CN106303354A - A kind of face specially good effect recommends method and electronic equipment - Google Patents
A kind of face specially good effect recommends method and electronic equipment Download PDFInfo
- Publication number
- CN106303354A CN106303354A CN201610685111.XA CN201610685111A CN106303354A CN 106303354 A CN106303354 A CN 106303354A CN 201610685111 A CN201610685111 A CN 201610685111A CN 106303354 A CN106303354 A CN 106303354A
- Authority
- CN
- China
- Prior art keywords
- good effect
- specially good
- image
- face feature
- region
- 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
- 230000000694 effects Effects 0.000 title claims abstract description 346
- 238000000034 method Methods 0.000 title claims abstract description 74
- 238000004422 calculation algorithm Methods 0.000 claims description 16
- 230000006835 compression Effects 0.000 claims description 8
- 238000007906 compression Methods 0.000 claims description 8
- 241000208340 Araliaceae Species 0.000 claims description 3
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 claims description 3
- 235000003140 Panax quinquefolius Nutrition 0.000 claims description 3
- 235000008434 ginseng Nutrition 0.000 claims description 3
- 238000005034 decoration Methods 0.000 claims 1
- 230000008569 process Effects 0.000 description 14
- 230000008901 benefit Effects 0.000 description 5
- 230000001815 facial effect Effects 0.000 description 5
- 210000004709 eyebrow Anatomy 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 230000001154 acute effect Effects 0.000 description 2
- 238000004590 computer program Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000013316 zoning Methods 0.000 description 2
- 241000196324 Embryophyta Species 0.000 description 1
- 235000011464 Pachycereus pringlei Nutrition 0.000 description 1
- 240000006939 Pachycereus weberi Species 0.000 description 1
- 235000011466 Pachycereus weberi Nutrition 0.000 description 1
- 241001501970 Prionailurus bengalensis Species 0.000 description 1
- 241000282487 Vulpes Species 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000001035 drying Methods 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 210000004209 hair Anatomy 0.000 description 1
- 210000003128 head Anatomy 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 238000009877 rendering Methods 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/14—Systems for two-way working
- H04N7/141—Systems for two-way working between two video terminals, e.g. videophone
- H04N7/147—Communication arrangements, e.g. identifying the communication as a video-communication, intermediate storage of the signals
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/14—Transformations for image registration, e.g. adjusting or mapping for alignment of images
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/47—End-user applications
- H04N21/478—Supplemental services, e.g. displaying phone caller identification, shopping application
- H04N21/4788—Supplemental services, e.g. displaying phone caller identification, shopping application communicating with other users, e.g. chatting
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- General Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a kind of face specially good effect and recommend method and electronic equipment, the method includes: obtain the first face feature image of user;Obtain the reference user that the second face feature image identical and/or similar with described first face feature image is corresponding;Obtaining described used with reference to specially good effect with reference to user, described being used in use with reference to specially good effect fills the specially good effect region that face feature image is corresponding;The described recommendation information with reference to specially good effect is sent to described user, selects to use described reference specially good effect for described user.In technique scheme, by recommending the reference user identical and/or similar with oneself face feature used with reference to specially good effect to user, make to select the match hit rate of the reference specially good effect used to be greatly improved according to recommendation information, thus solve specially good effect in prior art and there is the technical problem that match hit rate is relatively low in use, reach to improve the technique effect of specially good effect match hit rate.
Description
Technical field
The present invention relates to software technology field, particularly relate to a kind of face specially good effect and recommend method and electronic equipment.
Background technology
Along with the development of network communication, increasing user selects to be made friends by the network platform and entertain, these nets
Network platform includes chat with friends one to one platform, main broadcaster chatroom platform, forum's dating site etc., wherein, friendship of chatting one to one
Friend's platform, is more favored by user owing to exchanging by real-time video with main broadcaster chatroom platform.
In order to increase the use stickiness of platform user, each video platform often provides abundant special video effect, in order to use
Family is when carrying out video exchange, it is possible to use the mask class specially good effect that platform provides increases the recreational of video.But, due to flat
The value volume and range of product of the specially good effect that platform provides is various, and the most different specially good effects uses audient different, and user needs when selecting specially good effect
Devote a tremendous amount of time selection, be suitable for, compare, occur that when specially good effect is mated with user, match hit rate is relatively low, in some instances it may even be possible to occur
Repeatedly select the matching effect being suitable for the best, cause user to abandon using specially good effect, be unfavorable for using and promoting of specially good effect.
Visible, in use, there is the technical problem that hit rate is relatively low in specially good effect of the prior art.
Summary of the invention
In view of the above problems, the present invention proposes and a kind of overcome the problems referred to above or solve the problems referred to above at least in part
The method of face's specially good effect recommendation and electronic equipment.
One aspect of the present invention, it is provided that the method that a kind of face specially good effect is recommended, including:
Obtain the first face feature image of user;
Obtain reference corresponding to the second face feature image identical and/or similar with described first face feature image to use
Family;
Obtaining described used with reference to specially good effect with reference to user, described reference specially good effect is used for filling face feature in use
The region to be filled that image is corresponding;
The described recommendation information with reference to specially good effect is sent to described user, selects to use described reference special for described user
Effect.
Optionally, the second face feature image that described acquisition is identical and/or similar with described first face feature image
Corresponding reference user, including: obtain between described first face feature image image similarity more than the of setting threshold value
Two face feature images;Obtain the reference user that described second face feature image is corresponding.
Optionally, the second face feature image that described acquisition is identical and/or similar with described first face feature image
Corresponding reference user, including:
Obtain the face feature type belonging to described first face feature image;Obtain and described first face feature image
The second face feature image that affiliated face feature type is identical;Obtain reference corresponding to described second face feature image to use
Family.
Optionally, described first face feature image includes at least one sense in face contour image and/or face feature
Official's characteristic image.
Optionally, described acquisition described reference user used reference specially good effect, including:
Obtain the described specially good effect using frequency to be more than setpoint frequency with reference to user as described with reference to specially good effect;Or
Obtain the described specially good effect of numerical value that sets with reference to user's access times more than first as described reference specially good effect;Or
Obtain and when described reference user uses, obtain the number of times praising and/or the receiving present specially good effect work more than the second setting numerical value
For described with reference to specially good effect.
Optionally, described reference specially good effect is: specially good effect mask or specially good effect ornaments.
Optionally, described method also includes:
Receive for selecting the described selection instruction with reference to specially good effect, be divided into M with reference to specially good effect according to preset rules by described
Specially good effect region, M is the positive integer more than 1;
Identifying N number of characteristic point of described first face feature image, N is positive integer;
According to described N number of characteristic point, according to described preset rules, described first face feature image is divided into and described M
M the image-region that specially good effect region is corresponding;
Described M specially good effect region correspondence is filled into described M image-region, forms the 3rd face feature image;
Export described 3rd face feature image.
Optionally, described according to described N number of characteristic point, according to described preset rules, described first face feature image is divided
For M the image-region corresponding with described M specially good effect region, specifically include:
According to described N number of characteristic point, described first face feature image is divided into the M corresponding with described M specially good effect region
Individual image-region, wherein, described M image-region is delta-shaped region, bag in each image-region in described M image-region
The quantity of the described characteristic point included is less than or equal to 1.
