CN110084709A - Good friend's processing method, server and computer-readable medium based on facial characteristics - Google Patents

Good friend's processing method, server and computer-readable medium based on facial characteristics Download PDF

Info

Publication number
CN110084709A
CN110084709A CN201810064076.9A CN201810064076A CN110084709A CN 110084709 A CN110084709 A CN 110084709A CN 201810064076 A CN201810064076 A CN 201810064076A CN 110084709 A CN110084709 A CN 110084709A
Authority
CN
China
Prior art keywords
target
face
good friend
facial image
request user
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN201810064076.9A
Other languages
Chinese (zh)
Inventor
彭祥帅
范天航
熊雷
杨静
徐迎迎
尹家庆
田征绿
胡磊
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shanghai Youyang New Media Information Technology Co ltd
Original Assignee
Beijing Baidu Netcom Science and Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Beijing Baidu Netcom Science and Technology Co Ltd filed Critical Beijing Baidu Netcom Science and Technology Co Ltd
Priority to CN201810064076.9A priority Critical patent/CN110084709A/en
Publication of CN110084709A publication Critical patent/CN110084709A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
    • G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
    • G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
    • 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
    • G06Q50/01—Social networking
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G06V40/161—Detection; Localisation; Normalisation
    • G06V40/165—Detection; Localisation; Normalisation using facial parts and geometric relationships
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G06V40/168—Feature extraction; Face representation
    • G06V40/171—Local features and components; Facial parts ; Occluding parts, e.g. glasses; Geometrical relationships
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/40—Spoof detection, e.g. liveness detection
    • G06V40/45—Detection of the body part being alive

Abstract

The present invention provides a kind of good friend's processing method, server and computer-readable medium based on facial characteristics.Its method includes: to receive the stranger's inquiry request for the carrying target face feature that request user client is sent；According to target face feature and the friend information of request user, candidate face images that be not belonging to request user good friend, several are obtained from face database gathered in advance；Recommend several candidate face images to request user client.Using technical solution of the present invention, it may be implemented to carry out friend recommendation based on facial characteristics, overcome the recommendation for realizing good friend according only to interest or geographical location in the prior art, cause friend recommendation mode more inflexible, inflexible technological deficiency, so as to effectively enrich the function of the friend recommendation mode in social application, so that friend recommendation mode is more intelligent.And technical solution of the present invention, can direct commending friends facial image, friend recommendation mode is very intuitive, clear.

