CN108363999A - Operation based on recognition of face executes method and apparatus - Google Patents
Operation based on recognition of face executes method and apparatus Download PDFInfo
- Publication number
- CN108363999A CN108363999A CN201810239814.9A CN201810239814A CN108363999A CN 108363999 A CN108363999 A CN 108363999A CN 201810239814 A CN201810239814 A CN 201810239814A CN 108363999 A CN108363999 A CN 108363999A
- Authority
- CN
- China
- Prior art keywords
- face
- image sequence
- identified
- face image
- behavioural information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/172—Classification, e.g. identification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/48—Matching video sequences
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Human Computer Interaction (AREA)
- Collating Specific Patterns (AREA)
- Image Analysis (AREA)
Abstract
The embodiment of the present application discloses the operation based on recognition of face and executes method and apparatus.One specific implementation mode of this method includes：Obtain human face image sequence to be identified；Based on human face image sequence to be identified, the face behavioural information of the target user corresponding to human face image sequence to be identified is identified；According to the face behavioural information of target user, the operational order that target user sends out is determined using preset command recognition model, wherein, command recognition model is used to characterize the correspondence between the operational order indicated by the face behavioural information of pre-set user and the face behavioural information of pre-set user；The operation indicated by operational order that performance objective user sends out.The embodiment helps to simplify mode of operation.
Description
Technical field
The invention relates to field of computer technology, and in particular to the operation based on recognition of face executes method and dress
It sets.
Background technology
With the development of Internet technology, face recognition technology has been applied to more and more fields.For example, can pass through
Recognition of face unlocks terminal device etc..The existing method that terminal is operated be typically user unlock terminal device it
Afterwards, data are applied to achieve the purpose that access by executing clicking operation to corresponding application icon in screen.For example, user's tune
When with camera applications, it usually needs be unlocked first to terminal, click the icon of camera applications later；Or screen is waken up first
Curtain carries out scheduled prompt operation (for example, sliding screen from right to left) to call camera applications to screen later.
Invention content
The embodiment of the present application proposes the operation based on recognition of face and executes method and apparatus.
In a first aspect, the embodiment of the present application provides a kind of operation execution method based on recognition of face, including：Acquisition waits for
The human face image sequence of identification；Based on human face image sequence to be identified, identify corresponding to human face image sequence to be identified
Target user face behavioural information；It is true using preset command recognition model according to the face behavioural information of target user
The operational order that the user that sets the goal sends out, wherein command recognition model be used to characterize the face behavioural information of pre-set user with it is pre-
If the correspondence between operational order indicated by the face behavioural information of user；The operational order that performance objective user sends out
Indicated operation.
In some embodiments, this method further includes：Obtain registered face image sequence；To registered face image sequence into
Row Activity recognition determines the face behavioural information of the registration user corresponding to registered face image sequence；Obtain registration user's
Operational order indicated by face behavioural information；Operational order indicated by face behavioural information and face behavioural information it
Between correspondence build command recognition model.
In some embodiments, based on human face image sequence to be identified, human face image sequence to be identified is identified
Before the face behavioural information of corresponding target user, this method further includes：By human face image sequence to be identified with noted
The facial image of volume user matches；And based on human face image sequence to be identified, identify facial image to be identified
The face behavioural information of target user corresponding to sequence, including：In response to determine human face image sequence to be identified with
The facial image successful match of registration user identifies facial image sequence to be identified based on human face image sequence to be identified
The face behavioural information of the corresponding target user of row.
In some embodiments, based on human face image sequence to be identified, human face image sequence institute to be identified is identified
The face behavioural information of corresponding target user, including：Gone out using the face Activity recognition Model Identification trained to be identified
The face behavioural information of target user corresponding to human face image sequence.
In some embodiments, operational order includes operation information and executes the identification information of the application of operation；And it holds
The operation indicated by operational order that row target user sends out, including：Utilize answering indicated by the identification information in operational order
With the operation indicated by execution operation information.
Second aspect, the embodiment of the present application provide a kind of operation executive device based on recognition of face, including：It obtains single
Member, for obtaining human face image sequence to be identified；Recognition unit, for based on human face image sequence to be identified, identifying
The face behavioural information of target user corresponding to human face image sequence to be identified；Determination unit, for according to target user
Face behavioural information, the operational order that target user sends out is determined using preset command recognition model, wherein command recognition
Model be used to characterize operational order indicated by the face behavioural information of pre-set user and the face behavioural information of pre-set user it
Between correspondence；Execution unit, the operation indicated by operational order sent out for performance objective user.
In some embodiments, which further includes：Construction unit, construction unit are used for：Obtain registered face image sequence
Row；Activity recognition is carried out to registered face image sequence, determines the face of the registration user corresponding to registered face image sequence
Behavioural information；Obtain the operational order indicated by the face behavioural information of registration user；According to face behavioural information and face row
Correspondence between the operational order indicated by information builds command recognition model.
In some embodiments, which further includes：Matching unit, matching unit are used for：By facial image to be identified
Sequence is matched with the facial image of registered users；And recognition unit is further used for being based on waiting knowing as follows
Other human face image sequence identifies the face behavioural information of the target user corresponding to human face image sequence to be identified：It rings
Ying Yu determines the facial image successful match of human face image sequence to be identified and registered users, based on face to be identified
Image sequence identifies the face behavioural information of the target user corresponding to human face image sequence to be identified.
In some embodiments, recognition unit is further used for as follows based on facial image sequence to be identified
Row, identify the face behavioural information of the target user corresponding to human face image sequence to be identified：Utilize the face trained
Activity recognition Model Identification goes out the face behavioural information of the target user corresponding to human face image sequence to be identified.
In some embodiments, operational order includes operation information and executes the identification information of the application of operation；And it holds
Row unit is further used for the operation indicated by the operational order that performance objective user sends out as follows：It is ordered using operation
The application indicated by identification information in order executes the operation indicated by operation information.
The third aspect, the embodiment of the present application provide a kind of electronic equipment, including：One or more processors；Storage dress
It sets, for storing one or more programs, when one or more programs are executed by one or more processors so that one or more
The method that a processor realizes any embodiment in such as operation execution method based on recognition of face.
Fourth aspect, the embodiment of the present application provide a kind of computer-readable medium, are stored thereon with computer program, should
The method that any embodiment in such as operation execution method based on recognition of face is realized when program is executed by processor.
