CN107886559A - Method and apparatus for generating picture - Google Patents
Method and apparatus for generating picture Download PDFInfo
- Publication number
- CN107886559A CN107886559A CN201711223801.4A CN201711223801A CN107886559A CN 107886559 A CN107886559 A CN 107886559A CN 201711223801 A CN201711223801 A CN 201711223801A CN 107886559 A CN107886559 A CN 107886559A
- Authority
- CN
- China
- Prior art keywords
- dynamic picture
- dimensional
- dimensional dynamic
- picture
- face object
- 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
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T13/00—Animation
- G06T13/20—3D [Three Dimensional] animation
- G06T13/40—3D [Three Dimensional] animation of characters, e.g. humans, animals or virtual beings
-
- 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
- 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
- G06V40/161—Detection; Localisation; Normalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Library & Information Science (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Human Computer Interaction (AREA)
- Health & Medical Sciences (AREA)
- Multimedia (AREA)
- General Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Processing Or Creating Images (AREA)
Abstract
The embodiment of the present application discloses the method and apparatus for generating picture.One embodiment of this method includes：In response to determining to include face object in target video, the posture feature of the face object is extracted；The Three-Dimensional Dynamic picture matched with the posture feature of the face object is found out from default Three-Dimensional Dynamic picture set；Enter row format conversion to the target video, generate face dynamic picture；The Three-Dimensional Dynamic picture and the face dynamic picture that posture feature with the face object is matched are overlapped, and generate three-dimensional overlay dynamic picture.The embodiment of the present application enriches the available picture resource of user.
Description
Technical field
The invention relates to field of computer technology, and in particular to Internet technical field, it is more particularly, to raw
Into the method and apparatus of picture.
Background technology
Augmented reality (Augmented Reality, AR) picture is extraordinary for user because of its outstanding third dimension
Available resources, can be carrying out online chat or network comment etc..In existing input scene, user can make
The expression way of non-linguistic information is used as by the use of existing picture resource.
The content of the invention
The embodiment of the present application proposes the data capture method and device for server.
In a first aspect, the embodiment of the present application provides a kind of method for generating picture, including：In response to determining target
Face object is included in video, extracts the posture feature of face object；Found out from default Three-Dimensional Dynamic picture set with
The Three-Dimensional Dynamic picture of the posture feature matching of face object；Enter row format conversion to target video, generate face dynamic picture；
The Three-Dimensional Dynamic picture and face dynamic picture that posture feature with face object is matched are overlapped, and generation three-dimensional overlay moves
State picture.
In certain embodiments, each Three-Dimensional Dynamic picture in default Three-Dimensional Dynamic picture set is configured with corresponding appearance
State feature templates；The Three-Dimensional Dynamic matched with the posture feature of face object is found out from default Three-Dimensional Dynamic picture set
Picture, including：By at least one Three-Dimensional Dynamic figure in the posture feature of face object and default Three-Dimensional Dynamic picture set
The posture feature template of piece matches, to determine the Three-Dimensional Dynamic picture matched with the posture feature of face object.
In certain embodiments, the posture feature with face object is found out from default Three-Dimensional Dynamic picture set
The Three-Dimensional Dynamic picture matched somebody with somebody, including：Extract the feature of each Three-Dimensional Dynamic picture in Three-Dimensional Dynamic picture set；Utilize face object
The feature of posture feature and at least one Three-Dimensional Dynamic picture in default Three-Dimensional Dynamic picture set match, to determine
The Three-Dimensional Dynamic picture matched with the posture feature of face object.
In certain embodiments, Three-Dimensional Dynamic picture includes at least one Three-Dimensional Dynamic element, each Three-Dimensional Dynamic element point
A predeterminable area of face object is not corresponded to；The Three-Dimensional Dynamic picture and face that posture feature with face object is matched move
State picture is overlapped, and generates three-dimensional overlay dynamic picture, including：Determine position and the chi of each predeterminable area of face object
It is very little；Each Three-Dimensional Dynamic element in the Three-Dimensional Dynamic picture that will be matched with the posture feature of face object with corresponding preset areas
The positions and dimensions that domain matches are superimposed upon on face dynamic picture, generate three-dimensional overlay dynamic picture.
In certain embodiments, method also includes：Target video is obtained, and detects in target video whether include face pair
As, wherein, target video is to be selected by terminal device in response to detecting user in the expression figure chosen area of interface of input method
Surely input the operation of Three-Dimensional Dynamic picture and gather.
Second aspect, the embodiment of the present application provide a kind of device for being used to generate picture, including：Extraction unit, configuration
For in response to determining to include face object in target video, extracting the posture feature of face object；Searching unit, it is configured to
The Three-Dimensional Dynamic picture matched with the posture feature of face object is found out from default Three-Dimensional Dynamic picture set；Generation is single
Member, it is configured to enter target video row format conversion, generates face dynamic picture；Superpositing unit, be configured to by with face
The Three-Dimensional Dynamic picture and face dynamic picture of the posture feature matching of object are overlapped, and generate three-dimensional overlay dynamic picture.
In certain embodiments, each Three-Dimensional Dynamic picture in default Three-Dimensional Dynamic picture set is configured with corresponding appearance
State feature templates；Searching unit is further configured to：By the posture feature of face object and default Three-Dimensional Dynamic pictures
The posture feature template of at least one Three-Dimensional Dynamic picture in conjunction matches, to determine to match with the posture feature of face object
Three-Dimensional Dynamic picture.
In certain embodiments, searching unit, including：Extraction module, it is configured to extract in Three-Dimensional Dynamic picture set
The feature of each Three-Dimensional Dynamic picture；Determining module, it is configured to the posture feature using face object and default Three-Dimensional Dynamic
The feature of at least one Three-Dimensional Dynamic picture in picture set matches, to determine what is matched with the posture feature of face object
Three-Dimensional Dynamic picture.