Optionally, described described M specially good effect region correspondence is filled into described M image-region, including:
Use image compression algorithm and/or image stretch algorithm, described M specially good effect region correspondence is filled into described M
Image-region, so that the form fit of the image-region that the shape in each specially good effect region is corresponding in described M specially good effect region.
Another aspect of the present invention, also provides for a kind of electronic equipment, including:
Image acquisition unit, for obtaining the first face feature image of user;
User's acquiring unit, special for obtaining second face identical and/or similar with described first face feature image
Levy the reference user that image is corresponding;
Specially good effect acquiring unit, is used for obtaining described reference user used with reference to specially good effect, and described reference specially good effect is using
Time for filling the specially good effect region that face feature image is corresponding;
Push unit, for the described recommendation information with reference to specially good effect is sent to described user, selects for described user
Use described with reference to specially good effect.
Optionally, described user's acquiring unit is used for: obtain image similarity between described first face feature image
More than the second face feature image setting threshold value;Obtain the reference user that described second face feature image is corresponding.
Optionally, described user's acquiring unit is additionally operable to: obtain the face feature belonging to described first face feature image
Type;Obtain the second face feature image identical with the face feature type belonging to described first face feature image;Obtain
The reference user that described second face feature image is corresponding.
Optionally, described first face feature image includes at least one sense in face contour image and/or face feature
Official's characteristic image.
Optionally, described specially good effect acquiring unit, it is used for: obtain the described spy using frequency to be more than setpoint frequency with reference to user
Imitate as described with reference to specially good effect;Or, it is thus achieved that the described specially good effect of numerical value that sets more than first with reference to user's access times is as institute
State with reference to specially good effect;Or, it is thus achieved that described reference user obtains the number of times praising and/or receiving present more than the second setting numerical value when using
Specially good effect as described with reference to specially good effect.
Optionally, described reference specially good effect is: specially good effect mask or specially good effect ornaments.
Optionally, described electronic equipment also includes:
First division unit, for receiving for selecting the described selection instruction with reference to specially good effect, by described specially good effect according in advance
If rule is divided into M specially good effect region, M is the positive integer more than 1;
Recognition unit, for identify described first face feature image N number of characteristic point, N is positive integer;
Second division unit, for according to described N number of characteristic point, according to described preset rules by described first face feature
Image is divided into M the image-region corresponding with described M specially good effect region;
Filling unit, for described M specially good effect region correspondence being filled into described M image-region, forming the 3rd face
Characteristic image;
Output unit, is used for exporting described 3rd face feature image.
Optionally, described second division unit, specifically for: according to described N number of characteristic point, by described first face feature
Image is divided into M the image-region corresponding with described M specially good effect region, and wherein, described M image-region is delta-shaped region,
The quantity of the described characteristic point included in each image-region in described M image-region is less than or equal to 1.
Optionally, described filling unit, it is used for: use image compression algorithm and/or image stretch algorithm, by described M
Specially good effect region correspondence is filled into described M image-region so that in described M specially good effect region the shape in each specially good effect region and its
The form fit of corresponding image-region.
The technical scheme provided in the embodiment of the present application, at least has the following technical effect that or advantage:
The embodiment of the present application obtains the first face feature image of user;Obtain and described first face feature image phase
The reference user that the second same and/or similar face feature image is corresponding;Obtain described used with reference to specially good effect with reference to user,
Described being used in use with reference to specially good effect fills the specially good effect region that face feature image is corresponding;By the described recommendation with reference to specially good effect
Breath is sent to user, and the most recommended face feature with reference to specially good effect with user can be good at matching so that according to pushing away
When information of recommending selects to use with reference to specially good effect, the match hit rate of specially good effect is greatly improved, and solves specially good effect in prior art and is using
Time there is the technical problem that match hit rate is relatively low.
Described above is only the general introduction of technical solution of the present invention, in order to better understand the technological means of the present invention,
And can be practiced according to the content of description, and in order to allow above and other objects of the present invention, the feature and advantage can
Become apparent, below especially exemplified by the detailed description of the invention of the present invention.
Accompanying drawing explanation
By reading the detailed description of hereafter preferred implementation, various other advantage and benefit common for this area
Technical staff will be clear from understanding.Accompanying drawing is only used for illustrating the purpose of preferred implementation, and is not considered as the present invention
Restriction.And in whole accompanying drawing, it is denoted by the same reference numerals identical parts.In the accompanying drawings:
Fig. 1 shows the method flow diagram that a kind of face specially good effect is recommended;
Fig. 2 shows according to an embodiment of the invention with reference to the using method flow chart of specially good effect;
Fig. 3 shows the schematic diagram of a kind of electronic equipment.
Detailed description of the invention
It is more fully described the exemplary embodiment of the disclosure below with reference to accompanying drawings.Although accompanying drawing shows the disclosure
Exemplary embodiment, it being understood, however, that may be realized in various forms the disclosure and should be by embodiments set forth here
Limited.On the contrary, it is provided that these embodiments are able to be best understood from the disclosure, and can be by the scope of the present disclosure
Complete conveys to those skilled in the art.
Embodiments provide method and electronic equipment that a kind of face specially good effect is recommended, in order to solve in prior art
There is the technical problem that match hit rate is relatively low in use in specially good effect.
Refer to Fig. 1, the method that a kind of face specially good effect that the embodiment of the present application provides is recommended, the method includes:
S101: obtain the first face feature image of user;
S102: obtain the second face feature image identical and/or similar with described first face feature image corresponding
With reference to user;
S103: obtaining described used with reference to specially good effect with reference to user, described reference specially good effect is used for filling face in use
The region to be filled that portion's characteristic image is corresponding;
S104: the described recommendation information with reference to specially good effect is sent to described user, selects use described for described user
With reference to specially good effect.
In specific implementation process, the method that above-mentioned face specially good effect is recommended can apply to live software, U.S. figure software, regards
Frequency call software etc. needs in the middle of the application by using face's specially good effect to modify face, beautify and hide, permissible
By client executing, it is also possible to performed by server end.Below with time live to main broadcaster face or participate in live spectators' face
As a example by portion uses face's specially good effect, the method that the face's specially good effect providing the application is recommended is illustrated.
S101 can be acquired periodically the first face feature image of user, as every time confirmed live or spectators are true main broadcaster
Recognize participation live, when unlatching photographic head carries out image acquisition, it is thus achieved that main broadcaster or the first face feature image of spectators;In detection
During to new facial image, it is thus achieved that the first face feature image of this new user;Perform to use the behaviour of specially good effect main broadcaster or spectators
When making, it is thus achieved that the first face feature image of user.Wherein, face feature image comprises face mask image and/or face five
At least one organoleptic feature image in official, face mask image is for characterizing the shape of face of face, and organoleptic feature image is used for table
Levy the feature of eyebrow, eyes, nose, face or ear.
S102 obtains the second face feature image identical and/or similar with the first face feature image, and the second face
The reference user that characteristic image is corresponding.
