CN109919016A - A kind of method and device generating human face expression on the object of no face's organ - Google Patents
A kind of method and device generating human face expression on the object of no face's organ Download PDFInfo
- Publication number
- CN109919016A CN109919016A CN201910081812.6A CN201910081812A CN109919016A CN 109919016 A CN109919016 A CN 109919016A CN 201910081812 A CN201910081812 A CN 201910081812A CN 109919016 A CN109919016 A CN 109919016A
- Authority
- CN
- China
- Prior art keywords
- face
- organ
- feature
- model
- shape
- 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.)
- Granted
Links
Landscapes
- Processing Or Creating Images (AREA)
Abstract
The present invention relates to a kind of on the object of no face's organ generates the method and device of human face expression, and wherein method includes: to choose pending area on the surface of the data model of characterization object；Face's organ model of characterization face's organ is generated in the pending area；Face organ model of the migration human face expression to the generation.The technical solution that the embodiment of the present invention proposes, to assign the object without face's organ with anthropomorphic countenance, has widened the application scenarios of human face expression simulation, has enhanced user experience by forming human face expression on the data model of object of the characterization without face's organ.
Description
Technical field
The invention belongs to technical field of image processing, and in particular to a kind of that face table is generated on the object of no face's organ
The method and device of feelings.
Background technique
Facial expression recognition and human face expression migration are technologies relatively conventional at present, on this basis, quasi- in order to reach
People's effect also occurs assigning expression to animal or migrates the application of expression.The common point of these above-mentioned technologies all passes through
The technologies such as Expression Recognition, expression migration generate expression based on existing face, and application scenarios are limited, and user experience is poor.
Summary of the invention
Expression is generated to solve above-mentioned needs on existing face causes application scenarios limited, and user experience is poor
Technical problem, the embodiment of the present invention propose a kind of method and device that human face expression is generated on the object of no face's organ.
On the one hand, a kind of method that human face expression is generated on the object of no face's organ is provided, comprising:
On the surface of the data model of characterization object, pending area is chosen；
Face's organ model of characterization face's organ is generated in the pending area；
Face organ model of the migration human face expression to the generation.
In certain embodiments, the method also includes:
Obtain the data model of characterization subject surface shape；
Obtain the primary data feature of face's organ model of characterization face's organ to be generated；
The primary data feature includes that the shape feature of face's organ, the position feature of face's organ and human face expression are special
Sign, the three-dimensional shape of shape feature characterization face's organ of face's organ, the position feature of face's organ characterize face's organ institute
Position, human face expression characteristic present human face expression.
In certain embodiments, the surface of the data model in characterization object, chooses pending area, comprising:
Traverse the shape on the data model surface obtained, it is determined whether there is the shape for the shape feature for meeting face's organ
Shape；
If it is present pending area is chosen in the region where the shape based on the shape feature for meeting face's organ；
If it does not exist, then choosing pending area on the surface of data model；
Face's organ model that characterization face's organ is generated in the pending area, comprising:
The position feature of shape feature and face's organ based on face's organ generates face in the pending area
Portion's organ model, wherein if there is the shape for the shape feature for meeting face's organ, then it is special in the shape for meeting face's organ
The corresponding face's organ model of Area generation where the shape of sign.
In certain embodiments, the method also includes:
Obtain the data model of characterization subject surface pattern；
Obtain the primary data feature of face's organ model of characterization face's organ to be generated；
The primary data feature includes that the contour feature of face's organ, the position feature of face's organ and human face expression are special
Sign, the face profile of contour feature characterization face's organ of face's organ, the position feature of face's organ characterize face's organ institute
Position, human face expression characteristic present human face expression.
In certain embodiments, the surface of the data model in characterization object, chooses pending area, comprising:
Traverse the pattern on the data model surface obtained, it is determined whether there is the figure for the contour feature for meeting face's organ
Case；
If it is present pending area is chosen in the region where the pattern based on the contour feature for meeting face's organ；
If it does not exist, then choosing pending area on the surface of data model；
Face's organ model that characterization face's organ is generated in the pending area, comprising:
The position feature of contour feature and face's organ based on face's organ generates face in the pending area
Portion's organ model, wherein if there is the pattern for the contour feature for meeting face's organ, then it is special in the profile for meeting face's organ
The corresponding face's organ model of Area generation where the pattern of sign.
In certain embodiments, the data model also additionally characterizes material texture, gloss and the color of subject surface
One of or it is a variety of.
In certain embodiments, the primary data feature further includes the color characteristic of face's organ, described to be processed
When Area generation face organ model, also additionally the color characteristic based on face's organ generates face's organ model.
On the other hand, a kind of device that human face expression is generated on the object of no face's organ is additionally provided, comprising:
Pending area chooses component, for the surface of the data model in characterization object, chooses pending area；
Face's organ model generating unit, for generating face's organ mould of characterization face's organ in the pending area
Type；
Human face expression migrates component, face's organ model for migrating human face expression to the generation.