In certain embodiments, Three-Dimensional Dynamic picture includes at least one Three-Dimensional Dynamic element, each Three-Dimensional Dynamic element point
A predeterminable area of face object is not corresponded to；Superpositing unit, including：Parameter determination module, it is configured to determine face object
Each predeterminable area positions and dimensions；Laminating module, the three-dimensional for being configured to match the posture feature with face object are moved
Each Three-Dimensional Dynamic element in state picture is superimposed upon face Dynamic Graph with the positions and dimensions to match with corresponding predeterminable area
On piece, three-dimensional overlay dynamic picture is generated.
In certain embodiments, the device also includes：Acquiring unit, it is configured to obtain target video, and detects target
Whether face object is included in video, wherein, target video is in response to detecting user in interface of input method by terminal device
Expression figure chosen area in select input Three-Dimensional Dynamic picture operation and gather.
The third aspect, the embodiment of the present application provide a kind of electronic equipment, including：One or more processors；Storage dress
Put, for storing one or more programs, when one or more programs are executed by one or more processors so that one or more
Individual processor is realized such as the method for any embodiment in the method for handling image.
Fourth aspect, the embodiment of the present application provide a kind of computer-readable recording medium, are stored thereon with computer journey
Sequence, realized when the program is executed by processor such as the method for any embodiment in the method for handling image.
The method and apparatus for generating picture that the embodiment of the present application provides, first, in response to determining in target video
Include face object, the posture feature of extraction face object.Then, find out from default Three-Dimensional Dynamic picture set and people
The Three-Dimensional Dynamic picture of the posture feature matching of face object.Afterwards, row format conversion is entered to target video, generates face Dynamic Graph
Piece.Finally, the Three-Dimensional Dynamic picture and face dynamic picture posture feature with face object matched is overlapped, generation three
Dimension superposition dynamic picture.The embodiment of the present application enriches the available picture resource of user.
Brief description of the drawings
By reading the detailed description made to non-limiting example made with reference to the following drawings, the application's is other
Feature, objects and advantages will become more apparent upon：
Fig. 1 is that the application can apply to exemplary system architecture figure therein；
Fig. 2 is the flow chart for being used to generate one embodiment of the method for picture according to the application；
Fig. 3 is the schematic diagram for being used to generate an application scenarios of the method for picture according to the application；
Fig. 4 A are the flow charts for being used to generate another embodiment of the method for picture according to the application；
Fig. 4 B are the schematic diagrames for the three-dimensional overlay dynamic picture that the method flow according to Fig. 4 A is generated；
Fig. 5 is the flow chart for being used to generate another embodiment of the method for picture according to the application；
Fig. 6 is the structural representation for being used to generate one embodiment of the device of picture according to the application；
Fig. 7 is adapted for the structural representation of the computer system of the electronic equipment for realizing the embodiment of the present application.
Embodiment
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
Be easy to describe, illustrate only in accompanying drawing to about the related part of invention.
It should be noted that in the case where not conflicting, the feature in embodiment and embodiment in the application can phase
Mutually combination.Describe the application in detail below with reference to the accompanying drawings and in conjunction with the embodiments.
Fig. 1 shows the method for being used to generate picture that can apply the application or the implementation of the device for generating picture
The exemplary system architecture 100 of example.
As shown in figure 1, system architecture 100 can include terminal device 101,102,103, network 104 and server 105.
Network 104 between terminal device 101,102,103 and server 105 provide communication link medium.Network 104 can be with
Including various connection types, such as wired, wireless communication link or fiber optic cables etc..
User can be interacted with using terminal equipment 101,102,103 by network 104 with server 105, to receive or send out
Send message etc..Various telecommunication customer end applications can be installed, such as web browser should on terminal device 101,102,103
With, shopping class application, searching class application, JICQ, mailbox client, social platform software etc..
Terminal device 101,102,103 can be the various electronic equipments for having camera, including but not limited to intelligent hand
Machine, tablet personal computer, E-book reader, dynamic image expert's compression standard audio aspect 4) player, portable calculating on knee
Machine and desktop computer etc..
Server 105 can be to provide the server of various services, such as to the input on terminal device 101,102,103
Method provides the backstage input method server of the supports such as dictionary, expression storehouse.Backstage input method server can be to receiving input
Request is analyzed and processed, and result (such as input results) is fed back into terminal device.
It should be noted that the embodiment of the present application provided be used for generate picture method can by terminal device 101,
102nd, 103 or server 105 perform, correspondingly, the device for generating picture can be arranged at terminal device 101,102,
103 or server 105 in.
It should be understood that the number of the terminal device, network and server in Fig. 1 is only schematical.According to realizing need
Will, can have any number of terminal device, network and server.
With continued reference to Fig. 2, the flow for being used to generate one embodiment of the method for picture according to the application is shown
200.This is used for the method for generating picture, comprises the following steps：
Step 201, in response to determining to include face object in target video, the posture feature of face object is extracted.
In the present embodiment, electronic equipment (such as the terminal shown in Fig. 1 thereon is run for generating the method for picture
Equipment or server) after it is determined that including face object in target video, then respond：Extract the appearance of above-mentioned face object
State feature.Above-mentioned electronic equipment can pass through terminal device used in wired connection mode or radio connection from user
Receive above-mentioned target video.The target video can be that user is shot using above-mentioned terminal device or user uploads
Into above-mentioned terminal device.Posture feature is the feature of the posture of reflection face object, can be represented in vector form.Than
Such as, posture feature can be the position relationship between several characteristic points of face object.Characteristic point can be carried from picture
The point of the expression face characteristic taken out, can accurately indicate a site in face, for example can be face, can also
It is right eye angle, upper lip centre site of right eye etc..In actual scene, different posture features represents the different emotions of people
State, such as facial pose of the people when doing different expression (doing different facial actions in other words) are different.In the present embodiment
By extracting the posture feature of face object, to express the different emotional states that face object implies.