Description

Good friend's processing method, server and computer-readable medium based on facial characteristics
[technical field]
The present invention relates to computer application technology more particularly to a kind of good friend's processing method based on facial characteristics, Server and computer-readable medium.
[background technique]
As internet continues the development of blowout, as emerging rapidly in large numbersBamboo shoots after a spring rain, layer goes out more and more social application softwares It is not poor.Internet social activity field is made a general survey of, the scale of construction of either comprehensive or vertical disaggregated classification, each classification is gradually increasing It is more；Especially nearly 2 years social application industry market scales are by Continued.
Present people are often general that social activity is divided into acquaintance's social activity, stranger's social activity when talking about social activity, wherein acquaintance Social user viscosity is big, mainly wechat, QQ, everybody etc..Stranger's social application is more, including Baidu's discussion bar, microblogging, footpath between fields Footpath between fields, know, bean cotyledon etc..In social application in the prior art, the social interest that currently relies primarily on of stranger carrys out mutual plusing good friend.Example Interested stranger is such as speculated according to the search content of user, to form friend relation, such as discussion bar, bean cotyledon and is known It is all made of the relevant technologies.In the prior art, there are also one kind establishes friend relation, such as basis based on geographical location for stranger Neighbouring strange good friend is recommended in geographical location, to become good friend.
But existing friend recommendation mode is that social application server realizes good friend according to interest or geographical location Recommendation, cause friend recommendation mode more inflexible, it is inflexible.
[summary of the invention]
The present invention provides a kind of good friend's processing method, server and computer-readable medium based on facial characteristics, use In abundant friend recommendation mode, the intelligence of friend recommendation mode is improved.
The present invention provides a kind of good friend's processing method based on facial characteristics, which comprises
Receive the stranger's inquiry request for the carrying target face feature that request user client is sent；
According to the target face feature and the friend information of the request user, obtained from face database gathered in advance Take candidate face images that be not belonging to the request user good friend, several；
Recommend several candidate face images to the request user client.
Still optionally further, in method as described above, according to the target face feature and the request user Friend information, obtained from face database gathered in advance be not belonging to the request user good friend, several candidate face images it Before, the method also includes:
When each registration user, which opens the good friend based on facial characteristics, adds function, the face of each registration user is acquired Image；
Each facial image for registering user is verified whether as living body faces image；
If so, by the face database is stored in by the facial image of the registration user of verifying.
Still optionally further, in method as described above, recommend several candidates to the request user client After face image, the method also includes:
Receive the addition good friend request of the facial image for the carrying target good friend that the request user client is initiated； The addition good friend request is that the user for requesting user client selection target from several candidate face images is good It is initiated after the facial image of friend；
The facial image of the request user is obtained from the face database；
The addition good friend request for carrying the facial image of the request user is sent to the client of the target good friend；
After the user of the target good friend agrees to addition, the request user and the target good friend are mutually added For good friend.
Still optionally further, in method as described above, according to the target face feature and the request user Friend information obtains candidate face images that be not belonging to the request user good friend, several, tool from face database gathered in advance Body includes:
According to the target face feature, is obtained from the face database and meet all alternative of the target face feature Facial image；
According to it is described request user and it is described request user friend information, obtain it is described request user facial image and The facial image of the good friend of the request user；
According to the facial image of the facial image of the request user and the good friend of the request user, to described all standby Face image of choosing is filtered, and obtains multiple alternative facial images；
Filtered out from all alternative facial images it is described request user facial image and it is described request user it is good The facial image of friend, obtains multiple alternative facial images；
Several candidate face images are obtained from the multiple alternative facial image.
Still optionally further, in method as described above, several times are obtained from the multiple alternative facial image It chooses face image, specifically includes:
Obtain several candidate face images at random from the multiple alternative facial image；
Alternatively, being obtained from the good friend of the request user special by face according to the friend information of the request user Levy the target good friend of addition；The facial image of the target good friend is obtained from the face database；Calculate each alternative face The image similarity with the facial image of the target good friend respectively；According to each alternative facial image respectively with the target The similarity of the facial image of good friend obtains the high several alternative faces of similarity from the multiple alternative facial image Image, as several candidate face images.
Still optionally further, in method as described above, if the target face feature include target eye feature or Target mouth feature, according to the target face feature and the friend information of the request user, from face gathered in advance Candidate face images that be not belonging to the request user good friend, several are obtained in library, are specifically included:
According to the target eye feature and the friend information of the request user, acquisition and institute from the face database It states target eye feature unanimously and is not belonging to several candidate face images of the request user good friend；
Or it according to the target mouth feature and the friend information of the request user, is obtained from the face database Several candidate face images that are consistent with the target mouth feature and being not belonging to the request user good friend.
Still optionally further, in method as described above, if the target face feature includes target bridge of the nose feature, according to The friend information of the target face feature and the request user, obtain from face database gathered in advance described in being not belonging to Request user good friend, several candidate face image, specifically includes:
Using bridge of the nose feature identification model trained in advance, the bridge of the nose of each facial image in the face database is marked Feature；
According to the bridge of the nose feature of each facial image in the target bridge of the nose feature, the face database and described ask The friend information for asking user obtains consistent with the target bridge of the nose feature from the face database and is not belonging to the request use Several candidate face images of family good friend；
If the target face feature includes target features of skin colors, according to the target face feature, from gathered in advance Several candidate face images are obtained in face database, are specifically included:
Using features of skin colors identification model trained in advance, the colour of skin of each facial image in the face database is marked Feature；
According to the features of skin colors of each facial image in the target features of skin colors, the face database and described ask The friend information for asking user obtains consistent with the target features of skin colors from the face database and is not belonging to the request use Several candidate face images of family good friend.
The present invention provides a kind of social application server, and the server includes:
Receiving module, stranger's inquiry for receiving the carrying target face feature that request user client is sent are asked It asks；
Module is obtained, for the friend information according to the target face feature and the request user, is adopted from advance Candidate face images that be not belonging to the request user good friend, several are obtained in the face database of collection；
Sending module, for recommending several candidate face images to the request user client；
The face database, for storing the face of all registration users for opening good friend's addition function based on facial characteristics Image.
Still optionally further, in server as described above, the server further include:
Acquisition module, for when each registration user opens the good friend based on facial characteristics and adds function, acquisition to be each The facial image of the registration user；
Authentication module, for whether verifying each facial image for registering user as living body faces image；
The facial image of memory module, the registration user for that will be verified by the authentication module is stored in the people Face library.
Still optionally further, in server as described above, the server further includes adding module；
The receiving module is also used to receive the face for the carrying target good friend that the request user client is initiated The addition good friend of image requests；The addition good friend request is the user of the request user client from several candidates It is initiated after the facial image of selection target good friend in face image；
The acquisition module is also used to obtain the facial image of the request user from the face database；
The sending module is also used to send the face figure for carrying the request user to the client of the target good friend The addition good friend of picture requests；
The adding module, for the user of the target good friend agree to addition after, by the request user and institute Target good friend is stated to be mutually added as good friend.
Still optionally further, in server as described above, the acquisition module is specifically used for:
According to the target face feature, is obtained from the face database and meet all alternative of the target face feature Facial image；
According to it is described request user and it is described request user friend information, obtain it is described request user facial image and The facial image of the good friend of the request user；
According to the facial image of the facial image of the request user and the good friend of the request user, to described all standby Face image of choosing is filtered, and obtains multiple alternative facial images；
Filtered out from all alternative facial images it is described request user facial image and it is described request user it is good The facial image of friend, obtains multiple alternative facial images；
Several candidate face images are obtained from the multiple alternative facial image.
Still optionally further, in server as described above, the acquisition module is specifically used for:
Obtain several candidate face images at random from the multiple alternative facial image；