In certain embodiments, described device further include:
Data model obtaining widget, for obtaining the data model of characterization subject surface shape or pattern；
Primary data feature obtaining widget, for obtaining the initial of the face's organ model for characterizing face's organ to be generated
Data characteristics；
The primary data feature includes the shape of face's organ or the position feature and face of contour feature, face's organ
Expressive features, the three-dimensional shape or face profile of shape or contour feature characterization face's organ of face's organ, face's organ
Position feature characterizes the position where face's organ, human face expression characteristic present human face expression.
In certain embodiments, described device realizes such as preceding described in any item methods.
In certain embodiments, the pending area chooses component on the surface of the data model of characterization object, chooses
Pending area, comprising:
Traverse the shape on the data model surface obtained, it is determined whether there is the shape for the shape feature for meeting face's organ
Shape；
If it is present pending area is chosen in the region where the shape based on the shape feature for meeting face's organ；
If it does not exist, then choosing pending area on the surface of data model；
Face's organ model generating unit generates face's organ mould of characterization face's organ in the pending area
Type, comprising:
The position feature of shape feature and face's organ based on face's organ generates face in the pending area
Portion's organ model, wherein if there is the shape for the shape feature for meeting face's organ, then it is special in the shape for meeting face's organ
The corresponding face's organ model of Area generation where the shape of sign.
In certain embodiments, the pending area chooses component on the surface of the data model of characterization object, chooses
Pending area, comprising:
Traverse the pattern on the data model surface obtained, it is determined whether there is the figure for the contour feature for meeting face's organ
Case；
If it is present pending area is chosen in the region where the pattern based on the contour feature for meeting face's organ；
If it does not exist, then choosing pending area on the surface of data model；
Face's organ model generating unit generates face's organ mould of characterization face's organ in the pending area
Type, comprising:
The position feature of contour feature and face's organ based on face's organ generates face in the pending area
Portion's organ model, wherein if there is the pattern for the contour feature for meeting face's organ, then it is special in the profile for meeting face's organ
The corresponding face's organ model of Area generation where the pattern of sign.
In certain embodiments, the data model also additionally characterizes material texture, gloss and the color of subject surface
One of or it is a variety of.
In certain embodiments, the primary data feature further includes the color characteristic of face's organ, described to be processed
When Area generation face organ model, also additionally the color characteristic based on face's organ generates face's organ model.
The embodiment of the present invention propose on the object of no face's organ generate human face expression method and device, by
The face's organ model for simulating characterization face's organ on the data model of the object without face's organ is characterized, is recycled existing
Human face expression is given to the face's organ model simulated, by data model and face's organ by human face expression migrating technology
Model realization personification effect expresses personage's mood.Therefore, the technical solution that the embodiment of the present invention proposes is by characterizing without face
Human face expression is formed on the data model of the object of organ, to assign the object without face's organ with anthropomorphic countenance, is opened up
The wide application scenarios of human face expression simulation, enhance user experience.
Detailed description of the invention
Fig. 1 is the process for the method that human face expression is generated on the object of no face's organ that the embodiment of the present invention proposes
Figure；
Fig. 2 is that the structure for the device that human face expression is generated on the object of no face's organ that the embodiment of the present invention proposes is shown
It is intended to.
Specific embodiment
To make the objectives, technical solutions, and advantages of the present invention clearer, below in conjunction with specific embodiment, and reference
Attached drawing, the present invention is described in more detail.But as known to those skilled in the art, the invention is not limited to attached drawings and following reality
Apply example.
The embodiment of the present invention proposes a kind of method that human face expression is generated on the object of no face's organ, such as Fig. 1 institute
Show, comprising:
On the surface of the data model of characterization object, pending area is chosen；
Face's organ model of characterization face's organ is generated in the pending area；
Face organ model of the migration human face expression to the generation.
In embodiments of the present invention, the object for no face's organ object.The embodiment of the present invention propose in no face
The method that human face expression is generated on the object of portion's organ, by being simulated on the data model of object of the characterization without face's organ
The face's organ model for characterizing face's organ, recycles existing human face expression migrating technology, human face expression is given to simulation
Face's organ model out realizes anthropomorphic effect by data model and face's organ model, expresses personage's mood.Therefore, originally
Inventive embodiments propose technical solution by characterization the object without face's organ data model on form human face expression,
To assign the object without face's organ with anthropomorphic countenance, the application scenarios of human face expression simulation are widened, user is enhanced
Experience.
In one embodiment, the object can be with the three-dimensional structure (three-dimensional structure and irregular including rule
Three-dimensional structure) the object without face's organ, the data model can characterize the shape of subject surface.
