CN110231960A - A kind of target screen determines method, apparatus and storage medium - Google Patents
A kind of target screen determines method, apparatus and storage medium Download PDFInfo
- Publication number
- CN110231960A CN110231960A CN201810181679.7A CN201810181679A CN110231960A CN 110231960 A CN110231960 A CN 110231960A CN 201810181679 A CN201810181679 A CN 201810181679A CN 110231960 A CN110231960 A CN 110231960A
- Authority
- CN
- China
- Prior art keywords
- image
- screen
- target screen
- classification
- target
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 40
- 238000012545 processing Methods 0.000 claims abstract description 19
- 238000010801 machine learning Methods 0.000 claims description 12
- 238000012795 verification Methods 0.000 claims description 12
- 238000013135 deep learning Methods 0.000 claims description 6
- 238000012706 support-vector machine Methods 0.000 claims description 6
- 238000012937 correction Methods 0.000 claims description 2
- 238000004891 communication Methods 0.000 abstract description 2
- 238000013527 convolutional neural network Methods 0.000 description 6
- 235000013399 edible fruits Nutrition 0.000 description 5
- 238000002372 labelling Methods 0.000 description 3
- 230000006399 behavior Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 210000003128 head Anatomy 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 210000004709 eyebrow Anatomy 0.000 description 1
- 210000000887 face Anatomy 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000002618 waking effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/44—Arrangements for executing specific programs
- G06F9/4401—Bootstrapping
- G06F9/4418—Suspend and resume; Hibernate and awake
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/44—Arrangements for executing specific programs
- G06F9/4401—Bootstrapping
Landscapes
- Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Computer Security & Cryptography (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Image Analysis (AREA)
- Collating Specific Patterns (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
The embodiment of the invention discloses a kind of target screens to determine method, apparatus and storage medium, belongs to communication technique field.The method is suitable for the terminal equipped at least two screens, comprising: obtains the image of the image collecting device shooting of at least one screen；The image classification that classification processing obtains described image is carried out to described image；It is corresponding with target screen to judge whether described image classification is marked as；Target screen is determined according to judging result.Using the embodiment of the present invention, image classification is carried out by the image that the camera to different screens acquires, target screen is determined from multiple screens according to classification results and target screen corresponding relationship, compared with the prior art relies on merely face or fingerprint to determine target screen, not only increase accuracy rate, and whole process is participated in without user, improves user experience.
Description
Technical field
The present embodiments relate to communication technique fields more particularly to a kind of target screen to determine method, apparatus and storage
Medium.
Background technique
In recent years, intelligent terminal (such as mobile phone) is pursuing always the development trend of large screen, and still, the increase of screen is inevitable
The portability that will affect terminal carrying, when screen increases to a certain extent, people pursued large screen vision and to intelligent ends
Just there is contradiction in the portability requirements at end, in this case, double screen terminal occur.Double screen terminal is set there are two screen,
When user's wake-up device, it is thus necessary to determine which screen waken up.
Therefore, it is necessary to which providing a kind of target screen determines method, apparatus and storage medium, make the end with multiple screens
End can accurately wake up the screen close to user side.
Summary of the invention
In view of this, a kind of target screen of being designed to provide of the embodiment of the present invention determines that method, apparatus and storage are situated between
Matter needs user to participate in solve the terminal with multiple screens in the prior art when waking up screen, and accuracy rate is not high
Problem.
It is as follows that the embodiment of the present invention solves technical solution used by above-mentioned technical problem:
First aspect according to an embodiment of the present invention provides a kind of target screen and determines method, is suitable for being equipped at least
The terminal of two screens, which comprises
Obtain the image of the image collecting device shooting of at least one screen；
The image classification that classification processing obtains described image is carried out to described image；
It is corresponding with target screen to judge whether described image classification is marked as；
Target screen is determined according to judging result.