Operation provided by the embodiments of the present application based on recognition of face executes method and apparatus, by waiting knowing from what is got
The face behavioural information of the target user corresponding to human face image sequence to be identified is identified in other human face image sequence；It
Afterwards, according to the face behavioural information of above-mentioned target user, determine that above-mentioned target user sends out using preset command recognition model
Operational order, wherein mentioned order identification model be used for characterize pre-set user face behavioural information and pre-set user people
The correspondence between operational order indicated by face behavioural information；Finally, the operational order that above-mentioned target user sends out is executed
Indicated operation helps to which user can send operational order by making human face expression or human face action to terminal
In simplified mode of operation.
Description of the drawings
By reading a detailed description of non-restrictive embodiments in the light of the attached drawings below, the application's is other
Feature, objects and advantages will become more apparent upon：
Fig. 1 is that this application can be applied to exemplary system architecture figures therein；
Fig. 2 is the flow chart according to one embodiment of the operation execution method based on recognition of face of the application；
Fig. 3 is the schematic diagram according to an application scenarios of the operation execution method based on recognition of face of the application；
Fig. 4 is the flow chart according to another embodiment of the operation execution method based on recognition of face of the application；
Fig. 5 is the structural schematic diagram according to one embodiment of the operation executive device based on recognition of face of the application；
Fig. 6 is adapted for the structural schematic diagram of the computer system of the electronic equipment for realizing the embodiment of the present application.
Specific implementation mode
The application is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouched
The specific embodiment stated is used only for explaining related invention, rather than the restriction to the invention.It also should be noted that in order to
Convenient for description, is illustrated only in attached drawing and invent relevant part with related.
It should be noted that in the absence of conflict, the features in the embodiments and the embodiments of the present application can phase
Mutually combination.The application is described in detail below with reference to the accompanying drawings and in conjunction with the embodiments.
Fig. 1 shows the operation execution method based on recognition of face that can apply the application or the behaviour based on recognition of face
Make the exemplary system architecture 100 of the embodiment of executive device.
As shown in Figure 1, system architecture 100 may include user terminal 101,102, network 103 and server 104.Its
In, network 103 between user terminal 101,102 and server 104 provide communication link medium.Network 103 can be with
Including various connection types, such as wired, wireless communication link or fiber optic cables etc..
User can be interacted by network 103 with server 104 using user terminal 101,102, be disappeared with sending or receiving
Breath etc..
The human face image sequence to be identified got can be identified in user terminal 101,102, identify above-mentioned
The face behavioural information of target user corresponding to human face image sequence to be identified；It later, can be according to the target identified
The face behavioural information of user determines the operational order that above-mentioned target user sends out using preset command recognition model；Finally,
User terminal 101,102 can execute the operation indicated by the operational order that above-mentioned target user sends out.
User terminal 101,102 can be hardware, can also be software.It, can be with when user terminal 101,102 is hardware
It is the various electronic equipments that there is camera and support information exchange, including but not limited to smart mobile phone, tablet computer, electronics
Book reader, MP3 player (Moving Picture Experts Group Audio Layer III, dynamic image expert
Compression standard audio level 3), (Moving Picture Experts Group Audio Layer IV, dynamic image are special by MP4
Family's compression standard audio level 4) player, pocket computer on knee and desktop computer etc..When user terminal 101,102
For software when, may be mounted in above-mentioned cited electronic equipment.Multiple softwares or software module may be implemented into it, also may be used
To be implemented as single software or software module.It is not specifically limited herein.
Server 104 can be to provide the service of face Activity recognition and/or operational order identification server, such as to
The background server that the human face image sequence to be identified that family terminal 101,102 is sent is handled.Background server can be right
The human face image sequence to be identified received carries out the processing such as face Activity recognition, operational order identification, and by handling result
(such as face behavioural information and/operational order) feeds back to user terminal.
It should be noted that the operation based on recognition of face that the embodiment of the present application is provided executes method usually by user
Terminal 101,102 executes, and correspondingly, the operation executive device based on recognition of face is generally disposed in user terminal 101,102.
It should also be noted that, user terminal 101,102 can also carry out human face image sequence to be identified in local
Face behavioural information identifies and operational order identification.At this point, 104 He of server can be not present in exemplary system architecture 100
Network 103.
It should be noted that server, client can be hardware, can also be software.When server, client are hard
When part, the distributed apparatus cluster of multiple equipment composition may be implemented into, individual equipment can also be implemented as.As server, visitor
When family end is software, multiple softwares or software module may be implemented into (such as providing multiple software moulds of Distributed Services
Block), single software or software module can also be implemented as.It is not specifically limited herein.
It should be understood that the number of the user terminal, network and server in Fig. 1 is only schematical.According to realization need
It wants, can have any number of user terminal, network and server.
With continued reference to Fig. 2, one embodiment of the operation execution method based on recognition of face according to the application is shown
Flow 200.The operation based on recognition of face executes method, includes the following steps：
Step 201, human face image sequence to be identified is obtained.
In the present embodiment, (such as user shown in FIG. 1 is whole for the executive agent of the operation execution method based on recognition of face
End) human face image sequence to be identified can be obtained.Facial image to be identified is typically the image for including face, for example, packet
Image containing front face or side face.If above-mentioned executive agent is user terminal, used using face unlock needing user
Family terminal utilizes in the application scenarios such as face login user account, and above-mentioned executive agent usually can get shooting extremely
Few two facial images to be identified；If above-mentioned executive agent be server, user terminal take at least two it is to be identified
Facial image after, above-mentioned executive agent can obtain facial image to be identified from user terminal.Above-mentioned people to be identified
Face image sequence can be by above-mentioned facial image to be identified according to facial image shooting time sequence it is combined at people
Face image sequence.
Step 202, based on human face image sequence to be identified, the mesh corresponding to human face image sequence to be identified is identified
Mark the face behavioural information of user.
In the present embodiment, based on the human face image sequence to be identified got in step 201, above-mentioned executive agent
It can identify the face behavioural information of the target user corresponding to above-mentioned human face image sequence to be identified.Above-mentioned face behavior
Information usually may include human facial expression information and human face action information.Human facial expression information may include for characterize smile,
The information of the human face expressions such as beep mouth, eye closing, human face action information may include nodding for characterization, controlling and shake the head, blink et al.
The information of face action.Herein, above-mentioned face behavioural information may include the face behavior letter using face characteristic set characterization
Breath.
In the present embodiment, above-mentioned executive agent may be used the face behavioral value technology based on template matches and treat knowledge
Other human face image sequence carries out Activity recognition to identify the target user's corresponding to human face image sequence to be identified
Face behavioural information, recognition methods may include steps of：Labeled good person's face behavior letter is extracted from database first
The facial image template or facial image feature templates of breath, later according to preset template matches strategy to face figure to be identified
As sequence is matched with the facial image template of labeled good person's face behavioural information, or to facial image sequence to be identified
The feature of row is matched with the facial image feature templates of labeled good person's face behavioural information, determines the highest people of matching degree
Face image template or the face behavior letter that the corresponding face behavioural information of facial image feature templates is the target user identified
Breath.