In another embodiment, the object can be with two-dimensional structure (including regular two-dimensional structure and irregularly
Two-dimensional structure) the object without face's organ, the data model can characterize the pattern of subject surface.
In one embodiment, the data model can also characterize the material texture of subject surface, with the matter of expressive object
Sense, further enhances user experience.
In one embodiment, the data model can also characterize the gloss of subject surface, enhance the smart of expression, mention
The visual experience of high user.
In one embodiment, the data model can also characterize the color of subject surface, improve reduction degree and user
Visual experience.
In one embodiment, the surface of the data model can also render color according to the demand of user, for example,
The colouring of face's organ model, or be other regions colouring except face's organ, so that the expressive force of abundant data model, increases
Strong user experience.
In one embodiment, the object can be the object that the data model selected from database has been built up.
In another embodiment, the object can be material object, and it is described right that characterization is constructed using existing modeling technique
The data model of elephant, such as 3DMAX, SoftImage, Maya, UG, AutoCAD etc., detail are not detailed.
In one embodiment, on the surface of the data model of characterization object, pending area is chosen, it can be in data model
Any position on surface choose the pending area.
In another embodiment, on the surface of the data model of characterization object, pending area is chosen, it can be in data mould
The region that the surface search and face's organ of type match, and the pending area is chosen based on this region, be conducive to
The matching degree for improving the face's organ model and data model surface that are subsequently generated, increases the harmony between human face expression and object
Sense.
In one embodiment, the surface includes plane, and the plane based on data model provides the pending area.?
In one embodiment, the plane includes that curvature is less than 2m-1All planes.In one embodiment, the plane includes pixel number
It is more than or equal to the plane of 200*200 according to amount.
In one embodiment, face's organ model is generated in the pending area, can face's organ based on people,
Face's organ of animal or the face's organ for fabricating image generate face's organ model.The imaginary image may include
But the imaginary image with face's organ come out such as be not limited to cartoon character.
In one embodiment, face's organ includes at least eyes, and face's organ may be used also in addition to comprising eyes
To include one or more of nose, mouth, eyebrow and ear.In one embodiment, face's organ includes eyes and nose
Son.
In one embodiment, the human face expression can be selected from Facial expression database.
In another embodiment, the human face expression can be known using based on realistic individual face using existing human face expression
Other technology obtains, and detail is not detailed.
In embodiments of the present invention, the technology of the migration human face expression can migrate skill using existing human face expression
Art, detail are not detailed.
The embodiment of the present invention proposes a kind of device that expression simulation is carried out on the object of no face's organ, such as Fig. 2 institute
Show, comprising:
Pending area chooses component, for the surface of the data model in characterization object, chooses pending area；
Face's organ model generating unit, for generating face's organ mould of characterization face's organ in the pending area
Type；
Human face expression migrates component, face's organ model for migrating human face expression to the generation.
In embodiments of the present invention, the object for no face's organ object.The embodiment of the present invention propose in no face
The device that expression simulation is carried out on the object of portion's organ, by being simulated on the data model of object of the characterization without face's organ
The face's organ model for characterizing face's organ, recycles existing human face expression migrating technology, human face expression is given to simulation
Face's organ model out realizes anthropomorphic effect by data model and face's organ model, expresses personage's mood.Therefore, originally
Inventive embodiments propose technical solution by characterization the object without face's organ data model on form human face expression,
To assign the object without face's organ with anthropomorphic countenance, the application scenarios of human face expression simulation are widened, user is enhanced
Experience.
The device that expression simulation is carried out on the object of no face's organ that the embodiment of the present invention proposes, can refer to the present invention
Embodiment proposes a kind of description of method that expression simulation is carried out on the object of no face's organ, to save length, no longer
It repeats.
It is right below by taking a kind of object for no face's organ that the embodiment of the present invention proposes generates the method for human face expression as an example
The technical solution that the embodiment of the present invention proposes carries out exemplary description, but does not constitute the limit to the claim of this application protection scope
System.Those skilled in the art according to the descriptions of following embodiments, could be aware that the embodiment of the present invention proposes without face's organ
Object generates the implementation of the device of human face expression, to save length, pair without face's organ that the embodiment of the present invention proposes
Related content as generating the device of human face expression does not repeat them here.
Embodiment 1:
In the present embodiment, by the object have three-dimensional structure for, exemplary illustration the present embodiment propose in nothing
The embodiment of the method for human face expression is generated on the object of face's organ.