Alternatively, being obtained from the good friend of the request user special by face according to the friend information of the request user Levy the target good friend of addition；The facial image of the target good friend is obtained from the face database；Calculate each alternative face The image similarity with the facial image of the target good friend respectively；According to each alternative facial image respectively with the target The similarity of the facial image of good friend obtains the high several alternative faces of similarity from the multiple alternative facial image Image, as several candidate face images.
Still optionally further, in server as described above, if the target face feature includes target eye feature, institute Acquisition module is stated, specifically for the friend information according to the target eye feature and the request user, from the face Several candidate face figures that are consistent with the target eye feature and being not belonging to the request user good friend are obtained in library Picture；
If the target face feature includes target mouth feature, the acquisition module is specifically used for according to the target Mouth feature and it is described request user friend information, from the face database obtain it is consistent with the target mouth feature, And it is not belonging to several candidate face images of the request user good friend.
Still optionally further, in server as described above, if the target face feature includes target bridge of the nose feature, institute Acquisition module is stated, is specifically used for:
Using bridge of the nose feature identification model trained in advance, the bridge of the nose of each facial image in the face database is marked Feature；
According to the bridge of the nose feature of each facial image in the target bridge of the nose feature, the face database and described ask The friend information for asking user obtains consistent with the target bridge of the nose feature from the face database and is not belonging to the request use Several candidate face images of family good friend；
If the target face feature includes target features of skin colors, the acquisition module is specifically used for:
Using features of skin colors identification model trained in advance, the colour of skin of each facial image in the face database is marked Feature；
According to the features of skin colors of each facial image in the target features of skin colors, the face database and described ask The friend information for asking user obtains consistent with the target features of skin colors from the face database and is not belonging to the request use Several candidate face images of family good friend.
The present invention also provides a kind of computer equipment, the equipment includes:
One or more processors；
Memory, for storing one or more programs；
When one or more of programs are executed by one or more of processors, so that one or more of processing Device realizes good friend's processing method based on facial characteristics as described above.
The present invention also provides a kind of computer-readable mediums, are stored thereon with computer program, which is held by processor Information processing method as described above is realized when row.
Good friend's processing method, server and computer-readable medium based on facial characteristics of the invention is asked by receiving The stranger's inquiry request for the carrying target face feature for asking user client to send；It is used according to target face feature and request The friend information at family obtains candidate face images that be not belonging to request user good friend, several from face database gathered in advance；To User client is requested to recommend several candidate face images.Using technical solution of the present invention, may be implemented based on facial characteristics Friend recommendation is carried out, the recommendation for realizing good friend according only to interest or geographical location in the prior art is overcome, leads to good friend The way of recommendation is more inflexible, inflexible technological deficiency, so as to effectively enrich the friend recommendation side in social application The function of formula, so that friend recommendation mode is more intelligent.And technical solution of the present invention, can directly commending friends people Face image, friend recommendation mode is very intuitive, clear, can effectively improve the using experience degree of user.
[Detailed description of the invention]
Fig. 1 is the flow chart of good friend's processing method embodiment one of the invention based on facial characteristics.
Fig. 2 is the flow chart of good friend's processing method embodiment two of the invention based on facial characteristics.
Fig. 3 is the structure chart of social application server example one of the invention.
Fig. 4 is the structure chart of social application server example two of the invention.
Fig. 5 is the structure chart of computer equipment embodiment of the invention.
Fig. 6 is a kind of exemplary diagram of computer equipment provided by the invention.
[specific embodiment]
To make the objectives, technical solutions, and advantages of the present invention clearer, right in the following with reference to the drawings and specific embodiments The present invention is described in detail.
Fig. 1 is the flow chart of good friend's processing method embodiment one of the invention based on facial characteristics.As shown in Fig. 1, this Good friend's processing method based on facial characteristics of embodiment, can specifically include following steps:
100, the stranger's inquiry request for the carrying target face feature that request user client is sent is received；
The application scenarios of good friend's processing method based on facial characteristics of the present embodiment are as follows: in various social applications, use When family is wanted to add good friend from stranger, the interest that can only get server recommendation is similar or position is closer strange People, and good friend to be added is selected from the stranger of recommendation.And some users are more special to the facial characteristics requirement of good friend, For example, some users think that good friend to be added is that double-edged eyelid, Roman nose, the colour of skin are whiter etc., and these pass through existing good friend Good friend's addition that the way of recommendation is realized all is unable to satisfy the requirement of user.Based on this problem, the embodiment of the present invention provides a kind of intelligence Good friend's processing method based on facial characteristics of energyization, the executing subject for being somebody's turn to do good friend's processing method based on facial characteristics can be The server of social application, to realize friend recommendation and the subsequent good friend's addition processing based on facial characteristics.
In the present embodiment, social application is had registered, and any one user of social application client is installed, can be led to It crosses the client that it is used and sends stranger's inquiry request to social application server.It for ease of description, will in the present embodiment The user for issuing stranger's inquiry request is known as requesting user.Certainly, it is used to identify stranger's inquiry request as the request What family was sent, the mark of request user can also be carried in stranger's inquiry request.
The request user of the present embodiment can carry the mesh for wanting the stranger of inquiry when issuing stranger's inquiry request Mark facial characteristics.The target face feature of the present embodiment can in people's face portion some, two or more features, example The position of eye, nose, the colour of skin, mouth face can be such as defined.Such as in practical application, certain user is to strange The eyelid feature of people has particular preferences, and the target eye feature that can be limited can be double-edged eyelid or single-edge eyelid.Also some are used The stranger grinningly to smile is liked at family, and some users like reserved, usually habitual movement will not stranger grinningly, because This can limit target mouth feature by tooth, such as target mouth feature may include grinningly and not grinningly.For another example having A little users like the stranger of Roman nose, and some users can not have bridge of the nose requirement, and therefore, the target bridge of the nose that can be limited is special Sign can be Roman nose or non-Roman nose.Or for another example also some users can be to good in social application in practical application The colour of skin of friend has particular/special requirement, and the stranger that some users like adding casting skin is good friend, and some users like adding white skin The stranger of skin or yellow skin is good friend.The above is only the citings of partial target facial characteristics defined by the present invention, practical In, target face feature may include having cheekbone, shape of face, eyebrow etc. facial characteristics, and no longer citing repeats one by one herein. And in use, target face feature may include at least one of features above.
101, it according to target face feature and the friend information of request user, is obtained not from face database gathered in advance Belong to candidate face images that request user good friend, several；
Due to the information of social application server each registration user good at managing and its good friend, such as the good friend that it includes Identify (such as account) and gender, age, contact method, the hobby essential information of good friend.Social application server can root According to facial characteristics and the friend information of request user, is obtained from face database gathered in advance and be not belonging to request user good friend , several candidate face images.
For example, the face database gathered in advance in the present embodiment can specifically be generated using following steps:
(a1) when each registration user, which opens the good friend based on facial characteristics, adds function, the face of each registration user is acquired Image；
(b1) whether each facial image for registering user is verified as living body faces image；If so, the registration of verifying will be passed through The facial image of user is stored in face database；Otherwise, the unverified facial image for registering user is non-living body facial image When, face database cannot be stored.
That is, in social application, if registration user wants to add function using the good friend based on facial characteristics, Registration user must agree to the facial image of social application collection of server registration user.In addition, social application server Whether the face for also needing to verify acquisition is living body faces image, and that store in the face database to guarantee acquisition is all registration user Real human face.Wherein the verification process of living body faces image can use related art, for example, can be used by instruction The face that the face at family completes specified operation to verify user is the verification operation of the living body faces such as living body faces.Pass through above-mentioned behaviour Make, can store the facial image for opening all registration users of good friend's addition function based on facial characteristics in face database.
Still optionally further, the step 101 of the present embodiment can specifically include following steps:
(a2) according to target face feature, all alternative face figures for meeting target face feature are obtained from face database Picture；
(b2) according to the friend information of request user and request user, the facial image of acquisition request user and request user Good friend facial image；