Server end can prestore the face feature image of each main broadcaster, by the first face feature image obtained with prestore
The face feature image of main broadcaster is compared, therefrom to obtain the second face feature image.Concrete, it is possible to obtain with the first face
Between portion's characteristic image, image similarity is more than the second face feature image setting threshold value;Obtain described second face feature figure
As corresponding reference user.The similarity of image can use the methods such as Histogram Matching, matrix decomposition, Feature Points Matching to calculate
Obtaining, wherein, the image similarity of distinguished point based calculates, and is the characteristic point by extracting every piece image, these characteristic points
Some positions important in phenogram picture, more that than the flex point of relatively similar function, generally the more commonly used has Harris angle
Point and Sift characteristic point, then the image angle obtained point is compared, if similar angle point number is more, then can recognize
Similarity degree for this two width image is higher.
As a kind of optional embodiment, it is also possible to obtain the face belonging to the first face feature image by recognition of face
Characteristic type, such as: the shape of face identifying the first face feature image is oval face, state's word face, side's face etc., face feature mesophryon
Hairs type be arched eyebrows, horizontal eyebrow call together, tall eyebrow etc., nose types is aquiline nose, nose nose, flat nose etc..Based on acquisition
Face feature type, it is thus achieved that the second face feature figure identical with the face feature type belonging to the first face feature image
Picture, and then the reference user that the second face feature image is corresponding, such as: if the shape of face of the first face feature image is oval face,
So obtaining shape of face is also the reference user that the second face feature image of oval face is corresponding.
S103 obtains the reference specially good effect using process with reference to user.Wherein this reference specially good effect is specially specially good effect mask or specially good effect
Ornaments, this feature is in use for filling the region to be filled that face feature image is corresponding, such as: assume that with reference to specially good effect be Vulpes
Leopard cat eyeshield, then when user uses this specially good effect, in user's face image, eyes region is then filled to be fox eyeshield, to
User has carried a fox eyeshield the same.
In order to recommend the reference specially good effect more mated with user, when obtaining with reference to specially good effect, can obtain further
Using frequency to be more than the specially good effect of setpoint frequency with reference to user, the use frequency of specially good effect is more than setpoint frequency, shows with reference to user couple
The satisfaction of this specially good effect is higher, the highest with the face's matching degree with reference to user, for this as with reference to specially good effect.Same,
Can also obtain and set the specially good effect of numerical value as with reference to specially good effect with reference to user's access times more than first.Or, it is also possible to obtain
Obtaining the number of times praising and/or the receiving present specially good effect more than the second setting numerical value with reference to user when using, specially good effect obtains in use and praises
And/or the number of times receiving present sets numerical value more than second, show with reference to user's popularity when using this specially good effect the highest,
The highest with the probability of user's shape of face match hit, therefore using this specially good effect as with reference to specially good effect.
Recommendation information with reference to specially good effect is sent to the user that the first face feature image is corresponding by S104.Wherein, this recommendation
Information can be to recommend mark, when having this reference specially good effect in user's specially good effect that the first face feature image is corresponding, in this ginseng
Examine additional this recommendation mark in specially good effect.Recommendation information can also be an i.e. message of PUSH message, when the first face feature figure
During as corresponding user's specially good effect does not have this reference specially good effect, send this PUSH message to this user, this PUSH message also may be used
To comprise the link downloading this reference specially good effect, user can download this reference specially good effect by clicking on this PUSH message, and then
Select to use this reference specially good effect.
Refer to Fig. 2, in specific implementation process, the embodiment of the present application sent with reference to specially good effect pushed information it
After, also provide for a kind of adding method with reference to specially good effect, including:
S201: receive for selecting the described selection instruction with reference to specially good effect, divide described according to preset rules with reference to specially good effect
For M specially good effect region, M is the positive integer more than 1;
S202: identify N number of characteristic point of described first face feature image, N is positive integer;
S203: according to described N number of characteristic point, according to described preset rules, described first face feature image is divided into and institute
State M M image-region corresponding to specially good effect region;
S204: described M specially good effect region correspondence is filled into described M image-region, forms the 3rd face feature image;
S205: export described 3rd face feature image.
It should be noted that the specially good effect adding method that the application provides both may be used for the spy to single face feature image
Effect is added, it is also possible to for adding the specially good effect comprising face feature image/video, wherein, described video can be live regarding
Frequently, it is also possible to being the video recorded in advance, the application does not limit.When described method is applied to comprising face feature image
When the specially good effect of video is added, can be to use described method that each two field picture of video is carried out at above-mentioned specially good effect interpolation successively
Reason, to realize the interpolation of the specially good effect to whole video.
Below, be discussed in detail in conjunction with Fig. 2 this fixed reference feature adding method implement step:
Step S201, when receiving for selecting the selection instruction with reference to specially good effect, by described reference specially good effect according to presetting
Rule is divided into M specially good effect region in advance, and M is the positive integer more than 1.
In the embodiment of the present application, described selection instruction can be that user self performs to select specially good effect on an electronic device
The selection instruction generated during operation;Can also be that electronic equipment receives the selection of other equipment transmission with reference to refering in particular to order.Such as,
When described method is applied to main broadcaster's end of live platform, can be that main broadcaster performs to select the behaviour with reference to specially good effect on main broadcaster's end
Make, generate and select instruction;Can also be that main broadcaster terminates the instruction receiving the selection reference specially good effect that spectator client sends.
In the embodiment of the present application, described specially good effect can be picture or cardon form, and described specially good effect is divided into M specially good effect district
Territory, in order to make described M specially good effect region mate with described M image-region, its concrete zoning ordinance and follow-up first image
Zoning ordinance identical, be described in detail again in subsequent step S202 and step S203.
Step S202, identifies N number of characteristic point of described first face feature image, and N is positive integer.Wherein, described in identifying
The mode of the characteristic point of the first face feature image can have multiple, as a example by being set forth below two kinds:
The first, by preset rules Direct Recognition characteristic point.
I.e. directly on the first face feature image, identify N number of characteristic point according to default rule.Described default rule
Can be the profile identifying described target object on the first face feature image, profile extracts characteristic point, described pre-
If rule can also be on described first face feature image, to identify the dark strokes of described face, in described dark color
Extracting characteristic point on lines, this is not restricted.N number of characteristic point of the described first face feature image of described identification, Ke Yiwei:
Identify the face profile point on described first face feature image and/or face contour point.
Often collect a frame facial image for example, it is possible to preset, on image, just identify 95 characteristic points, described 95
Characteristic point includes: point on the point of facial contour, the point of eye contour, bridge of the nose line, the point of eyebrow center line, the point of lip outline and
The point of ear profile.
Further, the distribution of described N number of characteristic point can be preset and be uniformly distributed along profile or lines, or by the rule preset
Then in a part of profile or lines (such as face profile) dense distribution relatively, at other profile or lines (such as shape of face wheel
Wide) relative sparse distribution.
The second, the feature in conjunction with specially good effect identifies characteristic point.
I.e. combine the feature of the specially good effect of selection, on the first face feature image, identify N number of feature according to default rule
Point.Such as, if the specially good effect selected is glasses face mask specific effects, then understands according to the feature of specially good effect and only need to identify the first face feature
Facial contour point on image and eye contour point are as characteristic point.
The most such as, if the specially good effect selected is beard face mask specific effect, then understands according to the feature of specially good effect and only need to identify first
Facial contour point on face feature image and lip outline point are as characteristic point.
Certainly, in specific implementation process, identify that N number of characteristic point of described first face feature image is not limited to above several
Plant recognition methods, can determine that different recognition methodss based on different demands, this embodiment of the present invention is arranged the most in detail
Lift, and be not restricted.