A kind of method that human face expression is generated on the object of no face's organ that the present embodiment proposes, comprising:
Obtain the data model of characterization subject surface shape；
The primary data feature of face's organ model of characterization face's organ to be generated is obtained, primary data feature includes
The shape feature of the shape feature of face's organ, the position feature of face's organ and human face expression feature, face's organ characterizes face
The three-dimensional shape of portion's organ, the position where position feature characterization face's organ of face's organ, human face expression mark sheet traveller on a long journey
Face expression；
Traverse the shape on the data model surface obtained, it is determined whether there is the shape for the shape feature for meeting face's organ
Shape；
If it is present pending area is chosen in the region where the shape based on the shape feature for meeting face's organ；
The position feature of shape feature and face's organ based on face's organ generates face's organ mould in the pending area
Type, wherein the corresponding face's organ model of Area generation where meeting the shape of shape feature of face's organ；Migration institute
State human face expression feature to the generation face's organ model；
If it does not exist, then choosing pending area on the surface of data model；Shape based on face's organ is special
It seeks peace the position feature of face's organ, generates face's organ model in the pending area；Migrate the human face expression feature
To face's organ model of the generation.
In one embodiment, the primary data feature further includes the color characteristic of face's organ, in the pending district
When domain generates face's organ model, also additionally the color characteristic based on face's organ generates face's organ model, thus abundant
The expressive force of data model enhances user experience.
The method that human face expression is generated on the object of no face's organ that the present embodiment proposes, by data model
The region that surface search and the shape of face's organ match, and the pending area is chosen based on this region, rationally
Using the shape on data model surface, be conducive to the matching for improving the face's organ model and data model surface that are subsequently generated
Degree increases the harmonious feeling between human face expression and the data model for characterizing object.
Embodiment 2:
In the present embodiment, by the object have two-dimensional structure for, exemplary illustration the present embodiment propose in nothing
The embodiment of the method for human face expression is generated on the object of face's organ.
A kind of method that human face expression is generated on the object of no face's organ that the present embodiment proposes, comprising:
Obtain the data model of characterization subject surface pattern；
The primary data feature of face's organ model of characterization face's organ to be generated is obtained, primary data feature includes
The contour feature of the contour feature of face's organ, the position feature of face's organ and human face expression feature, face's organ characterizes face
The face profile of portion's organ, the position where position feature characterization face's organ of face's organ, human face expression mark sheet traveller on a long journey
Face expression；
Traverse the pattern on the data model surface obtained, it is determined whether there is the figure for the contour feature for meeting face's organ
Case；
If it is present pending area is chosen in the region where the pattern based on the contour feature for meeting face's organ；
The position feature of contour feature and face's organ based on face's organ generates face's organ mould in the pending area
Type, wherein the corresponding face's organ model of Area generation where meeting the pattern of contour feature of face's organ；Migration institute
State human face expression feature to the generation face's organ model；
If it does not exist, then choosing pending area on the surface of data model；Profile based on face's organ is special
It seeks peace the position feature of face's organ, generates face's organ model in the pending area；Migrate the human face expression feature
To face's organ model of the generation.
In one embodiment, the primary data feature further includes the color characteristic of face's organ, in the pending district
When domain generates face's organ model, also additionally the color characteristic based on face's organ generates face's organ model, thus abundant
The expressive force of data model enhances user experience.
The method that human face expression is generated on the object of no face's organ that the present embodiment proposes, by data model
The region that the pattern of surface search and face's organ matches, and the pending area is chosen based on this region, rationally
Using the pattern on data model surface, be conducive to the matching for improving the face's organ model and data model surface that are subsequently generated
Degree increases the harmonious feeling between human face expression and the data model for characterizing object.
Embodiment 3:
In the present embodiment, with the object have three-dimensional structure, and surface have material texture for, exemplary illustration
The embodiment for the method that human face expression is generated on the object of no face's organ that the present embodiment proposes.
A kind of method that human face expression is generated on the object of no face's organ that the present embodiment proposes, comprising:
Obtain the data model of characterization subject surface shape and material texture；
The primary data feature of face's organ model of characterization face's organ to be generated is obtained, primary data feature includes
The shape feature of the shape feature of face's organ, the position feature of face's organ and human face expression feature, face's organ characterizes face
The three-dimensional shape of portion's organ, the position where position feature characterization face's organ of face's organ, human face expression mark sheet traveller on a long journey
Face expression；
Traverse the shape on the data model surface obtained, it is determined whether there is the shape for the shape feature for meeting face's organ
Shape；
If it is present pending area is chosen in the region where the shape based on the shape feature for meeting face's organ；
The position feature of shape feature and face's organ based on face's organ generates face's organ mould in the pending area
Type, wherein the corresponding face's organ model of Area generation where meeting the shape of shape feature of face's organ；Migration institute
State human face expression feature to the generation face's organ model；
If it does not exist, then choosing pending area on the surface of data model；Shape based on face's organ is special
It seeks peace the position feature of face's organ, generates face's organ model in the pending area；Migrate the human face expression feature
To face's organ model of the generation.
In an alternative em bodiment, data model in addition to characterize subject surface shape, can also in data model table
Levy out the gloss and/or color of subject surface.