The second aspect according to an embodiment of the present invention provides a kind of target screen determining device, is suitable for being equipped at least
The terminal of two screens, described device include:
Module is obtained, the image that the image collecting device for obtaining at least one screen is shot；
Categorization module, for carrying out the image classification that classification processing obtains described image to described image；
Judgment module for judging it is corresponding with target screen whether described image classification is marked as, and is tied according to judgement
Fruit determines target screen.
In terms of third according to an embodiment of the present invention, a kind of storage medium is provided, the storage medium is stored with one
Or multiple programs, one or more of programs can be executed by one or more processor, to realize such as first aspect
The step.
The target screen of the embodiment of the present invention determines method, apparatus and storage medium, passes through the camera shooting to different screens
The image of head acquisition carries out image classification, and target screen is determined from multiple screens according to classification results and target screen corresponding relationship
Curtain, compared with the prior art relies on merely face or fingerprint to determine target screen, not only increases accuracy rate, and whole process
It is participated in without user, improves user experience.
Detailed description of the invention
Fig. 1 is the flow chart that a kind of target screen that the embodiment of the present invention one provides determines method；
Fig. 2 is that second embodiment of the present invention provides the flow charts that another target screen determines method；
Fig. 3 is a kind of modular structure schematic diagram for target screen determining device that the embodiment of the present invention three provides.
Realization, functional characteristics and the advantage of purpose of the embodiment of the present invention will be done furtherly referring to attached drawing in conjunction with the embodiments
It is bright.
Specific embodiment
In order to be clearer and more clear technical problem to be solved of the embodiment of the present invention, technical solution and beneficial effect,
Below in conjunction with drawings and examples, the embodiment of the present invention is further elaborated.It should be appreciated that tool described herein
Body embodiment is only used to explain the embodiment of the present invention, is not intended to limit the present invention embodiment.
In subsequent description, it is only using the suffix for indicating such as " module ", " component " or " unit " of element
The explanation for being conducive to the embodiment of the present invention, itself does not have a specific meaning.Therefore, " module ", " component " or " unit " can
Mixedly to use.
Inventor has found that the mode that the double screen terminal of the prior art wakes up screen is usually in the implementation of the present invention
Fixed screen is waken up by fixed mode or is dynamically determined target screen.Due to two screen diversity ratios of Dual-band Handy Phone
Smaller, discrimination is little, and therefore, when wake-up device is dynamically determined target screen, it is possible to reduce since target screen is back to user
And perplex to user's bring.
The method for being dynamically determined target screen at present is more, and more commonly used has the following two kinds:
One, using fingerprint identification technology, when user adds finger print information, it is desirable that user setting finger print information, often
A fingerprint can bind a screen, and when with some fingerprint wake-up device, system is according to the information being previously saved come some
The bright screen bound therewith.But the flexibility of this method is inadequate.For example some fingerprint of user's right hand binds screen one, is shielding
Also there is a strong possibility when curtain two faces oneself will use right hand progress fingerprint wake-up, and screen one is lighted at this time, target screen
Determine mistake and.The method needs user to be manually operated, and needs to keep firmly in mind to remember fingerprint binding information, and user experience is not
It is good.
Two, using face recognition technology, recognition of face is carried out when user wakes up mobile phone, is imaged if recognizing face
A face screen where head is lighted, and otherwise another screen is lighted.But this method discrimination is relatively low, because many times
Although camera is with user in the same side, face is determined not in camera viewfinder range so as to cause target screen
Mistake accuracy is relatively low.
The embodiment of the present invention one provides a kind of target screen and determines method, suitable for being equipped with the end of at least two screens
End, referring to Fig. 1, this method comprises:
The image that S101, the image collecting device for obtaining at least one screen are shot；
S102, the image classification that classification processing obtains the image is carried out to the image；
S103, to judge whether the image classification is marked as corresponding with target screen；
S104, target screen is determined according to judging result.