Step S203, according to described N number of characteristic point, is divided into described first face feature image according to described preset rules
Region filled by M the image-region i.e. band corresponding with described M specially good effect region.Wherein, according to described N number of characteristic point, according to institute
State preset rules and described first face feature image is divided into the mode of M the image-region corresponding with described M specially good effect region
Can have multiple, as a example by being set forth below two kinds:
The first, divide image-region using described characteristic point as summit.
I.e. according to described N number of characteristic point, described first face feature image is divided into corresponding with described M specially good effect region
M image-region, wherein, described M image-region is M with the triangle that described N number of characteristic point is all or part of summit
Region.
Specifically, described N number of characteristic point can be connected two-by-two, then with the image limit of described first face feature image
Edge be connected, with by described first face feature image division for M triangular image region, wherein, each characteristic point is institute
State the summit of delta-shaped region, but the summit of described delta-shaped region is not required for the most described characteristic point, concrete division
Rule is misaligned with described M triangular image region, and described first face feature image can be completely covered, at this not
It is restricted.
The second, is less than or equal to 1 to divide image-region with the characteristic point quantity comprised in each image-region.
I.e. according to described N number of characteristic point, described first face feature image is divided into corresponding with described M specially good effect region
M image-region, wherein, described M image-region is delta-shaped region, in described M image-region in each image-region
Including the quantity of described characteristic point less than or equal to 1.
Specifically, each region in described M image-region can be set and comprise 1 or 0 characteristic point, i.e. can be first
N number of image-region of default size is set and covers described N number of characteristic point one by one, then by described first face feature image not
The region filled by described N number of image-region is divided into M-N image-region, concrete so that described M image-region does not weighs
Close, and described first face feature image can be completely covered.
Certainly, in specific implementation process, described each image-region can also be rectangle or rhombus, does not limits at this
System.Preferably, described each image-region is triangle, in order to rendering of figure.
It should be noted that the value in view of N and M is the biggest, then show that the feature to described first face feature image is known
Other and region divides the thinnest, and follow-up filling effect is the best, but relative, and the value of N and M is the biggest, then need the characteristic point identified
The region filled is the most with needing, and amount of calculation is the biggest, and the time of follow-up filling specially good effect is the longest, such as when described approach application is in regarding
Time the most live, just it be easily caused specially good effect and add and postpone, therefore, in specific implementation process, can filling effect as required and making
By scene, the requirement of real-time arranged rational N and M value.
Also, it should be noted in order to make described M specially good effect region and described M image-region one_to_one corresponding, in order to
Step S204 can correspondence be filled one by one, the division rule in described M specially good effect region and method and described M image-region stroke
Dividing rules and methods identical, be to determine N number of specially good effect characteristic point in advance in described specially good effect the most equally, it determines specially good effect characteristic point
With on described first face feature image, method determines that the method for characteristic point is identical, further according to described N number of specially good effect characteristic point, adopt
M specially good effect region is gone out with the regular partition identical with described M image-region division.
Certainly, in specific implementation process, dividing described first face feature image, to be that M image-region is not limited to above
Several division methods, can determine that different division methods based on different demands, the most detailed to this embodiment of the present invention
Enumerate, and be not restricted.
Then, perform step S204, described M specially good effect region correspondence is filled into described M image-region, form specially good effect
Add image.Concrete, image compression algorithm and/or image stretch algorithm can be used, described M specially good effect region correspondence is filled out
It is charged to described M image-region, so that the image-region that in described M specially good effect region, the shape in each specially good effect region is corresponding
Form fit.
Such as, when described M specially good effect region correspondence is filled into described M image-region, if certain specially good effect region and its
Corresponding image-region shape size is the most identical, then be directly filled in by this specially good effect region overlay on the image-region of correspondence;Again
Such as, if the corresponding image-region shape in certain specially good effect region is identical but varies in size, then equal proportion zooms in or out institute
State specially good effect region extremely onesize with corresponding image-region, then this specially good effect region overlay is filled to corresponding image-region
On;The most such as, if the corresponding image-region shapes and sizes in certain specially good effect region are the most different, then partial compression and or/draw
Rise described specially good effect region extremely shapes and sizes as corresponding image-region, then this specially good effect region overlay is filled to correspondence
On image-region.
In specific implementation process, if certain specially good effect region is pure color, then simple in order to calculate, then can be the most right by it
The image-region answered is filled to this pure color, and certainly, described specially good effect region can also be all or part of transparent color, then have when this
After the specially good effect area filling of light colour covers corresponding image-region, transparent color region is shown as the true qualities in correspondence image region.
Specifically, in advance specially good effect is divided into M specially good effect region, when needs add specially good effect, first according to the target obtained
Subject image identifies characteristic point, marks off M the image district corresponding with M specially good effect region targetedly further according to characteristic point
Territory, finally fills described M image-region, so that specially good effect can be with the external appearance characteristic of target object by M specially good effect region correspondence
Coupling, makes same specially good effect go for different target object image, effectively expands the scope of application of specially good effect.
Finally, after interpolation completes to obtain specially good effect interpolation image, perform step S205, export described specially good effect and add image,
Show as specially good effect added image.
Recommend specially good effect the example added below by complete main broadcaster's end for live platform, the present embodiment is provided
Face's specially good effect recommends method to be illustrated:
During main broadcaster's net cast, when needing to add specially good effect mask, some katal effect mask list, triggers generation mask and pushes away
Recommending instruction, main broadcaster end A obtains the first face feature image comprising main broadcaster face by camera collection.Further, by institute
State the first face feature image to send to server.
Server, after receiving the first face feature image, extracts the of the first face feature image by recognition of face
One face contour image and each organoleptic feature image of face feature.Obtain identical with described first face contour image, and its
Each organoleptic feature image similarity of face feature is more than the second face feature image of setting threshold value, and the second face of reentrying is special
Levy the reference user that image is corresponding, as with reference to main broadcaster's end.
Server obtains the reference specially good effect using process with reference to main broadcaster's end.Assume with reference to the nearest one week 20 times specially good effects of main broadcaster's end
Use has the use frequency that have selected a certain Beijing opera mask, i.e. this Beijing opera mask to be 70% 14 times, more than setpoint frequency 50%, that
Using this Beijing opera mask as with reference to specially good effect.Further, the recommendation information of the reference specially good effect-Beijing opera mask obtained is sent extremely
Main broadcaster end A.
Main broadcaster have selected this Beijing opera face mask specific effect at main broadcaster end A according to the recommendation information received on APP platform;So
Main broadcaster end A generates and responds selection instruction, this Beijing opera mask is divided into 206 triangle specially good effect regions in advance, these 206 triangles
Shape specially good effect region is according to 95 the specially good effect characteristic points determined on Beijing opera mask in advance, divides by preset rules.
Main broadcaster's end group instructs in above-mentioned selection, obtains current first two field picture of net cast, and identifies the first face
95 characteristic points on characteristic image and this face feature image, described 95 characteristic points include face profile point, face contour
Point and hairline profile point, the recognition rule of described 95 characteristic points is established rules the most identical with described 95 specially good effect characteristic points really;Connect
Getting off, main broadcaster end A, will according to the division rules identical with 206 triangle specially good effect regions of division according to described 95 characteristic points
Described first face feature image is divided into 206 the triangular image regions corresponding with described 206 triangle specially good effect regions;So
After, main broadcaster end A uses to compress and/or draw high algorithm and described 206 triangle specially good effect region correspondences is filled into described 206 three
Dihedral image-region, forms the image after adding Beijing opera mask.
