CN110490162A - The methods, devices and systems of face variation are shown based on recognition of face unlocking function - Google Patents
The methods, devices and systems of face variation are shown based on recognition of face unlocking function Download PDFInfo
- Publication number
- CN110490162A CN110490162A CN201910786632.8A CN201910786632A CN110490162A CN 110490162 A CN110490162 A CN 110490162A CN 201910786632 A CN201910786632 A CN 201910786632A CN 110490162 A CN110490162 A CN 110490162A
- Authority
- CN
- China
- Prior art keywords
- image
- target
- face
- file destination
- time
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/53—Querying
- G06F16/538—Presentation of query results
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/54—Browsing; Visualisation therefor
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/5866—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using information manually generated, e.g. tags, keywords, comments, manually generated location and time information
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Library & Information Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Processing Or Creating Images (AREA)
Abstract
The embodiment of the present application discloses a kind of methods, devices and systems that face variation is shown based on recognition of face unlocking function, this method comprises: requesting in response to the generation, multiple corresponding target images of target object in target time section in acquisition image data base;File destination is generated according to the sequencing of the corresponding shooting time of target image based on the target image;The file destination is played, which is used to embody the face's variation of target object in the target time period.In this way, in the case where not depending on local photograph album, it is high frequency time behavior using unlock intelligent terminal and shoots the characteristics of main body of image is face, by obtaining and saving unlock image of the user when unlocking intelligent terminal by recognition of face, image will be unlocked as the resource of display user face variation, it therefrom obtains image to be displayed and generates file destination, realize the true effect for displaying for a user face's slight change by playing the file destination.
Description
Technical field
This application involves field of computer technology, show that face becomes based on recognition of face unlocking function more particularly to one kind
The methods, devices and systems of change.
Background technique
With the development of science and technology, more and more users use intelligent terminal, intelligent terminal is brought to people's lives
Many conveniences and enjoyment.Under some cases, user can obtain people in the photo on intelligent terminal through the processing to photo
The variation of object.
In general, a kind of mode, user can by specific image processing software, to the face of personage in current photo into
The special effect processings such as row facial deformations, makeups obtain the photo of user childhood or senectitude, bring enjoyment to user, still,
The result which obtains not is true photo, is frequently not the effect that user really wants.Another way, Yi Xiezhi
The photograph album of energy terminal has the function of to recall, that is, by the photo in local photograph album, can be related to people according to it by recognition of face
The difference of object is sorted out, and the photo for being related to identical personage is included into a memory photograph album, and according to bat in the memory photograph album
The time sequencing of these photos is taken the photograph, generates and recalls video, still, which must utilize the photo in local photograph album, on the one hand,
User is not high enough using the frequency that the intelligent terminals such as mobile phone are taken pictures, and is limited to the quality and quantity of photo in local photograph album, generates
Memory video can not show the careful variation of personage, on the other hand, intelligent terminal shooting photo posture is different, background is more
Become, obtained memory video is integrally generated based on photo, the face's variation that finely can not compare out personage.
Based on this, it would be highly desirable to provide a kind of method of display face variation that can be true, careful, can reflect it for user
The slight change of face.
Summary of the invention
Technical problems to be solved in this application be to provide it is a kind of based on recognition of face unlocking function show face variation
Methods, devices and systems, so that reflection user face slight change can be generated in the case where not depending on local photograph album
The file of the formats such as video, to really display for a user the variation of face.
In a first aspect, providing a kind of method for showing face variation based on recognition of face unlocking function, comprising:
It is requested in response to generating, multiple corresponding target figures of target object in target time section in acquisition image data base
Picture, wherein it include that the target time section and the target object identify in the generation request, described image database packet
Include: shot when unlocking intelligent terminal by recognition of face mode unlock image, it is described unlock image shooting time and
Object identity in the unlock image;
Target text is generated according to the sequencing of the corresponding shooting time of the target image based on the target image
Part, the file destination are used to characterize face variation of the target object in the target time section;
Play the file destination.
Optionally, if the unlock image is original image when unlocking the intelligent terminal,
It is described to be based on the target image, according to the sequencing of the corresponding shooting time of the target image, generate mesh
Mark file, comprising:
The target image is carried out to Face datection, characteristic point detection and face registration process respectively, obtains the target
The corresponding face image of image;
According to the sequencing of the corresponding target image shooting time of the face image, it is based on the face image
Generate the file destination.
Optionally, if the unlock image is when unlocking the intelligent terminal by Face datection, characteristic point detection and people
The intermediate image of face registration process, then,
It is described to be based on the target image, according to the sequencing of the corresponding shooting time of the target image, generate mesh
File is marked, specifically:
According to the sequencing of the shooting time of the intermediate image, the target text is generated based on the intermediate image
Part.
Optionally, if the target time section is greater than default first time period threshold value, it is described to be based on the target figure
Picture generates file destination according to the sequencing of the corresponding shooting time of the target image, comprising:
From the target image, select the image of preset quantity as display image, alternatively, in each preset time week
Select an image as display image in phase;
According to the sequencing of the shooting time of the display image, the target text is generated based on the display image
Part.
Optionally, if the target time section is not more than default second time period threshold value, it is described to be based on the target figure
Picture generates file destination according to the sequencing of the corresponding shooting time of the target image, comprising:
According to the sequencing of the shooting time of the target image, the mesh is generated based on all target images
Mark file.
It is optionally, described to play the file destination, specifically: the target is played according to preset play time interval
Two neighboring image to be played in file.
Optionally, the play time interval of each adjacent two image to be played is identical, alternatively, each adjacent two waits broadcasting
The shooting interval put between the play time interval of image and the two neighboring image to be played is positively correlated.
Optionally, this method further include:
Prompt information is generated based on the file destination, and shows the prompt information, wherein the prompt information includes
Face situation of change and/or countermeasure of the target object in the target time section.
Optionally, described to request in response to generating, target object is corresponding in target time section in acquisition image data base
Multiple target images, comprising:
The generation request is parsed, the target time section and the target object are obtained;
From described image database, the shooting time is searched in the target time section and the object identity is institute
The unlock image for stating target object, as the target object.
