CN107146275A - A kind of method and device of setting virtual image - Google Patents
A kind of method and device of setting virtual image Download PDFInfo
- Publication number
- CN107146275A CN107146275A CN201710207429.1A CN201710207429A CN107146275A CN 107146275 A CN107146275 A CN 107146275A CN 201710207429 A CN201710207429 A CN 201710207429A CN 107146275 A CN107146275 A CN 107146275A
- Authority
- CN
- China
- Prior art keywords
- good friend
- virtual image
- key message
- image
- users
- 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
- 238000000034 method Methods 0.000 title claims abstract description 48
- 230000001815 facial effect Effects 0.000 claims abstract description 38
- 239000000284 extract Substances 0.000 claims abstract description 15
- 238000000605 extraction Methods 0.000 claims description 9
- 238000001514 detection method Methods 0.000 claims description 5
- 238000007781 pre-processing Methods 0.000 claims 1
- 230000009467 reduction Effects 0.000 abstract description 2
- 230000000694 effects Effects 0.000 description 8
- 230000008569 process Effects 0.000 description 8
- 239000011800 void material Substances 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 5
- 238000004088 simulation Methods 0.000 description 4
- 230000008901 benefit Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 210000003128 head Anatomy 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 210000005252 bulbus oculi Anatomy 0.000 description 1
- 210000001508 eye Anatomy 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T15/00—3D [Three Dimensional] image rendering
- G06T15/10—Geometric effects
-
- 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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/01—Social networking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T19/00—Manipulating 3D models or images for computer graphics
- G06T19/20—Editing of 3D images, e.g. changing shapes or colours, aligning objects or positioning parts
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2219/00—Indexing scheme for manipulating 3D models or images for computer graphics
- G06T2219/20—Indexing scheme for editing of 3D models
- G06T2219/2021—Shape modification
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Graphics (AREA)
- Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Economics (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- General Health & Medical Sciences (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Health & Medical Sciences (AREA)
- Geometry (AREA)
- Computing Systems (AREA)
- Architecture (AREA)
- Computer Hardware Design (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Processing Or Creating Images (AREA)
Abstract
The embodiments of the invention provide a kind of method and device of setting virtual image, wherein, the method for setting virtual image includes：Obtain the frame of good friend；Extract in frame, the key message of good friend, wherein, key message includes facial key message；The key message of good friend is matched with the key message of all users in information bank, good friend is filtered out from all users, and obtain the user profile of good friend, wherein, stored in information bank all users user profile and all users user profile is corresponding, all users key message；According to the user profile of good friend, the original virtual image of good friend is obtained；By the frame of good friend, the original virtual image of good friend is fitted to, new virtual image is obtained.By the method and device of setting virtual image of the embodiment of the present invention, the distance between user feels during reduction virtual social, increases the viscosity of virtual social, lifts Consumer's Experience.
Description
Technical field
The present invention relates to virtual social technical field, more particularly to a kind of method and device of setting virtual image.
Background technology
Current virtual social is in the ground zero stage, and each application is creates the vivid storehouse of three dimensional virtual models, and user can be from
One is selected in existing default models, as oneself virtual presence in VR (Virtual Reality, virtual reality).
But, the fund cost for creating model true to nature is very high, and technology realizes that difficulty is high, and combines " terrified paddy " reason
By the virtual image model that each application creates for user can't realistically go back the reality image of original subscriber.So, existing
In some virtual socials, the virtual image for the good friend that user sees is that good friend oneself selects from the virtual image model of acquiescence
, not realistic virtual image.
And in VR, the direct feel of user is on the spot in person, talk with the simulation virtual image of existing this good friend
Distance perspective can be increased, the viscosity of virtual social is not high, and Consumer's Experience is bad.
The content of the invention
The purpose of the embodiment of the present invention is to provide a kind of method and device of setting virtual image, to realize that increase is virtual
Social viscosity, lifts Consumer's Experience.Concrete technical scheme is as follows：
On the one hand, the embodiments of the invention provide a kind of method for setting virtual image, including：
Obtain the frame of good friend；
Extract in described information image, the key message of the good friend, wherein, the key message includes the crucial letter of face
Breath；
The key message of the good friend is matched with the key message of all users in information bank, from all users
The good friend is filtered out, and obtains the user profile of the good friend, wherein, user's letter of all users is stored in described information storehouse
Breath and all users user profile is corresponding, all users key message；
According to the user profile of the good friend, the original virtual image of the good friend is obtained；
By the described information image of the good friend, the original virtual image of the good friend is fitted to, new virtual shape is obtained
As.
Optionally, the frame for obtaining good friend, including：
By way of taking pictures, selecting local picture and download online picture, the described information image of good friend is obtained.
