etc., output equipment 84 may include display, loudspeaker etc..
Memory 82 may include read-only memory and random access memory, and provide instruction sum number to processor 81
According to.Part or all of memory 82 can also include nonvolatile RAM.For example, memory 82 can be with
The information of storage device type.
Above-mentioned memory 82 is stored with computer program, and above-mentioned computer program can be run on above-mentioned processor 81, example
Such as, above-mentioned computer program is the program of paster loading method.Above-mentioned processor 81 is realized when executing above-mentioned computer program
State the step in paster loading method embodiment, such as step 101 shown in FIG. 1 is to step 104.Alternatively, above-mentioned processor 81
The function of each module/unit in above-mentioned each Installation practice, such as unit shown in Fig. 7 are realized when executing above-mentioned computer program
701 to 704 function.
Above-mentioned computer program can be divided into one or more module/units, and said one or multiple modules/mono-
Member is stored in above-mentioned memory 82, and is executed by above-mentioned processor 81, to complete the application.Said one or multiple moulds
Block/unit can be the series of computation machine program instruction section that can complete specific function, the instruction segment by describe it is above-mentioned based on
Implementation procedure of the calculation machine program in the above-mentioned terminal taken pictures.For example, above-mentioned computer program can be divided into acquisition
Unit, detection unit, generation unit and loading unit, each unit concrete function are as follows: acquiring unit, for obtaining figure to be processed
Picture；Detection unit, for detecting one of the target object for including in above-mentioned image to be processed and the attachment of above-mentioned target object
Or multiple sub-goal objects；Generation unit, for extracting the characteristic information of each sub-goal object, and according to features described above information
Generate the corresponding paster inquiry instruction of each sub-goal object；Loading unit, it is every for being obtained according to above-mentioned paster inquiry instruction
The corresponding paster of a sub- target object, and above-mentioned paster is loaded onto above-mentioned image to be processed on corresponding sub-goal object.
It is apparent to those skilled in the art that for convenience of description and succinctly, only with above-mentioned each function
Can unit, module division progress for example, in practical application, can according to need and by above-mentioned function distribution by different
Functional unit, module are completed, i.e., the internal structure of above-mentioned apparatus is divided into different functional unit or module, more than completing
The all or part of function of description.Each functional unit in embodiment, module can integrate in one processing unit, can also
To be that each unit physically exists alone, can also be integrated in one unit with two or more units, it is above-mentioned integrated
Unit both can take the form of hardware realization, can also realize in the form of software functional units.In addition, each function list
Member, the specific name of module are also only for convenience of distinguishing each other, the protection scope being not intended to limit this application.Above system
The specific work process of middle unit, module, can refer to corresponding processes in the foregoing method embodiment, and details are not described herein.
In the above-described embodiments, it all emphasizes particularly on different fields to the description of each embodiment, is not described in detail or remembers in some embodiment
The part of load may refer to the associated description of other embodiments.
Those of ordinary skill in the art may be aware that list described in conjunction with the examples disclosed in the embodiments of the present disclosure
Member and algorithm steps can be realized with the combination of electronic hardware or computer software and electronic hardware.These functions are actually
It is implemented in hardware or software, the specific application and design constraint depending on technical solution.Professional technician
Each specific application can be used different methods to achieve the described function, but this realization is it is not considered that exceed
Scope of the present application.
In embodiment provided herein, it should be understood that disclosed device/terminal and method can pass through
Other modes are realized.For example, device/terminal embodiment described above is only schematical, for example, above-mentioned module or
The division of unit, only a kind of logical function partition, there may be another division manner in actual implementation, such as multiple units
Or component can be combined or can be integrated into another system, or some features can be ignored or not executed.Another point, institute
Display or the mutual coupling or direct-coupling or communication connection discussed can be through some interfaces, device or unit
INDIRECT COUPLING or communication connection can be electrical property, mechanical or other forms.
Above-mentioned unit as illustrated by the separation member may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, it can and it is in one place, or may be distributed over multiple
In network unit.It can select some or all of unit therein according to the actual needs to realize the mesh of this embodiment scheme
's.
It, can also be in addition, each functional unit in each embodiment of the application can integrate in one processing unit
It is that each unit physically exists alone, can also be integrated in one unit with two or more units.Above-mentioned integrated list
Member both can take the form of hardware realization, can also realize in the form of software functional units.