In practice, the posture feature of face object can be extracted by the identification of human face posture.Specifically, can adopt
With the posture feature of various ways extraction face object.Specifically, local binary patterns (Local Binary can be used
Pattern, LBP), active appearance models (Active Appearance Model, AAM) etc. carry out the extraction of posture feature.
In the present embodiment, the posture of face object can be countenance, can also be facial action.Countenance is
In the emotion that facial expressiveness goes out.For example countenance can be indignation, happiness etc..Facial action is moved what face made
Make.For example facial action can be opened one's mouth, close one's eyes etc..
Step 202, three matched with the posture feature of face object are found out from default Three-Dimensional Dynamic picture set
Tie up dynamic picture.
In the present embodiment, above-mentioned electronic equipment is found out and face object from default Three-Dimensional Dynamic picture set
The Three-Dimensional Dynamic picture that matches of posture feature.Three-Dimensional Dynamic picture is the dynamic picture for showing three-dimensional stereo effect.Three
The set of dimension dynamic picture is the picture set being made up of Three-Dimensional Dynamic picture.Each Zhang San tie up dynamic picture all with face object
Corresponding relation be present in several posture features.Different Three-Dimensional Dynamic pictures corresponds to the combination of different posture features.This is corresponding
Relation can be stored in advance in local or other electronic equipments, for example is existed in a manner of mapping table.It is right by this
The posture feature with face object should be related to, the Three-Dimensional Dynamic figure corresponding with the posture feature of face object can be found
Piece.Herein, can be without using whole posture features of face object in Three-Dimensional Dynamic picture corresponding to lookup.Such as
The posture feature related to nose and eyes can only be used.
In practice, Three-Dimensional Dynamic picture can be AR dynamic pictures.
Step 203, row format conversion is entered to target video, generates face dynamic picture.
In the present embodiment, above-mentioned electronic equipment enters row format conversion to above-mentioned target video.Form conversion result be
Face dynamic picture.Herein, form conversion is the form that target video is converted to dynamic picture from video format.Such as
Target video can be converted to GIF forms from mpeg format.Face dynamic picture is the dynamic picture comprising face.
Step 204, the Three-Dimensional Dynamic picture and face dynamic picture posture feature with face object matched is folded
Add, generate three-dimensional overlay dynamic picture.
In the present embodiment, above-mentioned electronic equipment is folded the Three-Dimensional Dynamic picture found and face dynamic picture
Add, generate three-dimensional overlay dynamic picture.Presented in the three-dimensional overlay dynamic picture generated in above-mentioned Three-Dimensional Dynamic picture
Three-Dimensional Dynamic pattern, while also present above-mentioned face object.In practice, the three-dimensional overlay dynamic picture of generation can be through
Cross the AR dynamic pictures of superposition.Specifically, each frame picture of Three-Dimensional Dynamic picture can be first extracted, and extracts face Dynamic Graph
Each frame picture in piece.Afterwards, each frame picture in each the frame picture and face dynamic picture in Three-Dimensional Dynamic picture is entered
Row superposition.
With continued reference to Fig. 3, Fig. 3 is the signal for being used to generate the application scenarios of the method for picture according to the present embodiment
Figure.In Fig. 3 application scenarios, user shoots and uploads one section of video to server 301 by terminal device 302 first
303.Afterwards, above-mentioned server 301 extracts the posture of face object in response to determining to include face object in above-mentioned video 303
Feature 304.Above-mentioned server 301 is found out and the posture feature of face object 304 from default Three-Dimensional Dynamic picture set
The Three-Dimensional Dynamic picture 305 of matching.Above-mentioned server 301 enters row format conversion to above-mentioned video 303, generates face dynamic picture
306.The Three-Dimensional Dynamic picture 305 and face dynamic picture 306 that above-mentioned server 301 matches the posture feature with face object
It is overlapped, generation three-dimensional overlay dynamic picture 307.
The method that above-described embodiment of the application provides enriches the available picture resource of user.
With further reference to Fig. 4 A, it illustrates the flow 400 of another embodiment of the method for generating picture.The use
In the flow 400 of the method for generation picture, comprise the following steps：
Step 401, in response to determining to include face object in target video, the posture feature of face object is extracted.
In the present embodiment, electronic equipment (such as the service shown in Fig. 1 thereon is run for generating the method for picture
Device) after it is determined that including face object in target video, then respond：Extract the posture feature of above-mentioned face object.On
Stating electronic equipment can be above-mentioned by terminal device reception used in wired connection mode or radio connection from user
Target video.The target video can be that user is shot using above-mentioned terminal device or user uploads to above-mentioned end
In end equipment.Posture feature is the feature of the posture of reflection face object.Posture feature can show in vector form.
Step 402, by least one three-dimensional in the posture feature of face object and default Three-Dimensional Dynamic picture set
The posture feature template of dynamic picture matches, to determine the Three-Dimensional Dynamic picture matched with the posture feature of face object.
In the present embodiment, above-mentioned server is by the posture feature of face object and default Three-Dimensional Dynamic picture set
The posture feature template of at least one Three-Dimensional Dynamic picture match, to determine matched with the posture feature of face object three
Tie up dynamic picture.Each Three-Dimensional Dynamic picture in default Three-Dimensional Dynamic picture set is configured with corresponding posture feature template.
Posture feature template includes the posture feature of one group of fixation, and it is special that different Three-Dimensional Dynamic pictures corresponds to different postures
Levy template.The posture feature of above-mentioned face object is matched with posture feature template, can be the posture for calculating face object
Similarity between feature and posture feature template, posture feature is identical or the similarity of posture feature is more than default threshold value
It is then matching.In addition it is also possible to select the maximum posture feature template as matching of similarity.In practice, can be according to
Order set in advance is matched with each pose template.When the pose template for finding matching, then can stop matching
Journey.So the posture feature of face object needs to match with least one posture feature template in the matching process.
