CN110264566A - A kind of device and method of the multihead display based on the replacement of face AI color make-up - Google Patents
A kind of device and method of the multihead display based on the replacement of face AI color make-up Download PDFInfo
- Publication number
- CN110264566A CN110264566A CN201910474617.XA CN201910474617A CN110264566A CN 110264566 A CN110264566 A CN 110264566A CN 201910474617 A CN201910474617 A CN 201910474617A CN 110264566 A CN110264566 A CN 110264566A
- Authority
- CN
- China
- Prior art keywords
- facial
- threedimensional model
- color make
- customer
- face
- 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
- 238000000034 method Methods 0.000 title claims abstract description 28
- 230000001815 facial effect Effects 0.000 claims abstract description 115
- 230000000694 effects Effects 0.000 claims abstract description 27
- 238000001514 detection method Methods 0.000 claims abstract description 15
- 238000012790 confirmation Methods 0.000 claims abstract description 5
- 238000001931 thermography Methods 0.000 claims description 7
- 238000004891 communication Methods 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 6
- 238000013507 mapping Methods 0.000 claims description 4
- 239000002537 cosmetic Substances 0.000 description 4
- 238000012545 processing Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 210000004709 eyebrow Anatomy 0.000 description 2
- 238000004088 simulation Methods 0.000 description 2
- 235000016838 Pomo dAdamo Nutrition 0.000 description 1
- 244000003138 Pomo dAdamo Species 0.000 description 1
- 230000003796 beauty Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000005266 casting Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 210000000720 eyelash Anatomy 0.000 description 1
- 210000002454 frontal bone Anatomy 0.000 description 1
- 210000004392 genitalia Anatomy 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 210000004209 hair Anatomy 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 210000002050 maxilla Anatomy 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000007935 neutral effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 210000003455 parietal bone Anatomy 0.000 description 1
- 210000001747 pupil Anatomy 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 210000003582 temporal bone Anatomy 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 210000000216 zygoma Anatomy 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0641—Shopping interfaces
- G06Q30/0643—Graphical representation of items or shoppers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
- G06V40/168—Feature extraction; Face representation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2200/00—Indexing scheme for image data processing or generation, in general
- G06T2200/08—Indexing scheme for image data processing or generation, in general involving all processing steps from image acquisition to 3D model generation
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Multimedia (AREA)
- Business, Economics & Management (AREA)
- Human Computer Interaction (AREA)
- Finance (AREA)
- General Health & Medical Sciences (AREA)
- Accounting & Taxation (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- General Business, Economics & Management (AREA)
- Computer Graphics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Software Systems (AREA)
- Marketing (AREA)
- Economics (AREA)
- Geometry (AREA)
- Processing Or Creating Images (AREA)
- Image Processing (AREA)
Abstract
The present invention provides a kind of device and methods of multihead display based on the replacement of face AI color make-up.This method comprises: whether having customer in recognition detection area；When having customer in confirmation detection zone, the gender information of customer is confirmed；Obtain that customers first facial three-dimensional feature and first facial textural characteristics；Will be in customers first facial three-dimensional feature and the existing public facial threedimensional model of the first textural characteristics input, and then acquisition first facial threedimensional model；Obtain the first collocation information of the selected color make-up of customer；The first color make-up to match with the first collocation information is obtained using characteristic information, and then is inputted in first facial threedimensional model and obtains the second facial threedimensional model；First facial threedimensional model and the second facial threedimensional model are showed in such a way that multi-screen image is shown to customer.The present invention has and can establish color make-up effect threedimensional model according to customer's gender, facial characteristics, selected dressing come quick, and before and after energy multihead display color make-up use the advantages of effect.
Description
Technical field
The present invention relates to field of image processings, and in particular to a kind of device of the multihead display based on the replacement of face AI color make-up
And method.
Background technique
With the improvement of people ' s living standards with the ardent pursuit to appearance, various cosmetics manufactured
Come, and in order to improve the satisfaction of the sales volume of color make-up and customer, while reducing loss when customer buys cosmetics to product.One
A little AR shadow casting techniques and AI image recognition technology have been used in the intelligence experience equipment of color make-up, and then can be with Fast simulation
It sends as an envoy to the effect to apply some make up.Consumer is allowed quickly, intuitively to experience the practical effect of cosmetics, optimization is used
The experience at family.