(c2) according to the facial image of the facial image of request user and the good friend of request user, to all alternative face figures As being filtered, multiple alternative facial images are obtained；
In the present embodiment, first according to target face feature, is obtained from face database and all meet target face feature Alternative facial image.Due to may include in all alternative facial images of acquisition request user facial image and The facial image of the good friend of request user.It therefore is all the face figure of stranger in the alternative facial image in order to guarantee acquisition Picture needs the facial image of the good friend of the facial image and request user using request user in the present embodiment, to all alternative Facial image is filtered, and obtains multiple alternative facial images.Specifically, whether detect in all alternative facial images includes asking The facial image of user is sought, if including, the facial image of removal request user from all alternative facial images；Further detection It whether include the facial image for requesting the good friend of user in remaining all alternative facial images, if including, removal request user Good friend facial image, finally obtain multiple alternative facial images.
(d2) several candidate face images are obtained from multiple alternative facial images.
The quantity of several candidate face images of the present embodiment can be set to 10,15,20 or other quantity It is a.If the facial image quantity in face database is more, for example, it is thousands of a when, multiple alternative facial images of acquisition Quantity may be hundreds and thousands of.In addition, if under special screne, when as less such as the facial image in face database, if what is obtained is multiple The quantity of several candidate face images of the lazy weight setting of alternative facial image, at this time can be directly by multiple alternative faces Image is all used as candidate face image.
For example, the step (d2) can specifically include the following two kinds mode:
First way: several candidate face images are obtained at random from multiple alternative facial images；
The implementation of this kind of mode is relatively simple, if the quantity of the multiple alternative facial images obtained is more, if will When all alternative facial images obtained all recommend the client of request user, the experience that will cause user is poor.Therefore, may be used Therefrom to obtain several candidate face images at random.
The second way: it according to the friend information of request user, is obtained from the good friend of request user and passes through facial characteristics The target good friend of addition；The facial image of target good friend is obtained from face database；Calculate each alternative facial image respectively with target The similarity of the facial image of good friend；According to each alternative facial image similarity with the facial image of target good friend respectively, from The high several alternative facial images of similarity are obtained in multiple alternative facial images, as several candidate face images.
When the second way is realized, several candidate face images can be more targetedly obtained.For example, can first divide The good friend of request user is analysed, the mark of the target good friend added by facial characteristics is obtained, further according to the mark of target good friend The facial image of target good friend is obtained from face database.In the present embodiment, it is believed that the facial image of target good friend is request The appearance for the stranger that user prefers.The facial image that may then based on target good friend, from multiple alternative facial images It is middle to obtain several candidate face images.Specifically, if the facial image of target good friend has multiple, each alternative face is calculated The image similarity with the facial image of multiple target good friends respectively, and be averaged, it is good as the alternative facial image and target The similarity of friend's face image.By the above-mentioned means, available each alternative face figure into multiple alternative facial images As corresponding similarity, and the sequence according to similarity from high to low, the high several alternative facial images of similarity are therefrom obtained, As several candidate face images.In this manner it is ensured that the several candidate face images obtained most possibly meet request user Hobby, requested user is added to good friend.So the second way is realized more intelligent relative to first way.
102, recommend several candidate face images to request user client.
According to above-described embodiment, after getting several candidate face images, number can be sent to request user client A candidate face image intelligently carries out friend recommendation based on facial characteristics realization to realize.The technical side of the present embodiment Case, to request user client it is recommended that several candidate face images, the way of recommendation is very intuitive, request user may be intuitive Several candidate face images of recommendation are seen on ground, and therefrom select one, two or more facial images pair oneself liked The user answered is as good friend.Therefore, good friend's processing method based on facial characteristics of the present embodiment is very intelligent.
The processing of several target face features of the present embodiment is described below:
The first: if target face feature includes target eye feature, for example, target eye feature can for double-edged eyelid or Person's single-edge eyelid feature.Wherein double-edged eyelid feature or single-edge eyelid feature can pass through the eyes of the facial image in detection face database The lines of the eyelid of top determine.
Accordingly step 101 " according to target face feature and requests the friend information of user, from gathered in advance at this time Candidate face images that be not belonging to request user good friend, several are obtained in face database ", it can specifically include: according to target eye Feature and the friend information for requesting user obtain consistent with target eye feature from face database and are not belonging to request user Several candidate face images of good friend；Specific implementation can refer to the realization of above-mentioned steps (a2)-(d2), no longer superfluous herein It states.
Second: if target face feature includes target mouth feature, such as target mouth feature may include grinningly and Two kinds of features of tooth are not leaked；The two features can by detection face database in facial image in mouth part whether grinningly come It obtains.
Accordingly step 101 " according to target face feature and requests the friend information of user, from gathered in advance at this time Candidate face images that be not belonging to request user good friend, several are obtained in face database ", it can specifically include: according to target mouth Feature and the friend information for requesting user obtain consistent with target mouth feature from face database and are not belonging to request user Several candidate face images of good friend.Specific implementation can refer to the realization of above-mentioned steps (a2)-(d2), no longer superfluous herein It states.
The third: if target face feature includes target bridge of the nose feature, such as target bridge of the nose feature may include Roman nose Or non-Roman nose.The Roman nose of the present embodiment and non-Roman nose can be known by bridge of the nose feature identification model trained in advance Not.
Accordingly step 101 " according to target face feature and requests the friend information of user, from gathered in advance at this time Candidate face images that be not belonging to request user good friend, several are obtained in face database ", it can specifically include: using training in advance Bridge of the nose feature identification model, mark face database in each facial image bridge of the nose feature；According to target bridge of the nose feature, face database In each facial image bridge of the nose feature and request user friend information, from face database obtain with target bridge of the nose feature one Cause and be not belonging to several candidate face images of request user good friend.
It, can be in advance using several facial images for being labelled with Roman nose and non-Roman nose in the technical solution of the present embodiment Facial image bridge of the nose feature identification model is trained, enable training after bridge of the nose feature identification model to any people Bridge of the nose feature in face image is identified.Then, according to the bridge of the nose feature identification model after training to each one in face database The bridge of the nose feature of face image is identified.For example, the bridge of the nose feature identification model after training can identify the nose of each facial image Beam feature is the probability of Roman nose or the probability of non-Roman nose, and then the high bridge of the nose as the facial image of select probability is special Sign.Then according to the bridge of the nose feature of each facial image in target bridge of the nose feature, face database and request user friend information, Several candidate face images that are consistent with target bridge of the nose feature and being not belonging to request user good friend, tool are obtained from face database Body implementation can refer to the realization of above-mentioned steps (a2)-(d2), and details are not described herein.
4th kind: if target face feature includes target features of skin colors, such as there are two types of target features of skin colors can be set, White and non-white perhaps may be arranged as three kinds: white, black and its allochromatic colour may be arranged as other points Class such as black and non-black, no longer citing repeats one by one herein.
Accordingly step 101 " according to target face feature and requests the friend information of user, from gathered in advance at this time Candidate face images that be not belonging to request user good friend, several are obtained in face database ", it can specifically include: using training in advance Features of skin colors identification model, mark face database in each facial image features of skin colors；According to target features of skin colors, face database In each facial image features of skin colors and request user friend information, from face database obtain with target features of skin colors one Cause and be not belonging to several candidate face images of request user good friend.
It similarly, can also be in advance using several facial images for being labelled with the colour of skin to skin in the technical solution of the present embodiment Color characteristic identification model is trained, and enables the features of skin colors identification model after training to the colour of skin in any facial image Feature is identified.For example, the features of skin colors identification model after training can identify that the features of skin colors of each facial image is all kinds of The probability of the colour of skin is preset, then features of skin colors of the high default colour of skin of select probability as the facial image.Wherein preset the colour of skin The colour of skin of the facial image mark of training when as training.Then, the implementation of above-mentioned steps (a2)-(d2) can be referred to, It realizes the features of skin colors according to each facial image in target features of skin colors, face database and requests the friend information of user, from Several candidate face images that are consistent with target features of skin colors and being not belonging to request user good friend are obtained in face database, herein not It repeats again.