In practical application, when user's wake-up device, system is waken up from dormant state, and image collecting device is got started
Work opens camera and takes pictures, obtains image.
It should be noted that the image feature information mentioned in the embodiment of the present invention includes extracting from image data
Characteristic value, such as color space information, figure information, brightness information, neural network weight etc..
In a feasible scheme, the image classification that classification processing obtains the image step S102, is carried out to the image,
Include:
The image data of the image calculate and obtains image feature information；
The image feature information is matched with the preset features information in preset features library, and will be matching pre-
Set image classification of the corresponding image classification of characteristic information as described image.
In a feasible scheme, the image classification that classification processing obtains the image is carried out to the image, comprising:
Classification processing is carried out to the image using machine learning algorithm, comprising:
According to the machine learning algorithm to the degree of dependence of historical data, selectively read in image feature base pre-
Characteristic information is set to be matched, and learns new feature；
Wherein, which includes K- nearest neighbor algorithm algorithm of support vector machine or deep learning algorithm.
In practical application, the mode for carrying out classification processing to image includes but is not limited to conventional machine learning algorithm, such as
K- nearest neighbor algorithm, algorithm of support vector machine and deep learning algorithm (such as convolutional neural networks algorithm).
It during processing can be selective in characteristics of image number according to algorithms of different to the degree of dependence of historical data
It is matched according to historical data information is read in library, if this calculated image feature information is not included in preset features library
In, new image feature information can be saved in preset features library.
In a feasible scheme, when the terminal is set there are two when screen, this determines target screen according to judging result,
Include:
If obtaining the image of the image collecting device shooting of two screens, determine that image classification is marked as and target
Screen corresponding to the corresponding image of screen is target screen；
If only obtaining the image of image collecting device shooting, it is marked as and mesh in the image classification of the image
Mark screen is to determining that the corresponding screen of the image collecting device is target screen when corresponding to, otherwise, it determines another screen is target
Screen.
In practical application, if the screen more than two of terminal, and the screen of image collecting device would be not configured less than two
It is a, target screen directly can also be determined according to the result of image classification.
In a feasible scheme, after step S104, determining target screen according to judging result, this method is also wrapped
It includes:
Whether the screen that verification user is operated is consistent with determining target screen；
The preset features information is marked or revised according to check results.
In practical application, after target screen is lighted, if target screen determines that accurately user can be directly in the target
It is inputted, is operated, otherwise, user may be switched to other screens and operate, and user inputs screen on screen
Operation, the input mode of operation include but is not limited to the screen operators such as to click, double-click, slide.
In practical application, after lighting target screen, can also be asked the user whether by way of dialog box using
Current screen, then the selection for the user that follows up determine the screen that user is operated, and shortcut key or other quick behaviour also can be set
Make mode, user is helped to realize the quick switching between screen.
If the screen that user is operated is consistent with the target screen determined, check results are correct, otherwise verification knot
Fruit mistake.When check results correctly then add to the corresponding image classification of relevant preset features information in image feature base
Add correct labeling, otherwise adds error flag.Alternatively, it is corresponding to correct corresponding preset features information according to the operation to user
Image classification, whether correct and image classification is corresponding with target screen for the image classification including the prediction picture characteristic information
Whether relationship is correct.It can be further improved the accuracy of subsequent classification by verification classification correctness.
In practical application, image classification, prediction picture characteristic information and corresponding relationship such as 1 institute of table with target screen
Show, it should be noted that be only a simple citing in table 1, actual corresponding relationship can be different according to the actual situation:
Table 1
| Preset features information | Image classification | Whether target screen |
| Nose, eyes, eyebrow, mouth | Face | It is |
| Ground, metope, railing | Building | It is no |
| Trees, flower, desk | Environment | It is no |
In practical application, corresponding corresponding relationship, example can also be marked by way of to different image classification assignment
Such as, being assigned a value of 1 indicates that the image classification is corresponding with target screen, if the image that the camera of some screen is shot is corresponding
Image classification is assigned a value of 1, then the screen is target screen, lights the screen at this time；It is assigned a value of zero, then it represents that the image point
Class does not correspond to target screen, if the corresponding image classification of image that the camera of some screen is shot is assigned a value of 0, does not need
Light the screen.