Currently, as number of patent application be CN201810898285.3 " it is a kind of intelligence examination adornment dressing glass and method " it is this kind of specially
Benefit detects the face-image of examination adornment personnel according to the characteristic point of face, chooses the suitably image comprising face as examination adornment
Image, it is virtual to realize then to carry out image procossing to examination adornment image based on the processing parameter virtually made up according to practical operation
Adornment.The examination adornment precision of images that this mode obtains is lower, and it is thin often to lose a large amount of such as eyebrows, eye shadow, eyelashes, U.S. pupil details
Information is saved, causes the sense of reality of detail textures after mapping lower, only plays simple picture beauty Yan Xiaoguo, meeting and customer use
There are relatively large deviations for effect after color make-up.This examination adornment image three-dimensional sense is poor simultaneously, and customer is difficult to from multi-angle stereopsis
Facial effect after makeups.
And " three-dimensional tries cosmetic method and device " if number of patent application is CN201410689673.2 can solve two
The clarity of dimension examination adornment image and the problem of stereopsis effect, but when such methods cope with the simulation of a variety of color make-ups at the same time, it should
Textures replacement and the adjustment of effect between each face detail of class patent all independently carry out, it is difficult to handle face between color make-up
The problem of color effect is overlapped mutually.
Therefore, it is a kind of using AI image recognition technology, can be according to customer's gender, facial characteristics, selected dressing come fast run-up
Vertical color make-up effect threedimensional model, and the effect before and after energy multihead display color make-up use is a kind of based on the more of face AI color make-up replacement
The device and method of screen display becomes very necessary.
Summary of the invention
In order to solve the above-mentioned technical problems, the present invention provides a kind of dresses of multihead display based on the replacement of face AI color make-up
It sets and method, shows different color make-ups effect in the same shape of face simultaneously for multi-screen.
The present invention provides a kind of methods of multihead display based on the replacement of face AI color make-up, comprising the following steps: identification
Whether there is customer in detection zone；When having customer in confirmation detection zone, the gender information of customer is confirmed；Obtain customers first face three
Dimensional feature and first facial textural characteristics；It will customers first facial three-dimensional feature and the existing public face of the first textural characteristics input
In portion's threedimensional model, and then obtain first facial threedimensional model；The first collocation information of the selected color make-up of customer is obtained, it is described
First collocation information includes type, dosage, the using area information of selected color make-up；Obtain the to match with the first collocation information
One color make-up uses characteristic information, and then is inputted in first facial threedimensional model and obtains the second facial threedimensional model；By
One facial threedimensional model shows in such a way that multi-screen image is shown to customer with the second facial threedimensional model.
Further, " whether have customer in recognition detection area " specifically: by thermal imaging system to the heat source of identification region into
Row identification；After confirmly detecting heat source, the profile of heat source is judged, and then determines whether to be humanoid；When determining that heat source is big
After body is humanoid, start follow-up work.
Further, " gender information of confirmation customer " specifically: pass through the heat source shape knot of the thermal imaging of the customer of acquisition
Body characteristics caused by gender are closed, so that it is determined that the gender of customer, and generate gender information.
Further, " obtain customers first facial three-dimensional feature and first facial textural characteristics " specifically: from multiple angles
The face-image of customer is shot respectively；The face feature point of customer is positioned from face-image, and determines the three of each characteristic point
Positional relationship is tieed up, and then generates first facial three-dimensional feature；To the color of the sliding block formed between each adjacent characteristic point with
Texture is identified, and then generates first facial textural characteristics.
It further, " will customers first facial three-dimensional feature and the existing public face three-dimensional mould of the first textural characteristics input
In type, and then obtain first facial threedimensional model " specifically: it is three-dimensional according to the other public face of the Sex preference correspondence of customer
Model；First facial three-dimensional feature is inputted in public facial threedimensional model, it is preliminary regular to public facial threedimensional model progress,
It obtains and customer's shape of face preliminary threedimensional model unanimous on the whole；First textural characteristics are input in preliminary threedimensional model, by
Each sliding block of one textural characteristics is mutually sutured with preliminary threedimensional model；Preliminary threedimensional model is smoothed, to generate
First facial threedimensional model.
Further, " the first color make-up to match with the first collocation information is obtained using characteristic information, and then is inputted the
The second facial threedimensional model is obtained in one facial threedimensional model " specifically: according to the first collocation information from color make-up mapping library
Extract the Alpha channel parameters of color depth of the corresponding color make-up under matched doses；According to the use in the first collocation information
Area information obtains the projected position parameter of corresponding color make-up；The Alpha channel parameters of corresponding color make-up and projected position parameter are defeated
Enter into first facial threedimensional model, and then obtains the second facial threedimensional model for being added to corresponding color make-up effect.