Optionally, it is described extraction described information image in, the key message of the good friend, including：
By detecting face key point, the facial geometric feature of the good friend is obtained, wherein, the facial geometric feature table
Show the structure of good friend's face；
The face detail feature of good friend described in described information image is extracted, wherein, the face detail character representation institute
State the texture information of good friend's face；
With reference to the facial geometric feature and the face detail feature, the key message of the good friend is extracted.
Optionally, in the key message and information bank by the good friend all users key message carry out
Match somebody with somebody, before, methods described also includes：
Obtain the key message of each user；
The key message of all users is stored to described information storehouse.
Optionally, the described information image by the good friend, is fitted to the original virtual image of the good friend, obtains
New virtual image, including：
After the good friend is filtered out, the connection with the good friend is set up；
Upon establishment of a connection, by the described information image of the good friend, it is fitted to the original virtual image of the good friend.
Optionally, the described information image by the good friend, is fitted to the original virtual image of the good friend, obtains
New virtual image, including：
Described information image is pre-processed, the pre- fitting hum pattern being fitted with the original virtual image matching is obtained
Picture；
The pre- fitting frame is fitted to the original virtual image, the new virtual shape of the good friend is obtained
As.
On the other hand, the embodiment of the present invention additionally provides a kind of device of setting virtual image, including：
First acquisition module, the frame for obtaining good friend；
Extraction module, for extracting in described information image, the key message of the good friend, wherein, the key message
Including facial key message；
Matching module, the key message progress for all users in the key message and information bank by the good friend
Match somebody with somebody, the good friend is filtered out from all users, and obtain the user profile of the good friend, wherein, stored in described information storehouse
The user profile of all users and user profile of all users is corresponding, all users key message；
Original virtual image obtains module, for the user profile according to the good friend, obtains the original void of the good friend
Intend image；
Fitting module, for by the described information image of the good friend, being fitted to the original virtual image of the good friend, obtaining
To new virtual image.
Optionally, first acquisition module is further used for by taking pictures, selecting local picture and download online figure
The mode of piece, obtains the described information image of good friend.
Optionally, the extraction module includes：
Detection sub-module, for by detecting face key point, obtaining the facial geometric feature of the good friend, wherein, institute
State the structure that facial geometric feature represents good friend's face；
First extracting sub-module, the face detail feature for extracting good friend described in described information image, wherein, it is described
The texture information of good friend's face described in face detail character representation；
Second extracting sub-module, for reference to the facial geometric feature and the face detail feature, it to be described good to extract
The key message of friend.
Optionally, the device for setting virtual image also includes：
Second acquisition module, the key message for obtaining each user；
Memory module, for storing the key message of all users to described information storehouse.
Optionally, the fitting module includes：
Connection submodule is set up, for after the good friend is filtered out, setting up the connection with the good friend；
First fitting submodule, for upon establishment of a connection, by the described information image of the good friend, it is described good to be fitted to
The original virtual image of friend.
Optionally, the fitting module includes：
Submodule is pre-processed, for being pre-processed to described information image, is obtained and the original virtual image matching
The pre- fitting frame of fitting；
Second fitting submodule, for the pre- fitting frame to be fitted into the original virtual image, obtains institute
State the new virtual image of good friend.
A kind of method and device of setting virtual image provided in an embodiment of the present invention, can extract the frame of good friend
In, the facial key message of good friend；The facial key message is matched with the information in information bank, sieved from all good friends
The good friend is selected, and obtains the original virtual image of the good friend；By the frame of the good friend, the original void of the good friend is fitted to
Intend image, obtain new virtual image, complete to set virtual image in virtual social for good friend.So that in virtual social
In, the virtual image of the good friend that user sees is the image of the good friend of oneself selection, when reducing virtual social between user away from
From sense, and then the viscosity of virtual social is improved, lift Consumer's Experience.Certainly, any product or method for implementing the present invention must not
It is certain to need to reach all the above advantage simultaneously.
Brief description of the drawings
In order to illustrate more clearly about the embodiment of the present invention or technical scheme of the prior art, below will be to embodiment or existing
There is the accompanying drawing used required in technology description to be briefly described, it should be apparent that, drawings in the following description are only this
Some embodiments of invention, for those of ordinary skill in the art, on the premise of not paying creative work, can be with
Other accompanying drawings are obtained according to these accompanying drawings.