The matched preset features information pair of image feature information with the image of camera shooting can also be seen that by upper table
The image classification answered is exactly the corresponding image classification of the image.
In a feasible scheme, after step S104, determining target screen according to judging result, this method is also wrapped
It includes:
Light determining target screen.
The target screen of the present embodiment determines method, carries out image by the image that the camera to different screens acquires
Classification determines target screen according to classification results and target screen corresponding relationship from multiple screens, with the prior art merely according to
It determines that target screen is compared by face or fingerprint, not only increases accuracy rate, and whole process is participated in without user, is improved
User experience.
On the basis of previous embodiment, second embodiment of the present invention provides another target screens to determine method, the party
Method is illustrated so that the screen of Dual-band Handy Phone wakes up as an example, it is assumed that two screens of the Dual-band Handy Phone are equipped with and can work normally
Camera.Referring to Fig. 2, method flow includes:
S201, when cell phone system is waken up from dormant state, target screen determining device obtain image collecting device adopt
The image of collection.
In practical application, when cell phone system is waken up from dormant state, process quilt of the image collector setting in backstage
It wakes up, open camera and takes pictures, obtain image data.
S202, the predicted value that image is calculated using convolutional neural networks.
Wherein, predicted value is that is, image feature information.
In practical application, which includes:
1, image is pre-processed.
In practical application, which includes the resolution ratio that compression reduces image.
The resolution ratio of taking pictures of existing mobile phone is generally relatively high, and high-resolution will increase calculating cost, and simultaneously to image recognition
Without too many significant information, it is possible to reduce resolution ratio.In addition, picture size requirement of the convolutional neural networks to input
It is unified, it can use preparatory trained characteristic value information in this way.
2, pretreated image is calculated using convolutional neural networks.
Convolutional neural networks can be used in this step to calculate pretreated image.
In practical application, can only it calculate without being trained.
The network parameter needs of convolutional network are trained to obtain to a large amount of picture, and the similar devices such as mobile phone are can not be into
The such large-scale calculations of row, therefore preparatory trained characteristic value information on computers can be used, the instruction on computer
Practicing data can be used image library disclosed in ImageNet etc..Only need the extremely short time that can calculate figure in this way on mobile phone
The predicted value of picture.
S203, calculated predicted value is matched with the preset features information in preset features library.
Need to predefine a feature database (preset features library) on mobile phone, each preset features letter in the preset features library
Breath has corresponding image classification, and whether each image classification marks out it corresponding with target screen.
S204, target screen is determined according to matching result.
In this step, the predicted value of the image of the camera shooting of the first screen of the mobile phone is defined as with image classification
The preset features information matches of [face], [picture material is simple] (such as number of modes is simple less than 3), it is assumed that [face]
The target screen of image classification relevant be assigned a value of 1；And the prediction of the image of the camera shooting of the second screen of the mobile phone
Value and image classification are defined as the preset features information matches of [building], [trees], [figure viewed from behind] etc., it is assumed that these image classifications
Target screen it is relevant be assigned a value of 0, then being assigned a value of 1 according to table 1 and illustrating that corresponding screen (i.e. screen one) can determine
For target screen.
S205: determining target screen is lighted.
According to step S204's as a result, screen one should be lighted.
S206: whether the screen that verification user is operated is consistent with determining target screen, and according to check results mark
Note.
If the screen that user is operated is consistent with the target screen determined, check results are correct, otherwise verification knot
Fruit mistake.When check results correctly then add to the corresponding image classification of relevant preset features information in image feature base
Add correct labeling, otherwise adds error flag.