Further, when a variety of color make-ups of client's simultaneous selection, it can be sequentially generated according to the selecting sequence of color make-up and be selected with color make-up
Select corresponding multiple first collocation informations of sequence；And successively the corresponding color make-up effect of each first collocation information is added to
On second facial threedimensional model.
The present invention also provides a kind of devices of multihead display based on the replacement of face AI color make-up, which includes: first
Recognition unit can be used to identify the gender for whether having customer and customer in detection zone；First image acquisition unit is used for from polygonal
Degree obtains the face-image of customer；Fisrt feature extraction unit, it is three-dimensional for obtaining first facial from the face-image of customer
Feature and first facial textural characteristics；First model generation unit can generate the first face based on public facial threedimensional model
Portion's threedimensional model, the second facial threedimensional model；First color make-up information acquisition unit, for obtaining the first collocation information of client,
First collocation information includes type, dosage, the using area information of selected color make-up；Second feature extraction unit, for obtaining
It takes the first color make-up to match with the first collocation information using characteristic information, and the first model generation unit can be transmitted to；
First output unit, for first facial threedimensional model and the second facial threedimensional model to customer in such a way that multi-screen image is shown
Show.
Further, the first color make-up information acquisition unit includes the wireless communication unit being connected with Client handset client, shows
Field color make-up selecting unit；Live color make-up selecting unit selects type, dosage, the using area of required color make-up for customer scene
Information, to locally produce the first collocation information；Wireless communication unit can will be generated in client mobile device client first
Collocation information receives, and is sent to the first model generation unit.
Further, the first output unit includes multiple display screens, and each display screen can be respectively used to display first facial three
The stereo-picture of dimension module, each second facial threedimensional model generated using different first collocation informations.
The present invention quickly identifies whether customer enters detection zone by thermal imaging, while can also be according to body characteristics
Quickly confirm the gender of customer, to be conducive to quick, the accurate selection of public facial threedimensional model, solves traditional face
Gender identifies the fuzzy problem of the measurement boundary of individual unconspicuous to facial characteristics；First collocation information of difference of the invention comes not
It is disconnected to update the second facial threedimensional model, so that the replacement of the grid color between each face feature point and the adjustment of effect can be independent
While progress, moreover it is possible to different color make-up effects is sequentially overlaid on the second facial threedimensional model according to demand；The present invention is logical
It crosses multi-screen while showing the effect picture of first facial threedimensional model and the second facial threedimensional model, so that customer can be accurate
Comparison color make-up use before and after effect.
Detailed description of the invention
Fig. 1 is a kind of flow chart of the method for multihead display based on the replacement of face AI color make-up of the invention；
Fig. 2 is a kind of the first color make-up information acquisition unit of the device of multihead display based on the replacement of face AI color make-up of the invention
Information exchange figure；
Fig. 3 is a kind of overall structure diagram of the device of multihead display based on the replacement of face AI color make-up of the invention.
Specific embodiment
In order to illustrate the embodiments of the present invention more clearly and/or technical solution in the prior art, attached drawing will be compareed below
Illustrate a specific embodiment of the invention.It should be evident that drawings in the following description are only some embodiments of the invention,
For those of ordinary skill in the art, without creative efforts, it can also be obtained according to these attached drawings
Other attached drawings, and obtain other embodiments.In addition, the relative position belonged between only indicating each component for being related to orientation is closed
System, rather than absolute positional relation.
As shown in Figure 1, being used for multi-screen the present invention provides a kind of method of multihead display based on the replacement of face AI color make-up
Different color make-ups effect in the same shape of face is shown simultaneously, comprising the following steps:
S1: whether there is customer in recognition detection area.Step S1 specifically: known by heat source of the thermograph to identification region
Not；After confirmly detecting heat source, the profile of heat source is judged, and then determines whether to be humanoid；When determining heat source generally
After humanoid, start follow-up work.
S2: when having customer in confirmation detection zone, confirm the gender information of customer.