Fig. 1 is the flow chart for the method that the embodiment of the present invention sets virtual image；
Fig. 2 is the schematic diagram that the embodiment of the present invention extracts key message；
Fig. 3 is the structural representation for the device that the embodiment of the present invention sets virtual image.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete
Site preparation is described, it is clear that described embodiment is only a part of embodiment of the invention, rather than whole embodiments.It is based on
Embodiment in the present invention, it is every other that those of ordinary skill in the art are obtained under the premise of creative work is not made
Embodiment, belongs to the scope of protection of the invention.
In order to which in VR environment, when user carries out virtual social with good friend, the direct feel of user is more on the spot in person；Together
When reduce the distance between user sense, increase the viscosity of virtual social, lift Consumer's Experience, the embodiments of the invention provide one kind
The method and device of virtual image is set, below the method for virtual image will be set and set to provided in an embodiment of the present invention respectively
The device for putting virtual image is described in detail.
Fig. 1 is the flow chart for the method that the embodiment of the present invention sets virtual image, and reference picture 1 is set to the embodiment of the present invention
The method of virtual image is described in detail, including：
Step 101, the frame of good friend is obtained.
The frame of good friend, specifically can be understood as characterizing the image of friend information, for example, in actual application
In, can be the photo of good friend, the picture comprising good friend's face etc..
Specifically, the information of good friend can by way of taking pictures, selecting local picture and download online picture, be obtained
Image, using the advantage in mobile context, can more advantageously get the frame of good friend.
Because the method that the embodiment of the present invention sets virtual image, user is the frame for selecting oneself, it is fitted to
The original virtual image of good friend, and then generate the virtual image of more life-like good friend.Frame can influence to ultimately generate
The virtual image of good friend, so the frame for obtaining good friend first is the premise bar that the embodiment of the present invention sets virtual image
Part.
Step 102, extract in frame, the key message of good friend, wherein, key message includes facial key message.
Understandable to be, the frame of good friend includes many information.Hum pattern is extracted in the embodiment of the present invention
Information as in is, in order to screen the good friend of determination from all good friends, and only to need the key message and information in frame
All key messages in storehouse are matched, it is possible to reach the purpose for filtering out and determining good friend.Meanwhile, in order to calculate letter
It is single, so the embodiment of the present invention is by extracting in frame, the key message of good friend, carry out follow-up by the key message
Matching primitives.
It should be noted that key message can be understood as characterize good friend's feature it is obvious, be different from other people letter
Breath.Specifically, key message can include facial key message, figure and features characteristic information etc..Wherein, facial key message can be wrapped
Include face mask, face texture information etc.；Figure and features characteristic information can include appearance including personage appearance (face appearance, such as
Five official ranks) information, stature (high, short, fat, thin) information, clothing (dress) information and expression (pleasure, anger, sorrow, happiness) information
Deng.
It is emphasized that because during facial key message is frame, being compared to other information important
Information, in addition, the detection of facial information has been highly developed technology in this area, can be accurate using facial key message
Ground matches the corresponding key message of information bank, and then filters out the good friend of needs exactly, is provided well for calculating below
The precondition on ground, so emphasis is described in detail with extracting frame septum reset key message in the embodiment of the present invention.
Step 103, the key message of good friend is matched with the key message of all users in information bank, it is useful from institute
Good friend is filtered out in family, and obtains the user profile of good friend, wherein, stored in information bank all users user profile and
The user profile of all users is corresponding, all users key message.
The key message of all users is stored in information bank, when user will exchange with good friend, by the key of obtained good friend
Information is matched with the key message of all users in information bank, should in the key message and information bank in the good friend of acquisition
During the key information match of good friend, you can the good friend is filtered out from all users.
In addition, it is necessary to explanation, the key message of all users enters in the key message and information bank by good friend
Before row matching, the embodiment of the present invention sets the method for virtual image also to include：
Obtain the key message of each user.
The key message of all users is stored to information bank.
Each user preserves the key message of oneself into information bank when login is applied, wherein, each user preserves
Key message into information bank, is that user obtains including user pass by modes such as mobile phone photograph, the local pictures of acquisition first
The image of key information, the key message of the good friend then extracted from the image.
Step 104, according to the user profile of good friend, the original virtual image of good friend is obtained.
Each user is when login is applied, all oneself to set virtual image, i.e., from using the model provided the user
In, select a virtual image as oneself.User is that the virtual image of oneself selection is the original virtual shape of user
As.In actual application process, the corresponding presence of the user profile such as the original virtual image of user and account of user works as
During the user profile such as the account to user, it is possible to obtain the original virtual image of user.
Above-mentioned steps have obtained the user profile of good friend, then according to the user profile of good friend, obtain the original void of good friend
Intend image, condition is provided for the virtual image that is provided below new.
Step 105, by the frame of good friend, the original virtual image of good friend is fitted to, new virtual image is obtained.