Step 403, row format conversion is entered to target video, generates face dynamic picture.
In the present embodiment, above-mentioned server enters row format conversion to above-mentioned target video.The result that form is changed is people
Face dynamic picture.Herein, form conversion is the form that target video is converted to dynamic picture from video format.Such as can
So that target video is converted into GIF forms from mpeg format.Face dynamic picture is the dynamic picture for presenting face.
Step 404, the positions and dimensions of each predeterminable area of face object are determined.
In the present embodiment, above-mentioned server can determine the positions and dimensions of each predeterminable area of face object.Three
Dimension dynamic picture includes at least one Three-Dimensional Dynamic element, and each Three-Dimensional Dynamic element corresponds to a preset areas of face object respectively
Domain.Three-Dimensional Dynamic element is the part in the entirety for the three-D pattern that Three-Dimensional Dynamic picture is presented.Each Three-Dimensional Dynamic member
Element can form the complete three-D pattern of a width presented in Three-Dimensional Dynamic picture.Specifically, above-mentioned server can be advance
To face object zoning, to determine the predeterminable area of face object.By predetermined predeterminable area, above-mentioned people is determined
The positions and dimensions of each predeterminable area of face object.For example a predeterminable area is left eye, it may be determined that left in face object
The coordinate and width of the position of eye.In addition to the width, it can also determine that length etc. is used as size.
Step 405, each Three-Dimensional Dynamic element in the Three-Dimensional Dynamic picture posture feature with face object matched with
The positions and dimensions to match with corresponding predeterminable area are superimposed upon on face dynamic picture, generate three-dimensional overlay dynamic picture.
In the present embodiment, in the Three-Dimensional Dynamic picture that above-mentioned server can match the posture feature of face object
Each Three-Dimensional Dynamic element overlaid generates three-dimensional overlay dynamic picture on above-mentioned face dynamic picture.Specifically with it is each
The positions and dimensions that predeterminable area corresponding to Three-Dimensional Dynamic element matches are overlapped.Such as one in Three-Dimensional Dynamic picture
Individual Three-Dimensional Dynamic element is the left eye for having 3-D effect, the left eye in corresponding face object.This can be had to a left side for 3-D effect
The positions and dimensions of eye are arranged to the positions and dimensions of left eye in face object, are overlapped afterwards.The three-dimensional overlay of generation moves
State picture is as shown in Figure 4 B.
The present embodiment is by the way that the posture feature template of the posture feature of face object and Three-Dimensional Dynamic picture is matched, energy
Enough Three-Dimensional Dynamic pictures for quickly and accurately determining to be superimposed with face object, so as to the three-dimensional overlay dynamic picture energy of generation
The more accurately affective state for the people that expression target video is gathered.In addition by by each Three-Dimensional Dynamic element and face object
Each predeterminable area is corresponding to be superimposed, it is ensured that and Three-Dimensional Dynamic element adapts to size and the position of each predeterminable area of face object,
The effect of lifting superposition picture.
With further reference to Fig. 5, it illustrates the flow 500 of another embodiment of the method for generating picture.The use
In the flow 500 of the method for generation picture, comprise the following steps：
Step 501, target video is obtained, and detects in target video whether include face object.
In the present embodiment, target video is in response to detecting expression figure of the user in interface of input method by terminal device
The operation of input Three-Dimensional Dynamic picture is selected in chosen area and is gathered.Interface of input method for terminal device display screen to
The interface input that family is presented.Expression figure chosen area is to choose the region of expression figure.The target video can be with
It is that user is shot using above-mentioned terminal device or user is uploaded in above-mentioned terminal device.
In practice, terminal device can call camera, carry out video acquisition by camera, generate target video.
Afterwards, according to Face datection (such as detection of facial contour) etc., detect in target video whether include face object.
It should be noted that the electronic equipment for carrying out performing operation in the present embodiment can be server or end
End equipment.When electronic equipment is server, above-mentioned electronic equipment can pass through wired connection mode or radio connection
Above-mentioned target video is received from terminal device used in user.And when electronic equipment is terminal device, electronic equipment can be with
The target video that user uploads is received, or video is gathered by camera.
Step 502, in response to determining to include face object in target video, the posture feature of face object is extracted.
In the present embodiment, electronic equipment (such as the electronics shown in Fig. 1 thereon is run for generating the method for picture
Equipment) after it is determined that including face object in target video, then respond：Extract the posture feature of above-mentioned face object.
Posture feature is the feature of the posture of reflection face object.Posture feature can show in vector form.In practice, can be with
The posture feature of face object is extracted by the identification of human face posture.
Step 503, the feature of each Three-Dimensional Dynamic picture in Three-Dimensional Dynamic picture set is extracted.
In the present embodiment, above-mentioned electronic equipment extracts the spy of each Three-Dimensional Dynamic picture from Three-Dimensional Dynamic picture set
Sign.Here feature can use vector representation.Specifically, feature can be each three of the three-D pattern in Three-Dimensional Dynamic picture
Tie up the position relationship between dynamic element.The extraction of feature can use various ways, such as, local binary patterns can be used
(Local Binary Pattern, LBP), Deep ID (Deep hidden identity feature) etc. carry out feature
Extraction.
Step 504, the posture feature using face object and at least one three in default Three-Dimensional Dynamic picture set
The feature of dimension dynamic picture matches, to determine the Three-Dimensional Dynamic picture matched with the posture feature of face object.
In the present embodiment, above-mentioned electronic equipment is by the posture feature of face object and default Three-Dimensional Dynamic picture set
In the feature of at least one Three-Dimensional Dynamic picture match, to determine the Three-Dimensional Dynamic matched with the posture feature of face object
Picture.It is similar between the feature of Three-Dimensional Dynamic picture that step 503 extracts to calculate the posture feature of face object
Degree.It is then matching that similarity, which is more than default threshold value,.In practice, can be according to order set in advance and each Three-Dimensional Dynamic
The feature of picture is matched.When the feature for finding matching, then it can stop matching process.So people in the matching process
The posture feature of face object needs the feature with least one Three-Dimensional Dynamic picture to match.