The target screen of the present embodiment determines method, carries out image by the image that the camera to different screens acquires
Classification determines target screen according to classification results and target screen corresponding relationship from multiple screens, with the prior art merely according to
It determines that target screen is compared by face or fingerprint, not only increases accuracy rate, and whole process is participated in without user, is improved
User experience.
On the basis of previous embodiment, the embodiment of the present invention three provides a kind of target screen determining device, is suitable for
Terminal equipped at least two screens, referring to Fig. 3, the device includes:
Module 301 is obtained, the image that the image collecting device for obtaining at least one screen is shot；
Categorization module 302, for carrying out the image classification that classification processing obtains the image to the image；
Judgment module 303 is tied for judging it is corresponding with target screen whether the image classification is marked as, and according to judgement
Fruit determines target screen.
In practical application, when user's wake-up device, system is waken up from dormant state, and image collecting device is got started
Work opens camera and takes pictures, obtains image.
In a feasible scheme, the categorization module 302, comprising:
Computational submodule carries out calculating acquisition image feature information for the image data to the image；
Matching module, for the image feature information to be matched with the preset features information in preset features library, and
Using the matching corresponding image classification of preset features information as the image classification of described image.
In a feasible scheme, which is also used to classify to the image using machine learning algorithm
Processing, comprising: according to the machine learning algorithm to the degree of dependence of historical data, selectively read in image feature base
Preset features information learns new feature to be matched；
Wherein, which includes K- nearest neighbor algorithm, algorithm of support vector machine or deep learning algorithm.
In practical application, the mode for carrying out classification processing to image includes but is not limited to conventional machine learning algorithm, such as
K- nearest neighbor algorithm, algorithm of support vector machine and deep learning algorithm (such as convolutional neural networks algorithm).
It during processing can be selective in characteristics of image number according to algorithms of different to the degree of dependence of historical data
It is matched according to historical data information is read in library, if this calculated image feature information is not included in preset features library
In, new image feature information can be saved in preset features library.
In a feasible scheme, when the terminal is set there are two when screen, which is also used to obtaining
When the image of the image collecting device shooting of two screens, determine that image classification is marked as figure corresponding with target screen
As corresponding screen be target screen, or be also used to only obtain an image collecting device shooting image when,
When the image classification of the image is marked as corresponding with target screen, determine that the corresponding screen of the image collecting device is target screen
Curtain, otherwise, it determines another screen is target screen.
In practical application, if the screen more than two of terminal, and the screen of image collecting device would be not configured less than two
It is a, target screen directly can also be determined according to the result of image classification.
In a feasible scheme, the device further include:
Correction verification module, for after determining target screen, screen that verification user is operated whether with determining mesh
It is consistent to mark screen, and marks or revise the corresponding image classification of preset features information according to check results.
In practical application, after target screen is lighted, if target screen determines that accurately user can be directly in the target
It is inputted, is operated, otherwise, user may be switched to other screens and operate, and user inputs screen on screen
Operation, the input mode of operation include but is not limited to the screen operators such as to click, double-click, slide.
In practical application, after lighting target screen, can also be asked the user whether by way of dialog box using
Current screen, then the selection for the user that follows up determine the screen that user is operated, and shortcut key or other quick behaviour also can be set
Make mode, user is helped to realize the quick switching between screen.
If the screen that user is operated is consistent with the target screen determined, check results are correct, otherwise verification knot
Fruit mistake.When check results correctly then add to the corresponding image classification of relevant preset features information in image feature base
Add correct labeling, otherwise adds error flag.Alternatively, it is corresponding to correct corresponding preset features information according to the operation to user
Image classification, whether correct and image classification is corresponding with target screen for the image classification including the prediction picture characteristic information
Whether relationship is correct.It can be further improved the accuracy of subsequent classification by verification classification correctness.