Good friend's processing method based on facial characteristics of the present embodiment receives the carrying target that request user client is sent Stranger's inquiry request of facial characteristics；According to target face feature and the friend information of user is requested, from gathered in advance Candidate face images that be not belonging to request user good friend, several are obtained in face database；Recommend several times to request user client It chooses face image.Using the technical solution of the present embodiment, it may be implemented to carry out friend recommendation based on facial characteristics, overcome existing The recommendation for realizing good friend in technology according only to interest or geographical location, causes friend recommendation mode more inflexible, not clever enough Technological deficiency living, so as to effectively enrich the function of the friend recommendation mode in social application, so that friend recommendation side Formula is more intelligent.And the technical solution of the present embodiment, can direct commending friends facial image, friend recommendation mode is non- It is Chang Zhiguan, clear, the using experience degree of user can be effectively improved.
Fig. 2 is the flow chart of good friend's processing method embodiment two of the invention based on facial characteristics.Shown in above-mentioned Fig. 1 Good friend's processing method based on facial characteristics only describes the friend recommendation scheme based on facial characteristics, as shown in Fig. 2, this implementation Good friend's processing method based on facial characteristics of example is completely situated between on the basis of the technical solution of above-mentioned embodiment illustrated in fig. 1 Continued a kind of good friend's addition scheme based on facial characteristics.As shown in Fig. 2, at the good friend based on facial characteristics of the present embodiment Reason method, can specifically include following steps:
200, the stranger's inquiry request for the carrying target face feature that request user client is sent is received；
201, it according to target face feature and the friend information of request user, is obtained not from face database gathered in advance Belong to candidate face images that request user good friend, several；
202, recommend several candidate face images to request user client；
The implementation of above-mentioned steps 200-202 can refer to the record of above-mentioned embodiment illustrated in fig. 1 in detail, no longer superfluous herein It states.
203, the addition good friend request of the facial image for the carrying target good friend that request user client is initiated is received；This adds Plusing good friend request is the user of request user client after the facial image of selection target good friend in several candidate face images It initiates；
204, from face database acquisition request user facial image；
205, the addition good friend request for carrying the facial image of request user is sent to the client of target good friend；
206, after the user of target good friend agrees to addition, request user and target good friend are mutually added as good friend.
On the basis of the technical solution of above-mentioned embodiment illustrated in fig. 1, recommend several candidates to request user client After face image, request user can see several candidate faces that social application server is recommended from the client of request user Then image requests user that any one can therefrom be selected to have the application of eyes-affinity to add good friend.It is chosen when request user clicks When some candidate face image, the face that request user chooses the candidate face image as target good friend to be added is indicated Image.Then request user selects addition good friend, is just equivalent to the face for initiating to carry target good friend to social application server The addition good friend of image requests.Certainly since addition good friend request is that request user issues, in addition good friend request also The mark of request user can be carried.Then social application server also needs to obtain from face database according to the mark of request user Take the facial image of request user.Then social application server sends to the client of target good friend and carries request user's The addition good friend of facial image requests；Corresponding, target good friend can see request addition in its client, and it is good friend's The facial image of user is requested, if target good friend thinks that request user has eyes-affinity, agrees to plus it is good friend, click and agree to, Server receive target good friend client send agreement addition after, will request user and target good friend be mutually added for Good friend.Then target good friend just enters in the buddy list of request user, and request user also enters the buddy list of target good friend In, request user and target good friend to can be used as good friend and chat.
Good friend's processing method based on facial characteristics of the present embodiment may be implemented to carry out friend recommendation based on facial characteristics And addition, the friend recommendation mode and good friend's addition manner in social application can be effectively enriched, so that friend recommendation and adding Add mode is more intelligent.And the technical solution of the present embodiment, friend recommendation and addition are all based on face head portrait to realize, Whole process is very intuitive, clear, can effectively improve the using experience degree of user.
Fig. 3 is the structure chart of social application server example one of the invention.As shown in figure 3, the social activity of the present embodiment Application server can specifically include:
Stranger's inquiry that receiving module 10 is used to receive the carrying target face feature that request user client is sent is asked It asks；
Obtain module 11 be used for according in the received stranger's inquiry request of receiving module 10 target face feature and The friend information for requesting user obtains candidate faces that be not belonging to request user good friend, several from face database M gathered in advance Image；
Sending module 12 is used to recommend to obtain several candidate face images that module 11 obtains to request user client；
Face database M is used to store the face figure of all registration users for opening good friend's addition function based on facial characteristics Picture.
The social application server of the present embodiment realizes good friend's processing based on facial characteristics by using above-mentioned module Realization principle and technical effect are identical as the realization of above-mentioned related method embodiment, in detail can be real with reference to above-mentioned correlation technique The record of example is applied, details are not described herein.
Fig. 4 is the structure chart of social application server example two of the invention.As shown in figure 4, the social activity of the present embodiment Application server further can also include following technical side on the basis of the technical solution of above-mentioned embodiment illustrated in fig. 3 Case.
As shown in figure 4, the social application server of the present embodiment, further includes:
Acquisition module 13 is used to acquire each registration when each registration user opens the good friend based on facial characteristics and adds function The facial image of user；
Whether authentication module 14 is for verifying each facial image for registering user as living body faces image；
Memory module 15 will be for that will be stored in face database M by the facial image for the registration user that authentication module is verified.
It still optionally further, further include adding module 16 as shown in figure 4, in the social application server of the present embodiment；
Receiving module 10 is also used to receive the addition of the facial image for the carrying target good friend that request user client is initiated Good friend's request；Good friend's request is added to request the user of user client selection target good friend from several candidate face images It is initiated after facial image；
Module 11 is obtained to be also used to obtain asking for the received addition good friend request promoter of receiving module 10 from face database M Seek the facial image of user；
Sending module 12, which is also used to send to the client of target good friend, carries the request user's for obtaining that module 11 obtains The addition good friend of facial image requests；
Adding module 13 is used for after the user of target good friend agrees to addition, and request user and target good friend are added mutually It adds as a friend.
Still optionally further, it in the social application server of the present embodiment, obtains module 11 and is specifically used for:
According to target face feature, all alternative facial images for meeting target face feature are obtained from face database；
According to request user and request the friend information of user, the facial image of acquisition request user and request user's is good The facial image of friend；
According to request user facial image and request user good friend facial image, to all alternative facial images into Row filtering, obtains multiple alternative facial images；
The facial image of the facial image of request user and the good friend of request user is filtered out from all alternative facial images, Obtain multiple alternative facial images；
Several candidate face images are obtained from multiple alternative facial images.
Still optionally further, it in the social application server of the present embodiment, obtains module 11 and is specifically used for:
Obtain several candidate face images at random from multiple alternative facial images；
Alternatively, acquisition is added by facial characteristics from the good friend of request user according to the friend information of request user Target good friend；The facial image of target good friend is obtained from face database；Each alternative facial image is calculated respectively with target good friend's The similarity of facial image；According to each alternative facial image similarity with the facial image of target good friend respectively, from multiple standby The high several alternative facial images of similarity are obtained in face image of choosing, as several candidate face images.
Still optionally further, in the social application server of the present embodiment, if target face feature includes target eye spy Sign, obtain module 11 be specifically used for according to target eye feature and request user friend information, from face database obtain with Target eye feature is consistent and is not belonging to several candidate face images of request user good friend；
If target face feature includes target mouth feature, obtain module 11 be specifically used for according to target mouth feature and The friend information for requesting user obtains number that is consistent with target mouth feature and being not belonging to request user good friend from face database A candidate face image.
Still optionally further, in the social application server of the present embodiment, if target face feature includes that the target bridge of the nose is special Sign obtains module 11 and is specifically used for:
Using bridge of the nose feature identification model trained in advance, the bridge of the nose feature of each facial image in face database is marked；
According to the bridge of the nose feature of each facial image in target bridge of the nose feature, face database and the good friend of user is requested to believe Breath obtains several candidate face images that are consistent with target bridge of the nose feature and being not belonging to request user good friend from face database；
If target face feature includes target features of skin colors, obtains module 11 and is specifically used for:
Using features of skin colors identification model trained in advance, the features of skin colors of each facial image in face database is marked；
According to the features of skin colors of each facial image in target features of skin colors, face database and the good friend of user is requested to believe Breath obtains several candidate face images that are consistent with target features of skin colors and being not belonging to request user good friend from face database.
The social application server of the present embodiment realizes good friend's processing based on facial characteristics by using above-mentioned module Realization principle and technical effect are identical as the realization of above-mentioned related method embodiment, in detail can be real with reference to above-mentioned correlation technique The record of example is applied, details are not described herein.
Fig. 5 is the structure chart of computer equipment embodiment of the invention.As shown in figure 5, the computer equipment of the present embodiment, It include: one or more processors 30 and memory 40, memory 40 works as memory for storing one or more programs The one or more programs stored in 40 are executed by one or more processors 30, so that one or more processors 30 are realized Such as good friend's processing method based on facial characteristics of attached drawing 1- embodiment illustrated in fig. 2.To include multiple places in embodiment illustrated in fig. 5 For reason device 30.The computer equipment of the present embodiment can be used as the server apparatus of social application.
For example, Fig. 6 is a kind of exemplary diagram of computer equipment provided by the invention.Fig. 6, which is shown, to be suitable for being used to realizing this The block diagram of the exemplary computer device 12a of invention embodiment.The computer equipment 12a that Fig. 6 is shown is only an example, Should not function to the embodiment of the present invention and use scope bring any restrictions.Similarly, computer equipment shown in fig. 6 can be used Do the server apparatus of social application.
As shown in fig. 6, computer equipment 12a is showed in the form of universal computing device.The component of computer equipment 12a Can include but is not limited to: one or more processor 16a, system storage 28a, connecting different system components (including is Unite memory 28a and processor 16a) bus 18a.
Bus 18a indicates one of a few class bus structures or a variety of, including memory bus or Memory Controller, Peripheral bus, graphics acceleration port, processor or the local bus using any bus structures in a variety of bus structures.It lifts For example, these architectures include but is not limited to industry standard architecture (ISA) bus, microchannel architecture (MAC) Bus, enhanced isa bus, Video Electronics Standards Association (VESA) local bus and peripheral component interconnection (PCI) bus.
Computer equipment 12a typically comprises a variety of computer system readable media.These media can be it is any can The usable medium accessed by computer equipment 12a, including volatile and non-volatile media, moveable and immovable Jie Matter.
System storage 28a may include the computer system readable media of form of volatile memory, such as deposit at random Access to memory (RAM) 30a and/or cache memory 32a.Computer equipment 12a may further include other removable Dynamic/immovable, volatile/non-volatile computer system storage medium.Only as an example, storage system 34a can be used In reading and writing immovable, non-volatile magnetic media (Fig. 6 do not show, commonly referred to as " hard disk drive ").Although not showing in Fig. 6 Out, the disc driver for reading and writing to removable non-volatile magnetic disk (such as " floppy disk ") can be provided, and to removable The CD drive of anonvolatile optical disk (such as CD-ROM, DVD-ROM or other optical mediums) read-write.In these cases, Each driver can be connected by one or more data media interfaces with bus 18a.System storage 28a may include At least one program product, the program product have one group of (for example, at least one) program module, these program modules are configured To execute the function of the above-mentioned each embodiment of Fig. 1-Fig. 4 of the present invention.
Program with one group of (at least one) program module 42a/utility 40a, can store and deposit in such as system In reservoir 28a, such program module 42a include --- but being not limited to --- operating system, one or more application program, It may include the reality of network environment in other program modules and program data, each of these examples or certain combination It is existing.Program module 42a usually executes the function and/or method in above-mentioned each embodiment of Fig. 1-Fig. 4 described in the invention.
Computer equipment 12a can also be with one or more external equipment 14a (such as keyboard, sensing equipment, display 24a etc.) communication, the equipment interacted with computer equipment 12a communication can be also enabled a user to one or more, and/or (such as network interface card is adjusted with any equipment for enabling computer equipment 12a to be communicated with one or more of the other calculating equipment Modulator-demodulator etc.) communication.This communication can be carried out by input/output (I/O) interface 22a.Also, computer equipment 12a can also by network adapter 20a and one or more network (such as local area network (LAN), wide area network (WAN) and/ Or public network, such as internet) communication.As shown, network adapter 20a passes through bus 18a and computer equipment 12a Other modules communication.It should be understood that although not shown in the drawings, can in conjunction with computer equipment 12a using other hardware and/or Software module, including but not limited to: microcode, device driver, redundant processor, external disk drive array, RAID system, Tape drive and data backup storage system etc..
Processor 16a by the program that is stored in system storage 28a of operation, thereby executing various function application and Data processing, such as realize good friend's processing method based on facial characteristics shown in above-described embodiment.
The present invention also provides a kind of computer-readable mediums, are stored thereon with computer program, which is held by processor Good friend's processing method as shown in above-described embodiment based on facial characteristics is realized when row.
The computer-readable medium of the present embodiment may include in the system storage 28a in above-mentioned embodiment illustrated in fig. 6 RAM30a, and/or cache memory 32a, and/or storage system 34a.
With the development of science and technology, the route of transmission of computer program is no longer limited by tangible medium, it can also be directly from net Network downloading, or obtained using other modes.Therefore, the computer-readable medium in the present embodiment not only may include tangible Medium can also include invisible medium.
The computer-readable medium of the present embodiment can be using any combination of one or more computer-readable media. Computer-readable medium can be computer-readable signal media or computer readable storage medium.Computer-readable storage medium Matter for example may be-but not limited to-system, device or the device of electricity, magnetic, optical, electromagnetic, infrared ray or semiconductor, or Any above combination of person.The more specific example (non exhaustive list) of computer readable storage medium includes: with one Or the electrical connections of multiple conducting wires, portable computer diskette, hard disk, random access memory (RAM), read-only memory (ROM), Erasable programmable read only memory (EPROM or flash memory), optical fiber, portable compact disc read-only memory (CD-ROM), light Memory device, magnetic memory device or above-mentioned any appropriate combination.In this document, computer readable storage medium can With to be any include or the tangible medium of storage program, the program can be commanded execution system, device or device use or Person is in connection.
Computer-readable signal media may include in a base band or as carrier wave a part propagate data-signal, Wherein carry computer-readable program code.The data-signal of this propagation can take various forms, including --- but It is not limited to --- electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal media can also be Any computer-readable medium other than computer readable storage medium, which can send, propagate or Transmission is for by the use of instruction execution system, device or device or program in connection.
The program code for including on computer-readable medium can transmit with any suitable medium, including --- but it is unlimited In --- wireless, electric wire, optical cable, RF etc. or above-mentioned any appropriate combination.
The computer for executing operation of the present invention can be write with one or more programming languages or combinations thereof Program code, described program design language include object oriented program language-such as Java, Smalltalk, C++, Further include conventional procedural programming language-such as " C " language or similar programming language.Program code can be with It fully executes, partly execute on the user computer on the user computer, being executed as an independent software package, portion Divide and partially executes or executed on a remote computer or server completely on the remote computer on the user computer.? Be related in the situation of remote computer, remote computer can pass through the network of any kind --- including local area network (LAN) or Wide area network (WAN)-be connected to subscriber computer, or, it may be connected to outer computer (such as mentioned using Internet service It is connected for quotient by internet).
In several embodiments provided by the present invention, it should be understood that disclosed system, device and method can be with It realizes by another way.For example, the apparatus embodiments described above are merely exemplary, for example, the unit It divides, only a kind of logical function partition, there may be another division manner in actual implementation.
The unit as illustrated by the separation member may or may not be physically separated, aobvious as unit The component shown may or may not be physical unit, it can and it is in one place, or may be distributed over multiple In network unit.It can select some or all of unit therein according to the actual needs to realize the mesh of this embodiment scheme 's.
It, can also be in addition, the functional units in various embodiments of the present invention may be integrated into one processing unit It is that each unit physically exists alone, can also be integrated in one unit with two or more units.Above-mentioned integrated list Member both can take the form of hardware realization, can also realize in the form of hardware adds SFU software functional unit.
The above-mentioned integrated unit being realized in the form of SFU software functional unit can store and computer-readable deposit at one In storage media.Above-mentioned SFU software functional unit is stored in a storage medium, including some instructions are used so that a computer It is each that equipment (can be personal computer, server or the network equipment etc.) or processor (processor) execute the present invention The part steps of a embodiment the method.And storage medium above-mentioned includes: USB flash disk, mobile hard disk, read-only memory (Read- Only Memory, ROM), random access memory (Random Access Memory, RAM), magnetic or disk etc. it is various It can store the medium of program code.
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the invention, all in essence of the invention Within mind and principle, any modification, equivalent substitution, improvement and etc. done be should be included within the scope of the present invention.

Claims (16)

1. a kind of good friend's processing method based on facial characteristics, which is characterized in that the described method includes:
Receive the stranger's inquiry request for the carrying target face feature that request user client is sent；
According to the target face feature and the friend information of the request user, obtained not from face database gathered in advance Belong to the request user good friend, several candidate face images；
Recommend several candidate face images to the request user client.
2. the method according to claim 1, wherein according to the target face feature and the request user Friend information, obtained from face database gathered in advance and be not belonging to the request user good friend, several candidate face images Before, the method also includes:
When each registration user, which opens the good friend based on facial characteristics, adds function, the face figure of each registration user is acquired Picture；
Each facial image for registering user is verified whether as living body faces image；
If so, by the face database is stored in by the facial image of the registration user of verifying.
3. the method according to claim 1, wherein recommending several candidates to the request user client After facial image, the method also includes:
Receive the addition good friend request of the facial image for the carrying target good friend that the request user client is initiated；It is described Adding good friend's request is the user for requesting user client selection target good friend from several candidate face images It is initiated after facial image；
The facial image of the request user is obtained from the face database；
The addition good friend request for carrying the facial image of the request user is sent to the client of the target good friend；
After the user of the target good friend agrees to addition, the request user and the target good friend are mutually added preferably Friend.
4. the method according to claim 1, wherein according to the target face feature and the request user Friend information, obtained from face database gathered in advance and be not belonging to the request user good friend, several candidate face images, It specifically includes:
According to the target face feature, all alternative faces for meeting the target face feature are obtained from the face database Image；
According to the friend information of the request user and the request user, the request facial image of user and described is obtained Request the facial image of the good friend of user；
According to the facial image of the facial image of the request user and the good friend of the request user, to all alternative people Face image is filtered, and obtains multiple alternative facial images；
Filter out from all alternative facial images the facial image of the request user and the good friend of the request user Facial image obtains multiple alternative facial images；
Several candidate face images are obtained from the multiple alternative facial image.
5. according to the method described in claim 4, it is characterized in that, being obtained from the multiple alternative facial image described several Candidate face image, specifically includes:
Obtain several candidate face images at random from the multiple alternative facial image；
Alternatively, obtaining from the good friend of the request user and being added by facial characteristics according to the friend information of the request user The target good friend added；The facial image of the target good friend is obtained from the face database；Calculate each alternative facial image Respectively with the similarity of the facial image of the target good friend；According to each alternative facial image respectively with the target good friend Facial image similarity, the high several alternative face figures of similarity are obtained from the multiple alternative facial image Picture, as several candidate face images.
6. -5 any method according to claim 1, which is characterized in that if the target face feature includes target eye Feature or target mouth feature are adopted according to the target face feature and the friend information of the request user from advance Candidate face images that be not belonging to the request user good friend, several are obtained in the face database of collection, are specifically included:
According to the target eye feature and the friend information of the request user, obtained and the mesh from the face database Mark eye feature is consistent and is not belonging to several candidate face images of the request user good friend；
Or according to the target mouth feature and the friend information of the request user, acquisition and institute from the face database It states target mouth feature unanimously and is not belonging to several candidate face images of the request user good friend.
7. -5 any method according to claim 1, which is characterized in that if the target face feature includes the target bridge of the nose Feature is obtained from face database gathered in advance according to the target face feature and the friend information of the request user It is not belonging to the request user good friend, several candidate face images, is specifically included:
Using bridge of the nose feature identification model trained in advance, the bridge of the nose for marking each facial image in the face database is special Sign；
It is used according to the bridge of the nose feature of each facial image in the target bridge of the nose feature, the face database and the request The friend information at family, obtains that consistent with the target bridge of the nose feature and to be not belonging to the request user good from the face database Several candidate face images of friend；
If the target face feature includes target features of skin colors, according to the target face feature, from face gathered in advance Several candidate face images are obtained in library, are specifically included:
Using features of skin colors identification model trained in advance, the colour of skin for marking each facial image in the face database is special Sign；
It is used according to the features of skin colors of each facial image in the target features of skin colors, the face database and the request The friend information at family, obtains that consistent with the target features of skin colors and to be not belonging to the request user good from the face database Several candidate face images of friend.
8. a kind of social application server, which is characterized in that the server includes:
Receiving module, for receiving the stranger's inquiry request for the carrying target face feature that request user client is sent；
Module is obtained, for the friend information according to the target face feature and the request user, from gathered in advance Candidate face images that be not belonging to the request user good friend, several are obtained in face database；
Sending module, for recommending several candidate face images to the request user client；
The face database, for storing the face figure of all registration users for opening good friend's addition function based on facial characteristics Picture.
9. server according to claim 8, which is characterized in that the server further include:
Acquisition module, for acquiring each described when each registration user opens the good friend based on facial characteristics and adds function Register the facial image of user；
Authentication module, for whether verifying each facial image for registering user as living body faces image；
The facial image of memory module, the registration user for that will be verified by the authentication module is stored in the face Library.
10. server according to claim 8, which is characterized in that the server further includes adding module；
The receiving module is also used to receive the facial image for the carrying target good friend that the request user client is initiated Addition good friend request；The addition good friend request is the user of the request user client from several candidate face figures It is initiated after the facial image of selection target good friend as in；
The acquisition module is also used to obtain the facial image of the request user from the face database；
The sending module is also used to send the facial image for carrying the request user to the client of the target good friend Add good friend's request；
The adding module, for the user of the target good friend agree to addition after, by the request user and the mesh Mark good friend is mutually added as good friend.
11. server according to claim 8, which is characterized in that the acquisition module is specifically used for:
According to the target face feature, all alternative faces for meeting the target face feature are obtained from the face database Image；
According to the friend information of the request user and the request user, the request facial image of user and described is obtained Request the facial image of the good friend of user；
According to the facial image of the facial image of the request user and the good friend of the request user, to all alternative people Face image is filtered, and obtains multiple alternative facial images；
Filter out from all alternative facial images the facial image of the request user and the good friend of the request user Facial image obtains multiple alternative facial images；
Several candidate face images are obtained from the multiple alternative facial image.
12. server according to claim 11, which is characterized in that the acquisition module is specifically used for:
Obtain several candidate face images at random from the multiple alternative facial image；
Alternatively, obtaining from the good friend of the request user and being added by facial characteristics according to the friend information of the request user The target good friend added；The facial image of the target good friend is obtained from the face database；Calculate each alternative facial image Respectively with the similarity of the facial image of the target good friend；According to each alternative facial image respectively with the target good friend Facial image similarity, the high several alternative face figures of similarity are obtained from the multiple alternative facial image Picture, as several candidate face images.
13. according to any server of claim 8-12, which is characterized in that if the target face feature includes target Eye feature, the acquisition module, specifically for according to the target eye feature and it is described request user friend information, Several times that are consistent with the target eye feature and being not belonging to the request user good friend are obtained from the face database It chooses face image；
If the target face feature includes target mouth feature, the acquisition module is specifically used for according to the target mouth The friend information of feature and the request user, obtain consistent with the target mouth feature and not from the face database Belong to several candidate face images of the request user good friend.
14. according to any server of claim 8-12, which is characterized in that if the target face feature includes target Bridge of the nose feature, the acquisition module, is specifically used for:
Using bridge of the nose feature identification model trained in advance, the bridge of the nose for marking each facial image in the face database is special Sign；
It is used according to the bridge of the nose feature of each facial image in the target bridge of the nose feature, the face database and the request The friend information at family, obtains that consistent with the target bridge of the nose feature and to be not belonging to the request user good from the face database Several candidate face images of friend；
If the target face feature includes target features of skin colors, the acquisition module is specifically used for:
Using features of skin colors identification model trained in advance, the colour of skin for marking each facial image in the face database is special Sign；
It is used according to the features of skin colors of each facial image in the target features of skin colors, the face database and the request The friend information at family, obtains that consistent with the target features of skin colors and to be not belonging to the request user good from the face database Several candidate face images of friend.
15. a kind of computer equipment, which is characterized in that the equipment includes:
One or more processors；
Memory, for storing one or more programs；
When one or more of programs are executed by one or more of processors, so that one or more of processors are real The now method as described in any in claim 1-7.
16. a kind of computer-readable medium, is stored thereon with computer program, which is characterized in that the program is executed by processor Method of the Shi Shixian as described in any in claim 1-7.
CN201810064076.9A 2018-01-23 2018-01-23 Good friend's processing method, server and computer-readable medium based on facial characteristics Pending CN110084709A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201810064076.9A CN110084709A (en) 2018-01-23 2018-01-23 Good friend's processing method, server and computer-readable medium based on facial characteristics

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201810064076.9A CN110084709A (en) 2018-01-23 2018-01-23 Good friend's processing method, server and computer-readable medium based on facial characteristics

Publications (1)

Publication Number Publication Date
CN110084709A true CN110084709A (en) 2019-08-02

Family

ID=67411914

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201810064076.9A Pending CN110084709A (en) 2018-01-23 2018-01-23 Good friend's processing method, server and computer-readable medium based on facial characteristics

Country Status (1)

Country Link
CN (1) CN110084709A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110569758A (en) * 2019-08-26 2019-12-13 深圳市云歌人工智能技术有限公司 method, device and storage medium for determining user category
CN112269928A (en) * 2020-10-23 2021-01-26 百度在线网络技术（北京）有限公司 User recommendation method and device, electronic equipment and computer readable medium

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20130077833A1 (en) * 2011-09-22 2013-03-28 International Business Machines Corporation Searching with face recognition and social networking profiles
CN103324636A (en) * 2012-03-22 2013-09-25 三星电子（中国）研发中心 System and method for recommending friend in social network
CN103399896A (en) * 2013-07-19 2013-11-20 广州华多网络科技有限公司 Method and system for recognizing association relationships among users
CN103514286A (en) * 2013-09-30 2014-01-15 鸿富锦精密工业（深圳）有限公司 Friend recommending system and method
CN103970830A (en) * 2014-03-31 2014-08-06 小米科技有限责任公司 Information recommendation method and device
CN106484737A (en) * 2015-09-01 2017-03-08 腾讯科技（深圳）有限公司 A kind of network social intercourse method and network social intercourse device
CN107302492A (en) * 2017-06-28 2017-10-27 歌尔科技有限公司 Friend-making requesting method, server, client terminal device and the system of social software

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20130077833A1 (en) * 2011-09-22 2013-03-28 International Business Machines Corporation Searching with face recognition and social networking profiles
CN103324636A (en) * 2012-03-22 2013-09-25 三星电子（中国）研发中心 System and method for recommending friend in social network
CN103399896A (en) * 2013-07-19 2013-11-20 广州华多网络科技有限公司 Method and system for recognizing association relationships among users
CN103514286A (en) * 2013-09-30 2014-01-15 鸿富锦精密工业（深圳）有限公司 Friend recommending system and method
CN103970830A (en) * 2014-03-31 2014-08-06 小米科技有限责任公司 Information recommendation method and device
CN106484737A (en) * 2015-09-01 2017-03-08 腾讯科技（深圳）有限公司 A kind of network social intercourse method and network social intercourse device
CN107302492A (en) * 2017-06-28 2017-10-27 歌尔科技有限公司 Friend-making requesting method, server, client terminal device and the system of social software

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110569758A (en) * 2019-08-26 2019-12-13 深圳市云歌人工智能技术有限公司 method, device and storage medium for determining user category
CN112269928A (en) * 2020-10-23 2021-01-26 百度在线网络技术（北京）有限公司 User recommendation method and device, electronic equipment and computer readable medium

Similar Documents

Publication Publication Date Title
US10951602B2 (en) Server based methods and systems for conducting personalized, interactive and intelligent searches
JP6785305B2 (en) Equipment and methods for video analysis techniques to identify individuals with face recognition and contextual video streams
Yip et al. Contribution of color to face recognition
JP6850291B2 (en) Methods and devices for minimizing false positives in face recognition applications
US20210174146A1 (en) Training set sufficiency for image analysis
US20200142978A1 (en) Visual attribute determination for content selection
US11922661B2 (en) Augmented reality experiences of color palettes in a messaging system
JP2018045350A (en) Device, program and method for identifying state in specific object of predetermined object
US20150049953A1 (en) Emotion and appearance based spatiotemporal graphics systems and methods
US20210312533A1 (en) Identification of physical products for augmented reality experiences in a messaging system
CN107908641A (en) A kind of method and system for obtaining picture labeled data
US20210312678A1 (en) Generating augmented reality experiences with physical products using profile information
US11263436B1 (en) Systems and methods for matching facial images to reference images
KR20220163430A (en) Identification of Physical Products for Augmented Reality Experiences in Messaging Systems
CN110084289A (en) Image labeling method, device, electronic equipment and storage medium
WO2024060951A1 (en) Servicing method and apparatus for services
CN108197995A (en) A kind of accurate advertisement put-on method based on recognition of face
CN110084709A (en) Good friend's processing method, server and computer-readable medium based on facial characteristics
US20230111437A1 (en) System and method for content recognition and data categorization
US20230386255A1 (en) Method and system for verifying image identification
US10952661B2 (en) Analysis of cognitive status through object interaction
US20200226012A1 (en) File system manipulation using machine learning
Zinkernagel et al. The blenderFace method: video-based measurement of raw movement data during facial expressions of emotion using open-source software
US20180360370A1 (en) Analysis of cognitive status through object interaction
US11514082B1 (en) Dynamic content selection

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
TA01 Transfer of patent application right

Effective date of registration: 20191206

Address after: 201210 room j1328, floor 3, building 8, No. 55, Huiyuan Road, Jiading District, Shanghai

Applicant after: SHANGHAI YOUYANG NEW MEDIA INFORMATION TECHNOLOGY Co.,Ltd.

Address before: 100085 Baidu building, No. 10, ten Street, Haidian District, Beijing

Applicant before: BAIDU ONLINE NETWORK TECHNOLOGY (BEIJING) Co.,Ltd.

TA01 Transfer of patent application right
EE01 Entry into force of recordation of patent licensing contract

Application publication date: 20190802

Assignee: BAIDU ONLINE NETWORK TECHNOLOGY (BEIJING) Co.,Ltd.

Assignor: SHANGHAI YOUYANG NEW MEDIA INFORMATION TECHNOLOGY Co.,Ltd.

Contract record no.: X2019110000009

Denomination of invention: Face feature-based friend processing method, server and computer readable medium

License type: Exclusive License

Record date: 20191218

EE01 Entry into force of recordation of patent licensing contract
RJ01 Rejection of invention patent application after publication

Application publication date: 20190802

RJ01 Rejection of invention patent application after publication