After the original virtual image for obtaining good friend, the frame for the good friend that user selects oneself is fitted to good friend's
Virtual image, obtains the new virtual image of good friend.
It should be noted that the method that the embodiment of the present invention sets virtual image, can set virtual shape for good friend in advance
As；It can also be searched in real time according to the frame of good friend by key information match when wanting to exchange with good friend
Friend, and when searching good friend, is that good friend sets real-time virtual image, when user can so exchanged with good friend every time,
Good friend can be searched according to the frame of good friend in real time, and can be according to the hobby of oneself preferably when exchanging every time
Friend sets different virtual images.
User is in the virtual environment oneself seen, it is seen that the virtual image of good friend, is the information of the good friend of oneself selection
Effect after image, simulation to the original virtual image of good friend.In addition, if user is while and two good friends or more good
Friend then can be that two good friends or more good friends set new virtual image, the then good friend that user sees in exchange, chat
Virtual image effect, be that two good friends or the frame of multiple good friends, the simulation of oneself selection are original to good friend
Effect after virtual image.In this way, when virtual social is exchanged, it oneself is the new of good friend's setting that what each user saw, which is,
The distance between user sense, increases the viscosity of virtual social, lifts Consumer's Experience during virtual image, reduction virtual social.
The method that the embodiment of the present invention sets virtual image, user can select the hum pattern of good friend according to the hobby of oneself
Picture, extract good friend frame in, the facial key message of good friend；The facial key message and the information in information bank are entered
Row matching, filters out the good friend, and obtain the original virtual image of the good friend from all good friends；By the hum pattern of the good friend
Picture, is fitted to the original virtual image of the good friend, obtains new virtual image, completes to set virtual in virtual social for good friend
Image.So that, the distance between user sense when reducing virtual social, and then the viscosity of virtual social is improved, lift user
Experience.
The present invention set virtual image method a kind of optional embodiment in, extract good friend frame in, it is good
The key message of friend, including：
The first step, by detecting face key point, obtains the facial geometric feature of good friend, wherein, facial geometric feature table
Express friendship the structure of friendly face.
Second step, extracts the face detail feature of good friend in frame, wherein, face detail character representation good friend face
Texture information.
3rd step, with reference to facial geometric feature and face detail feature, extracts the key message of good friend.
Specifically, the detection method of face key feature points：The characteristic point of face is chosen, as shown in the white point in Fig. 2, its
In, Fig. 2 is the schematic diagram that the embodiment of the present invention extracts key message.The distribution of these characteristic points has angle invariability, including 2
These in individual eyeball central point, 4 canthus points, the midpoint in two nostrils and 2 corners of the mouth points, the frame by detecting good friend
Characteristic point, you can obtain the facial geometric features such as the face contour of good friend.
Understandable to be, face contour information can only roughly reflect the feature of good friend, so extracting the key of good friend
During information, except by detecting face key point, obtaining the facial geometric feature of good friend；Also need to extract frame
In, represent the face detail feature of good friend's face texture information；Finally, with reference to facial geometric feature and face detail feature, carry
The facial key message of good friend's feature can accurately be reflected by taking.It should be noted that the face texture information for extracting face is this
Technology known to art personnel, extracts the face detail feature that good friend's face texture information is represented in frame, with showing
The process of some face texture information for extracting face is similar, just repeats no more here.
From the frame of good friend, after the key message for extracting good friend, according to the key message of good friend, with storing
Key message in the information bank of the key message of all users, all is matched, and when key message result is matched, is filtered out
The good friend.By picture search, key message characteristic matching realize the social good friend of screening there is provided one kind it is more rich screen
The mode of friend, lifts the experience of user's virtual social.
Since in information bank, the user profile of good friend storage corresponding with the key message of user, so passing through key letter
Breath is while filter out good friend, can obtain the user profile of good friend, and then obtains by the user profile of user the original of user
Beginning virtual image.
Set in the present invention in a kind of optional embodiment of method of virtual image, by the frame of good friend, fitting
To the original virtual image of good friend, new virtual image is obtained, including：
After good friend is filtered out, the connection with good friend is set up；
Upon establishment of a connection, by the frame of good friend, it is fitted to the original virtual image of good friend.
The method that the embodiment of the present invention sets virtual image, can be set according to the hobby of user oneself for good friend in real time
New virtual image.When user wants to exchange with a certain position good friend, chatted, the frame of the good friend is selected, according to the letter of good friend
Breath image from user it is all in filter out the good friend, then set up and the connection of good friend；And setting up the connection with the good friend
Afterwards, it is that good friend sets new virtual image, so that user is in the virtual environment oneself seen, the virtual image of the good friend
It is the new virtual image that good friend is set for user oneself.During at the same time it can also be exchanged every time with the good friend, set by above-mentioned
The method for putting virtual image, sets different virtual images for good friend according to the selection of oneself, lifts Consumer's Experience.