It should be noted that above-mentioned executive agent can be by means of destination server to above-mentioned facial image sequence to be identified
Row are identified to obtain the face behavioural information of above-mentioned target user.Specifically, above-mentioned executive agent can will be above-mentioned to be identified
Human face image sequence be sent to destination server, then destination server can to above-mentioned human face image sequence to be identified into
Row identification, and will identify that the face behavioural information of the target user corresponding to above-mentioned human face image sequence to be identified is fed back to
Above-mentioned executive agent.
Step 203, according to the face behavioural information of target user, target user is determined using preset command recognition model
The operational order sent out.
In the present embodiment, according to the face behavioural information of the target user identified in step 202, above-mentioned execution master
Body may be used preset command recognition model and determine the operational order that target user sends out.The operational order that target user sends out
It may include the order of the systematic parameter for adjusting above-mentioned executive agent, for example, increasing or reducing the order of system sound volume, adjusting
The order of whole screen intensity, the order for opening flashlight and screen locking order etc..Mentioned order identification model can be used for characterizing pre-
If the correspondence between operational order indicated by the face behavioural information of user and the face behavioural information of pre-set user.Make
For example, mentioned order identification model can be the face row of the face behavioural information and pre-set user for characterizing pre-set user
For the mapping table between the operational order indicated by information.Above-mentioned executive agent can be looked by above-mentioned mapping table
Find operational order corresponding with the face behavioural information of target user.
It should be noted that above-mentioned executive agent can identify that the operation that target user sends out is ordered by means of destination server
It enables.Specifically, the face behavioural information of above-mentioned target user can be sent to destination server by above-mentioned executive agent, then mesh
The face behavioural information of above-mentioned target user can be identified in mark server, and will identify that above-mentioned target user sent out
Operational order feeds back to above-mentioned executive agent.
Step 204, the operation indicated by operational order that performance objective user sends out.
In the present embodiment, above-mentioned executive agent can carry out the operational order that the above-mentioned target user determined sends out
Parsing, to execute the operation indicated by the operational order that above-mentioned target user sends out.If as an example, parsing target user
The operational order sent out is used to open flashlight, then above-mentioned executive agent can open flashlight；If parsing target user's hair
The operational order gone out is used for screen locking, then above-mentioned executive agent can execute screen locking operation.
If above-mentioned executive agent is user terminal, corresponding operation can be executed according to operational order, such as open camera；
If above-mentioned executive agent is server, service implement body can execute the order of corresponding operating come real by being sent out to user terminal
Now to the execution of the operation indicated by operational order.
The method that above-described embodiment of the application provides from the human face image sequence got by identifying that target is used
The face behavioural information at family further identifies the operation that the target user corresponding to the face behavioural information of target user sends out
Order helps to simplify behaviour to which user can send operational order by making human face expression or human face action to terminal
Make mode.
In some optional realization methods of the present embodiment, user states executive agent and carries out face registration in use
In the process, above-mentioned executive agent can obtain the registered face image sequence of the active user (registration user) taken.Later,
Above-mentioned registered face image sequence can be identified, determine the registration user's corresponding to above-mentioned registered face image sequence
The face behavioral value technology based on template matches may be used to above-mentioned registered face in face behavioural information, above-mentioned executive agent
Image sequence is identified to identify the face behavioural information of the registration user corresponding to above-mentioned registered face image sequence,
Specific recognition methods is believed with the above-mentioned face behavior for identifying corresponding target user from human face image sequence to be identified
The recognition methods of breath is essentially identical, and details are not described herein.Then, above-mentioned executive agent can obtain the face of above-mentioned registration user
Operational order indicated by behavioural information, for example, registration user, which can be arranged in order in interface, fills in or select face row
For the operational order indicated by information, for example, user can select " flashlight " and " opening ", or fill in " screen intensity " and
" increase " etc..Finally, above-mentioned executive agent can be according to indicated by above-mentioned face behavioural information and above-mentioned face behavioural information
Operational order between correspondence build mentioned order identification model.Above-mentioned executive agent can establish above-mentioned face behavior
The mapping table between operational order indicated by information and above-mentioned face behavioural information determines the mapping table of foundation
For command recognition model.
In some optional realization methods of the present embodiment, above-mentioned executive agent can identify in the following way
State the face behavioural information of the target user corresponding to human face image sequence to be identified：Utilize the face Activity recognition trained
Model Identification goes out the face behavioural information of the target user corresponding to above-mentioned human face image sequence to be identified.Above-mentioned executive agent
Face characteristic can be extracted from above-mentioned human face image sequence to be identified first, generates face feature vector；It later, can be with
Above-mentioned face feature vector is input to and obtains above-mentioned human face image sequence institute to be identified in above-mentioned face Activity recognition model
The face behavioural information of corresponding target user.
It can train in the following way and obtain face Activity recognition model：It is possible, firstly, to obtain face Activity recognition sample
This set, wherein face Activity recognition sample may include corresponding to sample image sequence and the sample image sequence configured
User face behavioural information；Later, people can be extracted from the sample image sequence in each face Activity recognition sample
Face feature generates face feature vector；Finally, machine learning method can be utilized, above-mentioned face Activity recognition sample will be utilized
The face feature vector that sample image sequence in set in each face Activity recognition sample is generated is as input, by the people
Face behavioural information in face Activity recognition sample is as output, to preset initial model (for example, model-naive Bayesian
(Naive Bayesian Model, NBM) or support vector machines (Support Vector Machine, SVM) etc.) it is trained
Obtain face Activity recognition model.
Herein, above-mentioned face Activity recognition model may include facial expression recognition model and human face action identification mould
Type.Above-mentioned executive agent face feature vector can be input in above-mentioned facial expression recognition model obtain it is above-mentioned to be identified
Face feature vector can also be input to human face action by the human facial expression information of the target user corresponding to human face image sequence
The human face action information of the target user corresponding to above-mentioned human face image sequence to be identified is obtained in identification model.It needs to illustrate
, training obtains facial expression recognition model and the method for human face action identification model obtains face behavior knowledge with above-mentioned training
The method of other model is essentially identical, and details are not described herein.
In some optional realization methods of the present embodiment, aforesaid operations order may include operation information and execute behaviour
The identification information of the application of work, for example, the identification information for executing the application of operation may include Apply Names, using coding etc..