Subsequently, the specially good effect after described interpolation Beijing opera mask is added image and shows at described main broadcaster's end, main broadcaster's end A simultaneously
Specially good effect after described interpolation Beijing opera mask is added image and is uploaded to this live Platform Server, and capital will be added by server
Images share after acute mask is to spectator client corresponding for main broadcaster end A, so that live spectators and main broadcaster can see interpolation capital
Image after acute mask.
Based on same reason, main broadcaster end A obtains follow-up the second two field picture, the 3rd two field picture ..., use identical successively
Mask adding method to the second two field picture, the 3rd two field picture ... add face mask specific effect, and be sequentially output, it is achieved to live video
The interpolation of face mask specific effect.It should be noted that video often has 15 frames for 1 second, time-consuming about 66 milliseconds of 1 frame, therefore in order to ensure
The adding to calculate of specially good effect is not resulted in the pause of video and the most smooth, needs to identify characteristic point, and divide image-region and fill special
The time of effect controls in 66 milliseconds, to maintain the smoothness of live video.
Above-described embodiment provide in, by identify user face feature image, obtain with user's face contour and/
Or face feature is same or analogous with reference to user, obtains further with reference to the used fixed reference feature of user, will be with reference to specially good effect
Recommendation information be sent to user so that recommended with reference to specially good effect by selecting with reference to user, it is possible to with reference to user
Face feature well match, and then according to recommendation information select use with reference to specially good effect time, then this reference specially good effect and
The shape of face of user also can well match, and then solving specially good effect in prior art, to there is match hit rate in use relatively low
Technical problem.
Meanwhile, filled by the extraction of characteristic point and subregion so that though specially good effect when adding main broadcaster at video
During there is the change of face angle and distance, also can be by real time every two field picture being added specially good effect respectively, it is ensured that reference specially good effect
Can mate with main broadcaster face in real time.
Based on same inventive concept, the embodiment of the present invention additionally provides a kind of face of embodiment specially good effect and recommends method corresponding
Electronic equipment, refer to Fig. 3, and this electronic equipment includes:
Image acquisition unit 31, for obtaining the first face feature image of user;
User's acquiring unit 32, for obtaining second face identical and/or similar with described first face feature image
The reference user that characteristic image is corresponding;
Specially good effect acquiring unit 33, is used for obtaining described reference user used with reference to specially good effect, and described reference specially good effect makes
Used time is for filling the specially good effect region that face feature image is corresponding;
Push unit 34, for the described recommendation information with reference to specially good effect is sent to described user, selects for described user
Select use described with reference to specially good effect.
In specific implementation process, described user's acquiring unit 32 is used for: obtain with described first face feature image it
Between image similarity more than set threshold value the second face feature image;Obtain the reference that described second face feature image is corresponding
User.Optionally, described user's acquiring unit 32 is additionally operable to: obtain the face feature class belonging to described first face feature image
Type;Obtain the second face feature image identical with the face feature type belonging to described first face feature image;Obtain institute
State the reference user that the second face feature image is corresponding.Wherein, described first face feature image include face contour image and/
Or at least one organoleptic feature image in face feature.
In specific implementation process, described specially good effect acquiring unit 33, it is used for: obtain described reference user and use frequency to be more than
The specially good effect of setpoint frequency is as described reference specially good effect;Or, it is thus achieved that described reference user's access times are more than the first setting numerical value
Specially good effect as described with reference to specially good effect;Or, it is thus achieved that described obtaining when using with reference to user is praised and/or is received the number of times of present and be more than
Second sets the specially good effect of numerical value as described with reference to specially good effect.Described reference specially good effect is: specially good effect mask or specially good effect ornaments.
In specific implementation process, described electronic equipment also includes:
First division unit 35, for receiving for selecting the described instruction of the selection with reference to specially good effect, by described specially good effect according to
Preset rules is divided into M specially good effect region, and M is the positive integer more than 1;
Recognition unit 36, for identify described first face feature image N number of characteristic point, N is positive integer;
Second division unit 37, for according to described N number of characteristic point, according to described preset rules by special for described first face
Levy image and be divided into M the image-region corresponding with described M specially good effect region;
Filling unit 38, for described M specially good effect region correspondence being filled into described M image-region, forming the 3rd face
Portion's characteristic image;
Output unit 39, is used for exporting described 3rd face feature image.
Concrete, described second division unit 37, specifically for: according to described N number of characteristic point, by special for described first face
Levying image and be divided into M the image-region corresponding with described M specially good effect region, wherein, described M image-region is delta
Territory, the quantity of the described characteristic point included in each image-region in described M image-region is less than or equal to 1.
When filling, described filling unit 38, it is used for: use image compression algorithm and/or image stretch algorithm, by described
M specially good effect region correspondence is filled into described M image-region, so that the shape in each specially good effect region in described M specially good effect region
The form fit of corresponding image-region.
The technical scheme provided in the embodiment of the present application, at least has the following technical effect that or advantage:
1, by identify user face feature image, obtain identical with user's face contour and/or face feature or
Similar reference user, obtains further with reference to the used fixed reference feature of user, is sent to by the recommendation information with reference to specially good effect
User so that recommended reference specially good effect was selected by with reference to user, it is possible to good with the face feature with reference to user
Match, and then when selecting to use with reference to specially good effect according to recommendation information, then the shape of face of this reference specially good effect and user also can be very
Good matches, and then solves specially good effect in prior art and there is the technical problem that match hit rate is relatively low in use.
2, meanwhile, extraction and subregion by characteristic point are filled so that even if specially good effect main broadcaster when adding is regarding
The change of face angle and distance is there is during Pin, also can be by real time every two field picture being added specially good effect respectively, it is ensured that with reference to special
Usefulness is mated with main broadcaster face in real time.
Algorithm and display are not intrinsic to any certain computer, virtual system or miscellaneous equipment relevant provided herein.
Various general-purpose systems can also be used together with based on teaching in this.As described above, construct required by this kind of system
Structure be apparent from.Additionally, the present invention is also not for any certain programmed language.It is understood that, it is possible to use various
Programming language realizes the content of invention described herein, and the description done language-specific above is to disclose this
Bright preferred forms.
In description mentioned herein, illustrate a large amount of detail.It is to be appreciated, however, that the enforcement of the present invention
Example can be put into practice in the case of not having these details.In some instances, it is not shown specifically known method, structure
And technology, in order to do not obscure the understanding of this description.
Similarly, it will be appreciated that one or more in order to simplify that the disclosure helping understands in each inventive aspect, exist
Above in the description of the exemplary embodiment of the present invention, each feature of the present invention is grouped together into single enforcement sometimes
In example, figure or descriptions thereof.But, the method for the disclosure should not be construed to reflect an intention that i.e. required guarantor
The application claims feature more more than the feature being expressly recited in each claim protected.More precisely, as following
Claims reflected as, inventive aspect is all features less than single embodiment disclosed above.Therefore,
The claims following detailed description of the invention are thus expressly incorporated in this detailed description of the invention, the most each claim itself
All as the independent embodiment of the present invention.