Step 505, row format conversion is entered to target video, generates face dynamic picture.
In the present embodiment, above-mentioned electronic equipment enters row format conversion to above-mentioned target video.Form conversion result be
Face dynamic picture.Herein, form conversion is the form that target video is converted to dynamic picture from video format.Such as
Target video can be converted to GIF forms from mpeg format.Face dynamic picture is the dynamic picture for presenting face.
Step 506, the Three-Dimensional Dynamic picture and face dynamic picture posture feature with face object matched is folded
Add, generate three-dimensional overlay dynamic picture.
In the present embodiment, above-mentioned electronic equipment is folded the Three-Dimensional Dynamic picture found and face dynamic picture
Add, generate three-dimensional overlay dynamic picture.Presented in the three-dimensional overlay dynamic picture generated in above-mentioned Three-Dimensional Dynamic picture
Three-Dimensional Dynamic pattern, while also present above-mentioned face object.In practice, the three-dimensional overlay dynamic picture of generation can be through
Cross the AR dynamic pictures of superposition.Specifically, each frame picture of Three-Dimensional Dynamic picture can be first extracted, and extracts face Dynamic Graph
Each frame picture in piece.Afterwards, each frame picture in each the frame picture and face dynamic picture in Three-Dimensional Dynamic picture is entered
Row superposition.
The present embodiment by the way that the feature of the posture feature of face object and Three-Dimensional Dynamic picture is matched, can quickly,
The Three-Dimensional Dynamic picture being superimposed with face object is precisely determined, so as to which the three-dimensional overlay dynamic picture of generation can be more accurately
The affective state for the people that expression target video is gathered.
With further reference to Fig. 6 as the realization to method shown in above-mentioned each figure, it is used to generate figure this application provides one kind
One embodiment of the device of piece, the device embodiment is corresponding with the embodiment of the method shown in Fig. 2, and the device can specifically answer
For in various electronic equipments.
As Fig. 6 shows, the device 600 for being used to handle image of the present embodiment includes：Extraction unit 601, searching unit 602,
Generation unit 603 and superpositing unit 604.Wherein, extraction unit 601, it is configured in response to determining to include people in target video
Face object, extract the posture feature of face object；Searching unit 602, it is configured to from default Three-Dimensional Dynamic picture set
Find out the Three-Dimensional Dynamic picture matched with the posture feature of face object；Generation unit 603, it is configured to enter target video
Row format is changed, and generates face dynamic picture；Superpositing unit 604, it is configured to match the posture feature with face object
Three-Dimensional Dynamic picture and face dynamic picture are overlapped, and generate three-dimensional overlay dynamic picture.
In the present embodiment, extraction unit 601 then responds after it is determined that including face object in target video：
Extract the posture feature of above-mentioned face object.Said extracted unit 601 can pass through wired connection mode or wireless connection side
Terminal device used in formula from user receives above-mentioned target video.The target video can be that user uses above-mentioned terminal device
Shoot or user is uploaded in above-mentioned terminal device.Posture feature is the feature of the posture of reflection face object,
It can represent in vector form.For example posture feature can be the position relationship between several characteristic points of face object.
Characteristic point can be the point of the expression face characteristic extracted from picture, can accurately indicate a position in face
Point, for example can be the right eye angle of face or right eye, upper lip centre site etc..It is different in actual scene
Posture feature represents the different emotions state of people, such as people is when doing different expression (doing different facial actions in other words)
Facial pose is different.By extracting the posture feature of face object in the present embodiment, to express the difference that face object implies
Emotional state.
In the present embodiment, searching unit 602 is found out and face object from default Three-Dimensional Dynamic picture set
The Three-Dimensional Dynamic picture that posture feature matches.Three-Dimensional Dynamic picture is the dynamic picture for showing three-dimensional stereo effect.It is three-dimensional
Dynamic picture set is the picture set being made up of Three-Dimensional Dynamic picture.If each Zhang San tie up dynamic picture all with face object
Corresponding relation be present in a dry posture feature.Different Three-Dimensional Dynamic pictures corresponds to the combination of different posture features.The corresponding pass
System can be stored in advance in local or other electronic equipments, for example is existed in a manner of mapping table.It is corresponding by this
The posture feature of relation and face object, the Three-Dimensional Dynamic picture corresponding with the posture feature of face object can be found.
Herein, can be without using whole posture features of face object in Three-Dimensional Dynamic picture corresponding to lookup.Such as can be with
Only use the posture feature related to nose and eyes.
In the present embodiment, generation unit 603 enters row format conversion to above-mentioned target video.The result that form is changed is people
Face dynamic picture.Herein, form conversion is the form that target video is converted to dynamic picture from video format.Such as can
So that target video is converted into GIF forms from mpeg format.Face dynamic picture is the dynamic picture for presenting face.
In the present embodiment, the Three-Dimensional Dynamic picture found and face dynamic picture are overlapped by superpositing unit 604,
Generate three-dimensional overlay dynamic picture.The three-dimensional in above-mentioned Three-Dimensional Dynamic picture is presented in the three-dimensional overlay dynamic picture generated
Dynamic pattern, while also present above-mentioned face object.In practice, the three-dimensional overlay dynamic picture of generation can be by folded
The AR dynamic pictures added.Specifically, each frame picture of Three-Dimensional Dynamic picture can be first extracted, and is extracted in face dynamic picture
Each frame picture.Afterwards, each frame picture in each the frame picture and face dynamic picture in Three-Dimensional Dynamic picture is folded
Add.
