CN110458916A - Expression packet automatic generation method, device, computer equipment and storage medium - Google Patents
Expression packet automatic generation method, device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN110458916A CN110458916A CN201910602401.7A CN201910602401A CN110458916A CN 110458916 A CN110458916 A CN 110458916A CN 201910602401 A CN201910602401 A CN 201910602401A CN 110458916 A CN110458916 A CN 110458916A
- Authority
- CN
- China
- Prior art keywords
- expression
- facial image
- packet
- face
- picture
- 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 OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T11/00—2D [Two Dimensional] image generation
- G06T11/60—Editing figures and text; Combining figures or text
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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
- G06V40/174—Facial expression recognition
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer 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 invention discloses a kind of expression packet automatic generation method, device, computer equipment and storage mediums, which comprises extracts the micro- expression of face from facial image, and obtains the expression label of facial image according to the micro- expression of face；Expression packet picture is matched from default expression parcel according to the expression label of facial image, and determines the present position at the face position for the expression packet picture being matched to；The facial characteristics in facial image is extracted, and facial characteristics is covered into the present position from the face position for presetting the expression packet picture being matched in expression parcel, generates personalized emoticons packet.Operation of the present invention is convenient, and since the facial image in the personalized emoticons packet of generation is consistent with the expression of original expression packet picture, therefore the facial characteristics of facial image is fused to effect in original expression packet picture and consistency is more preferable, the user experience is improved, also improves user activity and participation.
Description
Technical field
The present invention relates to micro- Expression Recognition fields, and in particular to a kind of expression packet automatic generation method, device, computer are set
Standby and storage medium.
Background technique
With the development of communication technology, mobile phone using more and more extensive, greatly extend the social scope of people.Base
In the expansion of social scope, the case where user is exchanged using mobile phone instant communication software, is also more and more.In order to user it
Between exchange and conmmunication, all there is chat feature in many social applications, user can engage in the dialogue or mutually by chat box
Various expression packets are sent, mutually to express the mood for being difficult to state by text.
In practical application, the expression packet that user sends is obtained from the third party of special production expression packet mostly, i.e.,
The material that third party collects according to it is published in network, user obtains from the expression packet that third party provides after generating expression packet
Be derived from oneself interested expression packet carry out using.But in this case, user is passively to receive or passively select
Expression packet may often will appear the case where being unable to reach the effect oneself wanted.
Summary of the invention
The embodiment of the present invention provides a kind of expression packet automatic generation method, device, computer equipment and storage medium, this hair
Bright operation is simple, and the syncretizing effect and consistency of the personalized emoticons packet of generation are more preferable, and the user experience is improved, also improves use
Family liveness and participation.
A kind of expression packet automatic generation method, comprising:
Obtain facial image；
The micro- expression of face is extracted from the facial image, and the facial image is obtained according to the micro- expression of the face
Expression label；
Expression packet picture is matched from default expression parcel according to the expression label of the facial image, and determination is matched to
The expression packet picture face position present position；Wherein, the expression packet picture in the default expression parcel
At least one face position is all had, and each described expression packet picture is associated with expression label described at least one；
The facial characteristics in the facial image is extracted, and the facial characteristics is covered from the default expression parcel
In the present position at the face position of the expression packet picture that is matched to, generate personalized emoticons packet.
A kind of expression packet automatically generating device, comprising:
Module is obtained, for obtaining facial image；
Extraction module is obtained for extracting the micro- expression of face from the facial image, and according to the micro- expression of the face
The expression label of the facial image；
Matching module, for matching expression packet figure from default expression parcel according to the expression label of the facial image
Piece, and determine the present position at the face position for the expression packet picture being matched to；Wherein, in the default expression parcel
The expression packet picture all has at least one face position, and each described expression packet picture with table described at least one
The association of feelings label；
Overlay module is covered for extracting the facial characteristics in the facial image, and by the facial characteristics from institute
The present position at the face position for the expression packet picture being matched in default expression parcel is stated, personalized emoticons are generated
Packet.
A kind of computer equipment, including memory, processor and storage are in the memory and can be in the processing
The computer-readable instruction run on device, the processor realize that above-mentioned expression packet is automatic when executing the computer-readable instruction
Generation method.
A kind of computer readable storage medium, the computer-readable recording medium storage have computer-readable instruction, institute
It states and realizes above-mentioned expression packet automatic generation method when computer-readable instruction is executed by processor.
Expression packet automatic generation method, device, computer equipment and storage medium provided by the invention, it is only necessary to obtain and appoint
It anticipates after the facial image of shooting, can determine table corresponding with the facial image according to the micro- expression of face in the facial image
Feelings label (expression label corresponds to a kind of expression), and it is consistent with the expression of facial image according to expression label determination
Expression packet picture, and by the facial characteristics in facial image cover to the consistent expression packet picture of its expression (expression packet figure
Also expression corresponding with above-mentioned expression label is consistent for uncovered part in piece) in, ultimately generate personalized emoticons packet (this
All the elements expression corresponding with above-mentioned expression label in property expression packet is consistent).Present invention only requires shooting face figures
As can automatically generate and shoot the consistent personalized emoticons packet of facial image expression (and in the personalized emoticons packet may packet
Also expression corresponding with above-mentioned expression label is consistent for the other content contained), it is convenient to operate, and due to the personalized emoticons packet of generation
In facial image it is consistent with the expression of original expression packet picture, therefore in the personalized emoticons packet facial image face it is special
It levies the effect being fused in original expression packet picture and consistency is more preferable, the user experience is improved, and it is active to also improve user
Degree and participation.
Detailed description of the invention
In order to illustrate the technical solution of the embodiments of the present invention more clearly, below by institute in the description to the embodiment of the present invention
Attached drawing to be used is needed to be briefly described, it should be apparent that, the accompanying drawings in the following description is only some implementations of the invention
Example, for those of ordinary skill in the art, without creative efforts, can also obtain according to these attached drawings
Obtain other attached drawings.