Need to stress, by the frame of good friend, be fitted to the original virtual image of good friend, obtain new void
Intend image, including：
First, frame is pre-processed, obtains the pre- fitting frame being fitted with original virtual image matching；
Then, pre- fitting frame is fitted to original virtual image, obtains the new virtual image of good friend.
Because the original virtual image of good friend, is selected in being the model that good friend provides from application；And the embodiment of the present invention
In the method for setting virtual image, the frame of good friend is that user likes selection according to oneself, so should in actual
With process, it is necessary to first be pre-processed frame, the figure that can be fitted with the original virtual image matching of good friend is obtained
Picture, i.e., pre- fitting frame.Wherein, carrying out pretreatment to frame can include：Scratch figure, mapping, textures etc..
Specifically, by being pre-processed to frame, and then by the frame of good friend, it is fitted to the original virtual of good friend
The process of image can include：The position of the upper face of positioning original virtual image respectively, and on frame face position,
By the facial image on the frame oriented, the facial image on the original virtual image oriented is attached to, that is, completing will
The frame of good friend, is fitted to the process of the original virtual image of good friend, obtains new virtual image.
Or, respectively extract frame face characteristic, the characteristic image of such as hair, the characteristic image of nose, with
And the characteristic image of eyes etc., then respectively by these characteristic images, on corresponding simulation to original virtual image, simply may be used
To be interpreted as, on the image that these characteristic images are superimposed to original virtual image, so complete the frame of good friend, intend
It is bonded in the original virtual of good friend image, obtains new virtual image.So that user with good friend when exchanging, in virtual environment
The image of the good friend seen, is that the image (for example, photo of good friend etc.) of the good friend of oneself selection is fitted to the original void of good friend
Intend the effect after image.
The method that the embodiment of the present invention sets virtual image, the effect finally realized is specifically included：By the photograph of social good friend
Piece is fitted in the social image of the original virtual of good friend, and each user can select the photo of good friend, then pass through above-mentioned side
Formula is that good friend sets new virtual image so that the virtual image for the good friend that each user sees can be different.For example：User's second
In the virtual environment oneself seen, it is seen that user's first virtual image, be user's second shoot user's first front elevation, intend
Effect after closing in the original virtual image of user's first.Similarly, if the people of user first, user second and user the third three chats
My god, then user third sees, is the head portrait that oneself shoots for user's first and the people of user's second two, user's first and user are fitted to respectively
Effect after the original virtual image of the people of second two.See that oneself can be reduced for the image that other side is set in virtual environment virtual
The distance between social activity sense, the viscosity of increase virtual social.In addition, similar set remarks title in mobile phone application for user,
The embodiment of the present invention sets the method for virtual image to be simply appreciated that turning into user sets remarks head portrait.
The embodiment of the present invention additionally provides a kind of device of setting virtual image, and Fig. 3 is that the embodiment of the present invention is set virtually
The structural representation of the device of image, reference picture 3 sets the device of virtual image to be described in detail the embodiment of the present invention, wraps
Include：
First acquisition module 301, the frame for obtaining good friend.
Extraction module 302, for extracting in frame, the key message of good friend, wherein, key message includes face and closed
Key information.
Matching module 303, for the key message of good friend to be matched with the key message of all users in information bank,
Good friend is filtered out from all users, and obtains the user profile of good friend, wherein, user's letter of all users is stored in information bank
Breath and all users user profile is corresponding, all users key message.
Original virtual image obtains module 304, for the user profile according to good friend, obtains the original virtual shape of good friend
As.
Fitting module 305, for by the frame of good friend, being fitted to the original virtual image of good friend, obtaining new void
Intend image.
The embodiment of the present invention sets the device of virtual image, passes through the first acquisition module 301, extraction module 302, matching mould
Block 303, original virtual image obtain module 304 and fitting module 305, and user can select the letter of good friend according to the hobby of oneself
Cease image, extract good friend frame in, the facial key message of good friend；By the letter in the facial key message and information bank
Breath is matched, and the good friend is filtered out from all good friends, and obtain the original virtual image of the good friend；By the information of the good friend
Image, is fitted to the original virtual image of the good friend, obtains new virtual image, completes to set empty in virtual social for good friend
Intend image.So that in virtual social, the virtual image for the good friend that user sees is the image of the good friend of oneself selection, is subtracted
The distance between user sense during few virtual social, and then the viscosity of virtual social is improved, lift Consumer's Experience.