Second aspect additionally provides a kind of device that face variation is shown based on recognition of face unlocking function, comprising:
Acquiring unit, for requesting in response to generating, target object is corresponding in target time section in acquisition image data base
Multiple target images, wherein include that the target time section and the target object identify in generation request, the figure
As database includes: the bat of the unlock image shot when unlocking intelligent terminal by recognition of face mode, the unlock image
Take the photograph the object identity in time and the unlock image;
Generation unit, for being based on the target image, according to the successive suitable of the corresponding shooting time of the target image
Sequence, generates file destination, and the file destination is used to characterize face variation of the target object in the target time section;
Broadcast unit, for playing the file destination.
Optionally, if the unlock image is original image when unlocking the intelligent terminal,
The generation unit, comprising:
Subelement is handled, for carrying out the target image respectively at Face datection, characteristic point detection and face alignment
Reason, obtains the corresponding face image of the target image;
First generates subelement, for according to the successive suitable of the corresponding target image shooting time of the face image
Sequence generates the file destination based on the face image.
Optionally, if the unlock image is when unlocking the intelligent terminal by Face datection, characteristic point detection and people
The intermediate image of face registration process, then,
The generation unit, is specifically used for:
According to the sequencing of the shooting time of the intermediate image, the target text is generated based on the intermediate image
Part.
Optionally, if the target time section is greater than default first time period threshold value, the generation unit, comprising:
Subelement is selected, for from the target image, selecting the image of preset quantity as display image, alternatively,
Select an image as display image in each preset period of time;
Second generates subelement, for the sequencing of the shooting time according to the display image, is based on the display
Image generates the file destination.
Optionally, if the target time section is not more than default second time period threshold value, the generation unit, specifically
For:
According to the sequencing of the shooting time of the target image, the mesh is generated based on all target images
Mark file.
Optionally, the broadcast unit, is specifically used for: playing in the file destination according to preset play time interval
Two neighboring image to be played.
Optionally, the play time interval of each adjacent two image to be played is identical, alternatively, each adjacent two waits broadcasting
The shooting interval put between the play time interval of image and the two neighboring image to be played is positively correlated.
Optionally, the device further include:
Display unit for generating prompt information based on the file destination, and shows the prompt information, wherein institute
Stating prompt information includes face situation of change and/or countermeasure of the target object in the target time section.
Optionally, the acquiring unit, comprising:
Parsing subunit obtains the target time section and the target object for parsing the generation request;
Search subelement, for from described image database, search the shooting time in the target time section and
The object identity is the unlock image of the target object, as the target object.
The third aspect additionally provides a kind of system for showing face variation based on recognition of face unlocking function, comprising: service
Device and intelligent terminal, wherein the application that face variation is shown based on recognition of face unlocking function is installed on the intelligent terminal
Program, the server provide service for the application program;
Wherein, the server, the generation request generated for receiving the application program, executes above-mentioned first aspect and mentions
The operation such as the acquisition, generation in the method for confession, and the file destination is sent to the intelligent terminal;
The intelligent terminal is shown for executing the operations such as the broadcasting, display in the method that above-mentioned first aspect provides
Show face variation of the target object in the target time section.
In the embodiment of the present application, a kind of method that face variation is shown based on recognition of face unlocking function is provided, it should
Method can specifically include: by recognition of face unlock intelligent terminal when unlock image, the unlock image shooting time and
It unlocks in the corresponding image data base for being stored in local or cloud of object identity in image, when user wants to check face
When variation, it is possible, firstly, to the object (that is, target object) for inputting the period (that is, target time section) checked and checking, triggering
It generates and generates request, wherein include that target time section and target object identify in the first generation request;Then, in response to this
Request is generated, multiple corresponding target images of target object in target time section in acquisition image data base;Then, it can be based on
The target image generates file destination according to the sequencing of the corresponding shooting time of target image;Finally, playing the target
File, the file destination are used to embody the face's variation of target object in the target time period.In this way, not depending on local photograph album
In the case where, it is contemplated that recognition of face unlock intelligent terminal function is gradually popularized, and is high frequency time row using unlock intelligent terminal
For and shoot image main body be face the characteristics of, by obtain and save user by recognition of face unlock intelligent terminal when
Unlock image, will unlock image as display user face variation resource, therefrom obtain image to be displayed generate reflection use
The file destination of the formats such as the video of family face slight change really displays for a user face by playing file destination realization
The effect of portion's slight change.
Detailed description of the invention
In order to more clearly explain the technical solutions in the embodiments of the present application, make required in being described below to embodiment
Attached drawing is briefly described, it should be apparent that, the accompanying drawings in the following description is only some implementations as described in this application
Example, for those of ordinary skill in the art, is also possible to obtain other drawings based on these drawings.
Fig. 1 is network system block schematic illustration involved in an application scenarios in the embodiment of the present application;
Fig. 2 is shown for the process of the method for being shown face variation based on recognition of face unlocking function a kind of in the embodiment of the present application
It is intended to;
Fig. 3 is a kind of face alignment effect schematic diagram in the embodiment of the present application;
Fig. 4 is shown for the structure of the device for being shown face variation based on recognition of face unlocking function a kind of in the embodiment of the present application
It is intended to;
Fig. 5 is shown for the structure of the system for being shown face variation based on recognition of face unlocking function a kind of in the embodiment of the present application
It is intended to.
Specific embodiment
Currently, user can carry out face's change to the face of personage in current photo by specific image processing software
The special effect processings such as shape, makeups obtain the photo of user childhood or senectitude, bring enjoyment to user, still, at the image
The result that reason software obtains not is true photo, and the real change of the user cannot be only reflected for consumer entertainment.And
In some intelligent terminals, in order to bring memory effect to user, photograph album has the function of to recall, that is, can pass through face
Identification, by the photo in local photograph album, sorts out according to its difference for being related to personage, the photo for being related to identical personage is included into
One memory photograph album, and according to the time sequencing for shooting these photos in the memory photograph album, it generates and recalls video, memory view
Frequency can display for a user the variation that some identical personage occurs over time.But it should returning by intelligent terminal
Recall the mode of the real change of function reflection personage, must be requested that the photograph album of intelligent terminal has the function of to recall, moreover, depending on
Photo in local photograph album compares limitation for a user.Except before this, which also has following problems: on the one hand, user
The frequency taken pictures using intelligent terminals such as mobile phones is not high enough, is limited to the quality and quantity of photo in local photograph album, and generation is returned
The careful variation of personage can not be shown by recalling video;On the other hand, the photo posture of intelligent terminal shooting is different, background is changeable,
Obtained memory video is integrally generated based on photo, and face only may occupy minimum position in photo, thus can not
The fine face's variation for comparing out personage.