Those skilled in the art are appreciated that and can carry out the module in the equipment in embodiment adaptively
Change and they are arranged in one or more equipment different from this embodiment.Can be the module in embodiment or list
Unit or assembly are combined into a module or unit or assembly, and can put them in addition multiple submodule or subelement or
Sub-component.In addition at least some in such feature and/or process or unit excludes each other, can use any
Combine all features disclosed in this specification (including adjoint claim, summary and accompanying drawing) and so disclosed appoint
Where method or all processes of equipment or unit are combined.Unless expressly stated otherwise, this specification (includes adjoint power
Profit requires, summary and accompanying drawing) disclosed in each feature can be carried out generation by providing identical, equivalent or the alternative features of similar purpose
Replace.
Although additionally, it will be appreciated by those of skill in the art that embodiments more in this include institute in other embodiments
Including some feature rather than further feature, but the combination of the feature of different embodiment means to be in the scope of the present invention
Within and form different embodiments.Such as, in the following claims, embodiment required for protection any it
One can mode use in any combination.
The all parts embodiment of the present invention can realize with hardware, or to run on one or more processor
Software module realize, or with combinations thereof realize.It will be understood by those of skill in the art that and can use in practice
Microprocessor or digital signal processor (DSP) realize in gateway according to embodiments of the present invention, proxy server, system
The some or all functions of some or all parts.The present invention is also implemented as performing side as described herein
Part or all equipment of method or device program (such as, computer program and computer program).Such
The program realizing the present invention can store on a computer-readable medium, or can have the shape of one or more signal
Formula.Such signal can be downloaded from internet website and obtain, or provides on carrier signal, or with any other shape
Formula provides.
The present invention will be described rather than limits the invention to it should be noted above-described embodiment, and ability
Field technique personnel can design alternative embodiment without departing from the scope of the appended claims.In the claims,
Any reference marks that should not will be located between bracket is configured to limitations on claims.Word " comprises " and does not excludes the presence of not
Arrange element in the claims or step.Word "a" or "an" before being positioned at element does not excludes the presence of multiple such
Element.The present invention and can come real by means of including the hardware of some different elements by means of properly programmed computer
Existing.If in the unit claim listing equipment for drying, several in these devices can be by same hardware branch
Specifically embody.Word first, second and third use do not indicate that any order.These word explanations can be run after fame
Claim.
The invention discloses, A1, a kind of face specially good effect recommend method, it is characterised in that including:
Obtain the first face feature image of user;
Obtain reference corresponding to the second face feature image identical and/or similar with described first face feature image to use
Family;
Obtaining described used with reference to specially good effect with reference to user, described reference specially good effect is used for filling face feature in use
The region to be filled that image is corresponding;
The described recommendation information with reference to specially good effect is sent to described user, selects to use described reference special for described user
Effect.
A2, according to the method described in A1, it is characterised in that described acquisition identical with described first face feature image and/
Or the reference user that similar the second face feature image is corresponding, including:
Obtain image similarity between described first face feature image and be more than the second face feature figure setting threshold value
Picture;
Obtain the reference user that described second face feature image is corresponding.
A3, according to the method described in A1, it is characterised in that described acquisition identical with described first face feature image and/
Or the reference user that similar the second face feature image is corresponding, including:
Obtain the face feature type belonging to described first face feature image;
Obtain the second face feature image identical with the face feature type belonging to described first face feature image;
Obtain the reference user that described second face feature image is corresponding.
A4, according to the method described in A1, it is characterised in that described first face feature image includes face contour image
And/or at least one organoleptic feature image in face feature.
A5, according to the arbitrary described method of A1~A4, it is characterised in that described acquisition is described with reference to the used ginseng of user
Examine specially good effect, including:
Obtain the described specially good effect using frequency to be more than setpoint frequency with reference to user as described with reference to specially good effect;Or
Obtain the described specially good effect of numerical value that sets with reference to user's access times more than first as described reference specially good effect;Or
Obtain and when described reference user uses, obtain the number of times praising and/or the receiving present specially good effect work more than the second setting numerical value
For described with reference to specially good effect.
A6, according to the arbitrary described method of A1~A4, it is characterised in that described with reference to specially good effect be: specially good effect mask or specially good effect
Ornaments.
A7, according to the arbitrary described method of A1~A4, it is characterised in that described method also includes:
Receive for selecting the described selection instruction with reference to specially good effect, be divided into M with reference to specially good effect according to preset rules by described
Specially good effect region, M is the positive integer more than 1;
Identifying N number of characteristic point of described first face feature image, N is positive integer;
According to described N number of characteristic point, according to described preset rules, described first face feature image is divided into and described M
M the image-region that specially good effect region is corresponding;
Described M specially good effect region correspondence is filled into described M image-region, forms the 3rd face feature image;
Export described 3rd face feature image.
A8, according to the method described in A7, it is characterised in that described according to described N number of characteristic point, according to described preset rules
Described first face feature image is divided into M the image-region corresponding with described M specially good effect region, specifically includes:
According to described N number of characteristic point, described first face feature image is divided into the M corresponding with described M specially good effect region
Individual image-region, wherein, described M image-region is delta-shaped region, bag in each image-region in described M image-region
The quantity of the described characteristic point included is less than or equal to 1.
A9, according to the method described in A7, it is characterised in that described described M that described M specially good effect region correspondence is filled into
Image-region, including:
Use image compression algorithm and/or image stretch algorithm, described M specially good effect region correspondence is filled into described M
Image-region, so that the form fit of the image-region that the shape in each specially good effect region is corresponding in described M specially good effect region.
The present invention also provides for, B10, a kind of electronic equipment, it is characterised in that including:
Image acquisition unit, for obtaining the first face feature image of user;
User's acquiring unit, special for obtaining second face identical and/or similar with described first face feature image
Levy the reference user that image is corresponding;
Specially good effect acquiring unit, is used for obtaining described reference user used with reference to specially good effect, and described reference specially good effect is using
Time for filling the specially good effect region that face feature image is corresponding;
Push unit, for the described recommendation information with reference to specially good effect is sent to described user, selects for described user
Use described with reference to specially good effect.
B11, according to the electronic equipment described in B10, it is characterised in that described user's acquiring unit is used for:
Obtain image similarity between described first face feature image and be more than the second face feature figure setting threshold value
Picture;
Obtain the reference user that described second face feature image is corresponding.
B12, according to the electronic equipment described in B10, it is characterised in that described user's acquiring unit is additionally operable to:
Obtain the face feature type belonging to described first face feature image;
Obtain the second face feature image identical with the face feature type belonging to described first face feature image;
Obtain the reference user that described second face feature image is corresponding.
B13, according to the electronic equipment described in B10, it is characterised in that described first face feature image includes face contour
At least one organoleptic feature image in image and/or face feature.
B14, according to the arbitrary described electronic equipment of B10~B13, it is characterised in that described specially good effect acquiring unit, be used for:
Obtain the described specially good effect using frequency to be more than setpoint frequency with reference to user as described with reference to specially good effect;Or
Obtain the described specially good effect of numerical value that sets with reference to user's access times more than first as described reference specially good effect;Or
Obtain and when described reference user uses, obtain the number of times praising and/or the receiving present specially good effect work more than the second setting numerical value
For described with reference to specially good effect.