In practical application, image classification, prediction picture characteristic information and corresponding relationship such as 1 institute of table with target screen
Show.Corresponding corresponding relationship can also be marked by way of to different image classification assignment, for example, being assigned a value of 1 indicates
The image classification is corresponding with target screen, if the corresponding image classification of image that the camera of some screen is shot is assigned a value of
1, then the screen is target screen, lights the screen at this time；It is assigned a value of zero, then it represents that the image classification does not correspond to target screen
Curtain, if the corresponding image classification of image that the camera of some screen is shot is assigned a value of 0, does not need to light the screen.
In an optional scheme, the device further include:
Screen lights module, for lighting determining target screen.
The target screen determining device of the present embodiment carries out image by the image that the camera to different screens acquires
Classification determines target screen according to classification results and target screen corresponding relationship from multiple screens, with the prior art merely according to
It determines that target screen is compared by face or fingerprint, not only increases accuracy rate, and whole process is participated in without user, is improved
User experience.
On the basis of previous embodiment, the embodiment of the present invention three provides a kind of storage medium, which includes
The program of storage, equipment where controlling the storage medium in program operation execute the operation being somebody's turn to do such as embodiment one.
Above by reference to the preferred embodiment of the Detailed description of the invention embodiment of the present invention, not thereby limit to the embodiment of the present invention
Interest field.Those skilled in the art do not depart from made any modification in the scope and spirit of the embodiment of the present invention, equally replace
It changes and improves, it should all be within the interest field of the embodiment of the present invention.
Claims (11)
1. a kind of target screen determines method, suitable for being equipped with the terminal of at least two screens, which is characterized in that the method packet
It includes:
Obtain the image of the image collecting device shooting of at least one screen；
The image classification that classification processing obtains described image is carried out to described image；
It is corresponding with target screen to judge whether described image classification is marked as；
Target screen is determined according to judging result.
2. the method as described in claim 1, which is characterized in that described to carry out classification processing acquisition described image to described image
Image classification, comprising:
The image data of described image calculate and obtains image feature information；
Described image characteristic information is matched with the preset features information in preset features library, and will be matching preset
Image classification of the corresponding image classification of characteristic information as described image.
3. the method as described in claim 1, which is characterized in that described according to judgement when the terminal is set there are two screen
As a result target screen is determined, comprising:
If obtaining the image of the image collecting device shooting of described two screens, determine that image classification is marked as and target screen
Screen corresponding to the corresponding image of curtain is target screen；
If only obtaining the image of image collecting device shooting, it is marked as and target in the image classification of described image
Screen is to determining that the corresponding screen of described image acquisition device is target screen when corresponding to, otherwise, it determines another screen is target
Screen.
4. method as described in any one of claims 1 to 3, which is characterized in that described to determine target screen according to judging result
Later, the method also includes:
Whether the screen that verification user is operated is consistent with determining target screen；
The corresponding image classification of the preset features information is marked or revised according to check results.
5. method as described in any one of claims 1 to 3, which is characterized in that described to be obtained to described image progress classification processing
Take the image classification of the image, comprising:
Classification processing is carried out to described image using machine learning algorithm, comprising:
According to the machine learning algorithm to the degree of dependence of historical data, selectively read in image feature base preset
Characteristic information learns new feature to be matched；
Wherein, the machine learning algorithm includes K- nearest neighbor algorithm, algorithm of support vector machine or deep learning algorithm.
6. a kind of target screen determining device, suitable for being equipped with the terminal of at least two screens, which is characterized in that described device packet
It includes:
Module is obtained, the image that the image collecting device for obtaining at least one screen is shot；
Categorization module, for carrying out the image classification that classification processing obtains described image to described image；
Judgment module, for judging it is corresponding with target screen and true according to judging result whether described image classification is marked as
Set the goal screen.
7. device as claimed in claim 6, which is characterized in that the categorization module, comprising:
Computational submodule carries out calculating acquisition image feature information for the image data to described image；
Matching module, for described image characteristic information to be matched with the preset features information in preset features library, and will
Image classification of the matching corresponding image classification of preset features information as described image.