With the development of technology, recognition of face unlocking function is gradually gained popularity on many intelligent terminals, more and more
User is provided through the function of recognition of face unlock intelligent terminal screen on intelligent terminal, then, it is contemplated that unlock intelligence
The screen of terminal belongs to high frequency time behavior, moreover, passing through when recognition of face solution lock screen, main body is face, invention in shooting image
The unlock image that people shoots when the study found that can use recognition of face unlock intelligent terminal screen is image resource, is generated anti-
The file of the formats such as the video of user face slight change is reflected, to really display for a user the variation of face.
Specifically, a kind of side for showing face variation based on recognition of face unlocking function provided by the embodiments of the present application
Method, detailed process may include: by recognition of face unlock intelligent terminal when unlock image, the unlock image shooting time with
And in the corresponding image data base for being stored in local or cloud of object identity in unlock image, when user wants to check face
Variation when, it is possible, firstly, to the object (that is, target object) for inputting the period (that is, target time section) checked and checking, touching
Hair, which generates, generates request, wherein includes that target time section and target object identify in the first generation request;Then, in response to
The generation is requested, multiple corresponding target images of target object in target time section in acquisition image data base;Then, Ji Keji
File destination is generated according to the sequencing of the corresponding shooting time of target image in the target image;Finally, playing the mesh
File is marked, which is used to embody the face's variation of target object in the target time period.
In this way, in the case where not depending on local photograph album, it is contemplated that recognition of face unlocks the gradually general of intelligent terminal function
And be high frequency time behavior using unlock intelligent terminal and shoot the characteristics of main body of image is face, by obtaining and saving use
Unlock image of the family when unlocking intelligent terminal by recognition of face will unlock image as the money of display user face variation
Source therefrom obtains the file destination that image to be displayed generates the formats such as the video of reflection user face slight change, passes through broadcasting
The file destination realizes the effect for really displaying for a user face's slight change.
For example, one of the scene of the embodiment of the present application, can be applied in scene as shown in Figure 1.The scene
In include user 100, mobile phone 200 and cloud server 300, wherein be equipped on mobile phone 200 based on recognition of face unlocking function
Show the application program 210 of face variation, cloud server 300 is the server of the application program 210.Wherein, the mobile phone 200
Also there is front camera 220, facial image can be acquired by front camera 220 and realizes that recognition of face unlocks mobile phone 200
Screen 230 function.It is understood that if user 100 is preset on mobile phone 200 using recognition of face solution screen locking
Curtain, and the face verification image of typing user 100 and its friend User 110, then, user 100 and user 110 can pass through
Its face is directed to the front camera 220 of mobile phone 200, its face is acquired by front camera 220 and unlocks image, the mobile phone
200, which unlock image and face verification image by face, is matched, and the screen 230 of mobile phone 200 is unlocked, so as to user 100 or
The mobile phone 200 can be used in user 110.
As an example, application program 210 can obtain user 100 and user 110 every time using recognition of face solution
The user identifier in the shooting time for unlocking image, unlocking image and unlock image when locking 200 screen 230 of mobile phone, and will solution
Lock image, the shooting time of unlock image is corresponded to corresponding save to the application program 210 of user identifier in unlock image
Cloud server 300 in image data base 310 on.When the details that user 100 wants oneself face in viewing nearly 1 month becomes
When change, the application program 210 on its mobile phone 200 can be opened, and select in the selection of time frame on the interface of application program 210
It selects " 2019-7-8 to 2019-8-8 ", selects " 100 " (that is, mark of user 100) in Object Selection frame, and click " generation " and press
Button, then, the application program 210 produce generation request, the generation request in include " 2019-7-8 to 2019-8-8 " and
"100";Then, which sends generation request to cloud server 300, in a kind of situation, cloud server
300 can request in response to the generation, and from all unlock images in image data base 310, " 2019-7-8 is arrived for acquisition
The unlock image of user " 100 ", is determined as target image, and by cloud server 300 according to each target figure during 2019-8-8 "
The sequencing of the shooting time of picture generates target video based on each target image, and then, cloud server 300 can should
Target video returns to the application program 210 on mobile phone 200, plays the target video by the application program 210, sees for user 100
See the careful variation of its face during " 2019-7-8 to 2019-8-8 ";In another case, application program 210 can also be rung
It should be requested in the generation, from all unlock images in the image data base 310 of cloud server 300, obtain " 2019-7-8
To the unlock image of user " 100 " during 2019-8-8 ", it is determined as target image, and by application program 210 according to each target figure
The sequencing of the shooting time of picture generates target video based on each target image, then plays the target by the application program 210
Video watches the careful variation of its face during " 2019-7-8 to 2019-8-8 " for user 100.In this way, realizing true
It is the effect that user 100 shows face's slight change.
It should be noted that application program 210 can also by it is obtained unlock image, unlock image shooting time and
The user identifier in image is unlocked, the application program 210 that corresponding preservation is established into the local memory of the mobile phone 200 is corresponding
In image data base 240, then, application program 210 can also be requested in response to generating, from the image data base of local memory
Target image is obtained in 240.
It should be noted that the cloud server 300 in the scene can also use property server equipment replacement, mobile phone
200 are also possible to other intelligent terminals for being equipped with application program 210 and supporting recognition of face unlock screen function, such as: plate
The equipment such as computer, intelligent door lock, are not especially limited in the embodiment of the present application.
It is understood that above-mentioned scene is only a Sample Scenario provided by the embodiments of the present application, the embodiment of the present application
It is not limited to this scene.
With reference to the accompanying drawing, it is described in detail by embodiment in the embodiment of the present application a kind of based on recognition of face unlock function
It can show the specific implementation of the method for face variation.