In some optional implementations of the present embodiment, each Three-Dimensional Dynamic in default Three-Dimensional Dynamic picture set
Picture is configured with corresponding posture feature template；Searching unit is further configured to：By the posture feature of face object and in advance
If Three-Dimensional Dynamic picture set in the posture feature template of at least one Three-Dimensional Dynamic picture match, to determine and face
The Three-Dimensional Dynamic picture of the posture feature matching of object.
In some optional implementations of the present embodiment, searching unit, including：Extraction module, it is configured to extract
The feature of each Three-Dimensional Dynamic picture in Three-Dimensional Dynamic picture set；Determining module, it is configured to special using the posture of face object
Levy and match with the feature of at least one Three-Dimensional Dynamic picture in default Three-Dimensional Dynamic picture set, to determine and face pair
The Three-Dimensional Dynamic picture of the posture feature matching of elephant.
In some optional implementations of the present embodiment, Three-Dimensional Dynamic picture includes at least one Three-Dimensional Dynamic member
Element, each Three-Dimensional Dynamic element correspond to a predeterminable area of face object respectively；Superpositing unit, including：Parameter determination module, match somebody with somebody
Put the positions and dimensions of each predeterminable area for determining face object；Laminating module, it is configured to the appearance with face object
Each Three-Dimensional Dynamic element in the Three-Dimensional Dynamic picture of state characteristic matching is with the position to match with corresponding predeterminable area and chi
It is very little to be superimposed upon on face dynamic picture, generate three-dimensional overlay dynamic picture.
In some optional implementations of the present embodiment, the device also includes：Acquiring unit, it is configured to obtain mesh
Video is marked, and detects in target video whether include face object, wherein, target video is in response to detecting by terminal device
User selectes the operation of input Three-Dimensional Dynamic picture and gathered in the expression figure chosen area of interface of input method.
Fig. 7 shows the structural representation of the computer installation suitable for being used for the electronic equipment for realizing the embodiment of the present application.
As shown in fig. 7, computer installation 700 includes CPU (CPU) 701, it can be according to being stored in read-only storage
(ROM) program in 702 or performed each from the program that storage part 708 is loaded into random access storage device (RAM) 703
Kind appropriate action and processing.In RAM 703, also it is stored with device 700 and operates required various programs and data.CPU
701st, ROM 702 and RAM 703 are connected with each other by bus 704.Input/output (I/O) interface 705 is also connected to bus
704。
I/O interfaces 705 are connected to lower component：Importation 706 including keyboard, mouse etc.；Penetrated including such as negative electrode
The output par, c 707 of spool (CRT), liquid crystal display (LCD) etc. and loudspeaker etc.；Storage part 708 including hard disk etc.；
And the communications portion 709 of the NIC including LAN card, modem etc..Communications portion 709 via such as because
The network of spy's net performs communication process.Driver 710 is also according to needing to be connected to I/O interfaces 705.Detachable media 711, such as
Disk, CD, magneto-optic disk, semiconductor memory etc., it is arranged on as needed on driver 710, in order to read from it
Computer program be mounted into as needed storage part 708.
Especially, according to embodiments herein, computer is may be implemented as above with reference to the process of flow chart description
Software program.For example, embodiments herein includes a kind of computer program product, it includes being carried on computer-readable medium
On computer program, the computer program include be used for execution flow chart shown in method program code.In such reality
To apply in example, the computer program can be downloaded and installed by communications portion 709 from network, and/or from detachable media
711 are mounted.When the computer program is performed by CPU (CPU) 701, perform what is limited in the present processes
Above-mentioned function.It should be noted that the computer-readable medium of the application can be computer-readable signal media or calculating
Machine readable storage medium storing program for executing either the two any combination.Computer-readable recording medium for example can be --- but it is unlimited
In --- electricity, magnetic, optical, electromagnetic, infrared ray or arrangement of semiconductors, device or device, or any combination above.Calculate
The more specifically example of machine readable storage medium storing program for executing can include but is not limited to：Electrically connecting, be portable with one or more wires
Formula computer disk, hard disk, random access storage device (RAM), read-only storage (ROM), erasable programmable read only memory
(EPROM or flash memory), optical fiber, portable compact disc read-only storage (CD-ROM), light storage device, magnetic memory device or
The above-mentioned any appropriate combination of person.In this application, computer-readable recording medium can be any includes or storage program
Tangible medium, the program can be commanded performs device, device either device use or it is in connection.And in this Shen
Please in, computer-readable signal media can include in a base band or as carrier wave a part propagation data-signal, its
In carry computer-readable program code.The data-signal of this propagation can take various forms, and include but is not limited to
Electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal media can also be computer-readable
Any computer-readable medium beyond storage medium, the computer-readable medium can send, propagate or transmit for by
Instruction executing device, device either device use or program in connection.The journey included on computer-readable medium
Sequence code can be transmitted with any appropriate medium, be included but is not limited to：Wirelessly, electric wire, optical cable, RF etc., or it is above-mentioned
Any appropriate combination.
Flow chart and block diagram in accompanying drawing, it is illustrated that according to the system of the various embodiments of the application, method and computer journey
Architectural framework in the cards, function and the operation of sequence product.At this point, each square frame in flow chart or block diagram can generation
The part of one module of table, program segment or code, the part of the module, program segment or code include one or more use
In the executable instruction of logic function as defined in realization.It should also be noted that marked at some as in the realization replaced in square frame
The function of note can also be with different from the order marked in accompanying drawing generation.For example, two square frames succeedingly represented are actually
It can perform substantially in parallel, they can also be performed in the opposite order sometimes, and this is depending on involved function.Also to note
Meaning, the combination of each square frame and block diagram in block diagram and/or flow chart and/or the square frame in flow chart can be with holding
Function as defined in row or the special hardware based system of operation are realized, or can use specialized hardware and computer instruction
Combination realize.