Fig. 1 is the application environment schematic diagram of expression packet automatic generation method in one embodiment of the invention；
Fig. 2 is the flow chart of expression packet automatic generation method in one embodiment of the invention；
Fig. 3 is the flow chart of the step S20 of expression packet automatic generation method in one embodiment of the invention；
Fig. 4 is the flow chart of the step S30 of expression packet automatic generation method in one embodiment of the invention；
Fig. 5 is the flow chart of the step S40 of expression packet automatic generation method in one embodiment of the invention；
Fig. 6 is the flow chart of the step S407 of expression packet automatic generation method in one embodiment of the invention；
Fig. 7 is the functional block diagram of expression packet automatically generating device in one embodiment of the invention；
Fig. 8 is the functional block diagram of the extraction module of expression packet automatically generating device in one embodiment of the invention；
Fig. 9 is the schematic diagram of computer equipment in one embodiment of the invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are some of the embodiments of the present invention, instead of all the embodiments.Based on this hair
Embodiment in bright, every other implementation obtained by those of ordinary skill in the art without making creative efforts
Example, shall fall within the protection scope of the present invention.
Expression packet automatic generation method provided by the invention, can be applicable in the application environment such as Fig. 1, wherein client
(computer equipment) is communicated by network with server.Wherein, client (computer equipment) is including but not limited to each
Kind personal computer, laptop, smart phone, tablet computer, camera and portable wearable device.Server can be with
It is realized with the server cluster of the either multiple server compositions of independent server.
In one embodiment, it as shown in Fig. 2, providing a kind of expression packet automatic generation method, applies in Fig. 1 in this way
Server for be illustrated, include the following steps S10-S40:
S10 obtains facial image；
The facial image refers to that the image comprising part or all of human face five-sense-organ, the facial image can be led to by user
It crosses picture pick-up device and shoots and upload value server, can also be stored in advance in the database, server can according to demand at any time
It is transferred from database.
S20 extracts the micro- expression of face from the facial image, and obtains the face figure according to the micro- expression of the face
The expression label of picture；
That is, in this embodiment, needing to extract the micro- expression of face in the facial image first, and according to the people
The micro- expression of face goes to determine corresponding expression label, and the expression label is determined as to the expression label of the facial image.
In one embodiment, as shown in figure 3, the step S20 namely the extraction face from the facial image are micro-
Expression, and obtain according to the micro- expression of the face expression label of the facial image, comprising:
S201 extracts the everything cell type of the micro- expression of face from the facial image；
Wherein, the motor unit type may include but be not limited to for movement list general in the world in following table 1
First (AU) and eyeball dynamic etc., the eyeball dynamic are specially different movements and the visual angle of eyeball, for example, eyeball to the left, to
Right, upward, downward, upper right is seen, and different act in motor unit corresponding with visual angle of eyeball can also include to eyeball
The amplitude size of movement is judged.
S202 confirms the micro- of the facial image according to all motor unit types are extracted from the facial image
Expression type.
That is, being previously stored with various micro- expression types in database, (for example micro- expression type is to cry, laugh at or angry
Deng) corresponding to motor unit type, each micro- expression type is corresponding with the combination of various motion cell type, for example, micro-
Expression type is to laugh at, this micro- expression type is corresponding with the combination of at least following motor unit type: the corners of the mouth raises up (in table 1
AU12), the corners of the mouth raise up (AU12 in table 1)+outer eyebrow raises up (AU2 in table 1), the corners of the mouth raises up, and (AU12 in table 1)+lip is stretched
It opens up (AU20 in table 1)+upper lower lip and separates (AU25 in table 1) etc.；Therefore, as long as will extract in the step S201
All motor unit types are compared with the corresponding motor unit type of each micro- expression type stored in database
It is right, it can confirm the type of micro- expression.Understandably, in the present embodiment one side, as long as being mentioned in the step S201
In all motor unit types taken, the corresponding everything of a micro- expression type comprising being stored in database
Cell type is (that is, can also include other movements in all motor unit types extracted in the step S201
Unit), i.e., it is believed that micro- expression type is micro- expression type.It, can also be only in institute in the present embodiment another aspect
State all motor unit types extracted in step S201, the movement list with the micro- expression type stored in database
When element type and sequence correspond (can not more or few any one motor unit), just think that the people under the guardianship's is micro-
Expression type is micro- expression type.
1 part AU of table
| AU label | AU description |
| AU1 | Interior eyebrow raises up |
| AU2 | Outer eyebrow raises up |
| AU4 | Eyebrow pushes |
| AU5 | On the face raises up |
| AU6 | Cheek lifts |
| AU7 | Eyelid tightening |
| AU9 | Nose crease |
| AU10 | Upper lip raises up |
| AU12 | The corners of the mouth raises up |
| AU14 | Tighten the corners of the mouth |
| AU15 | Corners of the mouth drop-down |
| AU16 | Lower lip pushes |
| AU17 | Chin tightens |
| AU18 | Lip fold |
| AU20 | Lip stretching, extension |
| AU23 | Lip is shunk |
| AU24 | Lip compresses |
| AU25 | Upper lower lip separates |
| AU26 | Lower jaw drop-down |
S203 obtains all expression labels of micro- expression type association, while obtaining and each described table
The associated characteristic action unit of feelings label；
That is, being previously stored with the expression label with each micro- expression type association in database, and each micro- table
Feelings type corresponds to multiple expression labels, for example, micro- expression type is to laugh at, associated expression label be may include: laughing, is micro-
It laughs at, smile sinisterly, must not force a smile, laughs foolishly.Understandably, each has its corresponding with the expression label of micro- expression type association
At least one characteristic action unit.
S204, will extract all motor unit types from the facial image and each described expression label is closed
The characteristic action unit of connection is matched, and includes in extracting all motor unit types from the facial image
When the associated all characteristic action units of one expression label, the expression label is recorded as the facial image
Expression label.
In the present embodiment, all motor unit classes only extracted in the step S201 from facial image
When in type comprising the associated all characteristic action units of an expression label (that is, extracted in the step S201
It can also include other in addition to the corresponding characteristic action unit of the expression label in all motor unit types
Motor unit), i.e., it is believed that above-mentioned expression label is the expression label of facial image.In the above-described embodiments, basis first
The motor unit type extracted in facial image confirms that (micro- expression number of types is much smaller than the number of expression label to micro- expression type
Amount), just the feature of the motor unit type extracted in facial image and the expression label of micro- expression type association is moved later
It is matched as unit, in this way, the motor unit type extracted in facial image is not necessarily to compare with all expression labels,
The characteristic action unit of expression label corresponding with the micro- expression type of several classes is only needed to be compared, in the number of expression label
It measures in huge situation, greatly reduces calculation amount, alleviate server load.