Above-mentioned executive agent can execute the operation indicated by the operational order that above-mentioned target user sends out in the following way：Using upper
The application indicated by the identification information in operational order is stated, the operation indicated by aforesaid operations information is executed.If as an example, holding
Entitled " the XX payments " of the application of row operation, operation information are used to indicate presentation payment Quick Response Code, then above-mentioned executive agent can
Using the payment class application of entitled " XX payments ", payment Quick Response Code is presented.
It is the application scenarios according to the operation execution method based on recognition of face of the present embodiment with continued reference to Fig. 3, Fig. 3
One schematic diagram.In the application scenarios of Fig. 3, the executive agent (such as mobile phone) of the operation execution method based on recognition of face can
It to first turn on camera, takes pictures to the face of active user, to get human face image sequence (such as label to be identified
Shown in 301).It should be noted that the image sequence indicated by label 301 is only to illustrate.It then, can be from above-mentioned to be identified
The face behavioural information of the target user corresponding to above-mentioned human face image sequence to be identified is identified in human face image sequence (such as
Shown in label 301) it is " magnifying ".Later, can be known using preset order according to the face behavioural information of target user
Other model determines that the operational order (as shown in label 301) that above-mentioned target user sends out is " order for increasing system sound volume "；Most
Afterwards, the order for increasing system sound volume will can be executed to which volume is adjusted to three by a lattice for executing the executive agent of operation
Lattice, as shown in label 304.It should be noted that the adjustment indicated by image sequence and label 301 indicated by label 301
The process of volume is only to illustrate.
With further reference to Fig. 4, it illustrates the flows of another embodiment of the operation execution method based on recognition of face
400.The flow 400 of the operation execution method based on recognition of face, includes the following steps：
Step 401, human face image sequence to be identified is obtained.
In the present embodiment, the operation of step 201 is essentially identical in the operation of step 401 and previous embodiment, herein not
It repeats again.
Step 402, human face image sequence to be identified is matched with the facial image of registered users, determination waits knowing
Other human face image sequence and the facial image of registered users whether successful match.
In the present embodiment, above-mentioned executive agent can be by above-mentioned human face image sequence and registered users to be identified
Facial image is matched.Specifically, above-mentioned executive agent may be used the face matching technique based on template matches and treat knowledge
Other human face image sequence is matched with the facial image of registered users, and matching process may include steps of：First
Chartered facial image template or facial image feature templates are extracted from database；Later according to preset template matches
Strategy matches the facial image in human face image sequence to be identified with chartered facial image template or right
The feature of facial image in human face image sequence to be identified is matched with chartered facial image feature templates；And
Determine afterwards facial image in human face image sequence to be identified and chartered facial image template whether successful match, or
Whether the feature of the facial image in person's human face image sequence to be identified matches with chartered facial image feature templates
Success.
Step 403, in response to determining that human face image sequence to be identified is matched into the facial image of registered users
Work(identifies the face of the target user corresponding to human face image sequence to be identified based on human face image sequence to be identified
Behavioural information.
In the present embodiment, if determining above-mentioned human face image sequence to be identified and registered users in step 402
Facial image successful match, then can be confirmed that target user corresponding to facial image to be identified is registered users, from
And confirming the target user corresponding to facial image to be identified has operating right.At this moment, above-mentioned executive agent can be based on
The human face image sequence to be identified got in step 401, identifies the mesh corresponding to human face image sequence to be identified
Mark the face behavioural information of user.Above-mentioned face behavioural information usually may include human facial expression information and human face action information.
Human facial expression information may include the information for characterizing the human face expressions such as smile, beep mouth, eye closing, and human face action information can wrap
Include the information for characterizing the human face actions such as shake the head, blink of nodding, control.Herein, above-mentioned face behavioural information may include
The face behavioural information characterized using face characteristic set.
In the present embodiment, above-mentioned executive agent may be used the face behavioral value technology based on template matches and treat knowledge
Other human face image sequence carries out Activity recognition to identify the target user's corresponding to human face image sequence to be identified
Face behavioural information, recognition methods may include steps of：It is extracted from database first and has been configured good person's face behavior letter
The facial image template or facial image feature templates of breath, later according to preset template matches strategy to face figure to be identified
As sequence is matched with the facial image template for being configured good person's face behavioural information, or to facial image sequence to be identified
The feature of row is matched with the facial image feature templates for being configured good person's face behavioural information, determines the highest people of matching degree
Face image template or the face behavioural information that the corresponding face behavioural information of facial image feature templates is target user.
It should be noted that if occur the face of at least two different users in above-mentioned human face image sequence, then it can be true
Surely include the total number of images purpose ratio of the picture number and above-mentioned human face image sequence of the facial image of registered users, if should
Ratio is more than preset fractional threshold (for example, 0.5), then can determine above-mentioned human face image sequence to be identified and registered use
The facial image successful match at family.Step 404, according to the face behavioural information of target user, using preset command recognition mould
Type determines the operational order that target user sends out.
Step 405, the operation indicated by operational order that performance objective user sends out.
In the present embodiment, step 404, step 405 operation respectively with step 203 in previous embodiment, step 204
Operate essentially identical, details are not described herein.
Optionally, if determining the face of above-mentioned human face image sequence to be identified and registered users in step 402
Images match fails, then can determine that the target user corresponding to facial image to be identified is not registered users, to really
Recognize the target user corresponding to facial image to be identified and does not have operating right.At this moment, follow-up step can not be executed
403, step 404 and step 405, to ensure the safety of operation.
Figure 4, it is seen that compared with the corresponding embodiments of Fig. 2, the operation based on recognition of face in the present embodiment
The flow 400 of execution method, which is increased, matches human face image sequence to be identified with the facial image of registered users,
Determine human face image sequence to be identified and registered users facial image whether successful match step 402 and if it is determined that
The facial image successful match for going out human face image sequence to be identified and registered users, based on facial image sequence to be identified
Row, identify the step 403 of the face behavioural information of the target user corresponding to human face image sequence to be identified.As a result, originally
The scheme of embodiment description can indicate operational order after user is unlocked successfully using face using face behavior, contribute to
Promotion is to the information of user, the security protection performance of property.
With further reference to Fig. 5, as the realization to method shown in above-mentioned each figure, this application provides one kind to be known based on face
One embodiment of other operation executive device, the device embodiment is corresponding with embodiment of the method shown in Fig. 2, device tool
Body can be applied in various electronic equipments.