Being described in unit involved in the embodiment of the present application can be realized by way of software, can also be by hard
The mode of part is realized.Described unit can also be set within a processor, for example, can be described as：A kind of processor bag
Include extraction unit, searching unit, generation unit and superpositing unit.Wherein, the title of these units not structure under certain conditions
The paired restriction of the unit in itself, for example, extraction unit is also described as the " list of the posture feature of extraction face object
Member ".
As on the other hand, present invention also provides a kind of computer-readable medium, the computer-readable medium 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 computer-readable recording medium carries one or more program, when said one or multiple programs are performed by the device so that should
Device：In response to determining to include face object in target video, the posture feature of face object is extracted；From default Three-Dimensional Dynamic
The Three-Dimensional Dynamic picture matched with the posture feature of face object is found out in picture set；Enter row format to target video to turn
Change, generate face dynamic picture；The Three-Dimensional Dynamic picture and face dynamic picture that posture feature with face object is matched enter
Row superposition, generates three-dimensional overlay dynamic picture.
Above description is only the preferred embodiment of the application and the explanation to institute's application technology principle.People in the art
Member should be appreciated that invention scope involved in the application, however it is not limited to the technology that the particular combination of above-mentioned technical characteristic forms
Scheme, while should also cover in the case where not departing from foregoing invention design, carried out by above-mentioned technical characteristic or its equivalent feature
The other technical schemes for being combined and being formed.Such as features described above has similar work(with (but not limited to) disclosed herein
The technical scheme that the technical characteristic of energy is replaced mutually and formed.
Claims (12)
1. a kind of method for generating picture, including：
In response to determining to include face object in target video, the posture feature of the face object is extracted；
The Three-Dimensional Dynamic figure matched with the posture feature of the face object is found out from default Three-Dimensional Dynamic picture set
Piece；
Enter row format conversion to the target video, generate face dynamic picture；
The Three-Dimensional Dynamic picture and the face dynamic picture that posture feature with the face object is matched are overlapped, raw
Into three-dimensional overlay dynamic picture.
2. the method according to claim 11, wherein, each Three-Dimensional Dynamic figure in the default Three-Dimensional Dynamic picture set
Piece is configured with corresponding posture feature template；
The three-dimensional matched with the posture feature of the face object that found out from default Three-Dimensional Dynamic picture set is moved
State picture, including：
By at least one Three-Dimensional Dynamic in the posture feature of the face object and the default Three-Dimensional Dynamic picture set
The posture feature template of picture matches, to determine the Three-Dimensional Dynamic picture matched with the posture feature of the face object.
3. according to the method for claim 1, wherein, it is described found out from default Three-Dimensional Dynamic picture set with it is described
The Three-Dimensional Dynamic picture of the posture feature matching of face object, including：
Extract the feature of each Three-Dimensional Dynamic picture in the Three-Dimensional Dynamic picture set；
It is dynamic using the posture feature and at least one three-dimensional in the default Three-Dimensional Dynamic picture set of the face object
The feature of state picture matches, to determine the Three-Dimensional Dynamic picture matched with the posture feature of the face object.
4. according to the method for claim 1, wherein, the Three-Dimensional Dynamic picture includes at least one Three-Dimensional Dynamic element,
Each Three-Dimensional Dynamic element corresponds to a predeterminable area of the face object respectively；
The Three-Dimensional Dynamic picture that posture feature with the face object is matched and the face dynamic picture are folded
Add, generate three-dimensional overlay dynamic picture, including：
Determine the positions and dimensions of each predeterminable area of the face object；
Each Three-Dimensional Dynamic element in the Three-Dimensional Dynamic picture that the posture feature with the face object is matched with it is right
The positions and dimensions that the predeterminable area answered matches are superimposed upon on the face dynamic picture, generate three-dimensional overlay dynamic picture.
5. according to the method for claim 1, wherein, methods described also includes：
Target video is obtained, and detects in the target video whether include face object, wherein, the target video is by end
End equipment is in response to detecting user selected behaviour for inputting Three-Dimensional Dynamic picture in the expression figure chosen area of interface of input method
Make and gather.
6. a kind of device for being used to generate picture, including：
Extraction unit, it is configured to, in response to determining to include face object in target video, extract the posture of the face object
Feature；
Searching unit, it is configured to find out the posture feature with the face object from default Three-Dimensional Dynamic picture set
The Three-Dimensional Dynamic picture of matching；
Generation unit, it is configured to enter the target video row format conversion, generates face dynamic picture；
Superpositing unit, the Three-Dimensional Dynamic picture and the face for being configured to match the posture feature with the face object move
State picture is overlapped, and generates three-dimensional overlay dynamic picture.
7. device according to claim 6, wherein, each Three-Dimensional Dynamic figure in the default Three-Dimensional Dynamic picture set
Piece is configured with corresponding posture feature template；
The searching unit is further configured to：
By at least one Three-Dimensional Dynamic in the posture feature of the face object and the default Three-Dimensional Dynamic picture set
The posture feature template of picture matches, to determine the Three-Dimensional Dynamic picture matched with the posture feature of the face object.
8. device according to claim 6, wherein, the searching unit, including：
Extraction module, it is configured to extract the feature of each Three-Dimensional Dynamic picture in the Three-Dimensional Dynamic picture set；
Determining module, it is configured to using in the posture feature of the face object and the default Three-Dimensional Dynamic picture set
The feature of at least one Three-Dimensional Dynamic picture match, to determine that the three-dimensional matched with the posture feature of the face object is moved
State picture.
9. device according to claim 6, wherein, the Three-Dimensional Dynamic picture includes at least one Three-Dimensional Dynamic element,
Each Three-Dimensional Dynamic element corresponds to a predeterminable area of the face object respectively；
The superpositing unit, including：
Parameter determination module, it is configured to determine the positions and dimensions of each predeterminable area of the face object；
Laminating module, each three be configured in the Three-Dimensional Dynamic picture that matches the posture feature with the face object
Dimension dynamic element is superimposed upon on the face dynamic picture with the positions and dimensions to match with corresponding predeterminable area, generation three
Dimension superposition dynamic picture.