8. device as claimed in claim 7, which is characterized in that when the terminal is set there are two screen, the judgment module,
It is also used to determine that image classification is marked as and mesh in the image for the image collecting device shooting for obtaining described two screens
Marking screen corresponding to the corresponding image of screen is target screen, or is also used to only obtaining an image collecting device bat
When the image taken the photograph, when the image classification of described image is marked as corresponding with target screen, described image acquisition device is determined
Corresponding screen is target screen, otherwise, it determines another screen is target screen.
9. such as the described in any item devices of claim 6 to 7, which is characterized in that described device further include:
Correction verification module, for after determining target screen, screen that verification user is operated whether with determining target screen
Curtain is consistent, and marks or revise the corresponding image classification of the preset features information according to check results.
10. such as the described in any item devices of claim 6 to 7, which is characterized in that the categorization module is also used to using machine
Learning algorithm carries out classification processing to described image, comprising: according to the machine learning algorithm to the degree of dependence of historical data,
It reads preset features information selectively in image feature base to be matched, and learns new feature；
Wherein, the machine learning algorithm includes K- nearest neighbor algorithm, algorithm of support vector machine or deep learning algorithm；
Screen lights module, for lighting determining target screen.
11. a kind of storage medium, which is characterized in that the storage medium is stored with one or more program, it is one or
The multiple programs of person can be executed by one or more processor, to realize step as described in any one in claim 1-5.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810181679.7A CN110231960A (en) | 2018-03-06 | 2018-03-06 | A kind of target screen determines method, apparatus and storage medium |
| PCT/CN2019/076694 WO2019170038A1 (en) | 2018-03-06 | 2019-03-01 | Target screen determining method and device, and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810181679.7A CN110231960A (en) | 2018-03-06 | 2018-03-06 | A kind of target screen determines method, apparatus and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110231960A true CN110231960A (en) | 2019-09-13 |
Family
ID=67846879
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810181679.7A Pending CN110231960A (en) | 2018-03-06 | 2018-03-06 | A kind of target screen determines method, apparatus and storage medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN110231960A (en) |
| WO (1) | WO2019170038A1 (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111176524A (en) * | 2019-12-25 | 2020-05-19 | 歌尔股份有限公司 | Multi-screen display system and mouse switching control method thereof |
| CN114257670A (en) * | 2022-02-28 | 2022-03-29 | 荣耀终端有限公司 | Display method of electronic equipment with folding screen |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106200871A (en) * | 2016-07-01 | 2016-12-07 | 努比亚技术有限公司 | The control method of a kind of terminal and terminal |
| CN106569762A (en) * | 2016-10-17 | 2017-04-19 | 青岛海信移动通信技术股份有限公司 | Dual-screen terminal light-up method and device as well as dual-screen terminal |
| CN106598511A (en) * | 2016-11-10 | 2017-04-26 | 珠海格力电器股份有限公司 | Electronic equipment screen switching method and device and electronic equipment |
| CN106775206A (en) * | 2016-11-24 | 2017-05-31 | 广东小天才科技有限公司 | Screen awakening method and device of user terminal and user terminal |
| CN106774796A (en) * | 2016-11-30 | 2017-05-31 | 深圳市金立通信设备有限公司 | A kind of screen lighting method and terminal |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105302285B (en) * | 2014-08-01 | 2019-03-01 | 福州瑞芯微电子股份有限公司 | Multi-display method, equipment and system |
| CN106157247A (en) * | 2016-07-06 | 2016-11-23 | 北京元心科技有限公司 | A kind of image processing method and system |