In one embodiment, shape of the data model in addition to characterizing subject surface, can also symbolize in data model
The material texture and gloss of subject surface perhaps symbolize the material texture of subject surface and color or symbolize Object table
Material texture, gloss and the color in face.
The method that human face expression is generated on the object of no face's organ that the present embodiment proposes, by subject surface
Further the material texture and/or gloss of subject surface are incorporated in data model on the basis of shape, can vivo be showed
The texture of object out enhances the smart of expression, improves the visual experience of user, enhances user experience.
Embodiment 4:
In the present embodiment, with the object have two-dimensional structure, and surface have material texture for, exemplary illustration
The embodiment for the method that human face expression is generated on the object of no face's organ that the present embodiment proposes.
A kind of method that human face expression is generated on the object of no face's organ that the present embodiment proposes, comprising:
Obtain the data model of characterization subject surface pattern and material texture；
The primary data feature of face's organ model of characterization face's organ to be generated is obtained, primary data feature includes
The contour feature of the contour feature of face's organ, the position feature of face's organ and human face expression feature, face's organ characterizes face
The face profile of portion's organ, the position where position feature characterization face's organ of face's organ, human face expression mark sheet traveller on a long journey
Face expression；
Traverse the pattern on the data model surface obtained, it is determined whether there is the figure for the contour feature for meeting face's organ
Case；
If it is present pending area is chosen in the region where the pattern based on the contour feature for meeting face's organ；
The position feature of contour feature and face's organ based on face's organ generates face's organ mould in the pending area
Type, wherein the corresponding face's organ model of Area generation where meeting the pattern of contour feature of face's organ；Migration institute
State human face expression feature to the generation face's organ model；
If it does not exist, then choosing pending area on the surface of data model；Profile based on face's organ is special
It seeks peace the position feature of face's organ, generates face's organ model in the pending area；Migrate the human face expression feature
To face's organ model of the generation.
In an alternative em bodiment, data model in addition to characterize subject surface pattern, can also in data model table
Levy out the gloss and/or color of subject surface.
In one embodiment, pattern of the data model in addition to characterizing subject surface, can also symbolize in data model
The material texture and gloss of subject surface perhaps symbolize the material texture of subject surface and color or symbolize Object table
Material texture, gloss and the color in face.
The method that human face expression is generated on the object of no face's organ that the present embodiment proposes, by subject surface
Further the material texture and/or gloss of subject surface are incorporated in data model on the basis of pattern, can vivo be showed
The texture of object out enhances the smart of expression, improves the visual experience of user, enhances user experience.
Embodiment 5:
In the present embodiment, by taking face's organ includes eyes and nose as an example, exemplary illustration the present embodiment propose
The embodiment of the method for human face expression is generated on the object of no face's organ.
A kind of method that human face expression is generated on the object of no face's organ that the present embodiment proposes, comprising:
The surface of the data model of traversal characterization object, the shape or pattern that search matches with eyes or nose；
If searching the shape to match with eyes or pattern, such as there are two the close elemental areas of area to be more than
The facet of 30*30, or the elemental area that has two panels to be closely located to are more than the leaf of 30*30, then based on matching with eyes
Shape or pattern where region choose pending area, the region where the shape to match with eyes or pattern is raw
At eye model, and the nose model with relative positional relationship is generated according to the position where the eye model；Based on eye
Eyeball model and nose model optionally generate other face's organ model (such as mouth, ear and eyebrows with relative positional relationship
One or more of hair)；
If search the shape to match with nose or pattern, for example, a special-shaped cube angle outstanding shape
With nose match or an ellipsoid on there is an edge outstanding, and the shape of edge matches with nose, then be based on
Choose pending area, the shape to match with nose or pattern institute in region where shape or pattern that nose matches
Area generation nose model, and according to where the nose position generate have relative positional relationship eye model；
Based on nose model and eye model, other face's organ model (such as mouths, ear with relative positional relationship are optionally generated
Piece and one or more of eyebrow)；
If searching the shape to match with eyes and nose or pattern respectively, such as the pixel for thering is two panels to be closely located to
Area is more than the floral leaf of 30*30, and has a flower thorn on the spray below two panels floral leaf, and spends the shape of thorn and nose phase
Match, then pending area is chosen based on the region where the shape or pattern to match with eyes and nose, it is described with eyes phase
Area generation eye model where matched shape or pattern, the region where the shape to match with nose or pattern
Generate nose model；Based on eye model and nose model, other face's organs with relative positional relationship are optionally generated
Model (such as one or more of mouth, ear and eyebrow)；
Migrate the human face expression feature to the generation face's organ model, for example, in human face expression feature about
The feature of eyes moves to the eye model of generation, moves to the nose mould of generation in human face expression feature about the feature of nose
Type, if also generating mouth model, the feature in human face expression feature about mouth moves to the mouth model of generation.