B15, according to the arbitrary described electronic equipment of B10~B13, it is characterised in that described with reference to specially good effect be: specially good effect mask
Or specially good effect ornaments.
B16, according to the arbitrary described electronic equipment of B10~B13, it is characterised in that described electronic equipment also includes:
First division unit, for receiving for selecting the described selection instruction with reference to specially good effect, by described specially good effect according in advance
If rule is divided into M specially good effect region, M is the positive integer more than 1;
Recognition unit, for identify described first face feature image N number of characteristic point, N is positive integer;
Second division unit, for according to described N number of characteristic point, according to described preset rules by described first face feature
Image is divided into M the image-region corresponding with described M specially good effect region;
Filling unit, for described M specially good effect region correspondence being filled into described M image-region, forming the 3rd face
Characteristic image;
Output unit, is used for exporting described 3rd face feature image.
B17, according to the electronic equipment described in B16, it is characterised in that described second division unit, specifically for:
According to described N number of characteristic point, described first face feature image is divided into the M corresponding with described M specially good effect region
Individual image-region, wherein, described M image-region is delta-shaped region, bag in each image-region in described M image-region
The quantity of the described characteristic point included is less than or equal to 1.
B18, according to the electronic equipment described in B16, it is characterised in that described filling unit, be used for:
Use image compression algorithm and/or image stretch algorithm, described M specially good effect region correspondence is filled into described M
Image-region, so that the form fit of the image-region that the shape in each specially good effect region is corresponding in described M specially good effect region.
Claims (10)
1. face's specially good effect recommends method, it is characterised in that including:
Obtain the first face feature image of user;
Obtain the reference user that the second face feature image identical and/or similar with described first face feature image is corresponding;
Obtaining described used with reference to specially good effect with reference to user, described reference specially good effect is used for filling face feature image in use
Corresponding region to be filled;
The described recommendation information with reference to specially good effect is sent to described user, selects to use described reference specially good effect for described user.
2. the method for claim 1, it is characterised in that described acquisition identical with described first face feature image and/
Or the reference user that similar the second face feature image is corresponding, including:
Obtain image similarity between described first face feature image and be more than the second face feature image setting threshold value;
Obtain the reference user that described second face feature image is corresponding.
3. the method for claim 1, it is characterised in that described acquisition identical with described first face feature image and/
Or the reference user that similar the second face feature image is corresponding, including:
Obtain the face feature type belonging to described first face feature image;
Obtain the second face feature image identical with the face feature type belonging to described first face feature image;
Obtain the reference user that described second face feature image is corresponding.
4. the method for claim 1, it is characterised in that described first face feature image includes face contour image
And/or at least one organoleptic feature image in face feature.
5. the method as described in Claims 1 to 4 is arbitrary, it is characterised in that described acquisition is described with reference to the used ginseng of user
Examine specially good effect, including:
Obtain the described specially good effect using frequency to be more than setpoint frequency with reference to user as described with reference to specially good effect;Or
Obtain the described specially good effect of numerical value that sets with reference to user's access times more than first as described reference specially good effect;Or
Obtain and obtain the number of times praising and/or the receiving present specially good effect more than the second setting numerical value when described reference user uses as institute
State with reference to specially good effect.
6. the method as described in Claims 1 to 4 is arbitrary, it is characterised in that described reference specially good effect is: specially good effect mask or specially good effect decorations
Product.
7. the method as described in Claims 1 to 4 is arbitrary, it is characterised in that described method also includes:
Receive for selecting the described selection instruction with reference to specially good effect, be divided into M specially good effect with reference to specially good effect according to preset rules by described
Region, M is the positive integer more than 1;
Identifying N number of characteristic point of described first face feature image, N is positive integer;
According to described N number of characteristic point, according to described preset rules, described first face feature image is divided into and described M specially good effect
M the image-region that region is corresponding;
Described M specially good effect region correspondence is filled into described M image-region, forms the 3rd face feature image;
Export described 3rd face feature image.
8. method as claimed in claim 7, it is characterised in that described according to described N number of characteristic point, according to described preset rules
Described first face feature image is divided into M the image-region corresponding with described M specially good effect region, specifically includes:
According to described N number of characteristic point, described first face feature image is divided into M the figure corresponding with described M specially good effect region
As region, wherein, described M image-region is delta-shaped region, includes in described M image-region in each image-region
The quantity of described characteristic point is less than or equal to 1.
9. method as claimed in claim 7, it is characterised in that described that described M specially good effect region correspondence is filled into described M is individual
Image-region, including:
Use image compression algorithm and/or image stretch algorithm, described M specially good effect region correspondence is filled into described M image
Region, so that the form fit of the image-region that the shape in each specially good effect region is corresponding in described M specially good effect region.
10. an electronic equipment, it is characterised in that including:
Image acquisition unit, for obtaining the first face feature image of user;
User's acquiring unit, for obtaining the second face feature figure identical and/or similar with described first face feature image
As corresponding reference user;
Specially good effect acquiring unit, is used for obtaining described reference user used with reference to specially good effect, and described reference specially good effect is used in use
In filling the specially good effect region that face feature image is corresponding;
Push unit, for the described recommendation information with reference to specially good effect is sent to described user, selects to use for described user
Described with reference to specially good effect.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610685111.XA CN106303354B (en) | 2016-08-18 | 2016-08-18 | Face special effect recommendation method and electronic equipment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610685111.XA CN106303354B (en) | 2016-08-18 | 2016-08-18 | Face special effect recommendation method and electronic equipment |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106303354A true CN106303354A (en) | 2017-01-04 |
CN106303354B CN106303354B (en) | 2020-04-28 |
Family
ID=57679821