As shown in figure 5, the operation executive device 500 based on recognition of face of the present embodiment includes：Acquiring unit 501 is known
Other unit 502, determination unit 503 and execution unit 504.Wherein, acquiring unit 501 is for obtaining facial image sequence to be identified
Row；Recognition unit 502 is used to, based on human face image sequence to be identified, identify corresponding to human face image sequence to be identified
The face behavioural information of target user；Determination unit 503 is used for the face behavioural information according to target user, using preset life
The operational order for enabling identification model determine that target user sends out, wherein command recognition model is used to characterize the face of pre-set user
The correspondence between operational order indicated by behavioural information and the face behavioural information of pre-set user；Execution unit 504 is used
In the operation indicated by the operational order that performance objective user sends out.
In some optional realization methods of the present embodiment, the above-mentioned operation executive device 500 based on recognition of face is also
May include：Construction unit (not shown), it is above-mentioned during user states executive agent progress face registration in use
Construction unit can obtain the registered face image sequence of the active user (registration user) taken.Later, above-mentioned structure list
Above-mentioned registered face image sequence can be identified in member, determine the registration user corresponding to above-mentioned registered face image sequence
Face behavioural information, the face behavioral value technology based on template matches may be used to above-mentioned registrant in above-mentioned construction unit
Face image sequence is identified to identify the face behavior letter of the registration user corresponding to above-mentioned registered face image sequence
Breath, specific recognition methods and the above-mentioned face behavior that corresponding target user is identified from human face image sequence to be identified
The recognition methods of information is essentially identical, and details are not described herein.Then, above-mentioned construction unit can obtain the people of above-mentioned registration user
Operational order indicated by face behavioural information, for example, registration user, which can be arranged in order in interface, fills in or select face
Operational order indicated by behavioural information for example, user can select " flashlight " and " opening ", or fills in " screen intensity "
" increase " etc..Finally, above-mentioned construction unit can be signified according to above-mentioned face behavioural information and above-mentioned face behavioural information
Correspondence between the operational order shown builds mentioned order identification model.Above-mentioned construction unit can establish above-mentioned face row
It is for the mapping table between the operational order indicated by information and above-mentioned face behavioural information, the mapping table of foundation is true
It is set to command recognition model.
In some optional realization methods of the present embodiment, the above-mentioned operation executive device 500 based on recognition of face is also
May include：Matching unit (not shown), above-mentioned matching unit can by above-mentioned human face image sequence to be identified with
The facial image of registration user matches.Specifically, the matching of the face based on template matches may be used in above-mentioned matching unit
Technology matches human face image sequence to be identified with the facial image of registered users, and matching process may include as follows
Step：Chartered facial image template or facial image feature templates are extracted from database first；Later according to default
Template matches strategy the facial image in human face image sequence to be identified is carried out with chartered facial image template
Matching, or feature and chartered facial image feature templates to the facial image in human face image sequence to be identified
It is matched；Then determine whether are facial image in human face image sequence to be identified and chartered facial image template
Successful match or the feature of the facial image in human face image sequence to be identified and chartered facial image character modules
Plate whether successful match.
In some optional realization methods of the present embodiment, if above-mentioned matching unit determines above-mentioned face to be identified
The facial image successful match of image sequence and registered users, then can be confirmed the target corresponding to facial image to be identified
User is registered users, to confirm that the target user corresponding to facial image to be identified has operating right.At this moment, on
Human face image sequence to be identified can be identified based on the human face image sequence to be identified got by stating recognition unit 502
The face behavioural information of corresponding target user.Above-mentioned face behavioural information usually may include human facial expression information and face
Action message.Human facial expression information may include the information for characterizing the human face expressions such as smile, beep mouth, eye closing, human face action
Information may include the information for characterizing the human face actions such as shake the head, blink of nodding, control.Herein, above-mentioned face behavior letter
Breath may include the face behavioural information using face characteristic set characterization.Above-mentioned recognition unit 502 may be used based on template
Matched face behavioral value technology carries out Activity recognition to identify people to be identified to human face image sequence to be identified
The face behavioural information of target user corresponding to face image sequence, recognition methods may include steps of：First from data
The facial image template or facial image feature templates for being configured good person's face behavioural information are extracted in library, later according to preset
Template matches strategy carries out human face image sequence to be identified with the facial image template for being configured good person's face behavioural information
Matching, or to the feature of human face image sequence to be identified and it has been configured the facial image character modules of good person's face behavioural information
Plate is matched, and determines that the highest facial image template of matching degree or the corresponding face behavioural information of facial image feature templates are
The face behavioural information of target user.
It should be noted that if occur the face of at least two different users in above-mentioned human face image sequence, then it can be true
Surely include the total number of images purpose ratio of the picture number and above-mentioned human face image sequence of the facial image of registered users, if should
Ratio is more than preset fractional threshold (for example, 0.5), then can determine above-mentioned human face image sequence to be identified and registered use
The facial image successful match at family.
In some optional realization methods of the present embodiment, above-mentioned recognition unit 502 can identify in the following way
Go out the face behavioural information of the target user corresponding to above-mentioned human face image sequence to be identified：Utilize the face behavior trained
Identification model identifies the face behavioural information of the target user corresponding to the human face image sequence to be identified.Above-mentioned identification
Unit 502 can extract face characteristic from above-mentioned human face image sequence to be identified first, generate face feature vector；It
Afterwards, above-mentioned face feature vector can be input in above-mentioned face Activity recognition model and obtains above-mentioned facial image to be identified
The face behavioural information of target user corresponding to sequence.
It can train in the following way and obtain face Activity recognition model：It is possible, firstly, to obtain face Activity recognition sample
This set, wherein face Activity recognition sample may include corresponding to sample image sequence and the sample image sequence configured
User face behavioural information；Later, people can be extracted from the sample image sequence in each face Activity recognition sample
Face feature generates face feature vector；Finally, machine learning method can be utilized, above-mentioned face Activity recognition sample will be utilized
The face feature vector that sample image sequence in set in each face Activity recognition sample is generated is as input, by the people
Face behavioural information in face Activity recognition sample as output, to preset initial model (for example, model-naive Bayesian or
Support vector machines etc.) it is trained to obtain face Activity recognition model.
Herein, above-mentioned face Activity recognition model may include facial expression recognition model and human face action identification mould
Type.Face feature vector can be input in above-mentioned facial expression recognition model by above-mentioned recognition unit 502 to be obtained above-mentioned waiting knowing
Face feature vector can also be input to face by the human facial expression information of the target user corresponding to other human face image sequence
The human face action information of the target user corresponding to above-mentioned human face image sequence to be identified is obtained in action recognition model.It needs
Illustrate, training obtains facial expression recognition model and the method for human face action identification model obtains face row with above-mentioned training
Essentially identical for the method for identification model, details are not described herein.