If above-mentioned integrated module/unit be realized in the form of SFU software functional unit and as independent product sale or
In use, can store in a computer readable storage medium.Based on this understanding, the application realizes above-mentioned implementation
All or part of the process in example method, can also instruct relevant hardware to complete, above-mentioned meter by computer program
Calculation machine program can be stored in a computer readable storage medium, the computer program when being executed by processor, it can be achieved that on
The step of stating each embodiment of the method.Wherein, above-mentioned computer program includes computer program code, above-mentioned computer program generation
Code can be source code form, object identification code form, executable file or certain intermediate forms etc..Above-mentioned computer-readable medium
It may include: any entity or device, recording medium, USB flash disk, mobile hard disk, magnetic that can carry above-mentioned computer program code
Dish, CD, computer storage, read-only memory (Read-Only Memory, ROM), random access memory (Random
Access Memory, RAM), electric carrier signal, telecommunication signal and software distribution medium etc..It should be noted that above-mentioned meter
The content that calculation machine readable medium includes can carry out increase and decrease appropriate according to the requirement made laws in jurisdiction with patent practice,
It such as does not include electric carrier signal and telecommunications according to legislation and patent practice, computer-readable medium in certain jurisdictions
Signal.
Above above-described embodiment is only to illustrate the technical solution of the application, rather than its limitations；Although referring to aforementioned reality
Example is applied the application is described in detail, those skilled in the art should understand that: it still can be to aforementioned each
Technical solution documented by embodiment is modified or equivalent replacement of some of the technical features；And these are modified
Or replacement, the spirit and scope of each embodiment technical solution of the application that it does not separate the essence of the corresponding technical solution should all
Comprising within the scope of protection of this application.
Claims (10)
1. a kind of paster loading method characterized by comprising
Obtain image to be processed；
Detect one or more sub-goals of the target object for including in the image to be processed and target object attachment
Object；
The characteristic information of each sub-goal object is extracted, and the corresponding patch of each sub-goal object is generated according to the characteristic information
Paper inquiry instruction；
Obtain the corresponding paster of each sub-goal object according to the paster inquiry instruction, and by the paster be loaded onto it is described to
It handles in image on corresponding sub-goal object.
2. paster loading method as described in claim 1, which is characterized in that described to generate every height according to the characteristic information
The corresponding paster inquiry instruction of target object, comprising:
Obtain the paster type that user chooses；The paster type include price paster, brand paster, purchase link paster and
The subject description paster of target object；
The corresponding paster inquiry instruction of each sub-goal object is generated according to the characteristic information and the paster type.
3. paster loading method as claimed in claim 1 or 2, which is characterized in that it is described by the paster be loaded onto it is described to
It handles in image on corresponding sub-goal object, comprising:
If paster quantity is greater than preset threshold, it is right in the image to be processed that the corresponding paster label of the paster is loaded onto
On the sub-goal object answered；
When receiving the instruction of paster mark triggers, corresponding paster is instructed to be loaded onto the paster mark triggers described wait locate
It manages in image on corresponding sub-goal object；The paster mark triggers instruction clicks the paster mark triggers by user.
4. paster loading method as claimed in claim 3, which is characterized in that described to obtain image to be processed, comprising:
Obtain the preview frame image during camera preview；
Correspondingly, one of the target object and target object attachment that include in the detection image to be processed
Or multiple sub-goal objects, comprising:
During camera preview, treats reference object and carry out structure light detection, and depth of field detection is combined to obtain object to be captured
In target object and the target object on one or more sub-goal objects for adhering to, obtain in the preview frame image
The one or more sub-goal objects adhered on the target object and the target object for including.
5. paster loading method as described in claim 1, which is characterized in that include in the detection image to be processed
Target object and one or more sub-goal objects of target object attachment, comprising:
Detect one or more sub-goals of the target body for including in the image to be processed and target body attachment
Object.
6. paster loading method as described in claim 1, which is characterized in that described to be obtained often according to the paster inquiry instruction
The corresponding paster of a sub- target object, comprising:
The paster inquiry instruction is sent to server；
Receive the corresponding paster of each sub-goal object that server is inquired according to the paster inquiry instruction.
7. paster loading method as described in claim 1, which is characterized in that it is described the paster is loaded onto it is described to be processed
In image on corresponding sub-goal object after, comprising:
The image to be processed for completing paster load is saved as to the image file of Exif file format.
8. a kind of paster loading device characterized by comprising
Acquiring unit, for obtaining image to be processed；
Detection unit, for detecting the one of the target object for including in the image to be processed and target object attachment
A or multiple sub-goal objects；
Generation unit generates each specific item for extracting the characteristic information of each sub-goal object, and according to the characteristic information
Mark the corresponding paster inquiry instruction of object；
Loading unit, for obtaining the corresponding paster of each sub-goal object according to the paster inquiry instruction, and by the patch
Paper is loaded onto the image to be processed on corresponding sub-goal object.