Since the facial gender spy between male and female can only then be identified by face contour, but due to some customers'
Face contour partial neutral, and be difficult to determine its gender according to facial characteristics merely, thus the present invention it is complicated without using this operation,
The low method of accuracy.The present invention selects the heat source profile that customer is determined by infrared thermal imaging, and then to the feature of heat source
Point extracts compared with, to confirm the gender of customer.Due to the significant difference in some sex character of male and female, such as male
Property have Adam's apple heat source, with exclusive genitals heat source.So this gender differentiating method has higher accuracy, while identifying fortune
Calculation process is also simple.
S3: obtain that customers first facial three-dimensional feature and first facial textural characteristics.
Step S3 specifically: shoot the face-image of customer respectively from multiple angles；Position customer's from face-image
Face feature point, and determine the three-dimensional position relationship of each characteristic point, and then generate first facial three-dimensional feature；To each adjacent
Characteristic point between the color of sliding block that is formed identified with texture, and then generate first facial textural characteristics.Wherein first
Facial three-dimensional feature mainly includes such as maxilla, cheekbone, temporal bone, frontal bone and parietal bone face contour feature.First facial texture
Feature mainly includes the textural characteristics such as the colour of skin, eyebrow, lip.
S4: will in customers first facial three-dimensional feature and the existing public face threedimensional model of the first textural characteristics input,
And then obtain first facial threedimensional model.
Step S4 specifically: according to the other public facial threedimensional model of the Sex preference correspondence of customer；By first facial
It is preliminary regular to public facial threedimensional model progress in the public facial threedimensional model of three-dimensional feature input, it obtains and customer's shape of face
Preliminary threedimensional model unanimous on the whole；First textural characteristics are input in preliminary threedimensional model, by the every of the first textural characteristics
A sliding block is mutually sutured with preliminary threedimensional model；Preliminary threedimensional model is smoothed, to generate first facial three-dimensional mould
Type.This adjustment carried out on the basis of existing public facial threedimensional model can be saved effectively the modeling time, while public
Coplanar portion's threedimensional model is typically all the model after machine learning training, therefore versatility with higher.
S5: obtaining the first collocation information of the selected color make-up of customer, the first collocation information include selected color make-up type,
Dosage, using area information.
The selected color make-up of customer is wherein taken, can be obtained by the client of customer's mobile device, or by using
Selecting in menu for the device of this method obtains.First collocation information can then be obtained by matching in existing database.
S6: the first color make-up to match with the first collocation information is obtained using characteristic information, and then is inputted the first face
The second facial threedimensional model is obtained in portion's threedimensional model.
Step S6 is specifically included: extracting corresponding color make-up from color make-up mapping library according to the first collocation information in matched doses
Under color depth Alpha channel parameters；According to the using area information in the first collocation information, the throwing of corresponding color make-up is obtained
Shadow location parameter；The Alpha channel parameters of corresponding color make-up and projected position parameter are input in first facial threedimensional model, into
And obtain the second facial threedimensional model for being added to corresponding color make-up effect.
Wherein, when a variety of color make-ups of client's simultaneous selection, it can be sequentially generated according to the selecting sequence of color make-up and be selected with color make-up
Sequentially corresponding multiple first collocation informations；And the corresponding color make-up effect of each first collocation information is successively added to
On two facial threedimensional models.When client selects multiple color make-ups, the three-dimensional mould of one second face can be first generated by the sequence of selection
Type.If overlapping phenomenon occurs in the using area of the color make-up of visitor's selection, color make-up effect overlapping can be carried out according to sequencing
Reason, to generate the facial threedimensional model of new second.If client continues to select color make-up, using this method machine if can will be new
Color make-up color effect be added to before the second facial threedimensional model on.
If client is not desired to be cancelled selection using certain color make-up having selected for, be laid equal stress in subsequent selection
The sequence for the color make-up having selected for newly is adjusted, it is three-dimensional that the second facial threedimensional model can generate the second new face according to step S4
Model.
S7: by first facial threedimensional model and the second facial threedimensional model to customer's exhibition in such a way that multi-screen image is shown
It is existing.Can be shown by multiple display screens or display box in the present invention first facial threedimensional model, each different collocation modes the
Two facial threedimensional models, so that customer can accurately compare the effect before and after color make-up use.