Optionally, the embodiment of the present invention is set in the device of virtual image, and the first acquisition module 301 is further used for leading to
The mode of take pictures, select local picture and download online picture is crossed, the frame of good friend is obtained.
Optionally, the embodiment of the present invention is set in the device of virtual image, and extraction module 302 includes：
Detection sub-module, for by detecting face key point, obtaining the facial geometric feature of good friend, wherein, face is several
The structure of what character representation good friend face.
First extracting sub-module, the face detail feature for extracting good friend in frame, wherein, face detail feature
Represent the texture information of good friend's face.
Second extracting sub-module, for combining facial geometric feature and face detail feature, extracts the key message of good friend.
Optionally, the embodiment of the present invention sets the device of virtual image also to include：
Second acquisition module, the key message for obtaining each user.
Memory module, for storing the key message of all users to information bank.
Optionally, the embodiment of the present invention is set in the device of virtual image, and fitting module 305 includes：
Connection submodule is set up, for after good friend is filtered out, setting up the connection with good friend.
First fitting submodule, for upon establishment of a connection, by the frame of good friend, being fitted to the original virtual of good friend
Image.
Optionally, the embodiment of the present invention is set in the device of virtual image, and fitting module 305 includes：
Submodule is pre-processed, for being pre-processed to frame, obtains pre- with the fitting of original virtual image matching
It is fitted frame.
Second fitting submodule, for pre- fitting frame to be fitted into original virtual image, obtains the new of good friend
Virtual image.
It should be noted that the device of the embodiment of the present invention is the device using above-mentioned setting virtual image, then it is above-mentioned to set
All embodiments for putting the method for virtual image are applied to the device, and can reach same or analogous beneficial effect.
It should be noted that herein, such as first and second or the like relational terms are used merely to a reality
Body or operation make a distinction with another entity or operation, and not necessarily require or imply these entities or deposited between operating
In any this actual relation or order.Moreover, term " comprising ", "comprising" or its any other variant are intended to
Nonexcludability is included, so that process, method, article or equipment including a series of key elements not only will including those
Element, but also other key elements including being not expressly set out, or also include being this process, method, article or equipment
Intrinsic key element.In the absence of more restrictions, the key element limited by sentence "including a ...", it is not excluded that
Also there is other identical element in process, method, article or equipment including the key element.
Each embodiment in this specification is described by the way of related, identical similar portion between each embodiment
Divide mutually referring to what each embodiment was stressed is the difference with other embodiment.It is real especially for system
Apply for example, because it is substantially similar to embodiment of the method, so description is fairly simple, related part is referring to embodiment of the method
Part explanation.
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the scope of the present invention.It is all
Any modification, equivalent substitution and improvements made within the spirit and principles in the present invention etc., are all contained in protection scope of the present invention
It is interior.
Claims (12)
1. a kind of method that virtual image is set, it is characterised in that applied to virtual social, including：
Obtain the frame of good friend；
Extract in described information image, the key message of the good friend, wherein, the key message includes facial key message；
The key message of the good friend is matched with the key message of all users in information bank, screened from all users
Go out the good friend, and obtain the user profile of the good friend, wherein, stored in described information storehouse all users user profile,
And the user profile of all users is corresponding, all users key message；
According to the user profile of the good friend, the original virtual image of the good friend is obtained；
By the described information image of the good friend, the original virtual image of the good friend is fitted to, new virtual image is obtained.
2. the method according to claim 1 that virtual image is set, it is characterised in that the hum pattern of the acquisition good friend
Picture, including：
By way of taking pictures, selecting local picture and download online picture, the described information image of good friend is obtained.
3. the method according to claim 1 that virtual image is set, it is characterised in that the extraction described information image
In, the key message of the good friend, including：
By detecting face key point, the facial geometric feature of the good friend is obtained, wherein, the facial geometric feature represents institute
State the structure of good friend's face；
The face detail feature of good friend described in described information image is extracted, wherein, it is good described in the face detail character representation
The texture information of friendly face；
With reference to the facial geometric feature and the face detail feature, the key message of the good friend is extracted.
4. the method according to claim 1 that virtual image is set, it is characterised in that positioned at the pass by the good friend
Key information is matched with the key message of all users in information bank, before, and methods described also includes：
Obtain the key message of each user；
The key message of all users is stored to described information storehouse.
5. the method according to claim 1 that virtual image is set, it is characterised in that the letter by the good friend
Image is ceased, the original virtual image of the good friend is fitted to, obtains new virtual image, including：
After the good friend is filtered out, the connection with the good friend is set up；
Upon establishment of a connection, by the described information image of the good friend, it is fitted to the original virtual image of the good friend.