| CN106791571B (en) * | 2017-01-09 | 2020-05-19 | 宇龙计算机通信科技(深圳)有限公司 | Video display method and device for double-screen display terminal |
-
2018
- 2018-03-06 CN CN201810181679.7A patent/CN110231960A/en active Pending
-
2019
- 2019-03-01 WO PCT/CN2019/076694 patent/WO2019170038A1/en active Application Filing
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106200871A (en) * | 2016-07-01 | 2016-12-07 | 努比亚技术有限公司 | The control method of a kind of terminal and terminal |
| CN106569762A (en) * | 2016-10-17 | 2017-04-19 | 青岛海信移动通信技术股份有限公司 | Dual-screen terminal light-up method and device as well as dual-screen terminal |
| CN106598511A (en) * | 2016-11-10 | 2017-04-26 | 珠海格力电器股份有限公司 | Electronic equipment screen switching method and device and electronic equipment |
| CN106775206A (en) * | 2016-11-24 | 2017-05-31 | 广东小天才科技有限公司 | Screen awakening method and device of user terminal and user terminal |
| CN106774796A (en) * | 2016-11-30 | 2017-05-31 | 深圳市金立通信设备有限公司 | A kind of screen lighting method and terminal |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111176524A (en) * | 2019-12-25 | 2020-05-19 | 歌尔股份有限公司 | Multi-screen display system and mouse switching control method thereof |
| CN111176524B (en) * | 2019-12-25 | 2021-05-28 | 歌尔股份有限公司 | Multi-screen display system and mouse switching control method thereof |
| WO2021129144A1 (en) * | 2019-12-25 | 2021-07-01 | 歌尔股份有限公司 | Multi-screen display system and cursor switching control method therefor |
| US11740780B2 (en) | 2019-12-25 | 2023-08-29 | Goertek Inc. | Multi-screen display system and mouse switching control method thereof |
| CN114257670A (en) * | 2022-02-28 | 2022-03-29 | 荣耀终端有限公司 | Display method of electronic equipment with folding screen |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2019170038A1 (en) | 2019-09-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111260665B (en) | Image segmentation model training method and device | |
| CN104281847B (en) | A kind of reading method, device and equipment | |
| CN103366186B (en) | Method and apparatus for dynamically changing terminal background | |
| CN102096805B (en) | Apparatus and method for registering plurality of facial images for face recognition | |
| CN107832784B (en) | Image beautifying method and mobile terminal | |
| CN105654027B (en) | A kind of method and device of fingerprint recognition | |
| CN110163806A (en) | A kind of image processing method, device and storage medium | |
| CN107871001B (en) | Audio playing method and device, storage medium and electronic equipment | |
| CN108536638B (en) | Intelligent bookmark setting method, mobile terminal, system and readable storage medium | |
| CN108038431A (en) | Image processing method, device, computer equipment and computer-readable recording medium | |
| CN113808446B (en) | Fitness course interaction method and related device | |
| CN110188658A (en) | Personal identification method, device, electronic equipment and storage medium | |
| CN107347138A (en) | Image processing method, device, storage medium and terminal | |
| CN108898171A (en) | Recognition processing method, system and computer readable storage medium | |
| CN104834382B (en) | Application program for mobile terminal response system and method | |
| CN107463818A (en) | Solve lock control method and Related product | |
| CN112560649A (en) | Behavior action detection method, system, equipment and medium | |
| CN105069444B (en) | A kind of gesture identifying device | |
| CN107679473A (en) | Solve lock control method and Related product | |
| CN107179831A (en) | Start method, device, storage medium and the terminal of application | |
| CN109325518A (en) | Classification method, device, electronic equipment and the computer readable storage medium of image | |
| CN107871000A (en) | Audio frequency playing method, device, storage medium and electronic equipment | |
| CN113596344A (en) | Shooting processing method and device, electronic equipment and readable storage medium | |
| CN110231960A (en) | A kind of target screen determines method, apparatus and storage medium | |
| EP3200092A1 (en) | Method and terminal for implementing image sequencing |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20190913 |
|
| WD01 | Invention patent application deemed withdrawn after publication |