In some optional realization methods of the present embodiment, aforesaid operations order may include operation information and execute behaviour
The identification information of the application of work, for example, the identification information for executing the application of operation may include Apply Names, using coding etc..
Above-mentioned execution unit 504 can execute the operation indicated by the operational order that above-mentioned target user sends out in the following way：Profit
With the application indicated by the identification information in above-mentioned operational order, the operation indicated by aforesaid operations information is executed.As an example,
If executing entitled " the XX payments " of the application of operation, operation information is used to indicate presentation payment Quick Response Code, then above-mentioned execution list
Member 504 can utilize the payment class application of entitled " XX payments ", and payment Quick Response Code is presented.
All units described in device 500 are corresponding with reference to each step in figure 2 and the method for Fig. 4 descriptions.As a result,
Operation and feature above with respect to method description are equally applicable to device 500 and unit wherein included, and details are not described herein.
The operation executive device based on recognition of face that the above embodiments of the present application provide, by be identified from what is got
Human face image sequence in identify the face behavioural information of target user corresponding to human face image sequence to be identified；It
Afterwards, according to the face behavioural information of above-mentioned target user, determine that above-mentioned target user sends out using preset command recognition model
Operational order, wherein mentioned order identification model be used for characterize pre-set user face behavioural information and pre-set user people
The correspondence between operational order indicated by face behavioural information；Finally, the operational order that above-mentioned target user sends out is executed
Indicated operation helps to which user can send operational order by making human face expression or human face action to terminal
In simplified mode of operation.
Below with reference to Fig. 6, it illustrates the computer systems 600 suitable for the electronic equipment for realizing the embodiment of the present invention
Structural schematic diagram.Electronic equipment shown in Fig. 6 is only an example, to the function of the embodiment of the present application and should not use model
Shroud carrys out any restrictions.
As shown in fig. 6, computer system 600 includes central processing unit (CPU) 601, it can be read-only according to being stored in
Program in memory (ROM) 602 or be loaded into the program in random access storage device (RAM) 603 from storage section 608 and
Execute various actions appropriate and processing.In RAM 603, also it is stored with system 600 and operates required various programs and data.
CPU 601, ROM 602 and RAM 603 are connected with each other by bus 604.Input/output (I/O) interface 605 is also connected to always
Line 604.
It is connected to I/O interfaces 605 with lower component：Importation 606 including keyboard, mouse etc.；Including such as liquid crystal
Show the output par, c 607 of device (LCD) and loud speaker etc.；Storage section 608 including hard disk etc.；And including such as LAN card,
The communications portion 609 of the network interface card of modem etc..Communications portion 609 executes communication via the network of such as internet
Processing.Driver 610 is also according to needing to be connected to I/O interfaces 605.Detachable media 611, such as disk, CD, magneto-optic disk,
Semiconductor memory etc., as needed be mounted on driver 610 on, in order to from the computer program read thereon according to need
It is mounted into storage section 608.
Particularly, in accordance with an embodiment of the present disclosure, it may be implemented as computer above with reference to the process of flow chart description
Software program.For example, embodiment of the disclosure includes a kind of computer program product comprising be carried on computer-readable medium
On computer program, which includes the program code for method shown in execution flow chart.In such reality
It applies in example, which can be downloaded and installed by communications portion 609 from network, and/or from detachable media
611 are mounted.When the computer program is executed by central processing unit (CPU) 601, limited in execution the present processes
Above-mentioned function.It should be noted that the above-mentioned computer-readable medium of the application can be computer-readable signal media or
Computer readable storage medium either the two arbitrarily combines.Computer readable storage medium for example can be --- but
Be not limited to --- electricity, magnetic, optical, electromagnetic, infrared ray or semiconductor system, device or device, or arbitrary above combination.
The more specific example of computer readable storage medium can include but is not limited to：Electrical connection with one or more conducting wires,
Portable computer diskette, hard disk, random access storage device (RAM), read-only memory (ROM), erasable type may be programmed read-only deposit
Reservoir (EPROM or flash memory), optical fiber, portable compact disc read-only memory (CD-ROM), light storage device, magnetic memory
Part or above-mentioned any appropriate combination.In this application, computer readable storage medium can any be included or store
The tangible medium of program, the program can be commanded the either device use or in connection of execution system, device.And
In the application, computer-readable signal media may include the data letter propagated in a base band or as a carrier wave part
Number, wherein carrying computer-readable program code.Diversified forms may be used in the data-signal of this propagation, including but not
It is limited to electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal media can also be computer
Any computer-readable medium other than readable storage medium storing program for executing, the computer-readable medium can send, propagate or transmit use
In by instruction execution system, device either device use or program in connection.Include on computer-readable medium
Program code can transmit with any suitable medium, including but not limited to：Wirelessly, electric wire, optical cable, RF etc., Huo Zheshang
Any appropriate combination stated.
Flow chart in attached drawing and block diagram, it is illustrated that according to the system of various embodiments of the invention, method and computer journey
The architecture, function and operation in the cards of sequence product.In this regard, each box in flowchart or block diagram can generation
A part for a part for one module, program segment, or code of table, the module, program segment, or code includes one or more uses
The executable instruction of the logic function as defined in realization.It should also be noted that in some implementations as replacements, being marked in box
The function of note can also occur in a different order than that indicated in the drawings.For example, two boxes succeedingly indicated are actually
It can be basically executed in parallel, they can also be executed in the opposite order sometimes, this is depended on the functions involved.Also it to note
Meaning, the combination of each box in block diagram and or flow chart and the box in block diagram and or flow chart can be with holding
The dedicated hardware based system of functions or operations as defined in row is realized, or can use specialized hardware and computer instruction
Combination realize.
Being described in unit involved in the embodiment of the present invention can be realized by way of software, can also be by hard
The mode of part is realized.Described unit can also be arranged in the processor, for example, can be described as：A kind of processor packet
Include acquiring unit, recognition unit, determination unit and execution unit.Wherein, the title of these units not structure under certain conditions
The restriction of the pairs of unit itself.For example, acquiring unit is also described as " obtaining the list of human face image sequence to be identified
Member ".