As shown in Figure 2,3, in order to realize the method in the present invention, the present invention also provides one kind to be replaced based on face AI color make-up
The device for the multihead display changed.The device includes: the first recognition unit, can be used to identify in detection zone whether have customer and
The gender of customer；First image acquisition unit, for obtaining the face-image of customer from multi-angle；Fisrt feature extraction unit,
For obtaining first facial three-dimensional feature and first facial textural characteristics from the face-image of customer；First model generates single
Member can generate first facial threedimensional model, the second facial threedimensional model based on public facial threedimensional model；First color make-up letter
Acquiring unit is ceased, for obtaining the first collocation information of client, the first collocation information includes the type of selected color make-up, dosage, makes
Use area information；Second feature extraction unit is believed for obtaining the first color make-up to match with the first collocation information using feature
Breath, and the first model generation unit can be transmitted to；First output unit, for first facial threedimensional model and the second face
Threedimensional model shows in such a way that multi-screen image is shown to customer.
Wherein, the first recognition unit is infrared thermoviewer, in order to guarantee the precision of identification and the accuracy of thermal imaging, this hair
Bright middle selection FLIR T200 type infrared thermoviewer.And then while whether can having customer's use in other detection zone, moreover it is possible to according to
The heat source shape of the thermal imaging of customer carrys out the gender that quick discrimination goes out customer.The first image acquisition unit includes multiple in the present invention
High definition video camera outside device for the face-image from multiple angle shot customers.The place of first model generation unit
Reason core is ARM Cortex-A processor, and the efficient data processing ability of ARM Cortex-A processor makes threedimensional model
Formation efficiency be greatly improved.
As shown in Figure 2 in the apparatus of the present, the first color make-up information acquisition unit includes and Client handset client phase
Wireless communication unit even, live color make-up selecting unit；Live color make-up selecting unit is for color make-up needed for the selection of customer scene
Type, dosage, using area information, to locally produce the first collocation information；Wireless communication unit can set client's movement
The first collocation information generated in standby client receives, and is sent to the first model generation unit.
As shown in figure 3, the first output unit includes multiple display screens, each display screen can be respectively used to display first facial
The stereo-picture of threedimensional model, each second facial threedimensional model generated using different first collocation informations, so that caring for
Visitor can accurately compare the effect before and after color make-up use.
The above content is a further detailed description of the present invention in conjunction with specific preferred embodiments, and it cannot be said that
Specific implementation of the invention is only limited to these instructions.For those of ordinary skill in the art to which the present invention belongs, exist
Under the premise of not departing from present inventive concept, a number of simple deductions or replacements can also be made, all shall be regarded as belonging to of the invention
Protection scope.
Claims (10)
1. a kind of method of the multihead display based on the replacement of face AI color make-up, which is characterized in that show difference simultaneously for multi-screen
Color make-up effect in the same shape of face, comprising the following steps: whether have customer in recognition detection area；There is customer in confirmation detection zone
When, confirm the gender information of customer；Obtain that customers first facial three-dimensional feature and first facial textural characteristics；It will customers first face
In portion's three-dimensional feature and the existing public facial threedimensional model of the first textural characteristics input, and then obtain first facial three-dimensional mould
Type；The first collocation information of the selected color make-up of customer is obtained, first collocation information includes the type of selected color make-up, agent
Amount, using area information；The first color make-up to match with the first collocation information is obtained using characteristic information, and then is inputted the
The second facial threedimensional model is obtained in one facial threedimensional model；By first facial threedimensional model and the second facial threedimensional model with
The mode that multi-screen image is shown shows to customer.
2. a kind of method of multihead display based on the replacement of face AI color make-up as described in claim 1, which is characterized in that " know
Whether have customer in other detection zone " specifically: it is identified by heat source of the thermograph to identification region；Confirmly detect heat
Behind source, the profile of heat source is judged, and then determines whether to be humanoid；After determining that heat source is generally humanoid, start subsequent
Work.
3. a kind of method of multihead display based on the replacement of face AI color make-up as described in claim 1, which is characterized in that " really
Recognize the gender information of customer " specifically: shape caused by the heat source shape cooperation gender by the thermal imaging of the customer of acquisition
Body characteristics, so that it is determined that the gender of customer, and generate gender information.
4. a kind of method of multihead display based on the replacement of face AI color make-up as described in claim 1, which is characterized in that " obtain
Take that customers first facial three-dimensional feature and first facial textural characteristics " specifically: shoot the face of customer respectively from multiple angles
Image；The face feature point of customer is positioned from face-image, and determines the three-dimensional position relationship of each characteristic point, and then generate
First facial three-dimensional feature；The color of the sliding block formed between each adjacent characteristic point is identified with texture, Jin Ersheng
At first facial textural characteristics.