9. a kind of terminal, including memory, processor and storage can be run in the memory and on the processor
Computer program, which is characterized in that the processor is realized when executing the computer program as claim 1 to 7 is any
The step of one the method.
10. a kind of computer readable storage medium, the computer-readable recording medium storage has computer program, and feature exists
In realization is such as the step of claim 1 to 7 any one the method when the computer program is executed by processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810867377.5A CN109147007B (en) | 2018-08-01 | 2018-08-01 | Label loading method, label loading device, terminal and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810867377.5A CN109147007B (en) | 2018-08-01 | 2018-08-01 | Label loading method, label loading device, terminal and computer readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109147007A true CN109147007A (en) | 2019-01-04 |
| CN109147007B CN109147007B (en) | 2023-09-01 |
Family
ID=64798765
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810867377.5A Active CN109147007B (en) | 2018-08-01 | 2018-08-01 | Label loading method, label loading device, terminal and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109147007B (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111260600A (en) * | 2020-01-21 | 2020-06-09 | 维沃移动通信有限公司 | Image processing method, electronic device and medium |
| CN112001872A (en) * | 2020-08-26 | 2020-11-27 | 北京字节跳动网络技术有限公司 | Information display method, device and storage medium |
| CN112132859A (en) * | 2019-06-25 | 2020-12-25 | 北京字节跳动网络技术有限公司 | Sticker generation method, apparatus, medium, and electronic device |
| CN112463268A (en) * | 2019-09-06 | 2021-03-09 | 北京字节跳动网络技术有限公司 | Application data processing method, device, equipment and storage medium |
| CN113473246A (en) * | 2020-03-30 | 2021-10-01 | 阿里巴巴集团控股有限公司 | Media file publishing method and device and electronic equipment |
| CN114598939A (en) * | 2022-04-25 | 2022-06-07 | 镁佳(北京)科技有限公司 | Video watermark adding method and device and electronic equipment |
| RU2817182C1 (en) * | 2020-08-26 | 2024-04-11 | Бейджин Байтдэнс Нетворк Текнолоджи Ко., Лтд. | Information display method, device and data medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103218854A (en) * | 2013-04-01 | 2013-07-24 | 成都理想境界科技有限公司 | Method for realizing component marking during augmented reality process and augmented reality system |
| CN105095362A (en) * | 2015-06-25 | 2015-11-25 | 深圳码隆科技有限公司 | Image display method and device based on target object |
| CN105678686A (en) * | 2015-12-30 | 2016-06-15 | 北京金山安全软件有限公司 | Picture processing method and device |
| CN106777329A (en) * | 2017-01-11 | 2017-05-31 | 维沃移动通信有限公司 | The processing method and mobile terminal of a kind of image information |
| CN107169135A (en) * | 2017-06-12 | 2017-09-15 | 广州市动景计算机科技有限公司 | Image processing method, device and electronic equipment |
| US20170316034A1 (en) * | 2015-01-23 | 2017-11-02 | Alibaba Group Holding Limited | Information publishing method and apparatus |
| CN107343211A (en) * | 2016-08-19 | 2017-11-10 | 北京市商汤科技开发有限公司 | Method of video image processing, device and terminal device |
| CN107993131A (en) * | 2017-12-27 | 2018-05-04 | 广东欧珀移动通信有限公司 | Wear to take and recommend method, apparatus, server and storage medium |
-
2018
- 2018-08-01 CN CN201810867377.5A patent/CN109147007B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103218854A (en) * | 2013-04-01 | 2013-07-24 | 成都理想境界科技有限公司 | Method for realizing component marking during augmented reality process and augmented reality system |
| US20170316034A1 (en) * | 2015-01-23 | 2017-11-02 | Alibaba Group Holding Limited | Information publishing method and apparatus |
| CN105095362A (en) * | 2015-06-25 | 2015-11-25 | 深圳码隆科技有限公司 | Image display method and device based on target object |
| CN105678686A (en) * | 2015-12-30 | 2016-06-15 | 北京金山安全软件有限公司 | Picture processing method and device |
| CN107343211A (en) * | 2016-08-19 | 2017-11-10 | 北京市商汤科技开发有限公司 | Method of video image processing, device and terminal device |
| CN106777329A (en) * | 2017-01-11 | 2017-05-31 | 维沃移动通信有限公司 | The processing method and mobile terminal of a kind of image information |
| CN107169135A (en) * | 2017-06-12 | 2017-09-15 | 广州市动景计算机科技有限公司 | Image processing method, device and electronic equipment |
| CN107993131A (en) * | 2017-12-27 | 2018-05-04 | 广东欧珀移动通信有限公司 | Wear to take and recommend method, apparatus, server and storage medium |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112132859A (en) * | 2019-06-25 | 2020-12-25 | 北京字节跳动网络技术有限公司 | Sticker generation method, apparatus, medium, and electronic device |