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610685111.XA Active CN106303354B (en) | 2016-08-18 | 2016-08-18 | Face special effect recommendation method and electronic equipment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106303354B (en) |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107862277A (en) * | 2017-11-02 | 2018-03-30 | 北京奇虎科技有限公司 | Live dress ornament, which is dressed up, recommends method, apparatus, computing device and storage medium |
CN108122029A (en) * | 2017-12-29 | 2018-06-05 | 北京奇虎科技有限公司 | A kind of recommendation method and device of camera special effect |
WO2018219120A1 (en) * | 2017-05-31 | 2018-12-06 | 腾讯科技(深圳)有限公司 | Image display method, image processing method and device, terminal and server |
CN110880155A (en) * | 2018-09-05 | 2020-03-13 | 武汉斗鱼网络科技有限公司 | Method, storage medium, device and system for realizing long leg special effect |
CN111143663A (en) * | 2018-11-02 | 2020-05-12 | 百度在线网络技术(北京)有限公司 | Information pushing method and device |
CN112118410A (en) * | 2019-06-20 | 2020-12-22 | 腾讯科技(深圳)有限公司 | Service processing method, device, terminal and storage medium |
CN112929680A (en) * | 2021-01-19 | 2021-06-08 | 广州虎牙科技有限公司 | Live broadcast room image rendering method and device, computer equipment and storage medium |
CN115146087A (en) * | 2022-09-01 | 2022-10-04 | 北京达佳互联信息技术有限公司 | Resource recommendation method, device, equipment and storage medium |
CN115396716A (en) * | 2022-08-23 | 2022-11-25 | 北京字跳网络技术有限公司 | Live video processing method, device, equipment and medium |
WO2022268133A1 (en) * | 2021-06-24 | 2022-12-29 | 北京字跳网络技术有限公司 | Template recommendation method and apparatus, device, and storage medium |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101354789A (en) * | 2008-08-22 | 2009-01-28 | 北京中星微电子有限公司 | Method and device for implementing image face mask specific effect |
CN102436668A (en) * | 2011-09-05 | 2012-05-02 | 上海大学 | Automatic Beijing Opera facial mask making-up method |
CN102456232A (en) * | 2010-10-20 | 2012-05-16 | 鸿富锦精密工业(深圳)有限公司 | Face image replacing system and method thereof |
US20120163659A1 (en) * | 2010-12-22 | 2012-06-28 | Yasuo Asakura | Imaging apparatus, imaging method, and computer readable storage medium |
US20130169839A1 (en) * | 2011-12-28 | 2013-07-04 | Canon Kabushiki Kaisha | Imaging apparatus and method for controlling the same |
CN104751408A (en) * | 2015-03-26 | 2015-07-01 | 广东欧珀移动通信有限公司 | Face image adjusting method and device |
CN105096241A (en) * | 2015-07-28 | 2015-11-25 | 努比亚技术有限公司 | Face image beautifying device and method |
-
2016
- 2016-08-18 CN CN201610685111.XA patent/CN106303354B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101354789A (en) * | 2008-08-22 | 2009-01-28 | 北京中星微电子有限公司 | Method and device for implementing image face mask specific effect |
CN102456232A (en) * | 2010-10-20 | 2012-05-16 | 鸿富锦精密工业(深圳)有限公司 | Face image replacing system and method thereof |
US20120163659A1 (en) * | 2010-12-22 | 2012-06-28 | Yasuo Asakura | Imaging apparatus, imaging method, and computer readable storage medium |
CN102436668A (en) * | 2011-09-05 | 2012-05-02 | 上海大学 | Automatic Beijing Opera facial mask making-up method |
US20130169839A1 (en) * | 2011-12-28 | 2013-07-04 | Canon Kabushiki Kaisha | Imaging apparatus and method for controlling the same |
CN104751408A (en) * | 2015-03-26 | 2015-07-01 | 广东欧珀移动通信有限公司 | Face image adjusting method and device |
CN105096241A (en) * | 2015-07-28 | 2015-11-25 | 努比亚技术有限公司 | Face image beautifying device and method |
Cited By (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2018219120A1 (en) * | 2017-05-31 | 2018-12-06 | 腾讯科技(深圳)有限公司 | Image display method, image processing method and device, terminal and server |
CN107862277A (en) * | 2017-11-02 | 2018-03-30 | 北京奇虎科技有限公司 | Live dress ornament, which is dressed up, recommends method, apparatus, computing device and storage medium |
CN108122029A (en) * | 2017-12-29 | 2018-06-05 | 北京奇虎科技有限公司 | A kind of recommendation method and device of camera special effect |
CN110880155A (en) * | 2018-09-05 | 2020-03-13 | 武汉斗鱼网络科技有限公司 | Method, storage medium, device and system for realizing long leg special effect |
CN111143663B (en) * | 2018-11-02 | 2023-08-18 | 百度在线网络技术(北京)有限公司 | Information pushing method and device |
CN111143663A (en) * | 2018-11-02 | 2020-05-12 | 百度在线网络技术(北京)有限公司 | Information pushing method and device |
CN112118410A (en) * | 2019-06-20 | 2020-12-22 | 腾讯科技(深圳)有限公司 | Service processing method, device, terminal and storage medium |
CN112118410B (en) * | 2019-06-20 | 2022-04-01 | 腾讯科技(深圳)有限公司 | Service processing method, device, terminal and storage medium |
CN112929680A (en) * | 2021-01-19 | 2021-06-08 | 广州虎牙科技有限公司 | Live broadcast room image rendering method and device, computer equipment and storage medium |
CN112929680B (en) * | 2021-01-19 | 2023-09-05 | 广州虎牙科技有限公司 | Live broadcasting room image rendering method and device, computer equipment and storage medium |
WO2022268133A1 (en) * | 2021-06-24 | 2022-12-29 | 北京字跳网络技术有限公司 | Template recommendation method and apparatus, device, and storage medium |
CN115396716A (en) * | 2022-08-23 | 2022-11-25 | 北京字跳网络技术有限公司 | Live video processing method, device, equipment and medium |
CN115396716B (en) * | 2022-08-23 | 2024-01-26 | 北京字跳网络技术有限公司 | Live video processing method, device, equipment and medium |
CN115146087A (en) * | 2022-09-01 | 2022-10-04 | 北京达佳互联信息技术有限公司 | Resource recommendation method, device, equipment and storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN106303354B (en) | 2020-04-28 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106303354A (en) | A kind of face specially good effect recommends method and electronic equipment | |
CN106302124A (en) | A kind of method adding specially good effect and electronic equipment | |
CN108176048B (en) | Image processing method and device, storage medium and electronic device | |
US10013796B2 (en) | Rendering glasses shadows | |
CN108665408A (en) | Method for regulating skin color, device and electronic equipment | |
CN112258269A (en) | Virtual fitting method and device based on 2D image | |
CN108765520B (en) | Text information rendering method and device, storage medium and electronic device | |
CN107862277A (en) | Live dress ornament, which is dressed up, recommends method, apparatus, computing device and storage medium | |
CN106030665A (en) | Creating a realistic color for a virtual object in an augmented reality environment | |
CN104902180B (en) | A kind of mobile terminal camera parameter regulation means and mobile terminal | |
CN109472851A (en) | The constructive method of 3D human visual's image and use | |
CN109409979A (en) | Virtual cosmetic method, device and equipment | |
CN106815803A (en) | The processing method and processing device of picture | |
CN107766803A (en) | Video personage based on scene cut dresss up method, apparatus and computing device | |
KR20180042359A (en) | Method and apparatus for distinguishing objects | |
CN113069763A (en) | Game role reloading method and device and electronic equipment | |
CN110414596B (en) | Video processing method, video processing device, model training method, model training device, storage medium and electronic device | |
CN106358006B (en) | The bearing calibration of video and device | |
CN108805095A (en) | image processing method, device, mobile terminal and computer readable storage medium | |
CN106303646A (en) | Method, electronic equipment and the server of a kind of specially good effect coupling | |
CN108171716A (en) | Video personage based on the segmentation of adaptive tracing frame dresss up method and device | |
CN110276657A (en) | Determination method, apparatus, storage medium and the electronic device of target object | |
CN109413461A (en) | A kind of recommended method and relevant device of direct broadcasting room | |
CN114898122A (en) | Image processing method, storage medium, and computer terminal | |
CN110781782B (en) | Face model determination method and device |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
TR01 | Transfer of patent right | ||
TR01 | Transfer of patent right |
Effective date of registration: 20220707 Address after: Room 801, 8th floor, No. 104, floors 1-19, building 2, yard 6, Jiuxianqiao Road, Chaoyang District, Beijing 100015 Patentee after: BEIJING QIHOO TECHNOLOGY Co.,Ltd. Address before: 100088 room 112, block D, 28 new street, new street, Xicheng District, Beijing (Desheng Park) Patentee before: BEIJING QIHOO TECHNOLOGY Co.,Ltd. Patentee before: Qizhi software (Beijing) Co.,Ltd. |