5. a kind of method of multihead display based on the replacement of face AI color make-up as described in claim 1, which is characterized in that " will
In customers first facial three-dimensional feature and the existing public facial threedimensional model of the first textural characteristics input, and then the first face of acquisition
Portion's threedimensional model " specifically: according to the other public facial threedimensional model of the Sex preference correspondence of customer；By first facial three-dimensional
It is preliminary regular to public facial threedimensional model progress in the public facial threedimensional model of feature input, it obtains with customer's shape of face substantially
Consistent preliminary threedimensional model；First textural characteristics are input in preliminary threedimensional model, by each cunning of the first textural characteristics
Block is mutually sutured with preliminary threedimensional model；Preliminary threedimensional model is smoothed, to generate first facial threedimensional model.
6. a kind of method of multihead display based on the replacement of face AI color make-up as described in claim 1, which is characterized in that " obtain
It takes the first color make-up to match with the first collocation information using characteristic information, and then is inputted first facial threedimensional model
Obtain the second facial threedimensional model " specifically: corresponding color make-up is extracted from color make-up mapping library according to the first collocation information right
Answer the Alpha channel parameters of the color depth under dosage；According to the using area information in the first collocation information, obtain corresponding color
The projected position parameter of adornment；The Alpha channel parameters of corresponding color make-up and projected position parameter are input to first facial three-dimensional mould
In type, and then obtain the second facial threedimensional model for being added to corresponding color make-up effect.
7. a kind of method of multihead display based on the replacement of face AI color make-up as described in claim 1, it is characterised in that: work as visitor
When a variety of color make-ups of family simultaneous selection, corresponding with color make-up selecting sequence multiple the can be sequentially generated according to the selecting sequence of color make-up
One collocation information；And successively the corresponding color make-up effect of each first collocation information is added on the second facial threedimensional model.
8. a kind of device of the multihead display based on the replacement of face AI color make-up, characterized by comprising: the first recognition unit can be used
In the gender for whether having customer and customer in recognition detection area；First image acquisition unit, for obtaining customer from multi-angle
Face-image；Fisrt feature extraction unit, for obtaining first facial three-dimensional feature and first from the face-image of customer
Face texture feature；First model generation unit, can be generated based on public facial threedimensional model first facial threedimensional model,
Second facial threedimensional model；First color make-up information acquisition unit, for obtaining the first collocation information of client, first collocation
Information includes type, dosage, the using area information of selected color make-up；Second feature extraction unit, for obtaining and the first collocation
The first color make-up that information matches uses characteristic information, and can be transmitted to the first model generation unit；First output unit,
Show in such a way that multi-screen image is shown to customer for first facial threedimensional model and the second facial threedimensional model.
9. a kind of device of multihead display based on the replacement of face AI color make-up as claimed in claim 8, it is characterised in that: described
First color make-up information acquisition unit includes the wireless communication unit being connected with Client handset client, live color make-up selecting unit；
The scene color make-up selecting unit selects type, dosage, the using area information of required color make-up for customer scene, thus existing
Field generates the first collocation information；The first collocation information that the wireless communication unit can will generate in client mobile device client
It receives, and is sent to the first model generation unit.