6. the method according to claim 5 that virtual image is set, it is characterised in that the letter by the good friend
Image is ceased, the original virtual image of the good friend is fitted to, obtains new virtual image, including：
Described information image is pre-processed, the pre- fitting frame being fitted with the original virtual image matching is obtained；
The pre- fitting frame is fitted to the original virtual image, the new virtual image of the good friend is obtained.
7. a kind of device of setting virtual image, it is characterised in that including：
First acquisition module, the frame for obtaining good friend；
Extraction module, for extracting in described information image, the key message of the good friend, wherein, the key message includes
Facial key message；
Matching module, for the key message of the good friend to be matched with the key message of all users in information bank, from
The good friend is filtered out in all users, and obtains the user profile of the good friend, wherein, the institute of storage in described information storehouse is useful
The user profile at the family and user profile of all users is corresponding, all users key message；
Original virtual image obtains module, for the user profile according to the good friend, obtains the original virtual shape of the good friend
As；
Fitting module, for by the described information image of the good friend, being fitted to the original virtual image of the good friend, obtaining new
Virtual image.
8. the device of setting virtual image according to claim 7, it is characterised in that first acquisition module is further
For by way of taking pictures, selecting local picture and download online picture, obtaining the described information image of good friend.
9. the device of setting virtual image according to claim 7, it is characterised in that the extraction module includes：
Detection sub-module, for by detecting face key point, obtaining the facial geometric feature of the good friend, wherein, the face
Portion's geometric properties represent the structure of good friend's face；
First extracting sub-module, the face detail feature for extracting good friend described in described information image, wherein, the face
Minutia represents the texture information of good friend's face；
Second extracting sub-module, for reference to the facial geometric feature and the face detail feature, extracting the good friend's
Key message.
10. the device of setting virtual image according to claim 7, it is characterised in that the dress of the setting virtual image
Putting also includes：
Second acquisition module, the key message for obtaining each user；
Memory module, for storing the key message of all users to described information storehouse.
11. the device of setting virtual image according to claim 7, it is characterised in that the fitting module includes：
Connection submodule is set up, for after the good friend is filtered out, setting up the connection with the good friend；
First fitting submodule, for upon establishment of a connection, by the described information image of the good friend, being fitted to the good friend's
Original virtual image.
12. the device of setting virtual image according to claim 11, it is characterised in that the fitting module includes：
Submodule is pre-processed, for pre-processing described information image, obtains being fitted with the original virtual image matching
Pre- fitting frame；
Second fitting submodule, for the pre- fitting frame to be fitted into the original virtual image, obtains described good
The new virtual image of friend.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710207429.1A CN107146275B (en) | 2017-03-31 | 2017-03-31 | Method and device for setting virtual image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710207429.1A CN107146275B (en) | 2017-03-31 | 2017-03-31 | Method and device for setting virtual image |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107146275A true CN107146275A (en) | 2017-09-08 |
| CN107146275B CN107146275B (en) | 2020-10-27 |
Family
ID=59784176
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710207429.1A Active CN107146275B (en) | 2017-03-31 | 2017-03-31 | Method and device for setting virtual image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107146275B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108510437A (en) * | 2018-04-04 | 2018-09-07 | 科大讯飞股份有限公司 | A kind of virtual image generation method, device, equipment and readable storage medium storing program for executing |
| CN108629121A (en) * | 2018-05-08 | 2018-10-09 | 山东师范大学 | Based on the virtual reality crowd emulation mode and system for avoiding terrified paddy effect |
| CN110599359A (en) * | 2019-09-05 | 2019-12-20 | 深圳追一科技有限公司 | Social contact method, device, system, terminal equipment and storage medium |
| CN110674398A (en) * | 2019-09-05 | 2020-01-10 | 深圳追一科技有限公司 | Virtual character interaction method and device, terminal equipment and storage medium |
| CN110674706A (en) * | 2019-09-05 | 2020-01-10 | 深圳追一科技有限公司 | Social contact method and device, electronic equipment and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1787493A (en) * | 2004-12-08 | 2006-06-14 | 腾讯科技（深圳）有限公司 | System and method for personal virtual image interdynamic amusement based on istant communication platform |