Fig. 2 is a kind of stream of method that face variation is shown based on recognition of face unlocking function provided by the embodiments of the present application
Journey schematic diagram.Referring to fig. 2, this method can specifically include:
Step 201, requested in response to generating, obtain in image data base target object in target time section it is corresponding multiple
Target image, wherein generating in request includes that target time section and target object identify, and image data base includes: to pass through people
Face identification method unlocks the object in the unlock image shot when intelligent terminal, the shooting time for unlocking image and unlock image
Mark.
It is understood that and being equipped with based on face if having recognition of face unlocking function on the intelligent terminal of user
Identify that unlocking function shows the application program of face variation, then, when there is user some on its intelligent terminal of viewing to use people
When the face of the legitimate user of face identification unlock changes demand, it can open and function is unlocked based on recognition of face on its intelligent terminal
It can show the application program of face variation, and typing target time section and target object mark in the application program, such as: record
Enter target time section: " 2019-7-8 to 2019-8-8 " and target object identify " 100 ", and directly triggering, which generates, generates request, or
Person clicks " generation " or " determination " button by user, and triggering, which generates, generates request.
Wherein, it generates in request, may include target time section and target object mark, target time section can be in intelligence
It can install at the time of showing the application program of face variation based on recognition of face unlocking function in terminal between current time
Any time period, target object mark can be the intelligent terminal typing, be allowed through pair of recognition of face solution lock screen
The mark of elephant, such as: the mark of user's first can be the name of first, unlock number of first etc..Request is generated, for requesting from figure
As database all unlock images in obtain with generate request in carry information matches target image, specifically can be used for asking
Ask from all unlock images of image data base obtain shooting time in the target time period and object identity be target object
The target image of mark.
It is understood that before step 201, once user is mounted with based on recognition of face solution on its intelligent terminal
Lock function shows the application program of face variation, and for user when each recognition of face unlocks the intelligent terminal, the image of shooting is equal
By as unlock image, is obtained and existed to its corresponding image data base by the application program, simultaneously as recognition of face solution
When lock, each unlock image can correspond to the mark of the shooting time for generating the unlock image and the object for including in unlock image,
So, for the unlock image in the subsequent use that can be convenient image data base, the file destination of high quality is generated, for
Face's slight change of target object is watched at family, provides the user with better experience, the bat that can will be unlocked image, unlock image
Take the photograph the time with unlock the mark of objects in images is corresponding is stored in the corresponding image data base of the application program.Wherein, scheme
As preserving a plurality of data in database, what every data corresponding user generated when being unlocked by recognition of face: unlock is schemed
Picture-shoots shooting time (or being also possible to the unlocked time)-secondary unlock object identity of the unlock image.
It when specific implementation, is requested in step 201 in response to generating, target pair in target time section in acquisition image data base
As multiple corresponding target images, can specifically include: S11, parsing generate request, obtain target time section and target object;
S12 searches shooting time in the unlock image that target time section and object identity are target object, makees from image data base
For target object.
By step 201, it is high frequency time behavior using unlock intelligent terminal and shoots the characteristics of main body of image is face,
By obtaining and saving unlock image of the user when unlocking intelligent terminal by recognition of face, used unlock image as display
The resource of family face variation therefrom obtains the corresponding target image of user demand, to realize that true display user face is subtle
The effect of variation provides the data basis of high quality.
Step 202, it is based on target image, according to the sequencing of the corresponding shooting time of target image, generates target text
Part, file destination are used to characterize the face's variation of target object in the target time period.
It is understood that file destination can be based on target image generate one section of video, be also possible to one it is unreal
Lamp piece file can also be the file that can play other any formats of display, not limit specifically in the embodiment of the present application
It is fixed.
When specific implementation, after obtaining target image, can according to the sequence of the shooting time of target image from morning to night,
Or from evening to early sequence, target image is ranked up, and target image is generated into file destination according to the sequence, thus
So that when playing file destination, target is playd in order according to shooting time sequence from morning to night or from evening to early sequence
Image.
It is understood that the unlock image saved in image data base, in a kind of situation, it can be the intelligent terminal and exist
The original image shot when being unlocked, that is, without Face datection, the original image of characteristic point detection and face registration process;Separately
In a kind of situation, it is also possible to the intelligent terminal and Face datection, characteristic point detection and face is carried out to original image when being unlocked
Intermediate image after registration process.
As an example, if unlock image is original image when unlocking intelligent terminal, target is based in step 202
Image generates file destination, can specifically include according to the sequencing of the corresponding shooting time of target image: S21, by mesh
Logo image carries out Face datection, characteristic point detection and face registration process respectively, obtains the corresponding face image of target image;
S22 generates file destination based on face image according to the sequencing of the corresponding target image shooting time of face image.This
Sample obtains the corresponding face image of target image, then generate target text based on face image by handling target image
Part, so that can embody face variation of the user under equal angular in file destination, improving user, to observe its face thin
The experience of microvariations.
Wherein, Face datection, which refers to, detects the corresponding part of face in unlock image;Characteristic point detection can refer to
The image that Face datection is obtained carries out key point calibration, obtains the characteristic point in unlock image on face, such as: it can pass through
Dlib demarcates the algorithm of 68 key points of face, obtains 68 key point coordinates in unlock image on face, and scheme in unlock
It is marked as in;Face alignment, the key point on the face in image and average key point position corresponding on the face will be unlocked by referring to
Alignment, can specifically carry out face alignment using affine transformation method, and face alignment can be used for eliminating people in each unlock image
The angular deviation of object, make every unlock image in include be personage positive face, face alignment effect schematic diagram such as Fig. 3 institute
Show, wherein average face is the synthetic appearance of a certain group obtained by calculation before carrying out face alignment, is had average
The group of face largely has similar appearance, relatively easily hits face.
As another example, if by Face datection, characteristic point detection and people when unlock image is unlock intelligent terminal
The intermediate image of face registration process is then based on target image, according to the elder generation of the corresponding shooting time of target image in step 202
Sequence afterwards generates file destination, can specifically include: according to the sequencing of the shooting time of intermediate image, being based on middle graph
As generating file destination.In this way, intermediate image is all with regard to treated intermediate image when by obtaining and be stored in unlock
Face image, so that can directly obtain qualified face image from image data base before generating file destination and make
For target image, then file destination directly can be generated based on target image, exists so that user can be embodied in file destination
Face's variation under equal angular, improves the experience that user observes its face's slight change.