Understandably, in one embodiment, face directly can also be extracted from the facial image in step s 201
After the everything cell type of micro- expression, directly acquires all expression labels and closed with expression label described in each
The characteristic action unit of connection；Enter back into step S204 will be extracted from the facial image all motor unit types with
Each described associated described characteristic action unit of expression label is matched, and all institutes are being extracted from the facial image
When stating all characteristic action units associated comprising the expression label in motor unit type, by the expression mark
Label are recorded as the expression label of the facial image.In this embodiment, without first according to the movement extracted in facial image
Cell type confirms micro- expression type, but directly by the feature of the motor unit type and expression label extracted in facial image
Motor unit is matched, and comparison step is simplified, and when the quantity of expression label is relatively fewer, which can be preferential
It chooses and uses.
S30 matches expression packet picture, and determining from default expression parcel according to the expression label of the facial image
The present position at the face position for the expression packet picture being fitted on；Wherein, the expression packet in the default expression parcel
Picture all has at least one face position, and each described expression packet picture is closed with expression label described at least one
Connection；
That is, in the present embodiment, it is necessary first to be gone according to the expression label of the facial image got in step S20
Obtain in default expression parcel (an expression packet picture likely corresponds to one with the associated expression packet picture of the expression label
Or multiple expression labels), at this point, the quantity for the expression packet picture corresponding with the expression label that may be got is greater than one,
It at this time, it may be necessary to choose one of expression packet picture according to demand, and is from default by the expression packet picture record of selection
The expression packet picture being matched in expression parcel.And the expression with the facial image is being chosen from default expression parcel
After unique expression packet picture of tag match, it is thus necessary to determine that position locating for the face position in the expression packet picture
It sets, and then is covered with the facial characteristics extracted in the facial image to the face position, replaced in the expression packet picture
The corresponding image of face position, generate new personalized expression packet.
In one embodiment, as shown in figure 4, the step S30 namely the expression label according to the facial image
Expression packet picture is matched from default expression parcel, and determines the locating position at the face position for the expression packet picture being matched to
It sets, comprising:
S301 is obtained from the face face mask extracted in the facial image；In the present embodiment, the face face
Profile that is to say the edge contour of the face of the face in the facial image.
S302 chooses expression label institute's espressiove packet figure identical with the facial image from default expression parcel
Piece；
S303 determines the present position and the face position at the face position for each expression packet picture chosen
Present position profile；The present position at the face position refers to all objects with face in an expression packet picture
The face present position of (such as people, animal or cartoon character etc.), the present position profile refer to face position corresponding position
Profile (such as face mask of face).
S304 obtains the similarity between the face face mask and the present position profile；The similarity can
The similar parameters such as the contour line radian variation with the size, the two that are occupied according to the two are compared, and can give each phase
Like the different weight of parameter setting, and then after each similar parameter is normalized, respectively multiplied by corresponding weight it
Afterwards, by the sum of products of offset parameter and weight after normalized, as the judgment criteria of the similarity, product it
Bigger, the similarity is higher.
S305, by the corresponding expression packet picture of the highest present position profile of the similarity, be recorded as with
The expression packet picture of the facial image unique match, while obtaining the expression with the facial image unique match
The present position at the face position of packet picture.
That is, in this embodiment it is possible to referring to the expression label from the default expression parcel with the facial image
In corresponding institute's espressiove packet picture, the similarity for choosing the face mask of face mask and the facial image is highest described
Expression packet picture is recorded as the expression packet picture being matched to from default expression parcel, in this way, can be convenient subsequent
The facial characteristics extracted in the facial image is farthest adapted to covering to the face position, replaces the expression packet
The corresponding image of face position in picture generates new personalized expression packet.
In one embodiment, the expression label according to the facial image matches expression packet from default expression parcel
Picture, and determine the present position at the face position for the expression packet picture being matched to, comprising:
Expression label institute's espressiove packet picture identical with the facial image is chosen from default expression parcel；Institute
The expression packet for the legal acquisition of third party that the expression packet picture in default expression parcel can be from special production expression packet is stated, and
Expression packet picture in the default expression parcel is required to that (namely face can be part face or complete with face position
Portion).
According to preset screening rule, determination is unique with the facial image from all expression packet pictures chosen
The matched expression packet picture；Understandably, the screening rule, which can be, randomly selects, may also mean that according to use frequency
Rate is chosen, for example, the highest expression packet picture of the personal use frequency that can choose user namely user use the expression
The frequency of packet picture is higher, then its probability for being selected is bigger.Similarly, the screening rule can also be to count described pre- first
If above-mentioned institute's espressiove packet picture corresponding with the expression label in expression parcel is selected by total access times of all users
The wherein highest expression packet picture of total access times is taken, further, the screening rule can also lead to total access times
Cross (the association in a conversion rule between total access times and different popularities comprising different range of preset conversion rule
Relationship, a total access times are only capable of a corresponding popularity) popularity is converted to, at this time similarly, popularity is higher, is chosen
The probability taken is higher.
The expression packet picture that will be determined according to the screening rule, is recorded as and the facial image unique match
The expression packet picture, at the same from extract its face position in the expression packet picture of the facial image unique match
Present position.
In this embodiment it is possible to according to the expression of screening rule confirmation and the facial image unique match
Packet picture, the screening rule can confirm according to user's access times etc., use in this way, can be gone to choose according to user preferences
The template of family personalized emoticons packet to be generated, in this way, the personalized emoticons Bao Huigeng generated meets the use habit of user, band
Give user better usage experience.
S40 extracts the facial characteristics in the facial image, and the facial characteristics is covered from the default expression
The present position at the face position for the expression packet picture being matched in parcel generates personalized emoticons packet.
In this embodiment, matched unique with the expression label of the facial image when being chosen from default expression parcel
An expression packet picture after, it is thus necessary to determine that the present position at the face position in the expression packet picture, and then by the people
The facial characteristics extracted in face image, the present position profile for replacing original face position (refer to that face position is corresponding
The profile of position) in picture material, and then will replacement have the facial image facial characteristics above-mentioned expression packet picture close
Cheng Xin personalized emoticons packet (for example, in expression packet picture main body be one sell the kitten sprouted, at this point, by cat face position replace
For the facial characteristics of facial image, the personalized emoticons packet of generation is to sell the small of the facial characteristics with facial image sprouted
Cat).