As on the other hand, present invention also provides a kind of computer-readable medium, which can be
Included in device described in above-described embodiment；Can also be individualism, and without be incorporated the device in.Above-mentioned calculating
Machine readable medium carries one or more program, when said one or multiple programs are executed by the device so that should
Device：Obtain human face image sequence to be identified；Based on human face image sequence to be identified, facial image to be identified is identified
The face behavioural information of target user corresponding to sequence；According to the face behavioural information of target user, using preset order
Identification model determines the operational order that target user sends out, wherein command recognition model is used to characterize the face row of pre-set user
For the correspondence between the operational order indicated by information and the face behavioural information of pre-set user；Performance objective user sends out
Operational order indicated by operation.
Above description is only presently preferred embodiments of the present invention and the explanation to institute's application technology principle.People in the art
Member should be appreciated that invention scope involved in the present invention, however it is not limited to technology made of the specific combination of above-mentioned technical characteristic
Scheme, while should also cover in the case where not departing from foregoing invention design, it is carried out by above-mentioned technical characteristic or its equivalent feature
Other technical solutions of arbitrary combination and formation.Such as features described above has similar work(with (but not limited to) disclosed in the present invention
Can technical characteristic replaced mutually and the technical solution that is formed.
Claims (12)
1. a kind of operation based on recognition of face executes method, including：
Obtain human face image sequence to be identified；
Based on the human face image sequence to be identified, identify that the target corresponding to the human face image sequence to be identified is used
The face behavioural information at family；
According to the face behavioural information of the target user, determine that the target user sends out using preset command recognition model
Operational order, wherein the command recognition model be used for characterize pre-set user face behavioural information and pre-set user people
The correspondence between operational order indicated by face behavioural information；
Execute the operation indicated by the operational order that the target user sends out.
2. according to the method described in claim 1, wherein, the method further includes：
Obtain registered face image sequence；
Activity recognition is carried out to the registered face image sequence, determines that the registration corresponding to the registered face image sequence is used
The face behavioural information at family；
Obtain the operational order indicated by the face behavioural information of the registration user；
Correspondence structure between operational order indicated by the face behavioural information and the face behavioural information
The command recognition model.
3. according to the method described in claim 1, wherein, described based on the human face image sequence to be identified, identifying
Before the face behavioural information of target user corresponding to the human face image sequence to be identified, the method further includes：
The human face image sequence to be identified is matched with the facial image of registered users；And
It is described based on the human face image sequence to be identified, identify the mesh corresponding to the human face image sequence to be identified
The face behavioural information of user is marked, including：
In response to determining the facial image successful match of the human face image sequence to be identified and registered users, it is based on institute
Human face image sequence to be identified is stated, identifies the face row of the target user corresponding to the human face image sequence to be identified
For information.
4. it is described based on the human face image sequence to be identified according to the method described in claim 1, wherein, identify institute
The face behavioural information of the target user corresponding to human face image sequence to be identified is stated, including：
Go out the target corresponding to the human face image sequence to be identified using the face Activity recognition Model Identification trained to use
The face behavioural information at family.
5. according to the method described in one of claim 1-5, wherein the operational order includes operation information and execution operation
The identification information of application；And
The operation executed indicated by the operational order that the target user sends out, including：
Using the application indicated by the identification information in the operational order, the operation indicated by the operation information is executed.
6. a kind of operation executive device based on recognition of face, including：
Acquiring unit, for obtaining human face image sequence to be identified；
Recognition unit, for based on the human face image sequence to be identified, identifying the human face image sequence to be identified
The face behavioural information of corresponding target user；
Determination unit determines institute for the face behavioural information according to the target user using preset command recognition model
State the operational order that target user sends out, wherein the command recognition model is used to characterize the face behavioural information of pre-set user
The correspondence between the operational order indicated by face behavioural information with pre-set user；
Execution unit, for executing the operation indicated by the operational order that the target user sends out.
7. device according to claim 6, wherein described device further includes：Construction unit, the construction unit are used for：
Obtain registered face image sequence；
Activity recognition is carried out to the registered face image sequence, determines that the registration corresponding to the registered face image sequence is used
The face behavioural information at family；
Obtain the operational order indicated by the face behavioural information of the registration user；
Correspondence structure between operational order indicated by the face behavioural information and the face behavioural information
The command recognition model.
8. device according to claim 6, wherein described device further includes：Matching unit, the matching unit are used for：
The human face image sequence to be identified is matched with the facial image of registered users；And
The recognition unit is further used for identifying based on the human face image sequence to be identified as follows described
The face behavioural information of target user corresponding to human face image sequence to be identified：
In response to determining the facial image successful match of the human face image sequence to be identified and registered users, it is based on institute
Human face image sequence to be identified is stated, identifies the face row of the target user corresponding to the human face image sequence to be identified
For information.
9. device according to claim 6, wherein the recognition unit is further used for being based on as follows described
Human face image sequence to be identified identifies the face behavior of the target user corresponding to the human face image sequence to be identified
Information：
Go out the target corresponding to the human face image sequence to be identified using the face Activity recognition Model Identification trained to use
The face behavioural information at family.
10. according to the device described in one of claim 6-9, wherein the operational order includes operation information and executes operation
Application identification information；And
The execution unit is further used for executing as follows indicated by the operational order that the target user sends out
Operation：
Using the application indicated by the identification information in the operational order, the operation indicated by the operation information is executed.
11. a kind of electronic equipment, including：
One or more processors；
Storage device, for storing one or more programs,
When one or more of programs are executed by one or more of processors so that one or more of processors are real
The now method as described in any in claim 1-5.