| CN112463268A (en) * | 2019-09-06 | 2021-03-09 | 北京字节跳动网络技术有限公司 | Application data processing method, device, equipment and storage medium |
| CN111260600A (en) * | 2020-01-21 | 2020-06-09 | 维沃移动通信有限公司 | Image processing method, electronic device and medium |
| CN111260600B (en) * | 2020-01-21 | 2023-08-22 | 维沃移动通信有限公司 | Image processing method, electronic equipment and medium |
| CN113473246B (en) * | 2020-03-30 | 2023-09-01 | 阿里巴巴集团控股有限公司 | Method and device for publishing media file and electronic equipment |
| CN113473246A (en) * | 2020-03-30 | 2021-10-01 | 阿里巴巴集团控股有限公司 | Media file publishing method and device and electronic equipment |
| KR20230051294A (en) * | 2020-08-26 | 2023-04-17 | 베이징 바이트댄스 네트워크 테크놀로지 컴퍼니, 리미티드 | Information display method, device and storage medium |
| WO2022042624A1 (en) * | 2020-08-26 | 2022-03-03 | 北京字节跳动网络技术有限公司 | Information display method and device, and storage medium |
| CN112001872B (en) * | 2020-08-26 | 2021-09-14 | 北京字节跳动网络技术有限公司 | Information display method, device and storage medium |
| CN112001872A (en) * | 2020-08-26 | 2020-11-27 | 北京字节跳动网络技术有限公司 | Information display method, device and storage medium |
| JP2023541125A (en) * | 2020-08-26 | 2023-09-28 | 北京字節跳動網絡技術有限公司 | Information display method, device and storage medium |
| JP7421010B2 (en) | 2020-08-26 | 2024-01-23 | 北京字節跳動網絡技術有限公司 | Information display method, device and storage medium |
| US11922721B2 (en) | 2020-08-26 | 2024-03-05 | Beijing Bytedance Network Technology Co., Ltd. | Information display method, device and storage medium for superimposing material on image |
| KR102650900B1 (en) * | 2020-08-26 | 2024-03-22 | 베이징 바이트댄스 네트워크 테크놀로지 컴퍼니, 리미티드 | Information display methods, devices and storage media |
| RU2817182C1 (en) * | 2020-08-26 | 2024-04-11 | Бейджин Байтдэнс Нетворк Текнолоджи Ко., Лтд. | Information display method, device and data medium |
| CN114598939A (en) * | 2022-04-25 | 2022-06-07 | 镁佳(北京)科技有限公司 | Video watermark adding method and device and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109147007B (en) | 2023-09-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109147007A (en) | Paster loading method, device, terminal and computer readable storage medium | |
| US11915352B2 (en) | Processing user selectable product images and facilitating visualization-assisted virtual dressing | |
| US20190244407A1 (en) | System, device, and method of virtual dressing utilizing image processing, machine learning, and computer vision | |
| CN108765278A (en) | A kind of image processing method, mobile terminal and computer readable storage medium | |
| CN111325226B (en) | Information presentation method and device | |
| CN110021061A (en) | Collocation model building method, dress ornament recommended method, device, medium and terminal | |
| TR201815349T4 (en) | Improved virtual trial simulation service. | |
| CN107018323B (en) | Control method, control device and electronic device | |
| CN111787242A (en) | Method and apparatus for virtual fitting | |
| CN112614085A (en) | Object detection method and device and terminal equipment | |
| CN109117773A (en) | A kind of characteristics of image point detecting method, terminal device and storage medium | |
| CN106027902B (en) | A kind of photographic method and mobile terminal | |
| KR20140071693A (en) | Method for measuring foot size using autofocus | |
| CN106462772A (en) | Invariant-based dimensional reduction of object recognition features, systems and methods | |
| JP2017076315A (en) | Image processing device, image processing method, and program | |
| CN107633237A (en) | Image background segmentation method, device, equipment and medium | |
| CN110555903A (en) | Image processing method and device | |
| CN111506758A (en) | Method and device for determining article name, computer equipment and storage medium | |
| CN108875654A (en) | A kind of face characteristic acquisition method and device | |
| CN109255768A (en) | Image completion method, apparatus, terminal and computer readable storage medium | |
| CN109272546A (en) | A kind of fry length measurement method and system | |
| CN109726756A (en) | Image processing method, device, electronic equipment and storage medium | |
| CN109859216A (en) | Distance measuring method, device, equipment and storage medium based on deep learning | |
| CN107145741B (en) | Ear diagnosis data acquisition method and device based on image analysis | |
| CN108898649A (en) | Image processing method and device |
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 |