10. device according to claim 6, wherein, described device also includes：
Acquiring unit, it is configured to obtain target video, and detects in the target video whether include face object, wherein,
The target video be by terminal device in response to detect user in the expression figure chosen area of interface of input method select it is defeated
Enter the operation of Three-Dimensional Dynamic picture and gather.
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 by one or more of computing devices 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 recording medium, is stored thereon with computer program, wherein, when the program is executed by processor
Realize the method as described in any in claim 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711223801.4A CN107886559A (en) | 2017-11-29 | 2017-11-29 | Method and apparatus for generating picture |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711223801.4A CN107886559A (en) | 2017-11-29 | 2017-11-29 | Method and apparatus for generating picture |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107886559A true CN107886559A (en) | 2018-04-06 |
Family
ID=61775866
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711223801.4A Pending CN107886559A (en) | 2017-11-29 | 2017-11-29 | Method and apparatus for generating picture |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107886559A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108765522A (en) * | 2018-05-15 | 2018-11-06 | 维沃移动通信有限公司 | A kind of dynamic image generation method and mobile terminal |
| CN109671014A (en) * | 2018-11-26 | 2019-04-23 | 深圳艺达文化传媒有限公司 | From the plait stacking method and Related product to shoot the video |
| CN110176044A (en) * | 2018-06-08 | 2019-08-27 | 腾讯科技（深圳）有限公司 | Information processing method, device, storage medium and computer equipment |
| CN110188712A (en) * | 2019-06-03 | 2019-08-30 | 北京字节跳动网络技术有限公司 | Method and apparatus for handling image |
| CN110399764A (en) * | 2018-04-24 | 2019-11-01 | 华为技术有限公司 | Face identification method, device and computer-readable medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104637035A (en) * | 2015-02-15 | 2015-05-20 | 百度在线网络技术（北京）有限公司 | Method, device and system for generating cartoon face picture |
| CN104715447A (en) * | 2015-03-02 | 2015-06-17 | 百度在线网络技术（北京）有限公司 | Image synthesis method and device |
| CN104915634A (en) * | 2015-02-16 | 2015-09-16 | 百度在线网络技术（北京）有限公司 | Image generation method based on face recognition technology and apparatus |
-
2017
- 2017-11-29 CN CN201711223801.4A patent/CN107886559A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104637035A (en) * | 2015-02-15 | 2015-05-20 | 百度在线网络技术（北京）有限公司 | Method, device and system for generating cartoon face picture |
| CN104915634A (en) * | 2015-02-16 | 2015-09-16 | 百度在线网络技术（北京）有限公司 | Image generation method based on face recognition technology and apparatus |
| CN104715447A (en) * | 2015-03-02 | 2015-06-17 | 百度在线网络技术（北京）有限公司 | Image synthesis method and device |
Non-Patent Citations (1)
| Title |
|---|
| 樰篱: "阿里云首推免费人脸识别SDK让每个APP轻松拥有短视频AR特效", 《HTTPS://YQ.ALIYUN.COM/ARTICLES/216752?SPM=5176.100244.TEAMHOMELEFT.1.DLHTJZ》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110399764A (en) * | 2018-04-24 | 2019-11-01 | 华为技术有限公司 | Face identification method, device and computer-readable medium |
| CN108765522A (en) * | 2018-05-15 | 2018-11-06 | 维沃移动通信有限公司 | A kind of dynamic image generation method and mobile terminal |
| CN110176044A (en) * | 2018-06-08 | 2019-08-27 | 腾讯科技（深圳）有限公司 | Information processing method, device, storage medium and computer equipment |
| CN109671014A (en) * | 2018-11-26 | 2019-04-23 | 深圳艺达文化传媒有限公司 | From the plait stacking method and Related product to shoot the video |
| CN110188712A (en) * | 2019-06-03 | 2019-08-30 | 北京字节跳动网络技术有限公司 | Method and apparatus for handling image |
| CN110188712B (en) * | 2019-06-03 | 2021-10-12 | 北京字节跳动网络技术有限公司 | Method and apparatus for processing image |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10997445B2 (en) | Facial recognition-based authentication | |
| CN107886559A (en) | Method and apparatus for generating picture | |
| CN111787242B (en) | Method and apparatus for virtual fitting | |
| CN108525305B (en) | Image processing method, image processing device, storage medium and electronic equipment | |
| CN106682632B (en) | Method and device for processing face image | |
| TW505892B (en) | System and method for promptly tracking multiple faces | |
| WO2020078119A1 (en) | Method, device and system for simulating user wearing clothing and accessories | |
| CN108509915A (en) | The generation method and device of human face recognition model | |
| CN108898185A (en) | Method and apparatus for generating image recognition model | |
| CN108388889B (en) | Method and device for analyzing face image | |
| CN107153496A (en) | Method and apparatus for inputting emotion icons | |
| CN108073910A (en) | For generating the method and apparatus of face characteristic | |
| CN108491808B (en) | Method and device for acquiring information | |
| CN109344762A (en) | Image processing method and device | |
| CN108062544A (en) | For the method and apparatus of face In vivo detection | |
| CN108509916A (en) | Method and apparatus for generating image | |
| CN108229375B (en) | Method and device for detecting face image | |
| CN108171204A (en) | Detection method and device | |
| CN109241934A (en) | Method and apparatus for generating information | |
| Zhang et al. | Emotion detection using Kinect 3D facial points | |
| CN108491881A (en) | Method and apparatus for generating detection model | |
| CN110059624A (en) | Method and apparatus for detecting living body | |
| CN110110666A (en) | Object detection method and device | |
| CN110633677A (en) | Face recognition method and device | |
| JP6593949B1 (en) | Information processing apparatus and marketing activity support apparatus |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180406 |