12. a kind of computer-readable medium, is stored thereon with computer program, wherein the program is realized when being executed by processor
Method as described in any in claim 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810239814.9A CN108363999A (en) | 2018-03-22 | 2018-03-22 | Operation based on recognition of face executes method and apparatus |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810239814.9A CN108363999A (en) | 2018-03-22 | 2018-03-22 | Operation based on recognition of face executes method and apparatus |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108363999A true CN108363999A (en) | 2018-08-03 |
Family
ID=63000718
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810239814.9A Pending CN108363999A (en) | 2018-03-22 | 2018-03-22 | Operation based on recognition of face executes method and apparatus |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108363999A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109886697A (en) * | 2018-12-26 | 2019-06-14 | 广州市巽腾信息科技有限公司 | Method, apparatus and electronic equipment are determined based on the other operation of expression group |
| CN110032945A (en) * | 2019-03-21 | 2019-07-19 | 阿里巴巴集团控股有限公司 | Method and device based on recognition of face |
| CN110210194A (en) * | 2019-04-18 | 2019-09-06 | 深圳壹账通智能科技有限公司 | Electronic contract display methods, device, electronic equipment and storage medium |
| CN110874875A (en) * | 2018-08-13 | 2020-03-10 | 珠海格力电器股份有限公司 | Door lock control method and device |
| WO2020062671A1 (en) * | 2018-09-26 | 2020-04-02 | 深圳壹账通智能科技有限公司 | Identity identification method, computer-readable storage medium, terminal device, and apparatus |
| WO2020140686A1 (en) * | 2019-01-03 | 2020-07-09 | 阿里巴巴集团控股有限公司 | Method, device and apparatus for waking up intelligent apparatus based on face detection |
| WO2021128846A1 (en) * | 2019-12-23 | 2021-07-01 | 深圳壹账通智能科技有限公司 | Electronic file control method and apparatus, and computer device and storage medium |
| RU2791846C2 (en) * | 2018-12-26 | 2023-03-13 | Сюньтэн (Гуандун) Текнолоджи Ко., Лтд. | Method and device for decision-making to perform operation based on groups of face expressions and electronic device |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105159452A (en) * | 2015-08-28 | 2015-12-16 | 成都通甲优博科技有限责任公司 | Control method and system based on estimation of human face posture |
| CN105912120A (en) * | 2016-04-14 | 2016-08-31 | 中南大学 | Face recognition based man-machine interaction control method of mobile robot |
| CN106682578A (en) * | 2016-11-21 | 2017-05-17 | 北京交通大学 | Human face recognition method based on blink detection |
| CN106775424A (en) * | 2017-01-13 | 2017-05-31 | 维沃移动通信有限公司 | A kind of screenshotss processing method and mobile terminal |
| US9888211B1 (en) * | 2016-12-05 | 2018-02-06 | Getgo, Inc. | Replacing live video of a meeting participant with recorded video of the meeting participant during an online meeting |
-
2018
- 2018-03-22 CN CN201810239814.9A patent/CN108363999A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105159452A (en) * | 2015-08-28 | 2015-12-16 | 成都通甲优博科技有限责任公司 | Control method and system based on estimation of human face posture |
| CN105912120A (en) * | 2016-04-14 | 2016-08-31 | 中南大学 | Face recognition based man-machine interaction control method of mobile robot |
| CN106682578A (en) * | 2016-11-21 | 2017-05-17 | 北京交通大学 | Human face recognition method based on blink detection |
| US9888211B1 (en) * | 2016-12-05 | 2018-02-06 | Getgo, Inc. | Replacing live video of a meeting participant with recorded video of the meeting participant during an online meeting |
| CN106775424A (en) * | 2017-01-13 | 2017-05-31 | 维沃移动通信有限公司 | A kind of screenshotss processing method and mobile terminal |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110874875B (en) * | 2018-08-13 | 2021-01-29 | 珠海格力电器股份有限公司 | Door lock control method and device |
| CN110874875A (en) * | 2018-08-13 | 2020-03-10 | 珠海格力电器股份有限公司 | Door lock control method and device |
| WO2020062671A1 (en) * | 2018-09-26 | 2020-04-02 | 深圳壹账通智能科技有限公司 | Identity identification method, computer-readable storage medium, terminal device, and apparatus |
| CN109886697B (en) * | 2018-12-26 | 2023-09-08 | 巽腾(广东)科技有限公司 | Operation determination method and device based on expression group and electronic equipment |
| RU2791846C2 (en) * | 2018-12-26 | 2023-03-13 | Сюньтэн (Гуандун) Текнолоджи Ко., Лтд. | Method and device for decision-making to perform operation based on groups of face expressions and electronic device |
| WO2020135096A1 (en) * | 2018-12-26 | 2020-07-02 | 巽腾(广东)科技有限公司 | Method and device for determining operation based on facial expression groups, and electronic device |
| CN109886697A (en) * | 2018-12-26 | 2019-06-14 | 广州市巽腾信息科技有限公司 | Method, apparatus and electronic equipment are determined based on the other operation of expression group |
| JP2022513978A (en) * | 2018-12-26 | 2022-02-09 | 巽騰（広東）科技有限公司 | Operation decision method, device and electronic device based on facial expression group |
| WO2020140686A1 (en) * | 2019-01-03 | 2020-07-09 | 阿里巴巴集团控股有限公司 | Method, device and apparatus for waking up intelligent apparatus based on face detection |
| CN110032945A (en) * | 2019-03-21 | 2019-07-19 | 阿里巴巴集团控股有限公司 | Method and device based on recognition of face |
| WO2020211387A1 (en) * | 2019-04-18 | 2020-10-22 | 深圳壹账通智能科技有限公司 | Electronic contract displaying method and apparatus, electronic device, and computer readable storage medium |
| CN110210194A (en) * | 2019-04-18 | 2019-09-06 | 深圳壹账通智能科技有限公司 | Electronic contract display methods, device, electronic equipment and storage medium |
| WO2021128846A1 (en) * | 2019-12-23 | 2021-07-01 | 深圳壹账通智能科技有限公司 | Electronic file control method and apparatus, and computer device and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108363999A (en) | Operation based on recognition of face executes method and apparatus | |
| US20190080148A1 (en) | Method and apparatus for generating image | |
| CN108898185A (en) | Method and apparatus for generating image recognition model | |
| CN108416323A (en) | The method and apparatus of face for identification | |
| CN108446387A (en) | Method and apparatus for updating face registration library | |
| CN109858445A (en) | Method and apparatus for generating model | |
| CN108595628A (en) | Method and apparatus for pushed information | |
| CN110110811A (en) | Method and apparatus for training pattern, the method and apparatus for predictive information | |
| CN110288049A (en) | Method and apparatus for generating image recognition model | |
| CN110298319B (en) | Image synthesis method and device | |
| CN108985257A (en) | Method and apparatus for generating information | |
| CN109086719A (en) | Method and apparatus for output data | |
| CN109034069A (en) | Method and apparatus for generating information | |
| CN107910060A (en) | Method and apparatus for generating information | |
| CN109299477A (en) | Method and apparatus for generating text header | |
| CN109344752A (en) | Method and apparatus for handling mouth image | |
| CN108446650A (en) | The method and apparatus of face for identification | |
| CN108960110A (en) | Method and apparatus for generating information | |
| CN108510466A (en) | Method and apparatus for verifying face | |
| CN109871791A (en) | Image processing method and device | |
| CN108280422A (en) | The method and apparatus of face for identification | |
| CN109214501A (en) | The method and apparatus of information for identification | |
| CN108446658A (en) | The method and apparatus of facial image for identification | |
| CN108600250A (en) | Authentication method | |
| CN108491812A (en) | The generation method and device of human face recognition model |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180803 |
|
| RJ01 | Rejection of invention patent application after publication |