10. a kind of device of multihead display based on the replacement of face AI color make-up as claimed in claim 8, it is characterised in that: institute
Stating the first output unit includes multiple display screens, and each display screen can be respectively used to display first facial threedimensional model, make
With the stereo-picture for each second facial threedimensional model that different first collocation informations generate.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910474617.XA CN110264566A (en) | 2019-06-03 | 2019-06-03 | A kind of device and method of the multihead display based on the replacement of face AI color make-up |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910474617.XA CN110264566A (en) | 2019-06-03 | 2019-06-03 | A kind of device and method of the multihead display based on the replacement of face AI color make-up |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110264566A true CN110264566A (en) | 2019-09-20 |
Family
ID=67916383
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910474617.XA Pending CN110264566A (en) | 2019-06-03 | 2019-06-03 | A kind of device and method of the multihead display based on the replacement of face AI color make-up |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110264566A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2023225949A1 (en) * | 2022-05-26 | 2023-11-30 | 北京小米移动软件有限公司 | Photographic preview method and apparatus, and terminal device and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104463938A (en) * | 2014-11-25 | 2015-03-25 | 福建天晴数码有限公司 | Three-dimensional virtual make-up trial method and device |
| US20160042557A1 (en) * | 2014-08-08 | 2016-02-11 | Asustek Computer Inc. | Method of applying virtual makeup, virtual makeup electronic system, and electronic device having virtual makeup electronic system |
| CN108932654A (en) * | 2018-06-12 | 2018-12-04 | 苏州诚满信息技术有限公司 | A kind of virtually examination adornment guidance method and device |
| CN109190495A (en) * | 2018-08-09 | 2019-01-11 | 北京地平线机器人技术研发有限公司 | Gender identification method, device and electronic equipment |
-
2019
- 2019-06-03 CN CN201910474617.XA patent/CN110264566A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160042557A1 (en) * | 2014-08-08 | 2016-02-11 | Asustek Computer Inc. | Method of applying virtual makeup, virtual makeup electronic system, and electronic device having virtual makeup electronic system |
| CN104463938A (en) * | 2014-11-25 | 2015-03-25 | 福建天晴数码有限公司 | Three-dimensional virtual make-up trial method and device |
| CN108932654A (en) * | 2018-06-12 | 2018-12-04 | 苏州诚满信息技术有限公司 | A kind of virtually examination adornment guidance method and device |
| CN109190495A (en) * | 2018-08-09 | 2019-01-11 | 北京地平线机器人技术研发有限公司 | Gender identification method, device and electronic equipment |
Non-Patent Citations (4)
| Title |
|---|
| 尹宝才等: "基于形变模型的人脸建模及其应用综述", 《北京工业大学学报》, no. 03, 30 September 2003 (2003-09-30) * |
| 曾旭东 等: "《GDL参数化程序语言设计》", vol. 1, 重庆大学出版社, pages: 184 - 185 * |
| 胡文彬等: "基于ASP.NET的脸部试妆系统的研究与设计", 《计算机工程与设计》 * |
| 胡文彬等: "基于ASP.NET的脸部试妆系统的研究与设计", 《计算机工程与设计》, no. 13, 16 July 2008 (2008-07-16) * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2023225949A1 (en) * | 2022-05-26 | 2023-11-30 | 北京小米移动软件有限公司 | Photographic preview method and apparatus, and terminal device and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10945514B2 (en) | Information processing apparatus, information processing method, and computer-readable storage medium | |
| CN109690617B (en) | System and method for digital cosmetic mirror | |
| CN105354876B (en) | A kind of real-time volume fitting method based on mobile terminal | |
| RU2668408C2 (en) | Devices, systems and methods of virtualising mirror | |
| US9369638B2 (en) | Methods for extracting objects from digital images and for performing color change on the object | |
| US8976160B2 (en) | User interface and authentication for a virtual mirror | |
| US8982110B2 (en) | Method for image transformation, augmented reality, and teleperence | |
| US10109315B2 (en) | Devices, systems and methods for auto-delay video presentation | |
| US20140225977A1 (en) | Devices, systems and methods of virtualizing a mirror | |
| JP3779570B2 (en) | Makeup simulation apparatus, makeup simulation control method, and computer-readable recording medium recording makeup simulation program | |
| CN107211165A (en) | Devices, systems, and methods for automatically delaying video display | |
| CN108537126A (en) | A kind of face image processing system and method | |
| CN109377557A (en) | Real-time three-dimensional facial reconstruction method based on single frames facial image | |
| CN110807364A (en) | Modeling and capturing method and system for three-dimensional face and eyeball motion | |
| WO2014081394A1 (en) | Method, apparatus and system for virtual clothes modelling | |
| Yang et al. | Eye gaze correction with stereovision for video-teleconferencing | |
| WO2018005884A1 (en) | System and method for digital makeup mirror | |
| Zhao et al. | Mask-off: Synthesizing face images in the presence of head-mounted displays | |
| CN107610239A (en) | The virtual try-in method and device of a kind of types of facial makeup in Beijing operas | |
| KR102506352B1 (en) | Digital twin avatar provision system based on 3D anthropometric data for e-commerce | |
| CN114821675A (en) | Object processing method and system and processor | |
| CN116523579A (en) | Display equipment, virtual fitting system and method | |
| CN110264566A (en) | A kind of device and method of the multihead display based on the replacement of face AI color make-up | |
| CN112802031A (en) | Real-time virtual hair trial method based on three-dimensional human head tracking | |
| CN112353033A (en) | Human body data batch measurement system based on deep learning |
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 |