It should be noted that the Face datection of original image, characteristic point detection and people when unlocking intelligent terminal in the example
Face registration process specifically may refer to corresponding explanation in example shown in S21~S22, repeat no more in this example.
In some possible implementations, it is contemplated that the behavior that user unlocks intelligent terminal occurs more frequent, that is,
Unlock image in image data base is more, therefore, in order to generate the file destination that playing duration meets user's tolerance interval,
It can also include: based on the length for generating the target time section in request, using different strategy generatings in the embodiment of the present application
File destination, it is ensured that the volume of file destination is moderate and playing duration is suitable.
As an example, it can preset first time period threshold value (such as 7 days), and be somebody's turn to do determining that target time section is greater than
When default first time period threshold value, the parts of images in selection target image is as the material for generating file destination.A kind of situation
Under, if target time section is greater than default first time period threshold value, target image is based in step 202, according to target image pair
The sequencing for the shooting time answered generates file destination, can specifically include: S31 selects present count from target image
The image of amount (such as: 100) is as display image;S32, according to the sequencing of the shooting time of display image, based on aobvious
Diagram picture generates file destination.Such as: assuming that 1000 target images of user's first at nearly 30 days are determined based on step 201,
It is possible to select 100 images as display figure at random or according to other any modes from 1000 target images
Picture, and this 100 display images are based on, file destination is generated according to the sequencing of shooting time.In another case, if mesh
The period is marked greater than default first time period threshold value, then, target image is based in step 202, according to the corresponding bat of target image
The sequencing of time is taken the photograph, file destination is generated, can specifically include: S41, from target image, in each preset time week
Select an image as display image in phase (such as 12 hours);S42, according to the successive suitable of the shooting time for showing image
Sequence generates file destination based on display image.Such as: assuming that determining user's first in 1000 of nearly 30 days based on step 201
Target image, it is possible to, according to shooting time, select 1 from the target image of per half a day from 1000 target images
Image is opened as display image, total available 60 displays image, so that this 60 display images are based on, according to shooting time
Sequencing generate file destination.
In this way, the target image due to acquisition can be overcome more, cause the file destination generated tediously long to user experience
Poor problem, by presetting first time period threshold value, in the case that target time section is greater than default first time period threshold value,
It determines that the target time section is too long, needs to screen the part in target image as the material for generating file destination, to ensure mesh
The volume of mark file is moderate and playing duration is suitable.
As another example, it can preset second time period threshold value (such as 5 days), and determine that target time section is little
It when default second time period threshold value, determines that the target time section of this time selection is moderate, whole target images can be made
For the material for generating file destination.So, target image is based in step 202, according to the corresponding shooting time of target image
Sequencing generates file destination, comprising: according to the sequencing of the shooting time of target image, based on all target figures
It include all target images in the file destination as generating file destination.It should be noted that the default second time period threshold
Value can be equal to default first time period threshold value, might be less that default first time period threshold value, in the embodiment of the present application not
Make specific limit.
In this way, by presetting second time period threshold value, when target time section is not more than the feelings of default second time period threshold value
Under condition, determine that the target time section is moderate, it, can be literary as target is generated using whole target images without screening target image
The material of part, so that the volume of file destination is moderate and playing duration is suitable.
Step 203, file destination is played.
When specific implementation, when generating file destination, that is, determine in file destination between two neighboring image to be played
According to playing out for preset play time interval, then, it, can be according to the preset broadcasting when playing the file destination
Time interval plays two neighboring image to be played in file destination.Wherein, play time interval refers to that broadcasting one is to be played
Time difference between at the time of image and at the time of next image to be played of broadcasting.
As an example, the play time interval of each adjacent two image to be played can be identical, such as: play time
Interval can be 0.1 second, then, it is assumed that it include 100 images in file destination, then, first image starts to play, and passes through
Start within 0.1 second to play second image, started to play third image using 0.1 second, and so on, play target text
Part takes around 10 seconds.
As another example, the play time interval of each adjacent two image to be played can be two neighboring wait broadcast with this
The shooting interval put between image is positively correlated.Wherein, the shooting interval between two neighboring image to be played, can be with
Refer to the time difference between at the time of shooting an image to be played and at the time of next image to be played of shooting.The example
In, in order to preferably show the linear character of face variation in time, the viewing experience of user is improved, in file destination
In, the play time interval of two neighboring image to be played, the shooting interval between two images to be played is related,
Specifically: the shooting interval between two images to be played is longer, and the play time interval of the two images to be played is set
That sets is longer, conversely, the shooting interval between two images to be played is shorter, the play time of the two images to be played
It is spaced shorter.Such as: it include image 1 to be played, image to be played 2 and image to be played 3 in file destination, and wait broadcast
It puts image 1 and image to be played 2 is adjacent, image 2 and image to be played 3 to be played are adjacent, it is assumed that image 1 to be played and to be played
The shooting interval of image 2 is 1 hour, and the shooting interval of image 2 and image to be played 3 to be played is 1 day, then,
It can be set and be divided between image 1 to be played and the play time of image to be played 2 0.1 second, image 2 to be played and image to be played
It is divided between 3 play time 2.4 seconds.
In addition, the embodiment of the present application not only can be generated and play file destination, it is watched within certain time for user
Face's variation, moreover, the embodiment of the present application can also include: while playing file destination, alternatively, literary playing target
After part, it is based on the file destination, prompt information is generated for user, and the prompt information is shown on intelligent terminal, the prompt
Information can specifically include: target object face's situation of change in the target time period and/or countermeasure.
When specific implementation, it should show that the application program of face variation can be by target based on recognition of face unlocking function
Image in file carries out analysis comparison, obtains the situation of change of the face of target object, such as: black eye exacerbation, decree line
Deepen etc., also, can also be intelligent provide the corresponding countermeasure of face's situation of change, such as: take a good rest, reinforce eye
Nursing, reinforcement decree line nursing etc., finally, generating prompt information is shown to user, such as: nearest one week black eye aggravates, and asks
It takes a good rest and reinforces eye maintenance.
As it can be seen that in the embodiment of the present application, providing a kind of side for showing face variation based on recognition of face unlocking function
Method, this method can specifically include: recognition of face is unlocked to the shooting time for unlocking image, unlock image when intelligent terminal
And in the corresponding image data base for being stored in local or cloud of object identity in unlock image, when user wants to check face
When the variation in portion, it is possible, firstly, to the object (that is, target object) for inputting the period (that is, target time section) checked and checking,
Triggering, which generates, generates request, wherein includes that target time section and target object identify in the first generation request;Then, it responds
It is requested in the generation, multiple corresponding target images of target object in target time section in acquisition image data base;Then
File destination is generated according to the sequencing of the corresponding shooting time of target image based on the target image;It should finally, playing
File destination, the file destination are used to embody the face's variation of target object in the target time period.In this way, not depending on local
In the case where photograph album, it is contemplated that recognition of face unlock intelligent terminal function is gradually popularized, and is high frequency using unlock intelligent terminal
The characteristics of main body of secondary behavior and shooting image is face is unlocking intelligence eventually by recognition of face by obtaining and saving user
Unlock image when end will unlock image as the resource of display user face variation, it is anti-therefrom to obtain image to be displayed generation
The file destination for reflecting the formats such as the video of user face slight change, it is really aobvious for user by playing file destination realization
Show the effect of face's slight change.
Fig. 4 is a kind of device 400 that face variation is shown based on recognition of face unlocking function provided by the embodiments of the present application
Structural schematic diagram.Referring to fig. 4, which can specifically include: acquiring unit 401, generation unit 402 and broadcast unit
403。
Wherein, acquiring unit 401, for being requested in response to generating, target in target time section in acquisition image data base
Multiple corresponding target images of object, wherein include the target time section and the target object mark in the generation request
Know, described image database includes: the unlock image shot when unlocking intelligent terminal by recognition of face mode, the unlock
Object identity in the shooting time of image and the unlock image;
Generation unit 402, for being based on the target image, according to the successive of the corresponding shooting time of the target image
Sequentially, file destination is generated, the file destination is used to characterize face of the target object in the target time section and becomes
Change;
Broadcast unit 403, for playing the file destination.
Optionally, if the unlock image is original image when unlocking the intelligent terminal,
The generation unit 402, comprising:
Subelement is handled, for carrying out the target image respectively at Face datection, characteristic point detection and face alignment
Reason, obtains the corresponding face image of the target image;
First generates subelement, for according to the successive suitable of the corresponding target image shooting time of the face image
Sequence generates the file destination based on the face image.
Optionally, if the unlock image is when unlocking the intelligent terminal by Face datection, characteristic point detection and people
The intermediate image of face registration process, then,
The generation unit 402, is specifically used for:
According to the sequencing of the shooting time of the intermediate image, the target text is generated based on the intermediate image
Part.
Optionally, if the target time section is greater than default first time period threshold value, the generation unit 402, packet
It includes:
Subelement is selected, for from the target image, selecting the image of preset quantity as display image, alternatively,
Select an image as display image in each preset period of time;
Second generates subelement, for the sequencing of the shooting time according to the display image, is based on the display
Image generates the file destination.
Optionally, if the target time section is not more than default second time period threshold value, the generation unit 402, tool
Body is used for:
According to the sequencing of the shooting time of the target image, the mesh is generated based on all target images
Mark file.
Optionally, the broadcast unit 403, is specifically used for: playing the target text according to preset play time interval
Two neighboring image to be played in part.
Optionally, the play time interval of each adjacent two image to be played is identical, alternatively, each adjacent two waits broadcasting
The shooting interval put between the play time interval of image and the two neighboring image to be played is positively correlated.
Optionally, the device 400 further include:
Display unit for generating prompt information based on the file destination, and shows the prompt information, wherein institute
Stating prompt information includes face situation of change and/or countermeasure of the target object in the target time section.
Optionally, the acquiring unit 401, comprising:
Parsing subunit obtains the target time section and the target object for parsing the generation request;
Search subelement, for from described image database, search the shooting time in the target time section and
The object identity is the unlock image of the target object, as the target object.
Foregoing description is a kind of associated description of device 400 that face variation is shown based on recognition of face unlocking function,
In, specific implementation and the effect reached may refer to shown in Fig. 2 a kind of based on recognition of face unlocking function display people
The description of the embodiment of the method for face variation, which is not described herein again.
In addition, the embodiment of the present application also provides a kind of systems for showing face variation based on recognition of face unlocking function
500, as shown in figure 5, the system 500 includes: server 510 and intelligent terminal 520, wherein installed on the intelligent terminal 520
There is the application program 521 that face variation is shown based on recognition of face unlocking function, the server 510 is the application program
521 provide service;
Wherein, the server 510, the generation request generated for receiving the application program, executes shown in above-mentioned Fig. 2
Embodiment in the acquisition, the operation such as generation, and the file destination is sent to the intelligent terminal 520;
The intelligent terminal 520 is shown for executing the operation such as the broadcasting, display in above-mentioned embodiment shown in Fig. 2
Show face variation of the target object in the target time section.
Foregoing description is a kind of associated description of system 500 that face variation is shown based on recognition of face unlocking function,
In, specific implementation and the effect reached may refer to shown in Fig. 2 a kind of based on recognition of face unlocking function display people
The description of the embodiment of the method for face variation, which is not described herein again.
" first " in the titles such as " the first generation unit " mentioned in the embodiment of the present application, " first time period threshold value " is only
It is not represent first sequentially for doing name mark.The rule is equally applicable to " second " etc..
As seen through the above description of the embodiments, those skilled in the art can be understood that above-mentioned implementation
All or part of the steps in example method can add the mode of general hardware platform to realize by software.Based on this understanding,
The technical solution of the application can be embodied in the form of software products, which can store is situated between in storage
In matter, such as read-only memory (English: read-only memory, ROM)/RAM, magnetic disk, CD etc., including some instructions to
So that a computer equipment (can be the network communication equipments such as personal computer, server, or router) executes
Method described in certain parts of each embodiment of the application or embodiment.
All the embodiments in this specification are described in a progressive manner, same and similar portion between each embodiment
Dividing may refer to each other, and each embodiment focuses on the differences from other embodiments.Especially for device reality
For applying example and system embodiment, since it is substantially similar to the method embodiment, so describe fairly simple, related place ginseng
See the part explanation of embodiment of the method.Apparatus and system embodiment described above is only schematical, wherein making
It may or may not be physically separated for the module of separate part description, the component shown as module can be
Or it may not be physical module, it can it is in one place, or may be distributed over multiple network units.It can be with
Some or all of the modules therein is selected to achieve the purpose of the solution of this embodiment according to the actual needs.The common skill in this field
Art personnel can understand and implement without creative efforts.
The above is only the preferred embodiment of the application, is not intended to limit the protection scope of the application.It should refer to
Out, for those skilled in the art, it under the premise of not departing from the application, can also make several improvements
And retouching, these improvements and modifications also should be regarded as the protection scope of the application.
Claims (19)
1. a kind of method for showing face variation based on recognition of face unlocking function characterized by comprising
It is requested in response to generating, multiple corresponding target images of target object in target time section in acquisition image data base,
In, it include that the target time section and the target object identify in the generation request, described image database includes: logical
The shooting time of the unlock image, the unlock image that are shot when crossing face identification method unlock intelligent terminal and the unlock
Object identity in image;
File destination, institute are generated according to the sequencing of the corresponding shooting time of the target image based on the target image
File destination is stated for characterizing face variation of the target object in the target time section;
Play the file destination.
2. the method according to claim 1, wherein if the unlock image is when unlocking the intelligent terminal
Original image, then,
It is described to be based on the target image, according to the sequencing of the corresponding shooting time of the target image, generate target text
Part, comprising:
The target image is carried out to Face datection, characteristic point detection and face registration process respectively, obtains the target image
Corresponding face image;
According to the sequencing of the corresponding target image shooting time of the face image, generated based on the face image
The file destination.
3. the method according to claim 1, wherein if the unlock image is to pass through when unlocking the intelligent terminal
Cross the intermediate image of Face datection, characteristic point detection and face registration process, then,
It is described to be based on the target image, according to the sequencing of the corresponding shooting time of the target image, generate target text
Part, specifically:
According to the sequencing of the shooting time of the intermediate image, the file destination is generated based on the intermediate image.
4. the method according to claim 1, wherein if the target time section is greater than default first time period threshold
Value, then it is, described to be based on the target image, according to the sequencing of the corresponding shooting time of the target image, generate target
File, comprising:
From the target image, select the image of preset quantity as display image, alternatively, in each preset period of time
Select an image as display image;
According to the sequencing of the shooting time of the display image, the file destination is generated based on the display image.
5. the method according to claim 1, wherein if the target time section is not more than default second time period
Threshold value, then it is, described to be based on the target image, according to the sequencing of the corresponding shooting time of the target image, generate mesh
Mark file, comprising:
According to the sequencing of the shooting time of the target image, the target text is generated based on all target images
Part.
6. the method according to claim 1, wherein described play the file destination, specifically: according to default
Play time interval play two neighboring image to be played in the file destination.
7. according to the method described in claim 6, it is characterized in that, between the play time of each adjacent two image to be played
Every identical, alternatively, between the play time interval of each adjacent two image to be played and the two neighboring image to be played
Shooting interval be positively correlated.
8. the method according to claim 1, wherein further include:
Prompt information is generated based on the file destination, and shows the prompt information, wherein the prompt information includes described
Face situation of change and/or countermeasure of the target object in the target time section.
9. being obtained in image data base the method according to claim 1, wherein described request in response to generating
Multiple corresponding target images of target object in target time section, comprising:
The generation request is parsed, the target time section and the target object are obtained;
From described image database, the shooting time is searched in the target time section and the object identity is the mesh
The unlock image for marking object, as the target object.
10. a kind of device for showing face variation based on recognition of face unlocking function characterized by comprising
Acquiring unit, for requesting in response to generating, target object is corresponding more in target time section in acquisition image data base
Open target image, wherein it include that the target time section and the target object identify in the generation request, described image number
When including: the unlock image shot when unlocking intelligent terminal by recognition of face mode, the shooting of the unlock image according to library
Between and it is described unlock image in object identity;
Generation unit, it is raw according to the sequencing of the corresponding shooting time of the target image for being based on the target image
At file destination, the file destination is used to characterize face variation of the target object in the target time section;
Broadcast unit, for playing the file destination.
11. device according to claim 10, which is characterized in that if the unlock image is when unlocking the intelligent terminal
Original image, then,
The generation unit, comprising:
Subelement is handled, for the target image to be carried out to Face datection, characteristic point detection and face registration process respectively, is obtained
To the corresponding face image of the target image;
First generates subelement, for the sequencing according to the corresponding target image shooting time of the face image,
The file destination is generated based on the face image.
12. device according to claim 10, which is characterized in that if the unlock image is when unlocking the intelligent terminal
By Face datection, the intermediate image of characteristic point detection and face registration process, then,
The generation unit, is specifically used for:
According to the sequencing of the shooting time of the intermediate image, the file destination is generated based on the intermediate image.
13. device according to claim 10, which is characterized in that if the target time section is greater than default first time period
Threshold value, then, and the generation unit, comprising:
Subelement is selected, for from the target image, selecting the image of preset quantity as display image, alternatively, every
Select an image as display image in a preset period of time;
Second generates subelement, for the sequencing of the shooting time according to the display image, is based on the display image
Generate the file destination.
14. device according to claim 10, which is characterized in that if the target time section is not more than default second time
Section threshold value, then, the generation unit is specifically used for:
According to the sequencing of the shooting time of the target image, the target text is generated based on all target images
Part.
15. device according to claim 10, which is characterized in that the broadcast unit is specifically used for: broadcasting according to preset
It puts time interval and plays two neighboring image to be played in the file destination.
16. device according to claim 15, which is characterized in that the play time of each adjacent two image to be played
Be spaced it is identical, alternatively, the play time interval of each adjacent two image to be played and the two neighboring image to be played it
Between shooting interval be positively correlated.
17. device according to claim 10, which is characterized in that further include:
Display unit for generating prompt information based on the file destination, and shows the prompt information, wherein described to mention
Show that information includes face situation of change and/or countermeasure of the target object in the target time section.
18. device according to claim 10, which is characterized in that the acquiring unit, comprising:
Parsing subunit obtains the target time section and the target object for parsing the generation request;
Subelement is searched, for from described image database, searches the shooting time in the target time section and described
Object identity is the unlock image of the target object, as the target object.
19. a kind of system for showing face variation based on recognition of face unlocking function characterized by comprising server and intelligence
Energy terminal, wherein the application program that face variation is shown based on recognition of face unlocking function, institute are equipped on the intelligent terminal
It states server and provides service for the application program;
Wherein, the server, the generation request generated for receiving the application program, executes the claims 1~9
The operation such as described acquisition, generation in method described in meaning one, and the file destination is sent to the intelligent terminal;
The intelligent terminal, for executing the broadcasting, display in method described in 1~9 any one of the claims
Deng operation, face variation of the target object in the target time section is shown.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910786632.8A CN110490162A (en) | 2019-08-23 | 2019-08-23 | The methods, devices and systems of face variation are shown based on recognition of face unlocking function |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910786632.8A CN110490162A (en) | 2019-08-23 | 2019-08-23 | The methods, devices and systems of face variation are shown based on recognition of face unlocking function |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110490162A true CN110490162A (en) | 2019-11-22 |
Family
ID=68553765
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910786632.8A Pending CN110490162A (en) | 2019-08-23 | 2019-08-23 | The methods, devices and systems of face variation are shown based on recognition of face unlocking function |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110490162A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111680175A (en) * | 2020-05-15 | 2020-09-18 | 浙江大华技术股份有限公司 | Face database building method, computer equipment and computer readable storage medium |
CN111835987A (en) * | 2020-06-08 | 2020-10-27 | 广东以诺通讯有限公司 | Video generation method based on face recognition |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107563328A (en) * | 2017-09-01 | 2018-01-09 | 广州智慧城市发展研究院 | A kind of face identification method and system based under complex environment |
CN108022274A (en) * | 2017-11-29 | 2018-05-11 | 广东欧珀移动通信有限公司 | Image processing method, device, computer equipment and computer-readable recording medium |
CN108108415A (en) * | 2017-12-13 | 2018-06-01 | 广东欧珀移动通信有限公司 | Image processing method, device, storage medium and electronic equipment |
CN108875491A (en) * | 2017-10-11 | 2018-11-23 | 北京旷视科技有限公司 | Data-updating method, authenticating device and the system and non-volatile memory medium of face unlock certification |
CN109147017A (en) * | 2018-08-28 | 2019-01-04 | 百度在线网络技术(北京)有限公司 | Dynamic image generation method, device, equipment and storage medium |
-
2019
- 2019-08-23 CN CN201910786632.8A patent/CN110490162A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107563328A (en) * | 2017-09-01 | 2018-01-09 | 广州智慧城市发展研究院 | A kind of face identification method and system based under complex environment |
CN108875491A (en) * | 2017-10-11 | 2018-11-23 | 北京旷视科技有限公司 | Data-updating method, authenticating device and the system and non-volatile memory medium of face unlock certification |
CN108022274A (en) * | 2017-11-29 | 2018-05-11 | 广东欧珀移动通信有限公司 | Image processing method, device, computer equipment and computer-readable recording medium |
CN108108415A (en) * | 2017-12-13 | 2018-06-01 | 广东欧珀移动通信有限公司 | Image processing method, device, storage medium and electronic equipment |
CN109147017A (en) * | 2018-08-28 | 2019-01-04 | 百度在线网络技术(北京)有限公司 | Dynamic image generation method, device, equipment and storage medium |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111680175A (en) * | 2020-05-15 | 2020-09-18 | 浙江大华技术股份有限公司 | Face database building method, computer equipment and computer readable storage medium |
CN111680175B (en) * | 2020-05-15 | 2023-04-25 | 浙江大华技术股份有限公司 | Face database construction method, computer equipment and computer readable storage medium |
CN111835987A (en) * | 2020-06-08 | 2020-10-27 | 广东以诺通讯有限公司 | Video generation method based on face recognition |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11394708B2 (en) | Account information obtaining method, terminal, server and system | |
CN104618803B (en) | Information-pushing method, device, terminal and server | |
CN105144156B (en) | Metadata is associated with the image in personal images set | |
CN105917359A (en) | Mobile video search | |
CN105825721B (en) | Photographing question asking method and device and intelligent device | |
TWI781554B (en) | Method of determining item name of object, device, computer equipment and storage medium | |
CN108197336B (en) | Video searching method and device | |
CN104506946B (en) | A kind of TV programme recognition methods and system based on image recognition | |
CN106375193A (en) | Remote group photographing method | |
US11503110B2 (en) | Method for presenting schedule reminder information, terminal device, and cloud server | |
CN103609098B (en) | Method and apparatus for being registered in telepresence system | |
CN110490162A (en) | The methods, devices and systems of face variation are shown based on recognition of face unlocking function | |
CN106021506A (en) | File storage method and apparatus for cluster system | |
CN110489659A (en) | Data matching method and device | |
CN107872713A (en) | Short processing system for video, method and device | |
CN103984931A (en) | Information processing method and first electronic equipment | |
CN112163993A (en) | Image processing method, device, equipment and storage medium | |
CN106649592A (en) | Display method and display device for application search results | |
CN113128278B (en) | Image recognition method and device | |
CN110381372A (en) | A kind of method and device carrying out video playing based on selection result | |
US11222494B2 (en) | Indexing a video surveillance stream to match an access control credential or token with best facial image detected at a security portal method of operation and system | |
CN107491934A (en) | A kind of 3D interview exam systems based on virtual reality | |
KR102142530B1 (en) | Information processing systems, information processing devices and programs | |
US9529984B2 (en) | System and method for verification of user identification based on multimedia content elements | |
CN106202341A (en) | Relational network construction method in conjunction with photographic intelligence Yu Identification of Images |
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: 20191122 |
|
RJ01 | Rejection of invention patent application after publication |