| CN101098241A (en) * | 2006-06-26 | 2008-01-02 | 腾讯科技（深圳）有限公司 | Method and system for implementing virtual image |
| CN101127737A (en) * | 2007-09-25 | 2008-02-20 | 腾讯科技（深圳）有限公司 | Implementation method of UI, user terminal and instant communication system |
| JP5827445B2 (en) * | 2012-05-22 | 2015-12-02 | テンセント テクノロジー （シェンジェン） カンパニー リミテッド | Method and system for realizing augmented reality interaction |
| CN105868716A (en) * | 2016-03-29 | 2016-08-17 | 中国科学院上海高等研究院 | Method for human face recognition based on face geometrical features |
| 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 |
-
2017
- 2017-03-31 CN CN201710207429.1A patent/CN107146275B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1787493A (en) * | 2004-12-08 | 2006-06-14 | 腾讯科技（深圳）有限公司 | System and method for personal virtual image interdynamic amusement based on istant communication platform |
| CN101098241A (en) * | 2006-06-26 | 2008-01-02 | 腾讯科技（深圳）有限公司 | Method and system for implementing virtual image |
| CN101127737A (en) * | 2007-09-25 | 2008-02-20 | 腾讯科技（深圳）有限公司 | Implementation method of UI, user terminal and instant communication system |
| JP5827445B2 (en) * | 2012-05-22 | 2015-12-02 | テンセント テクノロジー （シェンジェン） カンパニー リミテッド | Method and system for realizing augmented reality interaction |
| 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 |
| CN105868716A (en) * | 2016-03-29 | 2016-08-17 | 中国科学院上海高等研究院 | Method for human face recognition based on face geometrical features |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108510437A (en) * | 2018-04-04 | 2018-09-07 | 科大讯飞股份有限公司 | A kind of virtual image generation method, device, equipment and readable storage medium storing program for executing |
| CN108629121A (en) * | 2018-05-08 | 2018-10-09 | 山东师范大学 | Based on the virtual reality crowd emulation mode and system for avoiding terrified paddy effect |
| CN108629121B (en) * | 2018-05-08 | 2022-04-01 | 山东师范大学 | Virtual reality crowd simulation method and system based on terrorist valley effect avoidance |
| CN110599359A (en) * | 2019-09-05 | 2019-12-20 | 深圳追一科技有限公司 | Social contact method, device, system, terminal equipment and storage medium |
| CN110674398A (en) * | 2019-09-05 | 2020-01-10 | 深圳追一科技有限公司 | Virtual character interaction method and device, terminal equipment and storage medium |
| CN110674706A (en) * | 2019-09-05 | 2020-01-10 | 深圳追一科技有限公司 | Social contact method and device, electronic equipment and storage medium |
| CN110674706B (en) * | 2019-09-05 | 2021-07-23 | 深圳追一科技有限公司 | Social contact method and device, electronic equipment and storage medium |
| CN110599359B (en) * | 2019-09-05 | 2022-09-16 | 深圳追一科技有限公司 | Social contact method, device, system, terminal equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107146275B (en) | 2020-10-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107146275A (en) | A kind of method and device of setting virtual image | |
| US20200160415A1 (en) | Methods and devices for providing fashion advice | |
| CN107392110A (en) | Beautifying faces system based on internet | |
| CN104809638B (en) | A kind of virtual try-in method of glasses based on mobile terminal and system | |
| US11734866B2 (en) | Controlling interactive fashion based on voice | |
| US20240257484A1 (en) | 3d upper garment tracking | |
| WO2022227393A1 (en) | Image photographing method and apparatus, electronic device, and computer readable storage medium | |
| US20230111489A1 (en) | Inferring intent from pose and speech input | |
| CN108537126A (en) | A kind of face image processing system and method | |
| US20230100509A1 (en) | Body normal network light and rendering control | |
| KR20240049844A (en) | Control AR games on fashion items | |
| CN108460398A (en) | Image processing method, device, cloud processing equipment and computer program product | |
| CN110210449A (en) | A kind of face identification system and method for virtual reality friend-making | |
| CN107370831B (en) | Multiusers interaction realization method and system based on MR aobvious equipment | |
| CN110197420A (en) | A kind of intelligent dressing system | |
| CN108932654A (en) | A kind of virtually examination adornment guidance method and device | |
| CN108109037A (en) | Simulation fitting method, apparatus, system and storage medium based on mobile terminal | |
| CN109074680A (en) | Realtime graphic and signal processing method and system in augmented reality based on communication | |
| JP6204315B2 (en) | Caricature image generating apparatus, caricature image generating method, and caricature image generating program | |
| KR102466408B1 (en) | Styling device and the driving method thereof | |
| CN109550230A (en) | A kind of interactive experience device and method | |
| CN109118590A (en) | A kind of 3D fitting platform based on machine learning | |
| WO2023082737A1 (en) | Data processing method and apparatus, and device and readable storage medium | |
| KR102570735B1 (en) | Apparatus and method for suggesting an augmented reality avatar pose based on artificial intelligence reflecting the structure of the surrounding environment and user preferences | |
| CN109965493A (en) | A kind of split screen interactive display method and device |
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 |