In one embodiment, shape or pattern of the data model in addition to characterizing subject surface, can also symbolize Object table
One of material texture, gloss and the color in face are a variety of.
In one embodiment, the method also includes carrying out colouring operation to face's organ model of generation, this step can
It, can also be after migration step, so that the expressive force of abundant data model, enhances user experience with before migration step.
The embodiment of the present invention also proposes a kind of computer readable storage medium, is stored with the computer journey for executing preceding method
Sequence.
The embodiment of the present invention also proposes a kind of computer equipment, including what is be connected to the processor on processor and operation
Above-mentioned computer readable storage medium, the processor operation execute the computer program in computer-readable medium.
It will be understood by those skilled in the art that in flow charts indicate or logic described otherwise above herein and/or
Step may be embodied in and appoint for example, being considered the order list of the executable instruction for realizing logic function
In what computer-readable medium, for instruction execution system, device or equipment (such as computer based system including processor
System or other can be from instruction execution system, device or equipment instruction fetch and the system executed instruction) use, or combine this
A little instruction execution systems, device or equipment and use.For the purpose of this specification, " computer-readable medium " can be it is any can be with
Include, store, communicate, propagate, or transport program is for instruction execution system, device or equipment or in conjunction with these instruction execution systems
System, device or equipment and the device used.
The more specific example (non-exhaustive list) of computer-readable medium include the following: there are one or more wirings
Electrical connection section (electronic device), portable computer diskette box (magnetic device), random access memory (RAM), read-only memory
(ROM), erasable edit read-only storage (EPROM or flash memory), fiber device and portable optic disk is read-only deposits
Reservoir (CDROM).In addition, computer-readable medium can even is that the paper that can print described program on it or other are suitable
Medium, because can then be edited, be interpreted or when necessary with it for example by carrying out optical scanner to paper or other media
His suitable method is handled electronically to obtain described program, is then stored in computer storage.
It should be appreciated that each section of the invention can be realized with hardware, software, firmware or their combination.Above-mentioned
In embodiment, software that multiple steps or method can be executed in memory and by suitable instruction execution system with storage
Or firmware is realized.It, and in another embodiment, can be under well known in the art for example, if realized with hardware
Any one of column technology or their combination are realized: having a logic gates for realizing logic function to data-signal
Discrete logic, with suitable combinational logic gate circuit specific integrated circuit, programmable gate array (PGA), scene
Programmable gate array (FPGA) etc..
In the description of this specification, term " includes " and its various variants are construed as open-ended term, meaning
Taste " including but not limited to ".Term "based" is construed as " being based at least partially on ".A reference term " implementation
The description of example ", " some embodiments ", " example ", " specific example " or " some examples " etc. means to combine the embodiment or example
Particular features, structures, materials, or characteristics described are included at least one embodiment or example of the invention.In this explanation
In book, schematic expression of the above terms be may not refer to the same embodiment or example.Moreover, the specific spy of description
Sign, structure, material or feature can be combined in any suitable manner in any one or more of the embodiments or examples.
More than, embodiments of the present invention are illustrated.But the present invention is not limited to above embodiment.It is all
Within the spirit and principles in the present invention, any modification, equivalent substitution, improvement and etc. done should be included in guarantor of the invention
Within the scope of shield.
Claims (10)
1. a kind of method for generating human face expression on the object of no face's organ characterized by comprising
On the surface of the data model of characterization object, pending area is chosen；
Face's organ model of characterization face's organ is generated in the pending area；
Face organ model of the migration human face expression to the generation.
2. the method according to claim 1, wherein the method also includes:
Obtain the data model of characterization subject surface shape；
Obtain the primary data feature of face's organ model of characterization face's organ to be generated；
The primary data feature includes the shape feature of face's organ, the position feature of face's organ and human face expression feature,
The three-dimensional shape of shape feature characterization face's organ of face's organ, the position feature of face's organ characterize where face's organ
Position, human face expression characteristic present human face expression.
3. according to the method described in claim 2, it is characterized in that, the surface of the data model in characterization object, chooses
Pending area, comprising:
Traverse the shape on the data model surface obtained, it is determined whether there is the shape for the shape feature for meeting face's organ；
If it is present pending area is chosen in the region where the shape based on the shape feature for meeting face's organ；
If it does not exist, then choosing pending area on the surface of data model；
Face's organ model that characterization face's organ is generated in the pending area, comprising:
The position feature of shape feature and face's organ based on face's organ generates face's device in the pending area
Official's model, wherein then meeting the shape feature of face's organ if there is the shape for the shape feature for meeting face's organ
The corresponding face's organ model of Area generation where shape.