In one embodiment, as shown in figure 5, in the step S40, the face extracted in the facial image is special
It levies, and the facial characteristics is covered to the face for the expression packet picture being matched to from the default expression parcel
The present position at position, comprising:
S401 is obtained from the institute at the face position for the expression packet picture being matched in the default expression parcel
Locate position profile, the whole placed angle at the face position, face position contour area；Wherein, the face position
Present position profile refer to the edge contour of area occupied by the face position in the expression packet picture；The face portion
The whole placed angle of position refers to the size of face position tilt angle, is just setting or be inverted, which can be with
It is determined on the basis of wherein one or more face, such as straight to be linked to be between opposite two canthus of one eye eyeball
(similarly, also whether the angle between line and horizontal line is located at the lower section of eyes to determine its tilt angle, then with nose or mouth
Can be determined so that whether mouth is located at the conditions such as underthe nose) just set or be inverted that (nose or mouth are located at eyes to determine that it is
Lower section be positive set, otherwise for be inverted)；Face position contour area refers to the gross area of the present position profile.
S402 extracts all facial characteristics being located within face face mask in the facial image, and determines each institute
State the positional relationship between facial characteristics central point and the linear distance between each facial characteristics central point；Wherein, institute
Stating facial characteristics to include but is not limited to is ear, eyebrow, eye, nose, mouth etc..Positional relationship between each facial characteristics central point
Refer to the distance between each facial characteristics central point distance, relative bearing etc..
S403, creates painting canvas, and the painting canvas profile of the painting canvas is consistent with the present position profile at the face position；By institute
Facial characteristics is stated to be pre-processed according to preset image procossing mode；That is, the painting canvas profile of the painting canvas and the face
The present position profile at position can be completely overlapped.The preset image procossing mode is including but not limited to the face
Portion's feature carries out transparency adjustment, toning processing etc., so that the personalized emoticons packet generated is more naturally beautiful.
S404 will will be located in advance in the case where keeping the position relationship between the facial characteristics central point
All facial characteristics after reason are placed in the painting canvas profile of the painting canvas according to the whole placed angle；That is,
When all facial characteristics are placed into the painting canvas profile, need to keep its position relationship with respect between, in turn
Maintain constant (the face spy if the relative positional relationship between each facial characteristics changes, after variation of the expression of facial image
The facial image expression expression corresponding with facial image before this of sign composition may change).It understandably, can be with
The center of all facial characteristics and the center of the painting canvas profile are loci, and all facial characteristics are put
It sets into the painting canvas profile；And the entirety formed between all facial characteristics and the whole placed angle are different
When cause, need to be adjusted to consistent with the whole placed angle and then all facial characteristics are placed into the picture
In cloth profile.
S405, with the linear distance between the same facial characteristics central point more each than column adjustment, and according to described same
The graphics area that the facial characteristics of the outermost in each facial characteristics after ratio adjustment surrounds, with the face
Ratio between the contour area of position is in default ratio range；That is, uniformly adjusting each face by same ratio
Linear distance between characteristic central point carrys out the size of each facial characteristics of integrated regulation；And each face after adjusting
Ratio between the graphics area that the facial characteristics of outermost in portion's feature surrounds, with face position contour area
When interior in default ratio range (can set according to demand), size of each facial characteristics on the face position will opposite association
It adjusts, otherwise, facial characteristics may be too large or too small and uncoordinated in painting canvas profile.That is, above-mentioned same ratio needs root
According to " the graphics area that the facial characteristics of the outermost in each facial characteristics after adjustment surrounds, with the face
Ratio between the contour area of position is in default ratio range " condition is chosen (can arrange in advance according to priority level
And store in the database, and the screening from database meets the same than arranging of above-mentioned condition automatically by server), if making institute
Stating the same ratio that ratio is in default ratio range has multiple selections, then can randomly select one or according to preferential
The sequencing of rank is chosen.
S406, by the painting canvas comprising the facial characteristics, corresponding cover from the default expression parcel is matched
To the expression packet picture the face position present position profile on；That is, due to the painting canvas profile of the painting canvas
Present position profile with the face position can be completely overlapped, therefore is directly replaced in this step with the painting canvas original
The face position present position profile in picture material.
S407 carries out image synthesis processing to the expression packet picture for being covered with the painting canvas profile, generates described
Property expression packet.Described image synthesis processing is including but not limited to for the expression packet figure for being covered with the facial characteristics
Piece merges into same picture and carries out unified exposure toning processing, keeps it more natural.
It is in one embodiment, described to generate the personalized emoticons packet as shown in fig. 6, in the step S407, comprising:
S4071 receives text addition instruction, obtains the expression text of user's typing, the text box that the user chooses is compiled
Number；Wherein, after the text addition instruction refers to progress image synthesis processing in step S 407, if user also wants a
Property expression packet in autonomous typing expression text when, at this point it is possible to will after triggering programmable button by the modes such as clicking, slide
Text addition instruction is sent to server；The expression text just refers to that user is intended for the text of the personalized emoticons packet configuration
This；The text box number refers to the unique identification for the text box that can be added into personalized emoticons packet, each text
Frame number corresponds to the pattern of a text box.
S4072 is obtained and is numbered associated text box size and default text format with the text box；That is, each
A text box number all has the text box size that can be received in expression text, and each text box is one corresponding
Default text format, if user does not modify the default text format, the expression text will be with the default text lattice
Formula is inserted in the text box.
S4073 obtains the character quantity of the expression text, and according to the character quantity and the text box size
Adjust the character boundary in the default text format；That is, character quantity for expression text (namely character can be passed through
Length) judgement, character boundary etc. is automatically adjusted；Understandably, except the character is big in the default text format
Other text formatting projects except small can also be adjusted according to demand.
S4074, predeterminated position or user's selected location in the expression packet picture are generated numbers with the text box
Corresponding text box, and expression text is inserted according to the default text format after adjustment in the text box；That is,
After user adjusts the default text format, the expression text will insert institute with the default text format after adjusting
It states in text box.
S4075 generates the personalized emoticons after carrying out assembled processing to the expression packet picture and the text box
Packet.The assembled processing refers to that the expression packet picture merging for synthesizing the text box after processing with progress image is same
Personalized expression packet.
That is, in the above-described embodiments, also supporting the customized input expression text of user, and by for expression text
The judgement of character quantity (namely character length), is automatically adjusted character boundary etc., and will be described in filling expression character
Text box and expression packet picture automatic assembling are personalized emoticons packet.Understandably, it can equally be wrapped in the personalized emoticons
Stage property effect is added, for example is increased, the stage property of heart, cap, star and other effects.
In one embodiment, as shown in fig. 7, providing a kind of expression packet automatically generating device, which automatically generates dress
It sets and is corresponded with expression packet automatic generation method in above-described embodiment.The expression packet automatically generating device includes:
Module 11 is obtained, for obtaining facial image；
Extraction module 12 for extracting the micro- expression of face from the facial image, and is obtained according to the micro- expression of the face
Take the expression label of the facial image；
Matching module 13, for matching expression packet figure from default expression parcel according to the expression label of the facial image
Piece, and determine the present position at the face position for the expression packet picture being matched to；Wherein, in the default expression parcel
The expression packet picture all has at least one face position, and each described expression packet picture with table described at least one
The association of feelings label；
Overlay module 14 covers certainly for extracting the facial characteristics in the facial image, and by the facial characteristics
The present position at the face position for the expression packet picture being matched in the default expression parcel generates personalized table
Feelings packet.
In one embodiment, as shown in figure 8, the extraction module 12 includes:
Extraction unit 121, for extracting the everything cell type of the micro- expression of face from the facial image；
Confirmation unit 122, for according to being extracted from the facial image described in all motor unit types confirmations
Micro- expression type of facial image；
Acquiring unit 123, for obtaining all expression labels of micro- expression type association, while obtain with it is every
One associated characteristic action unit of expression label；
Matching unit 124, for all motor unit types and each institute will to be extracted from the facial image
It states the associated characteristic action unit of expression label to be matched, extracting from the facial image, all movements are single
In element type when all characteristic action units associated comprising the expression label, the expression label is recorded as
The expression label of the facial image.
Specific restriction about expression packet automatically generating device may refer to above for expression packet automatic generation method
Restriction, details are not described herein.Modules in above-mentioned expression packet automatically generating device can be fully or partially through software, hard
Part and combinations thereof is realized.Above-mentioned each module can be embedded in the form of hardware or independently of in the processor in computer equipment,
It can also be stored in a software form in the memory in computer equipment, execute the above modules in order to which processor calls
Corresponding operation.
In one embodiment, a kind of computer equipment is provided, which can be server, internal junction
Composition can be as shown in Figure 9.The computer equipment include by system bus connect processor, memory, network interface and
Database.Wherein, the processor of the computer equipment is for providing calculating and control ability.The memory packet of the computer equipment
Include non-volatile memory medium, built-in storage.The non-volatile memory medium be stored with operating system, computer-readable instruction and
Database.The built-in storage provides ring for the operation of operating system and computer-readable instruction in non-volatile memory medium
Border.To realize a kind of expression packet automatic generation method when the computer-readable instruction is executed by processor.
In one embodiment, a kind of computer equipment is provided, including memory, processor and storage are on a memory
And the computer-readable instruction that can be run on a processor, processor perform the steps of when executing computer-readable instruction
Obtain facial image；
The micro- expression of face is extracted from the facial image, and the facial image is obtained according to the micro- expression of the face
Expression label；
Expression packet picture is matched from default expression parcel according to the expression label of the facial image, and determination is matched to
The expression packet picture face position present position；Wherein, the expression packet picture in the default expression parcel
At least one face position is all had, and each described expression packet picture is associated with expression label described at least one；
The facial characteristics in the facial image is extracted, and the facial characteristics is covered from the default expression parcel
In the present position at the face position of the expression packet picture that is matched to, generate personalized emoticons packet.
In one embodiment, a kind of computer readable storage medium is provided, computer-readable instruction is stored thereon with,
It is performed the steps of when computer-readable instruction is executed by processor
Obtain facial image；
The micro- expression of face is extracted from the facial image, and the facial image is obtained according to the micro- expression of the face
Expression label；
Expression packet picture is matched from default expression parcel according to the expression label of the facial image, and determination is matched to
The expression packet picture face position present position；Wherein, the expression packet picture in the default expression parcel
At least one face position is all had, and each described expression packet picture is associated with expression label described at least one；
The facial characteristics in the facial image is extracted, and the facial characteristics is covered from the default expression parcel
In the present position at the face position of the expression packet picture that is matched to, generate personalized emoticons packet.
Those of ordinary skill in the art will appreciate that realizing all or part of the process in above-described embodiment method, being can be with
Relevant hardware is instructed to complete by computer-readable instruction, it is non-volatile that the computer-readable instruction can be stored in one
Property computer-readable storage medium in, the computer-readable instruction is when being executed, it may include as above-mentioned each method embodiment
Process.Wherein, to memory, storage, database or other media used in each embodiment provided by the present invention
Any reference may each comprise non-volatile and/or volatile memory.Nonvolatile memory may include read-only memory
(ROM), programming ROM (PROM), electrically programmable ROM (EPROM), electrically erasable ROM (EEPROM) or flash memory.It is volatile
Property memory may include random access memory (RAM) or external cache.By way of illustration and not limitation, RAM
It is available in many forms, such as static state RAM (SRAM), dynamic ram (DRAM), synchronous dram (SDRAM), double data rate sdram
(DDRSDRAM), enhanced SDRAM (ESDRAM), synchronization link DRAM (SLDRAM), the direct RAM of memory bus (RDRAM),
Direct memory bus dynamic ram (DRDRAM) and memory bus dynamic ram (RDRAM) etc..
It is apparent to those skilled in the art that for convenience of description and succinctly, only with above-mentioned each function
Can unit or module division progress for example, in practical application, can according to need and by above-mentioned function distribution by difference
Functional unit or module complete, i.e., the internal structure of described device is divided into different functional unit or module, with complete
All or part of function described above.
Embodiment described above is merely illustrative of the technical solution of the present invention, rather than its limitations；Although referring to aforementioned reality
Applying example, invention is explained in detail, those skilled in the art should understand that: it still can be to aforementioned each
Technical solution documented by embodiment is modified or equivalent replacement of some of the technical features；And these are modified
Or replacement, the spirit and scope for technical solution of various embodiments of the present invention that it does not separate the essence of the corresponding technical solution should all
It is included within protection scope of the present invention.
Claims (10)
1. a kind of expression packet automatic generation method characterized by comprising
Obtain facial image；
The micro- expression of face is extracted from the facial image, and the expression of the facial image is obtained according to the micro- expression of the face
Label；
Expression packet picture is matched from default expression parcel according to the expression label of the facial image, and determines the institute being matched to
State the present position at the face position of expression packet picture；Wherein, the expression packet picture in the default expression parcel has
There is at least one face position, and each described expression packet picture is associated with expression label described at least one；
It extracts the facial characteristics in the facial image, and the facial characteristics is covered from the default expression parcel
The present position at the face position for the expression packet picture being fitted on generates personalized emoticons packet.
2. expression packet automatic generation method as described in claim 1, which is characterized in that described to be extracted from the facial image
The micro- expression of face, and obtain according to the micro- expression of the face expression label of the facial image, comprising:
The everything cell type of the micro- expression of face is extracted from the facial image；
According to the micro- expression type for extracting all motor unit types from the facial image and confirming the facial image；
All expression labels of micro- expression type association are obtained, while obtaining and being associated with expression label described in each
Characteristic action unit；
All motor unit types will be extracted from the facial image and each described expression label is associated described
Characteristic action unit is matched, comprising described in one in extracting all motor unit types from the facial image
When the associated all characteristic action units of expression label, the expression label is recorded as to the expression mark of the facial image
Label.
3. the method that expression packet as described in claim 1 automatically generates, which is characterized in that the table according to the facial image
Feelings label matches expression packet picture from default expression parcel, and determine the face position for the expression packet picture being matched to
Present position, comprising:
It is obtained from the face face mask extracted in the facial image；
Expression label institute's espressiove packet picture identical with the facial image is chosen from default expression parcel；
Determine the present position at the face position for each expression packet picture chosen and the present position at the face position
Profile；
Obtain the similarity between the face face mask and the present position profile；
By the corresponding expression packet picture of the highest present position profile of the similarity, it is recorded as and the face figure
As the expression packet picture of unique match, at the same obtain with the expression packet picture of the facial image unique match five
The present position at official position.
4. expression packet automatic generation method as described in claim 1, which is characterized in that the table according to the facial image
Feelings label matches expression packet picture from default expression parcel, and determine the face position for the expression packet picture being matched to
Present position, comprising:
Expression label institute's espressiove packet picture identical with the facial image is chosen from default expression parcel；
According to preset screening rule, the determining and facial image unique match from all expression packet pictures chosen
The expression packet picture；
Will according to the screening rule determine the expression packet picture, be recorded as with described in the facial image unique match
Expression packet picture, at the same from extracted locating for its face position in the expression packet picture of the facial image unique match
Position.
5. expression packet automatic generation method as described in claim 1, which is characterized in that described to extract in the facial image
Facial characteristics, and the facial characteristics is covered to the institute for the expression packet picture being matched to from the default expression parcel
State the present position at face position, comprising:
It is obtained from the present position wheel at the face position for the expression packet picture being matched in the default expression parcel
Whole placed angle, the face position contour area at wide, described face position；
All facial characteristics being located within face face mask in the facial image are extracted, and determine each facial characteristics
The linear distance between positional relationship and each facial characteristics central point between central point；
Newly-built painting canvas, the painting canvas profile of the painting canvas are consistent with the present position profile at the face position；The face is special
Sign is pre-processed according to preset image procossing mode；
In the case where keeping the position relationship between the facial characteristics central point, by the institute after being pre-processed
There is the facial characteristics to be placed in the painting canvas profile of the painting canvas according to the whole placed angle；
With the linear distance between the same facial characteristics central point more each than column adjustment, and it is adjusted according to the same ratio
The graphics area that the facial characteristics of the outermost in each facial characteristics afterwards surrounds, with face position contoured surface
Ratio between product is in default ratio range；
By the painting canvas comprising the facial characteristics, correspondence covers the table being matched to from the default expression parcel
On the present position profile at the face position of feelings packet picture；
Image synthesis processing is carried out to the expression packet picture for being covered with the painting canvas profile, generates the personalized emoticons
Packet.
6. expression packet automatic generation method as described in claim 1, which is characterized in that described to generate the personalized emoticons
Packet, comprising:
Text addition instruction is received, obtains the expression text of user's typing, the text box number that the user chooses；
It obtains and numbers associated text box size and default text format with the text box；
The character quantity of the expression text is obtained, and described silent according to the character quantity and text box size adjustment
Recognize the character boundary in text formatting；
Predeterminated position or user's selected location in the expression packet picture generate text corresponding with text box number
Frame, and expression text is inserted according to the default text format after adjustment in the text box；
After carrying out assembled processing to the expression packet picture and the text box, the personalized emoticons packet is generated.
7. a kind of expression packet automatically generating device characterized by comprising
Module is obtained, for obtaining facial image；
Extraction module, for extracting the micro- expression of face from the facial image, and according to the micro- expression acquisition of the face
The expression label of facial image；
Matching module, for matching expression packet picture from default expression parcel according to the expression label of the facial image, and
Determine the present position at the face position for the expression packet picture being matched to；Wherein, described in the default expression parcel
Expression packet picture all has at least one face position, and each described expression packet picture with expression mark described at least one
Label association；
Overlay module is covered for extracting the facial characteristics in the facial image, and by the facial characteristics from described pre-
If the present position at the face position for the expression packet picture being matched in expression parcel, personalized emoticons packet is generated.
8. expression packet automatically generating device as claimed in claim 7, which is characterized in that the extraction module includes:
Extraction unit, for extracting the everything cell type of the micro- expression of face from the facial image；
Confirmation unit extracts all motor unit types from the facial image for basis and confirms the facial image
Micro- expression type；
Acquiring unit for obtaining all expression labels of micro- expression type association, while obtaining and each institute
State the associated characteristic action unit of expression label；
Matching unit, for all motor unit types and each described expression mark will to be extracted from the facial image
It signs the associated characteristic action unit to be matched, in extracting all motor unit types from the facial image
When all characteristic action units associated comprising the expression label, the expression label is recorded as the face
The expression label of image.
9. a kind of computer equipment, including memory, processor and storage are in the memory and can be in the processor
The computer-readable instruction of upper operation, which is characterized in that the processor is realized when executing the computer-readable instruction as weighed
Benefit requires any one of 1 to the 6 expression packet automatic generation method.
10. a kind of computer readable storage medium, the computer-readable recording medium storage has computer-readable instruction, special
Sign is, realizes that the expression packet as described in any one of claim 1 to 6 is automatic when the computer-readable instruction is executed by processor
Generation method.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910602401.7A CN110458916A (en) | 2019-07-05 | 2019-07-05 | Expression packet automatic generation method, device, computer equipment and storage medium |
| PCT/CN2020/085573 WO2021004114A1 (en) | 2019-07-05 | 2020-04-20 | Automatic meme generation method and apparatus, computer device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910602401.7A CN110458916A (en) | 2019-07-05 | 2019-07-05 | Expression packet automatic generation method, device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110458916A true CN110458916A (en) | 2019-11-15 |
Family
ID=68482133
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910602401.7A Pending CN110458916A (en) | 2019-07-05 | 2019-07-05 | Expression packet automatic generation method, device, computer equipment and storage medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN110458916A (en) |
| WO (1) | WO2021004114A1 (en) |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110889379A (en) * | 2019-11-29 | 2020-03-17 | 深圳先进技术研究院 | Expression package generation method and device and terminal equipment |
| CN111046814A (en) * | 2019-12-18 | 2020-04-21 | 维沃移动通信有限公司 | Image processing method and electronic device |
| CN111145283A (en) * | 2019-12-13 | 2020-05-12 | 北京智慧章鱼科技有限公司 | Expression personalized generation method and device for input method |
| CN111368127A (en) * | 2020-03-06 | 2020-07-03 | 腾讯科技（深圳）有限公司 | Image processing method, image processing device, computer equipment and storage medium |
| CN111476154A (en) * | 2020-04-03 | 2020-07-31 | 深圳传音控股股份有限公司 | Expression package generation method, device, device, and computer-readable storage medium |
| CN111860372A (en) * | 2020-07-24 | 2020-10-30 | 中国平安人寿保险股份有限公司 | Artificial intelligence-based expression package generation method, device, device and storage medium |
| CN112102157A (en) * | 2020-09-09 | 2020-12-18 | 咪咕文化科技有限公司 | Video face changing method, electronic device and computer readable storage medium |
| CN112214632A (en) * | 2020-11-03 | 2021-01-12 | 虎博网络技术(上海)有限公司 | File retrieval method and device and electronic equipment |
| WO2021004114A1 (en) * | 2019-07-05 | 2021-01-14 | 深圳壹账通智能科技有限公司 | Automatic meme generation method and apparatus, computer device and storage medium |
| CN112270733A (en) * | 2020-09-29 | 2021-01-26 | 北京五八信息技术有限公司 | AR expression package generation method and device, electronic equipment and storage medium |
| CN112905791A (en) * | 2021-02-20 | 2021-06-04 | 北京小米松果电子有限公司 | Expression package generation method and device and storage medium |
| CN113727024A (en) * | 2021-08-30 | 2021-11-30 | 北京达佳互联信息技术有限公司 | Multimedia information generation method, apparatus, electronic device, storage medium, and program product |
| CN113781666A (en) * | 2021-09-15 | 2021-12-10 | 广州虎牙科技有限公司 | Image generation method, device and electronic device |
| CN114419177A (en) * | 2022-01-07 | 2022-04-29 | 上海序言泽网络科技有限公司 | Personalized expression package generation method and system, electronic equipment and readable medium |
| CN114816599A (en) * | 2021-01-22 | 2022-07-29 | 北京字跳网络技术有限公司 | Image display method, apparatus, device and medium |
| CN115589453A (en) * | 2022-09-27 | 2023-01-10 | 维沃移动通信有限公司 | Video processing method and device, electronic equipment and storage medium |
| CN117974853A (en) * | 2024-03-29 | 2024-05-03 | 成都工业学院 | Self-adaptive switching generation method, system, terminal and medium for homologous micro-expression image |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113177994B (en) * | 2021-03-25 | 2022-09-06 | 云南大学 | Network social emoticon synthesis method based on image-text semantics, electronic equipment and computer readable storage medium |
| CN113485596B (en) * | 2021-07-07 | 2023-12-22 | 游艺星际(北京)科技有限公司 | Virtual model processing method and device, electronic equipment and storage medium |
| CN114693827B (en) * | 2022-04-07 | 2025-03-25 | 深圳云之家网络有限公司 | Expression generation method, device, computer equipment and storage medium |
| CN115294388A (en) * | 2022-07-25 | 2022-11-04 | 深圳市百川数安科技有限公司 | Expression package identification method and device based on Internet community and storage medium |
| CN117150063B (en) * | 2023-10-26 | 2024-02-06 | 深圳慢云智能科技有限公司 | Image generation method and system based on scene recognition |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104063683A (en) * | 2014-06-06 | 2014-09-24 | 北京搜狗科技发展有限公司 | Expression input method and device based on face identification |
| US20180024726A1 (en) * | 2016-07-21 | 2018-01-25 | Cives Consulting AS | Personified Emoji |
| CN108573527A (en) * | 2018-04-18 | 2018-09-25 | 腾讯科技（深圳）有限公司 | A kind of expression picture generation method and its equipment, storage medium |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107219917A (en) * | 2017-04-28 | 2017-09-29 | 北京百度网讯科技有限公司 | Emoticon generation method and device, computer equipment and computer-readable recording medium |
| CN108197206A (en) * | 2017-12-28 | 2018-06-22 | 努比亚技术有限公司 | Expression packet generation method, mobile terminal and computer readable storage medium |
| CN110458916A (en) * | 2019-07-05 | 2019-11-15 | 深圳壹账通智能科技有限公司 | Expression packet automatic generation method, device, computer equipment and storage medium |
-
2019
- 2019-07-05 CN CN201910602401.7A patent/CN110458916A/en active Pending
-
2020
- 2020-04-20 WO PCT/CN2020/085573 patent/WO2021004114A1/en not_active Ceased
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104063683A (en) * | 2014-06-06 | 2014-09-24 | 北京搜狗科技发展有限公司 | Expression input method and device based on face identification |
| US20180024726A1 (en) * | 2016-07-21 | 2018-01-25 | Cives Consulting AS | Personified Emoji |
| CN108573527A (en) * | 2018-04-18 | 2018-09-25 | 腾讯科技（深圳）有限公司 | A kind of expression picture generation method and its equipment, storage medium |
Cited By (27)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021004114A1 (en) * | 2019-07-05 | 2021-01-14 | 深圳壹账通智能科技有限公司 | Automatic meme generation method and apparatus, computer device and storage medium |
| CN110889379A (en) * | 2019-11-29 | 2020-03-17 | 深圳先进技术研究院 | Expression package generation method and device and terminal equipment |
| CN110889379B (en) * | 2019-11-29 | 2024-02-20 | 深圳先进技术研究院 | Expression package generation method and device and terminal equipment |
| CN111145283A (en) * | 2019-12-13 | 2020-05-12 | 北京智慧章鱼科技有限公司 | Expression personalized generation method and device for input method |
| CN111046814A (en) * | 2019-12-18 | 2020-04-21 | 维沃移动通信有限公司 | Image processing method and electronic device |
| CN111368127B (en) * | 2020-03-06 | 2023-03-24 | 腾讯科技（深圳）有限公司 | Image processing method, image processing device, computer equipment and storage medium |
| CN111368127A (en) * | 2020-03-06 | 2020-07-03 | 腾讯科技（深圳）有限公司 | Image processing method, image processing device, computer equipment and storage medium |
| CN111476154A (en) * | 2020-04-03 | 2020-07-31 | 深圳传音控股股份有限公司 | Expression package generation method, device, device, and computer-readable storage medium |
| CN111860372A (en) * | 2020-07-24 | 2020-10-30 | 中国平安人寿保险股份有限公司 | Artificial intelligence-based expression package generation method, device, device and storage medium |
| CN111860372B (en) * | 2020-07-24 | 2024-11-19 | 中国平安人寿保险股份有限公司 | Artificial intelligence-based expression package generation method, device, equipment and storage medium |
| CN112102157A (en) * | 2020-09-09 | 2020-12-18 | 咪咕文化科技有限公司 | Video face changing method, electronic device and computer readable storage medium |
| CN112102157B (en) * | 2020-09-09 | 2024-07-09 | 咪咕文化科技有限公司 | Video face changing method, electronic device and computer readable storage medium |
| CN112270733A (en) * | 2020-09-29 | 2021-01-26 | 北京五八信息技术有限公司 | AR expression package generation method and device, electronic equipment and storage medium |
| CN112214632B (en) * | 2020-11-03 | 2023-11-17 | 虎博网络技术(上海)有限公司 | Text retrieval method and device and electronic equipment |
| CN112214632A (en) * | 2020-11-03 | 2021-01-12 | 虎博网络技术(上海)有限公司 | File retrieval method and device and electronic equipment |
| CN114816599B (en) * | 2021-01-22 | 2024-02-27 | 北京字跳网络技术有限公司 | Image display method, device, equipment and medium |
| CN114816599A (en) * | 2021-01-22 | 2022-07-29 | 北京字跳网络技术有限公司 | Image display method, apparatus, device and medium |
| US12106410B2 (en) | 2021-01-22 | 2024-10-01 | Beijing Zitiao Network Technology Co., Ltd. | Customizing emojis for users in chat applications |
| CN112905791A (en) * | 2021-02-20 | 2021-06-04 | 北京小米松果电子有限公司 | Expression package generation method and device and storage medium |
| US11922725B2 (en) | 2021-02-20 | 2024-03-05 | Beijing Xiaomi Pinecone Electronics Co., Ltd. | Method and device for generating emoticon, and storage medium |
| CN113727024A (en) * | 2021-08-30 | 2021-11-30 | 北京达佳互联信息技术有限公司 | Multimedia information generation method, apparatus, electronic device, storage medium, and program product |
| CN113781666A (en) * | 2021-09-15 | 2021-12-10 | 广州虎牙科技有限公司 | Image generation method, device and electronic device |
| CN114419177A (en) * | 2022-01-07 | 2022-04-29 | 上海序言泽网络科技有限公司 | Personalized expression package generation method and system, electronic equipment and readable medium |
| CN114419177B (en) * | 2022-01-07 | 2025-06-17 | 上海序言泽网络科技有限公司 | Personalized expression package generation method, system, electronic device and readable medium |
| CN115589453A (en) * | 2022-09-27 | 2023-01-10 | 维沃移动通信有限公司 | Video processing method and device, electronic equipment and storage medium |
| CN117974853A (en) * | 2024-03-29 | 2024-05-03 | 成都工业学院 | Self-adaptive switching generation method, system, terminal and medium for homologous micro-expression image |
| CN117974853B (en) * | 2024-03-29 | 2024-06-11 | 成都工业学院 | Method, system, terminal and medium for adaptive switching generation of homologous micro-expression images |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2021004114A1 (en) | 2021-01-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110458916A (en) | Expression packet automatic generation method, device, computer equipment and storage medium | |
| US11889230B2 (en) | Video conferencing method | |
| KR102241153B1 (en) | Method, apparatus, and system generating 3d avartar from 2d image | |
| JP6972043B2 (en) | Information processing equipment, information processing methods and programs | |
| JP2021519995A (en) | Image processing methods, devices, computer devices and computer programs | |
| CN110390632B (en) | Image processing method and device based on dressing template, storage medium and terminal | |
| JP6956389B2 (en) | Makeup support device and makeup support method | |
| KR101635730B1 (en) | Apparatus and method for generating montage, recording medium for performing the method | |
| JPWO2008102440A1 (en) | Makeup face image generating apparatus and method | |
| JP7278724B2 (en) | Information processing device, information processing method, and information processing program | |
| US11145091B2 (en) | Makeup simulation device, method, and non-transitory recording medium | |
| CN104951770B (en) | Construction method, application process and the related device of face database | |
| CN110755847B (en) | Virtual operation object generation method and device, storage medium and electronic device | |
| EP3370207B1 (en) | Makeup parts generating device and makeup parts generating method | |
| JP2022505746A (en) | Digital character blending and generation systems and methods | |
| CN109886144A (en) | Virtual examination forwarding method, device, computer equipment and storage medium | |
| CN109509141A (en) | Image processing method, head portrait setting method and device | |
| WO2025066458A1 (en) | Try-on image generation method and generation system, electronic device, and storage medium | |
| US10152827B2 (en) | Three-dimensional modeling method and electronic apparatus thereof | |
| CN114841851B (en) | Image generation method, device, electronic device and storage medium | |
| WO2022146766A1 (en) | Digital makeup artist | |
| KR102136137B1 (en) | Customized LED mask pack manufacturing apparatus thereof | |
| US20180181110A1 (en) | System and method of generating a custom eyebrow stencil | |
| CN115826835A (en) | Data processing method and device and readable storage medium | |
| CN104715505A (en) | Three-dimensional avatar generation system, device and method thereof |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20191115 |