4. the method according to claim 1, wherein the method also includes:
Obtain the data model of characterization subject surface pattern；
Obtain the primary data feature of face's organ model of characterization face's organ to be generated；
The primary data feature includes the contour feature of face's organ, the position feature of face's organ and human face expression feature,
The face profile of contour feature characterization face's organ of face's organ, the position feature of face's organ characterize where face's organ
Position, human face expression characteristic present human face expression.
5. according to the method described in claim 4, it is characterized in that, the surface of the data model in characterization object, chooses
Pending area, comprising:
Traverse the pattern on the data model surface obtained, it is determined whether there is the pattern for the contour feature for meeting face's organ；
If it is present pending area is chosen in the region where the pattern based on the contour feature for meeting face's organ；
If it does not exist, then choosing pending area on the surface of data model；
Face's organ model that characterization face's organ is generated in the pending area, comprising:
The position feature of contour feature and face's organ based on face's organ generates face's device in the pending area
Official's model, wherein then meeting the contour feature of face's organ if there is the pattern for the contour feature for meeting face's organ
The corresponding face's organ model of Area generation where pattern.
6. method according to claim 2 or 4, which is characterized in that the data model also additionally characterizes subject surface
One of material texture, gloss and color or a variety of.
7. the method according to claim 3 or 5, which is characterized in that the primary data feature further includes face's organ
Color characteristic, when the pending area generates face's organ model, also additionally the color characteristic based on face's organ is raw
At face's organ model.
8. a kind of device for generating human face expression on the object of no face's organ characterized by comprising
Pending area chooses component, for the surface of the data model in characterization object, chooses pending area；
Face's organ model generating unit, for generating face's organ model of characterization face's organ in the pending area；
Human face expression migrates component, face's organ model for migrating human face expression to the generation.
9. device according to claim 8, which is characterized in that described device further include:
Data model obtaining widget, for obtaining the data model of characterization subject surface shape or pattern；
Primary data feature obtaining widget, the primary data of face's organ model for obtaining characterization face's organ to be generated
Feature；
The primary data feature includes the shape of face's organ or the position feature and human face expression of contour feature, face's organ
Feature, the three-dimensional shape or face profile of shape or contour feature characterization face's organ of face's organ, the position of face's organ
Position where characteristic present face organ, human face expression characteristic present human face expression.
10. device according to claim 9, which is characterized in that described device is realized as any in claim 3,5 to 7
Method described in.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910081812.6A CN109919016B (en) | 2019-01-28 | 2019-01-28 | Method and device for generating facial expression on object without facial organs |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910081812.6A CN109919016B (en) | 2019-01-28 | 2019-01-28 | Method and device for generating facial expression on object without facial organs |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109919016A true CN109919016A (en) | 2019-06-21 |
| CN109919016B CN109919016B (en) | 2020-11-03 |
Family
ID=66961028
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910081812.6A Active CN109919016B (en) | 2019-01-28 | 2019-01-28 | Method and device for generating facial expression on object without facial organs |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109919016B (en) |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101604387A (en) * | 2008-06-11 | 2009-12-16 | 索尼株式会社 | Image processing apparatus and image processing method |
| CN103516951A (en) * | 2012-06-22 | 2014-01-15 | 卡西欧计算机株式会社 | Image creating device and image creating method |
| CN104157001A (en) * | 2014-08-08 | 2014-11-19 | 中科创达软件股份有限公司 | Method and device for drawing head caricature |
| CN104205171A (en) * | 2012-04-09 | 2014-12-10 | 英特尔公司 | System and method for avatar generation, rendering and animation |
| WO2015057733A1 (en) * | 2013-10-14 | 2015-04-23 | Fuhu, Inc. | Widgetized avatar and a method and system of creating and using same |
| CN105374055A (en) * | 2014-08-20 | 2016-03-02 | 腾讯科技（深圳）有限公司 | Image processing method and device |
| CN106104633A (en) * | 2014-03-19 | 2016-11-09 | 英特尔公司 | Facial expression and/or the mutual incarnation apparatus and method driving |
| CN106204698A (en) * | 2015-05-06 | 2016-12-07 | 北京蓝犀时空科技有限公司 | Virtual image for independent assortment creation generates and uses the method and system of expression |
| WO2017003031A1 (en) * | 2015-06-29 | 2017-01-05 | 김영자 | Method for providing lifelike avatar emoticon-based ultralight data animation creation system, and terminal device providing lifelike avatar emoticon for implementing same |
| CN106599817A (en) * | 2016-12-07 | 2017-04-26 | 腾讯科技（深圳）有限公司 | Face replacement method and device |
| CN107852533A (en) * | 2015-07-14 | 2018-03-27 | 三星电子株式会社 | Three-dimensional content generating means and its three-dimensional content generation method |
| CN108171789A (en) * | 2017-12-21 | 2018-06-15 | 迈吉客科技（北京）有限公司 | A kind of virtual image generation method and system |
| WO2019005182A1 (en) * | 2017-06-30 | 2019-01-03 | Tobii Ab | Systems and methods for displaying images in a virtual world environment |
| CN109173263A (en) * | 2018-08-31 | 2019-01-11 | 腾讯科技（深圳）有限公司 | A kind of image processing method and device |
-
2019
- 2019-01-28 CN CN201910081812.6A patent/CN109919016B/en active Active
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101604387A (en) * | 2008-06-11 | 2009-12-16 | 索尼株式会社 | Image processing apparatus and image processing method |
| CN104205171A (en) * | 2012-04-09 | 2014-12-10 | 英特尔公司 | System and method for avatar generation, rendering and animation |
| CN103516951A (en) * | 2012-06-22 | 2014-01-15 | 卡西欧计算机株式会社 | Image creating device and image creating method |
| WO2015057733A1 (en) * | 2013-10-14 | 2015-04-23 | Fuhu, Inc. | Widgetized avatar and a method and system of creating and using same |
| CN106104633A (en) * | 2014-03-19 | 2016-11-09 | 英特尔公司 | Facial expression and/or the mutual incarnation apparatus and method driving |
| CN104157001A (en) * | 2014-08-08 | 2014-11-19 | 中科创达软件股份有限公司 | Method and device for drawing head caricature |
| CN105374055A (en) * | 2014-08-20 | 2016-03-02 | 腾讯科技（深圳）有限公司 | Image processing method and device |
| CN106204698A (en) * | 2015-05-06 | 2016-12-07 | 北京蓝犀时空科技有限公司 | Virtual image for independent assortment creation generates and uses the method and system of expression |
| WO2017003031A1 (en) * | 2015-06-29 | 2017-01-05 | 김영자 | Method for providing lifelike avatar emoticon-based ultralight data animation creation system, and terminal device providing lifelike avatar emoticon for implementing same |
| CN107852533A (en) * | 2015-07-14 | 2018-03-27 | 三星电子株式会社 | Three-dimensional content generating means and its three-dimensional content generation method |
| CN106599817A (en) * | 2016-12-07 | 2017-04-26 | 腾讯科技（深圳）有限公司 | Face replacement method and device |
| WO2019005182A1 (en) * | 2017-06-30 | 2019-01-03 | Tobii Ab | Systems and methods for displaying images in a virtual world environment |
| CN108171789A (en) * | 2017-12-21 | 2018-06-15 | 迈吉客科技（北京）有限公司 | A kind of virtual image generation method and system |
| CN109173263A (en) * | 2018-08-31 | 2019-01-11 | 腾讯科技（深圳）有限公司 | A kind of image processing method and device |
Non-Patent Citations (1)
| Title |
|---|
| 于佳骏: "数据驱动的人像卡通与表情动画生成技术", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109919016B (en) | 2020-11-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11688120B2 (en) | System and method for creating avatars or animated sequences using human body features extracted from a still image | |
| Liao et al. | Tada! text to animatable digital avatars | |
| CN107798726B (en) | Method and device for manufacturing three-dimensional cartoon | |
| CN107797959A (en) | System and method for processing facial image and system for animating facial image | |
| Hahn et al. | Sketch abstractions for character posing | |
| CN113850169B (en) | Face attribute migration method based on image segmentation and generation countermeasure network | |
| Zhang et al. | Avatarverse: High-quality & stable 3d avatar creation from text and pose | |
| CN111950430A (en) | Color texture based multi-scale makeup style difference measurement and migration method and system | |
| Cheng et al. | Cross-modal 3d shape generation and manipulation | |
| CN110751733A (en) | Method and apparatus for converting 3D scanned object into avatar | |
| Wang et al. | Wuju opera cultural creative products and research on visual image under VR technology | |
| CN110443872B (en) | Expression synthesis method with dynamic texture details | |
| Orvalho et al. | Transferring the rig and animations from a character to different face models | |
| Yu et al. | On generating realistic avatars: dress in your own style | |
| Kawai et al. | Data-driven speech animation synthesis focusing on realistic inside of the mouth | |
| CN109919016A (en) | A kind of method and device generating human face expression on the object of no face's organ | |
| Yang et al. | Binary image carving for 3D printing | |
| Pawaskar et al. | Expression transfer: A system to build 3d blend shapes for facial animation | |
| Lee et al. | CartoonModes: Cartoon stylization of video objects through modal analysis | |
| KR102652652B1 (en) | Apparatus and method for generating avatar | |
| CN110751710A (en) | Method and apparatus for fitting an accessory object to an avatar | |
| Mahendran et al. | GAN Based Photo-Realistic Image Generation from Sketch using Nested U-Net | |
| Chai et al. | Efficient mesh-based face beautifier on mobile devices | |
| Li et al. | Visual saliency‐based bas‐relief generation with symmetry composition rule | |
| Kratt et al. | Non-realistic 3D object stylization |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |