CN110163170A - The method and apparatus at age for identification - Google Patents
The method and apparatus at age for identification Download PDFInfo
- Publication number
- CN110163170A CN110163170A CN201910447129.XA CN201910447129A CN110163170A CN 110163170 A CN110163170 A CN 110163170A CN 201910447129 A CN201910447129 A CN 201910447129A CN 110163170 A CN110163170 A CN 110163170A
- Authority
- CN
- China
- Prior art keywords
- facial image
- age
- face
- information
- image group
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
- G06V40/178—Human faces, e.g. facial parts, sketches or expressions estimating age from face image; using age information for improving recognition
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
- Collating Specific Patterns (AREA)
- Processing Or Creating Images (AREA)
Abstract
Embodiment of the disclosure discloses the method and apparatus at age for identification.One specific embodiment of this method includes: at least one personage's video in response to getting user's publication, extracts face image set from least one personage's video；For every facial image in face image set, which is parsed, determines age information corresponding with the facial image；Based on the matching relationship between facial image, face image set is divided at least one facial image group, wherein different facial image groups correspond to different personages；Age recognition result corresponding with personage corresponding to the facial image group is determined based on age information corresponding to the facial image in the facial image group for each of at least one facial image group face image group.The embodiment may be implemented one or more personages shown by least one the personage's video issued to user and carry out age identification.
Description
Technical field
Embodiment of the disclosure is related to field of computer technology, and in particular to the method and apparatus at age for identification.
Background technique
With the rapid development of development of Mobile Internet technology, various applications emerge one after another, such as social application etc..Its
In, user can carry out personal information setting, such as setting head portrait, the pet name, age etc. in social application.Some users in order to
Individual privacy is protected, the picture that may will be displayed with my non-head portrait is set as head portrait in social application, and not in society
It hands over and the age is set in application, or at will one non-genuine age of setting.In addition, user can also be carried out using social application
Video record, and issue recorded video.
Summary of the invention
Embodiment of the disclosure proposes the method and apparatus at age for identification.
In a first aspect, embodiment of the disclosure provides a kind of method at age for identification, this method comprises: in response to
At least one the personage's video for getting user's publication, extracts face image set from least one above-mentioned personage's video；
For every facial image in face image set, which is parsed, determination is corresponding with the facial image
Age information；Based on the matching relationship between facial image, face image set is divided at least one facial image group,
In, different facial image groups corresponds to different personages；For each of at least one above-mentioned facial image group face image
Group, based on age information corresponding to the facial image in the facial image group, determination and people corresponding to the facial image group
The corresponding age recognition result of object.
In some embodiments, face image set is extracted from least one above-mentioned personage's video, comprising: to above-mentioned
At least one personage's video carries out pumping frame respectively, and the image extracted is formed image collection；To each in image collection
Image carries out Face datection respectively, obtains Face datection result, wherein Face datection corresponding to the image including human face region
It as a result include the location information of human face region；Based on the location information in Face datection result, people is extracted from image collection
Face image set.
In some embodiments, Face datection result corresponding to the image including human face region further includes face characteristic letter
Breath；And based on the matching relationship between facial image, face image set is divided at least one facial image group, is wrapped
It includes: the corresponding face characteristic information of each facial image in face image set is clustered, and based on cluster knot
Face image set is divided at least one facial image group by fruit.
In some embodiments, it for every facial image in face image set, is solved to the facial image
Analysis, when determining the corresponding age information of the facial image, the above method further include: determine that the corresponding association of the facial image is believed
Breath, related information include at least one of the following: 3 d pose information, quality information；And based on the people in the facial image group
Age information corresponding to face image determines age recognition result corresponding with personage corresponding to the facial image group, packet
It includes: based on the corresponding age information of facial image and related information in the facial image group, the determining and facial image group institute
The corresponding age recognition result of corresponding personage.
In some embodiments, for every facial image in face image set, which is parsed,
Determine the corresponding age information of the facial image and related information, comprising: for every facial image in face image set,
The facial image is inputted into multiple identification models, obtains much information corresponding with the facial image, multiple identification model packet
Include the first identification model for carrying out age identification and the second identification model for being associated information identification, a variety of letters
Breath includes the corresponding age information of the facial image and related information.
In some embodiments, based on the corresponding age information of facial image and related information in the facial image group,
Determine age recognition result corresponding with personage corresponding to the facial image group, comprising: in the facial image group
Every facial image determines weighted value corresponding with the facial image based on related information corresponding to the facial image；It is based on
The corresponding weighted value of multiple facial images and age information in the facial image group, it is right with the facial image group institute to determine
The corresponding age recognition result of the personage answered.
In some embodiments, related information includes 3 d pose information, and 3 d pose information includes pitch angle value, partially
Navigate angle value and rolling angle value；And based on related information corresponding to the facial image, determination is corresponding with the facial image
Weighted value, comprising: determine pitch angle angle value, yaw angle angle value corresponding to the facial image and roll angle value absolute value
Between summation, and the ratio between the first preset value and identified summation is determined as weight corresponding to the facial image
Value.
In some embodiments, related information includes 3 d pose information and quality information, and 3 d pose information includes bowing
Elevation angle angle value, yaw angle angle value and rolling angle value, quality information includes fog-level value；And it is right based on the facial image
The related information answered determines weighted value corresponding with the facial image, comprising: determine pitch angle corresponding to the facial image
Summation between value, yaw angle angle value and the absolute value and corresponding fog-level value of the angle value that rolls, and it is pre- by first
If the ratio between value and identified summation is determined as weighted value corresponding to the facial image.
In some embodiments, based in the facial image group the corresponding weighted value of multiple facial images and the age
Information determines age recognition result corresponding with personage corresponding to the facial image group, comprising: is determined using following formula
Age recognition result corresponding with personage corresponding to the facial image group:
Wherein, C represents age recognition result；N is the quantity of multiple facial images；I is the nature in [1, n]
Number；W represents weighted value, WiRepresent the corresponding weighted value of i-th facial image in multiple facial images, WnRepresent this multiple
The corresponding weighted value of n-th facial image in facial image；V represents the age value in age information, ViRepresent multiple people
The age value in the corresponding age information of i-th facial image in face image.
In some embodiments, it based on age information corresponding to the facial image in the facial image group, determines and is somebody's turn to do
The corresponding age recognition result of personage corresponding to facial image group, comprising: to each face figure in the facial image group
As the age value in corresponding age information is averaged, average value is determined as and people corresponding to the facial image group
The corresponding age recognition result of object.
Second aspect, embodiment of the disclosure provide a kind of device at age for identification, which includes: to extract list
Member is configured in response to get at least one personage's video of user's publication, mention from least one above-mentioned personage's video
Take out face image set；First determination unit is configured to for every facial image in face image set, to the people
Face image is parsed, and determines age information corresponding with the facial image；Division unit, be configured to based on facial image it
Between matching relationship, face image set is divided at least one facial image group, wherein different facial image group is corresponding
Different personages；Second determination unit is configured to for each of at least one above-mentioned facial image group face image group,
Based on age information corresponding to the facial image in the facial image group, determination and figure picture corresponding to the facial image group
Corresponding age recognition result.
In some embodiments, extraction unit is further configured to: being carried out respectively at least one above-mentioned personage's video
Frame is taken out, and the image extracted is formed into image collection；Face datection is carried out to each image in image collection respectively, is obtained
Face datection result, wherein Face datection result corresponding to the image including human face region includes the position letter of human face region
Breath；Based on the location information in Face datection result, face image set is extracted from image collection.
In some embodiments, Face datection result corresponding to the image including human face region further includes face characteristic letter
Breath；And division unit is further configured to: special to the corresponding face of each facial image in face image set
Reference breath is clustered, and is based on cluster result, and face image set is divided at least one facial image group.
In some embodiments, the first determination unit is further configured to: for every people in face image set
Face image is parsed to the facial image, when determining age information corresponding with the facial image, also determines the face figure
As corresponding related information, related information includes at least one of the following: 3 d pose information, quality information；And second determine
Unit is further configured to: for each of at least one above-mentioned facial image group face image group, being based on the face figure
As the corresponding age information of facial image and related information in group, determination is corresponding with personage corresponding to the facial image group
Age recognition result.
In some embodiments, the first determination unit is further configured to: for every people in face image set
The facial image is inputted multiple identification models, obtains much information corresponding with the facial image, multiple identification by face image
Model includes the first identification model for carrying out age identification and the second identification model for being associated information identification, is somebody's turn to do
Much information includes the corresponding age information of the facial image and related information.
In some embodiments, the second determination unit is further configured to: at least one above-mentioned facial image group
Each of face image group, for every facial image in the facial image group, based on pass corresponding to the facial image
Join information, determines weighted value corresponding with the facial image；It is respectively corresponded based on multiple facial images in the facial image group
Weighted value and age information, determine corresponding with personage corresponding to facial image group age recognition result.
In some embodiments, related information includes 3 d pose information, and 3 d pose information includes pitch angle value, partially
Navigate angle value and rolling angle value；And second determination unit be further configured to: at least one above-mentioned facial image
Each of group face image group determines corresponding to the facial image every facial image in the facial image group
Pitch angle angle value, yaw angle angle value and roll angle value absolute value between summation, and by the first preset value with it is identified
Ratio between summation is determined as weighted value corresponding to the facial image.
In some embodiments, related information includes 3 d pose information and quality information, and 3 d pose information includes bowing
Elevation angle angle value, yaw angle angle value and rolling angle value, quality information includes fog-level value；And second determination unit it is further
It is configured to: for each of at least one above-mentioned facial image group face image group, for every in the facial image group
Facial image, determine the absolute value of pitch angle angle value, yaw angle angle value corresponding to the facial image and the angle value that rolls with
And the summation between corresponding fog-level value, and the ratio between the first preset value and identified summation is determined as this
Weighted value corresponding to facial image.
In some embodiments, the second determination unit is further configured to: at least one above-mentioned facial image group
Each of face image group, the identification of corresponding with personage corresponding to facial image group age is determined using following formula
As a result:
Wherein, C represents age recognition result；N is the quantity of multiple facial images in facial image group；I be in [1,
N] in natural number；W represents weighted value, WiRepresent the corresponding weighted value of i-th facial image in multiple facial images, Wn
Represent the corresponding weighted value of n-th facial image in multiple facial images；V represents the age value in age information, ViGeneration
The age value in the corresponding age information of i-th facial image in table multiple facial images.
In some embodiments, the second determination unit is further configured to: at least one above-mentioned facial image group
Each of face image group, to the age value in the corresponding age information of each facial image in the facial image group
It averages, average value is determined as age recognition result corresponding with personage corresponding to the facial image group.
The third aspect, embodiment of the disclosure provide a kind of electronic equipment, which includes: one or more places
Manage device；Storage device is stored thereon with one or more programs；When the one or more program is by the one or more processors
It executes, so that the one or more processors realize the method as described in implementation any in first aspect.
Fourth aspect, embodiment of the disclosure provide a kind of computer-readable medium, are stored thereon with computer program,
The method as described in implementation any in first aspect is realized when the program is executed by processor.
The method and apparatus at the age for identification provided by the above embodiment of the disclosure, by response to getting user
At least one personage's video of publication, extracts face image set from least one personage's video, then for face
Every facial image in image collection, parses the facial image, determines age information corresponding with the facial image,
And based on the matching relationship between facial image, face image set is divided at least one facial image group, wherein different
Facial image group correspond to different personages, so as to for each of at least one above-mentioned facial image group face image group,
Based on age information corresponding to the facial image in the facial image group, determination and figure picture corresponding to the facial image group
Corresponding age recognition result.At least one issued to user may be implemented in the scheme provided by the above embodiment of the disclosure
One or more personages shown by personage's video carry out age identification.In addition, when at least one personage's video of user's publication
When being by the resulting video of user's progress video record, it may be implemented to accurately identify the age of the user.
Detailed description of the invention
By reading a detailed description of non-restrictive embodiments in the light of the attached drawings below, the disclosure is other
Feature, objects and advantages will become more apparent upon:
Fig. 1 is that some embodiments of the present disclosure can be applied to exemplary system architecture figure therein；
Fig. 2 is the flow chart according to one embodiment of the method at the age for identification of the disclosure；
Fig. 3 is the schematic diagram according to an application scenarios of the method at the age for identification of the disclosure；
Fig. 4 is the flow chart according to another embodiment of the method at the age for identification of the disclosure；
Fig. 5 is the structural schematic diagram according to one embodiment of the device at the age for identification of the disclosure；
Fig. 6 is adapted for the structural representation for the computer system for realizing the electronic equipment of some embodiments of the present disclosure
Figure.
Specific embodiment
The disclosure is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouched
The specific embodiment stated is used only for explaining that correlation is open, rather than the restriction to the disclosure.It also should be noted that in order to
Convenient for description, is illustrated only in attached drawing and disclose relevant part to related.
It should be noted that in the absence of conflict, the feature in embodiment and embodiment in the disclosure can phase
Mutually combination.The disclosure is described in detail below with reference to the accompanying drawings and in conjunction with the embodiments.
Fig. 1 is shown can be using the method or the implementation of the device at age for identification at the age for identification of the disclosure
The exemplary system architecture 100 of example.
As shown in Figure 1, system architecture 100 may include server 101,103 and network 102.Network 102 is to service
The medium of communication link is provided between device 101 and server 103.Network 102 may include various connection types, such as wired,
Wireless communication link or fiber optic cables etc..
Server 101 can be to provide the server of various services, such as the information of the video for storing user's publication
Server is used in storage.Server 103 can be to provide the server of various services, such as personage's view for being issued based on user
Frequency carries out the server of age identification, which for example can obtain at least one personage that user issues from server 101
Video, and age identification operation is carried out based at least one personage's video.
Wherein, server can be hardware, be also possible to software.When server is hardware, multiple clothes may be implemented into
The distributed server cluster of business device composition, also may be implemented into individual server.When server is software, may be implemented into
Multiple softwares or software module (such as providing Distributed Services), also may be implemented into single software or software module.?
This is not specifically limited.
It should be noted that the method at the age for identification that some embodiments of the present disclosure provide is generally by server
103 execute, and correspondingly, the device at age is generally positioned in server 103 for identification.
It should be pointed out that system architecture 100 can not wrap when the video of user's publication stores in server 103
Include server 101.
It should be understood that the number of network and server in Fig. 1 is only schematical.According to needs are realized, can have
There are any number of network and server.
With continued reference to Fig. 2, it illustrates the processes according to one embodiment of the method at age for identification of the disclosure
200.The process 200 of the method at age for identification, comprising the following steps:
Step 201, at least one the personage's video issued in response to getting user, mentions from least one personage's video
Take out face image set.
In the present embodiment, the executing subject (such as server 103 shown in FIG. 1) of the method at age can be with for identification
In response to getting at least one personage's video of user's publication, face image set is extracted from least one personage's video
It closes.Wherein, which can be above-mentioned executing subject from server that is local or being connected (such as Fig. 1 institute
The server 101 shown) obtain, it is not specifically limited herein.
It should be noted that above-mentioned user can be the user of specified social application.Specifically, above-mentioned user for example may be used
To be to be not provided with real age in the social application or be not provided with the user at age.Wherein, at least one above-mentioned personage
Video can be the video for showing personage that above-mentioned user is issued by the social application.In addition, at least one above-mentioned personage
Video can be the video that above-mentioned user uses the social application to record.
In the present embodiment, if at least one above-mentioned personage's video has corresponded to Face datection in advance as a result, above-mentioned execution master
Body can be based on the face testing result, extract face image set from least one above-mentioned personage's video.Wherein, above-mentioned
Face datection result corresponding to the image including human face region at least one personage's video may include the human face region
Location information specifically, above-mentioned executing subject first can carry out pumping frame at least one above-mentioned personage's video respectively, such as take out
All images are taken out, or each of at least one above-mentioned personage's video object is regarded according to interval frame number (such as 1 or 2 etc.)
Frequency carries out interval and takes out frame.It should be understood that interval frame number can be set according to actual needs, it is not specifically limited herein.And
Afterwards, the image extracted can be formed image collection by above-mentioned executing subject.Then, above-mentioned executing subject can be examined based on face
The location information in result is surveyed, face image set is extracted from image collection.
Step 202, for every facial image in face image set, which is parsed, determine with
The corresponding age information of the facial image.
In the present embodiment, for every facial image in face image set, above-mentioned executing subject can be to the people
Face image is parsed, and determines age information corresponding with the facial image.
As an example, above-mentioned executing subject locally can store face character template corresponding with age attribute.Wherein,
The face attribute templates for example may include multiple facial images age information corresponding with multiple facial images.By people
For every facial image in face image set as facial image to be identified, above-mentioned executing subject can be by the face figure to be identified
It is determined as being matched with the facial image in face character template, and by age information corresponding to the facial image matched
For age information corresponding with the facial image to be identified.
Step 203, based on the matching relationship between facial image, face image set is divided at least one face figure
As group.
In the present embodiment, above-mentioned executing subject can be based on the matching relationship between facial image, by face image set
Conjunction is divided at least one facial image group.Wherein, different facial image groups corresponds to different personages.For example, working as face figure
When image set conjunction is divided into multiple facial image groups, it is meant that at least one above-mentioned personage's video shows multiple personages, this is more
Each of a facial image group face image group corresponds to a personage in multiple personage, and multiple facial image component
Not corresponding personage is different.
It should be noted that above-mentioned executing subject can for example use the face alignment algorithm based on deep learning, to people
Facial image in face image set is compared two-by-two, to judge whether any two facial images belong to same people.Then,
Above-mentioned executing subject can be based on comparison result, and the facial image for belonging to same people is divided into same person's face image group.
Step 204, for each of at least one facial image group face image group, based in the facial image group
Age information corresponding to facial image determines age recognition result corresponding with personage corresponding to the facial image group.
In the present embodiment, for each of at least one above-mentioned facial image group face image group, above-mentioned execution master
Body can be based on age information corresponding to the facial image in the facial image group, corresponding to the determining and facial image group
The corresponding age recognition result of personage.For example, above-mentioned executing subject can be to each facial image in the facial image group
Age value in corresponding age information is averaged, which is determined as and people corresponding to the facial image group
The corresponding age recognition result of object.
In some optional implementations of the present embodiment, for every facial image in face image set, on
It states executing subject to parse to the facial image, when determining the corresponding age information of the facial image, can also determine this
The corresponding related information of facial image.The related information includes at least one of the following: 3 d pose information, quality information.Wherein,
3 d pose information may include pitch angle angle value, yaw angle angle value and rolling angle value.Pitch angle angle value can be pitch angle
(pitch) angle value.Yaw angle angle value can be the angle value of yaw angle (yaw).Rolling angle value can be roll angle
(roll) angle value.Quality information may include fog-level value.Fog-level value for example can be in [0,100]
Numerical value.Fog-level value is bigger, and the facial image that can be characterized corresponding to it is fuzzyyer.Fog-level value is lower, can characterize
Facial image corresponding to it is more clear.
As an example, above-mentioned executing subject can also locally be stored with pose template.Pose template for example may include more
Open facial image and posture information corresponding with multiple facial images.By every facial image in face image set
As facial image to be identified, above-mentioned executing subject can by the facial image in the facial image to be identified and pose template into
Row attitude matching, and posture information corresponding to the facial image matched is determined as corresponding with the facial image to be identified
Posture information.
For every facial image in face image set, above-mentioned execution can be calculated using various image quality measures
Method, such as mean absolute difference (Mean Absolute Difference, MAD), absolute error and (Sum of Absolute
Difference, SAD), squared difference and (Sum of Squared Difference, SSD) etc., to the facial image into
Row quality evaluation obtains quality information corresponding with the facial image.
In some optional implementations of the present embodiment, for every facial image in face image set, on
Multiple identification models can be inputted for the facial image by stating executing subject, obtain much information corresponding with the facial image.It should
Multiple identification models include that the first identification model for carrying out age identification and second for being associated information identification is known
Other model.The much information includes the corresponding age information of the facial image and related information.Here, the number of the second identification model
Amount can be one or more, be not specifically limited herein.
It should be pointed out that identification model can be using convolutional neural networks (Convolutional Neural
Networks, CNN) or the models such as Recognition with Recurrent Neural Network (Recurrent Neural Network, RNN) be trained to obtain
's.
In some optional implementations of the present embodiment, for each of at least one above-mentioned facial image group
Face image group, it is above-mentioned in order to improve the accuracy of age recognition result corresponding with personage corresponding to the facial image group
Executing subject can be based on the corresponding age information of facial image and related information in the facial image group, the determining and face
The corresponding age recognition result of personage corresponding to image group.
As an example, above-mentioned executing subject for example can be using following steps determination and people corresponding to the facial image group
The corresponding age recognition result of object:
Step 2041, for every facial image in the facial image group, based on association corresponding to the facial image
Information determines weighted value corresponding with the facial image.
For example, quality information includes fog-level value, in the facial image group if related information includes quality information
Every facial image, above-mentioned executing subject can be by fuzzy journey corresponding to the first preset value (such as 1) and the facial image
Ratio between angle value is determined as weighted value corresponding to the facial image.Optionally, if related information includes 3 d pose letter
Breath, 3 d pose information includes pitch angle value, yaw angle angle value and rolling angle value, for every in the facial image group
Facial image, above-mentioned executing subject can determine pitch angle angle value, yaw angle angle value corresponding to the facial image and roll angle
Summation between the absolute value of angle value, and the ratio between the first preset value and the summation is determined as corresponding to the facial image
Weighted value.
Step 2042, based on the corresponding weighted value of multiple facial images and age information in the facial image group,
Determine age recognition result corresponding with personage corresponding to the facial image group.
Wherein, which can be all images or parts of images in the facial image group.Determine with
Before the corresponding age recognition result of personage corresponding to the facial image group, above-mentioned executing subject can be first from the face figure
As selecting multiple facial images in group, such as directly select all images in the facial image group.Optionally, above-mentioned to hold
The quantity of facial image in the facial image group can also be compared by row main body with the second preset value, if the quantity exceeds
Second preset value, it is pre- that above-mentioned executing subject can select corresponding weighted value maximum preceding second from the facial image group
If value facial image；If the quantity can be chosen without departing from the second preset value, above-mentioned executing subject from the facial image group
Face images out.Wherein, the second preset value for example can be the length of preset Priority Queues.Above-mentioned executing subject is being selected
After taking out multiple facial images, the preferential team can be written into age information corresponding to multiple facial images and related information
Column.
After selecting multiple facial images in the facial image group, above-mentioned executing subject can be true using following formula
Fixed age recognition result corresponding with personage corresponding to the facial image group:
Wherein, C represents age recognition result；N is the quantity of multiple facial images；I is the nature in [1, n]
Number；W represents weighted value, WiRepresent the corresponding weighted value of i-th facial image in multiple facial images, WnRepresent this multiple
The corresponding weighted value of n-th facial image in facial image；V represents the age value in age information, ViRepresent multiple people
The age value in the corresponding age information of i-th facial image in face image.
With continued reference to the signal that Fig. 3, Fig. 3 are according to the application scenarios of the method at the age for identification of the present embodiment
Figure.In the application scenarios of Fig. 3, personage's video C that user A is issued by social application B can store on server 301.
Wherein, personage's video C can be user A and carry out the resulting video of video record to its people using social application B.In addition, with
Family A not set age in social application B.Age prediction, packet are carried out to user A when server 302 receives to be used to indicate
When including the predictions request of the mark of personage's video C, server 302 can obtain personage's video from server 301 according to the mark
C.Then, server 302 can extract face image set from personage's video C.Later, in face image set
Every facial image, server 302 can parse the facial image, determine age letter corresponding with the facial image
Breath.In addition, server 302 is also based on the matching relationship between facial image, face image set is divided into a people
Face image group.Wherein, facial image group corresponds to user A.Then, server 302 can be based on the face in the facial image group
Age information corresponding to image determines age recognition result corresponding with user A.
The method provided by the above embodiment of the disclosure, by being regarded in response at least one personage for getting user's publication
Frequently, face image set is extracted from least one personage's video, then for every face in face image set
Image parses the facial image, determines age information corresponding with the facial image, and based between facial image
Face image set is divided at least one facial image group by matching relationship, wherein different facial image groups is corresponding different
Personage, so as to for each of at least one above-mentioned facial image group face image group, based in the facial image group
Age information corresponding to facial image determines age recognition result corresponding with personage corresponding to the facial image group.
The scheme provided by the above embodiment of the disclosure may be implemented shown by least one the personage's video issued to user one
Or multiple personages carry out age identification.In addition, when at least one personage's video of user's publication is by carrying out to user
When the resulting video of video record, it may be implemented to accurately identify the age of the user.
With further reference to Fig. 4, it illustrates the processes 400 of another embodiment of the method at age for identification.The use
In the process 400 of the method at identification age, comprising the following steps:
Step 401, at least one the personage's video issued in response to getting user, distinguishes at least one personage's video
Pumping frame is carried out, and the image extracted is formed into image collection.
In the present embodiment, the executing subject (such as server 105 shown in FIG. 1) of the method at age can be with for identification
In response to getting at least one personage's video of user's publication, pumping frame is carried out respectively at least one personage's video, and will
The image composition image collection extracted.Wherein, which can be above-mentioned executing subject from local or institute
What the server (such as server 101 shown in FIG. 1) of connection obtained, it is not specifically limited herein.
It should be noted that above-mentioned user can be the user of specified social application.Specifically, above-mentioned user for example may be used
To be to be not provided with real age in the social application or be not provided with the user at age.Wherein, at least one above-mentioned personage
Video can be the video for showing personage that above-mentioned user is issued by the social application.In addition, at least one above-mentioned personage
Video can be the video that above-mentioned user uses the social application to record.
In the present embodiment, above-mentioned executing subject for example can extract all figures from least one above-mentioned personage's video
Picture, or each of at least one above-mentioned personage's video object image is spaced according to interval frame number (such as 1 or 2 etc.)
Take out frame.It should be understood that interval frame number can be set according to actual needs, it is not specifically limited herein.
Step 402, Face datection is carried out to each image in image collection respectively, obtains Face datection result, wherein
Face datection result corresponding to image including human face region includes the location information and face characteristic information of human face region.
In the present embodiment, above-mentioned executing subject can carry out Face datection to each image in image collection respectively,
Obtain Face datection result, wherein Face datection result corresponding to the image including human face region includes the position of human face region
Confidence breath and face characteristic information.Face characteristic information can be used for characterizing the human face region corresponding to it.
Here, face detection model can have been run in above-mentioned executing subject, above-mentioned executing subject can be by image collection
In every image input the face detection model, obtain corresponding Face datection result.Wherein, Face datection model for example may be used
To be using model-naive Bayesian (Naive Bayesian Model, NBM), support vector machines (Support Vector
Machine, SVM), the models such as XGBoost (eXtreme Gradient Boosting) or convolutional neural networks are trained
It arrives.Whether the image that Face datection model can be used for detecting input includes human face region, when detect the image include people
When face region, it is also used to further carry out positioning to the human face region and face characteristic extracts.
Step 403, based on the location information in Face datection result, face image set is extracted from image collection.
In the present embodiment, above-mentioned executing subject can be based on the location information in Face datection result, from image collection
In extract face image set.
Step 404, for every facial image in face image set, which is parsed, determining should
The corresponding age information of facial image and related information, related information include 3 d pose information and quality information, 3 d pose
Information includes pitch angle value, yaw angle angle value and rolling angle value, and quality information includes fog-level value.
In the present embodiment, for every facial image in face image set, above-mentioned executing subject can be to the people
Face image is parsed, and determines the corresponding age information of the facial image and related information.Wherein, related information includes three-dimensional appearance
State information and quality information.3 d pose information includes pitch angle value, yaw angle angle value and rolling angle value.Quality information packet
Include fog-level value.
As an example, above-mentioned executing subject can be by the face figure for every facial image in face image set
As inputting multiple identification models, much information corresponding with the facial image is obtained.Multiple identification model includes for carrying out
First identification model of age identification and the second identification model identified for being associated information.The much information includes the people
The corresponding age information of face image and related information.Wherein, identification model can be using convolutional neural networks or circulation nerve
What the models such as network were trained.
Step 405, the corresponding face characteristic information of each facial image in face image set is clustered,
And it is based on cluster result, face image set is divided at least one facial image group.
In the present embodiment, above-mentioned executing subject can for example use preset clustering algorithm, such as K mean cluster algorithm
(k-means clustering algorithm) etc., to the corresponding face of each facial image in face image set
Characteristic information is clustered, and is based on cluster result, and face image set is divided at least one facial image group.Here,
Above-mentioned executing subject can will include facial image corresponding to face characteristic information in same class cluster be divided into it is same
In facial image group.
Step 406, for each of at least one facial image group face image group, in the facial image group
Every facial image determines the absolute value of pitch angle angle value, yaw angle angle value corresponding to the facial image and the angle value that rolls
And the summation between corresponding fog-level value, and the ratio between the first preset value and identified summation is determined as
Weighted value corresponding to the facial image.
In the present embodiment, for each of at least one above-mentioned facial image group face image group, for the face
Every facial image in image group, above-mentioned executing subject can determine pitch angle angle value corresponding to the facial image, yaw
Summation between angle value and the absolute value and corresponding fog-level value of the angle value that rolls, and by the first preset value (example
As the ratio 1) between identified summation is determined as weighted value corresponding to the facial image.It should be noted that passing through
Determine weighted value corresponding with facial image, it can be based on identified weighted value, to the facial image institute in facial image group
Age value in corresponding age information is weighted, and can help improve subsequent identified and face figure in this way
As the accuracy of the corresponding age recognition result of the corresponding personage of group.
Step 407, for each of at least one facial image group face image group, based in the facial image group
The corresponding weighted value of multiple facial images and age information, determination are corresponding with personage corresponding to the facial image group
Age recognition result.
In the present embodiment, for each of at least one above-mentioned facial image group face image group, above-mentioned execution master
Body can be based on the corresponding weighted value of multiple facial images and age information in the facial image group, the determining and face
The corresponding age recognition result of personage corresponding to image group.It here, can be referring to Fig. 2 institute for the explanation of step 407
Show the related description of the step 2042 in embodiment, details are not described herein.
Figure 4, it is seen that compared with the corresponding embodiment of Fig. 2, the method at the age for identification in the present embodiment
Process 400 highlight the step of being extended to face image set extracting method；It is determining with it is every in face image set
The step of opening the corresponding age information of facial image and related information；The step that the division methods of facial image group are extended
Suddenly；The step of method for determining age recognition result corresponding with personage corresponding to facial image group is extended.By
This, the diversity of information processing may be implemented in the scheme of the present embodiment description, and can be further improved age recognition result
Accuracy.
With further reference to Fig. 5, as the realization to method shown in above-mentioned each figure, present disclose provides a kind of years for identification
One embodiment of the device in age, the Installation practice is corresponding with embodiment of the method shown in Fig. 2, which can specifically answer
For in various electronic equipments.
As shown in figure 5, the device 500 at the age for identification of the present embodiment may include: that extraction unit 501 is configured to
In response to getting at least one personage's video of user's publication, facial image is extracted from least one above-mentioned personage's video
Set；First determination unit 502 is configured to carry out the facial image every facial image in face image set
Parsing determines age information corresponding with the facial image；Division unit 503 is configured to based on the matching between facial image
Face image set is divided at least one facial image group, wherein different facial image groups correspond to different people by relationship
Object；Second determination unit 504 is configured to for each of at least one above-mentioned facial image group face image group, and being based on should
Age information corresponding to facial image in facial image group, determination are corresponding with personage corresponding to the facial image group
Age recognition result.
In the present embodiment, for identification in the device 500 at age: extraction unit 501, divides first determination unit 502
The specific processing of unit 503 and the second determination unit 504 and its brought technical effect can refer to implementation shown in Fig. 2 respectively
Step 201, step 202, the related description of step 203 and step 204 in example, details are not described herein.
In some optional implementations of the present embodiment, extraction unit 501 can be further configured to: to above-mentioned
At least one personage's video carries out pumping frame respectively, and the image extracted is formed image collection；To each in image collection
Image carries out Face datection respectively, obtains Face datection result, wherein Face datection corresponding to the image including human face region
It as a result include the location information of human face region；Based on the location information in Face datection result, people is extracted from image collection
Face image set.
In some optional implementations of the present embodiment, Face datection knot corresponding to the image including human face region
Fruit further includes face characteristic information；And division unit 503 can be further configured to: to each in face image set
The corresponding face characteristic information of facial image is clustered, and be based on cluster result, by face image set be divided into
A few facial image group.
In some optional implementations of the present embodiment, the first determination unit 502 can be further configured to: right
Every facial image in face image set, parses to the facial image, and determination is corresponding with the facial image
When age information, also determine that the corresponding related information of the facial image, related information include at least one of the following: that 3 d pose is believed
Breath, quality information；And second determination unit 504 can be further configured to: at least one above-mentioned facial image group
Each of face image group determined based on the corresponding age information of facial image and related information in the facial image group
Age recognition result corresponding with personage corresponding to the facial image group.
In some optional implementations of the present embodiment, the first determination unit 502 can be further configured to: right
The facial image is inputted multiple identification models, obtained and the facial image by every facial image in face image set
Corresponding much information, multiple identification model include the first identification model for carrying out age identification and for being associated
Second identification model of information identification, which includes the corresponding age information of the facial image and related information.
In some optional implementations of the present embodiment, the second determination unit 504 can be further configured to: right
In each of at least one above-mentioned facial image group face image group, for every facial image in the facial image group,
Based on related information corresponding to the facial image, weighted value corresponding with the facial image is determined；Based on the facial image group
In the corresponding weighted value of multiple facial images and age information, it is determining with figure picture pair corresponding to the facial image group
The age recognition result answered.
In some optional implementations of the present embodiment, related information may include 3 d pose information, three-dimensional appearance
State information may include pitch angle angle value, yaw angle angle value and rolling angle value；And second determination unit 504 can be further
It is configured to: for each of at least one above-mentioned facial image group face image group, for every in the facial image group
Facial image, determine pitch angle angle value, yaw angle angle value corresponding to the facial image and the angle value that rolls absolute value it
Between summation, and the ratio between the first preset value and identified summation is determined as weight corresponding to the facial image
Value.
In some optional implementations of the present embodiment, related information may include 3 d pose information and quality letter
Breath, 3 d pose information may include pitch angle angle value, yaw angle angle value and rolling angle value, and quality information may include obscuring
Degree value；And second determination unit 504 can be further configured to: for every at least one above-mentioned facial image group
A facial image group determines pitch angle corresponding to the facial image for every facial image in the facial image group
Summation between value, yaw angle angle value and the absolute value and corresponding fog-level value of the angle value that rolls, and it is pre- by first
If the ratio between value and identified summation is determined as weighted value corresponding to the facial image.
In some optional implementations of the present embodiment, the second determination unit 504 can be further configured to: right
In each of at least one above-mentioned facial image group face image group, it is right with the facial image group institute to be determined using following formula
The corresponding age recognition result of the personage answered:
Wherein, C represents age recognition result；N is the quantity of multiple facial images in facial image group；I be in [1,
N] in natural number；W represents weighted value, WiRepresent the corresponding weighted value of i-th facial image in multiple facial images, Wn
Represent the corresponding weighted value of n-th facial image in multiple facial images；V represents the age value in age information, ViGeneration
The age value in the corresponding age information of i-th facial image in table multiple facial images.
In some optional implementations of the present embodiment, the second determination unit 504 can be further configured to: right
In each of at least one above-mentioned facial image group face image group, each facial image in the facial image group is distinguished
Age value in corresponding age information is averaged, and average value is determined as and figure picture pair corresponding to the facial image group
The age recognition result answered.
The device provided by the above embodiment of the disclosure, by being regarded in response at least one personage for getting user's publication
Frequently, face image set is extracted from least one personage's video, then for every face in face image set
Image parses the facial image, determines age information corresponding with the facial image, and based between facial image
Face image set is divided at least one facial image group by matching relationship, wherein different facial image groups is corresponding different
Personage, so as to for each of at least one above-mentioned facial image group face image group, based in the facial image group
Age information corresponding to facial image determines age recognition result corresponding with personage corresponding to the facial image group.
The scheme provided by the above embodiment of the disclosure may be implemented shown by least one the personage's video issued to user one
Or multiple personages carry out age identification.In addition, when at least one personage's video of user's publication is by carrying out to user
When the resulting video of video record, it may be implemented to accurately identify the age of the user.
Below with reference to Fig. 6, it illustrates the electronic equipment that is suitable for being used to realize embodiment of the disclosure, (example is as shown in figure 1
Server 103) 600 structural schematic diagram.Terminal device in embodiment of the disclosure can include but is not limited to such as move
Phone, laptop, digit broadcasting receiver, PDA (personal digital assistant), PAD (tablet computer), PMP (portable more matchmakers
Body player), the mobile terminal of car-mounted terminal (such as vehicle mounted guidance terminal) etc. and number TV, desktop computer etc.
Deng fixed terminal.Electronic equipment shown in Fig. 6 is only an example, should not function and use to embodiment of the disclosure
Range band carrys out any restrictions.
As shown in fig. 6, electronic equipment 600 may include processing unit (such as central processing unit, graphics processor etc.)
601, random access can be loaded into according to the program being stored in read-only memory (ROM) 602 or from storage device 608
Program in memory (RAM) 603 and execute various movements appropriate and processing.In RAM 603, it is also stored with electronic equipment
Various programs and data needed for 600 operations.Processing unit 601, ROM 602 and RAM 603 pass through the phase each other of bus 604
Even.Input/output (I/O) interface 605 is also connected to bus 604.
In general, following device can connect to I/O interface 605: including such as touch screen, touch tablet, keyboard, mouse, taking the photograph
As the input unit 606 of head, microphone, accelerometer, gyroscope etc.；Including such as liquid crystal display (LCD), loudspeaker, vibration
The output device 607 of dynamic device etc.；Storage device 608 including such as hard disk etc.；And communication device 609.Communication device 609 can
To allow electronic equipment 600 wirelessly or non-wirelessly to be communicated with other equipment to exchange data.Although Fig. 6 is shown with various
The electronic equipment 600 of device, it should be understood that being not required for implementing or having all devices shown.It can be alternatively
Implement or have more or fewer devices.Each box shown in Fig. 6 can represent a device, also can according to need
Represent multiple devices.
Particularly, in accordance with an embodiment of the present disclosure, it may be implemented as computer above with reference to the process of flow chart description
Software program.For example, embodiment of the disclosure includes a kind of computer program product comprising be carried on computer-readable medium
On computer program, which includes the program code for method shown in execution flow chart.In such reality
It applies in example, which can be downloaded and installed from network by communication device 609, or from storage device 608
It is mounted, or is mounted from ROM 602.When the computer program is executed by processing unit 601, the implementation of the disclosure is executed
The above-mentioned function of being limited in the method for example.
It is situated between it should be noted that computer-readable medium described in embodiment of the disclosure can be computer-readable signal
Matter or computer readable storage medium either the two any combination.Computer readable storage medium for example can be with
System, device or the device of --- but being not limited to --- electricity, magnetic, optical, electromagnetic, infrared ray or semiconductor, or it is any more than
Combination.The more specific example of computer readable storage medium can include but is not limited to: have one or more conducting wires
Electrical connection, portable computer diskette, hard disk, random access storage device (RAM), read-only memory (ROM), erasable type are programmable
Read-only memory (EPROM or flash memory), optical fiber, portable compact disc read-only memory (CD-ROM), light storage device, magnetic are deposited
Memory device or above-mentioned any appropriate combination.In embodiment of the disclosure, computer readable storage medium, which can be, appoints
What include or the tangible medium of storage program that the program can be commanded execution system, device or device use or and its
It is used in combination.And in embodiment of the disclosure, computer-readable signal media may include in a base band or as carrier wave
The data-signal that a part is propagated, wherein carrying computer-readable program code.The data-signal of this propagation can be adopted
With diversified forms, including but not limited to electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal is situated between
Matter can also be any computer-readable medium other than computer readable storage medium, which can be with
It sends, propagate or transmits for by the use of instruction execution system, device or device or program in connection.Meter
The program code for including on calculation machine readable medium can transmit with any suitable medium, including but not limited to: electric wire, optical cable,
RF (radio frequency) etc. or above-mentioned any appropriate combination.
Above-mentioned computer-readable medium can be included in above-mentioned electronic equipment；It is also possible to individualism, and not
It is fitted into the electronic equipment.Above-mentioned computer-readable medium carries one or more program, when said one or more
When a program is executed by the electronic equipment, so that the electronic equipment: at least one personage in response to getting user's publication regards
Frequently, face image set is extracted from least one above-mentioned personage's video；For every face figure in face image set
Picture parses the facial image, determines age information corresponding with the facial image；Based on the matching between facial image
Face image set is divided at least one facial image group, wherein different facial image groups correspond to different people by relationship
Object；For each of at least one above-mentioned facial image group face image group, based on the facial image in the facial image group
Corresponding age information determines age recognition result corresponding with personage corresponding to the facial image group.
The behaviour for executing embodiment of the disclosure can be write with one or more programming languages or combinations thereof
The computer program code of work, 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 program design language
Speech.Program code can be executed fully on the user computer, partly be executed on the user computer, as an independence
Software package execute, part on the user computer part execute on the remote computer or completely in remote computer or
It is executed on server.In situations involving remote computers, remote computer can pass through the network of any kind --- packet
It includes local area network (LAN) or wide area network (WAN)-is connected to subscriber computer, or, it may be connected to outer computer (such as benefit
It is connected with ISP by internet).
Flow chart and block diagram in attached drawing are illustrated according to the system of the various embodiments of the disclosure, method and computer journey
The architecture, function and operation in the cards of sequence product.In this regard, each box in flowchart or block diagram can generation
A part of one module, program segment or code of table, a part of the module, program segment or code include one or more use
The executable instruction of the logic function as defined in realizing.It should also be noted that in some implementations as replacements, being marked in box
The function of note can also occur in a different order than that indicated in the drawings.For example, two boxes succeedingly indicated are actually
It can be basically executed in parallel, they can also be executed in the opposite order sometimes, and this depends on the function involved.Also it to infuse
Meaning, the combination of each box in block diagram and or flow chart and the box in block diagram and or flow chart can be with holding
The dedicated hardware based system of functions or operations as defined in row is realized, or can use specialized hardware and computer instruction
Combination realize.
Being described in unit involved in the embodiment of the present disclosure can be realized by way of software, can also be by hard
The mode of part is realized.Wherein, the title of unit does not constitute the restriction to the unit itself under certain conditions, for example, mentioning
Unit is taken to be also described as " extracting the unit of face image set from least one personage's video ".
Above description is only the preferred embodiment of the disclosure and the explanation to institute's application technology principle.Those skilled in the art
Member is it should be appreciated that the open scope involved in the disclosure, however it is not limited to technology made of the specific combination of above-mentioned technical characteristic
Scheme, while should also cover in the case where not departing from design disclosed above, it is carried out by above-mentioned technical characteristic or its equivalent feature
Any combination and the other technical solutions formed.Such as features described above has similar function with (but being not limited to) disclosed in the disclosure
Can technical characteristic replaced mutually and the technical solution that is formed.
Claims (15)
1. a kind of method at age for identification, comprising:
In response to getting at least one personage's video of user's publication, face is extracted from least one described personage's video
Image collection；
For every facial image in the face image set, which is parsed, the determining and face figure
As corresponding age information；
Based on the matching relationship between facial image, the face image set is divided at least one facial image group,
In, different facial image groups corresponds to different personages；
For each of at least one facial image group face image group, based on the facial image in the facial image group
Corresponding age information determines age recognition result corresponding with personage corresponding to the facial image group.
2. described to extract facial image from least one described personage's video according to the method described in claim 1, wherein
Set, comprising:
Pumping frame is carried out at least one described personage's video respectively, and the image extracted is formed into image collection；
Face datection is carried out to each image in described image set respectively, obtains Face datection result, wherein including face
Face datection result corresponding to the image in region includes the location information of human face region；
Based on the location information in Face datection result, face image set is extracted from described image set.
3. according to the method described in claim 2, wherein, Face datection result corresponding to the image including human face region is also wrapped
Include face characteristic information；And
The face image set is divided at least one facial image by the matching relationship based between facial image
Group, comprising:
The corresponding face characteristic information of each facial image in the face image set is clustered, and based on poly-
Class is as a result, be divided at least one facial image group for the face image set.
4. method described in one of -3 according to claim 1, wherein for every face figure in the face image set
Picture is parsed to the facial image, when determining the corresponding age information of the facial image, the method also includes:
Determine that the corresponding related information of the facial image, the related information include at least one of the following: 3 d pose information, matter
Measure information；And
Age information corresponding to the facial image based in the facial image group, it is determining with corresponding to the facial image group
The corresponding age recognition result of personage, comprising:
Based on the corresponding age information of facial image and related information in the facial image group, the determining and facial image group institute
The corresponding age recognition result of corresponding personage.
5. according to the method described in claim 4, wherein, for every facial image in the face image set, to this
Facial image is parsed, and determines the corresponding age information of the facial image and related information, comprising:
For every facial image in the face image set, which is inputted into multiple identification models, obtain with
The corresponding much information of the facial image, the multiple identification model include for carry out the first identification model of age identification and
For be associated information identification the second identification model, the much information include the corresponding age information of the facial image and
Related information.
6. according to the method described in claim 4, wherein, the facial image corresponding age based in the facial image group
Information and related information determine age recognition result corresponding with personage corresponding to the facial image group, comprising:
For every facial image in the facial image group, based on related information corresponding to the facial image, determines and be somebody's turn to do
The corresponding weighted value of facial image；Based on the corresponding weighted value of multiple facial images and age letter in the facial image group
Breath determines age recognition result corresponding with personage corresponding to the facial image group.
7. 3 d pose information includes according to the method described in claim 6, wherein, related information includes 3 d pose information
Pitch angle angle value, yaw angle angle value and rolling angle value；And
It is described based on related information corresponding to the facial image, determine weighted value corresponding with the facial image, comprising:
It determines total between pitch angle angle value, yaw angle angle value corresponding to the facial image and the absolute value for the angle value that rolls
With, and the ratio between the first preset value and identified summation is determined as weighted value corresponding to the facial image.
8. according to the method described in claim 6, wherein, related information includes 3 d pose information and quality information, three-dimensional appearance
State information includes pitch angle value, yaw angle angle value and rolling angle value, and quality information includes fog-level value；And
It is described based on related information corresponding to the facial image, determine weighted value corresponding with the facial image, comprising:
Determine pitch angle angle value, yaw angle angle value corresponding to the facial image and the absolute value of angle value and corresponding of rolling
Fog-level value between summation, and the ratio between the first preset value and identified summation is determined as the facial image
Corresponding weighted value.
9. described right respectively based on multiple facial images in the facial image group according to the method described in claim 6, wherein
The weighted value and age information answered determine age recognition result corresponding with personage corresponding to the facial image group, comprising:
Age recognition result corresponding with personage corresponding to the facial image group is determined using following formula:
Wherein, C represents age recognition result；N is the quantity of multiple facial images；I is the natural number in [1, n]；W
Represent weighted value, WiRepresent the corresponding weighted value of i-th facial image in multiple described facial images, WnRepresent it is described multiple
The corresponding weighted value of n-th facial image in facial image；V represents the age value in age information, ViRepresent it is described multiple
The age value in the corresponding age information of i-th facial image in facial image.
10. method described in one of -3 according to claim 1, wherein the facial image institute based in the facial image group
Corresponding age information determines age recognition result corresponding with personage corresponding to the facial image group, comprising:
It averages to the age value in the corresponding age information of each facial image in the facial image group, it will be described
Average value is determined as age recognition result corresponding with personage corresponding to the facial image group.
11. a kind of device at age for identification, comprising:
Extraction unit is configured in response to get at least one personage's video of user's publication, from least one described people
Face image set is extracted in object video；
First determination unit, is configured to for every facial image in the face image set, to the facial image into
Row parsing, determines age information corresponding with the facial image；
Division unit is configured to be divided into the face image set at least based on the matching relationship between facial image
One facial image group, wherein different facial image groups correspond to different personages；
Second determination unit is configured to for each of at least one facial image group face image group, and being based on should
Age information corresponding to facial image in facial image group, determination are corresponding with personage corresponding to the facial image group
Age recognition result.
12. device according to claim 11, wherein first determination unit is further configured to:
It for every facial image in the face image set, is parsed to the facial image, the determining and face
When the corresponding age information of image, also determine the corresponding related information of the facial image, the related information include it is following at least
One: 3 d pose information, quality information；And
Second determination unit is further configured to:
For each of at least one facial image group face image group, based on the facial image in the facial image group
Corresponding age information and related information determine age recognition result corresponding with personage corresponding to the facial image group.
13. device according to claim 12, wherein second determination unit is further configured to:
For each of at least one facial image group face image group, for every face in the facial image group
Image determines weighted value corresponding with the facial image based on related information corresponding to the facial image；Based on the face figure
As the corresponding weighted value of multiple facial images and age information in group, determination and personage corresponding to the facial image group
Corresponding age recognition result.
14. a kind of electronic equipment, comprising:
One or more processors；
Storage device is stored thereon with 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 1-10.
15. a kind of computer-readable medium, is stored thereon with computer program, wherein real when described program is executed by processor
The now method as described in any in claim 1-10.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910447129.XA CN110163170A (en) | 2019-05-27 | 2019-05-27 | The method and apparatus at age for identification |
| PCT/CN2020/078589 WO2020238321A1 (en) | 2019-05-27 | 2020-03-10 | Method and device for age identification |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910447129.XA CN110163170A (en) | 2019-05-27 | 2019-05-27 | The method and apparatus at age for identification |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110163170A true CN110163170A (en) | 2019-08-23 |
Family
ID=67629048
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910447129.XA Pending CN110163170A (en) | 2019-05-27 | 2019-05-27 | The method and apparatus at age for identification |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN110163170A (en) |
| WO (1) | WO2020238321A1 (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020238321A1 (en) * | 2019-05-27 | 2020-12-03 | 北京字节跳动网络技术有限公司 | Method and device for age identification |
| CN114022156A (en) * | 2022-01-05 | 2022-02-08 | 浙江口碑网络技术有限公司 | Easy-to-check mode selection method and device and electronic equipment |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112766238B (en) * | 2021-03-15 | 2023-09-26 | 电子科技大学中山学院 | Age prediction method and device |
| CN115471893B (en) * | 2022-09-16 | 2023-11-21 | 北京百度网讯科技有限公司 | Face recognition model training, face recognition method and device |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101584575A (en) * | 2009-06-19 | 2009-11-25 | 无锡骏聿科技有限公司 | Age assessment method based on face recognition technology |
| KR20160110741A (en) * | 2015-03-11 | 2016-09-22 | 동국대학교 산학협력단 | Device and method for human age estimation |
| CN108131791A (en) * | 2017-12-04 | 2018-06-08 | 广东美的制冷设备有限公司 | Control method, device and the server of home appliance |
| CN109190449A (en) * | 2018-07-09 | 2019-01-11 | 北京达佳互联信息技术有限公司 | Age recognition methods, device, electronic equipment and storage medium |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104036236B (en) * | 2014-05-27 | 2017-03-29 | 厦门瑞为信息技术有限公司 | A kind of face gender identification method based on multiparameter exponential weighting |
| CN108734146A (en) * | 2018-05-28 | 2018-11-02 | 北京达佳互联信息技术有限公司 | Facial image Age estimation method, apparatus, computer equipment and storage medium |
| CN109086680A (en) * | 2018-07-10 | 2018-12-25 | Oppo广东移动通信有限公司 | Image processing method, device, storage medium and electronic equipment |
| CN110163171B (en) * | 2019-05-27 | 2020-07-31 | 北京字节跳动网络技术有限公司 | Method and device for recognizing human face attributes |
| CN110163170A (en) * | 2019-05-27 | 2019-08-23 | 北京字节跳动网络技术有限公司 | The method and apparatus at age for identification |
| CN110188660B (en) * | 2019-05-27 | 2021-07-02 | 北京字节跳动网络技术有限公司 | Method and device for identifying age |
-
2019
- 2019-05-27 CN CN201910447129.XA patent/CN110163170A/en active Pending
-
2020
- 2020-03-10 WO PCT/CN2020/078589 patent/WO2020238321A1/en active Application Filing
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101584575A (en) * | 2009-06-19 | 2009-11-25 | 无锡骏聿科技有限公司 | Age assessment method based on face recognition technology |
| KR20160110741A (en) * | 2015-03-11 | 2016-09-22 | 동국대학교 산학협력단 | Device and method for human age estimation |
| CN108131791A (en) * | 2017-12-04 | 2018-06-08 | 广东美的制冷设备有限公司 | Control method, device and the server of home appliance |
| CN109190449A (en) * | 2018-07-09 | 2019-01-11 | 北京达佳互联信息技术有限公司 | Age recognition methods, device, electronic equipment and storage medium |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020238321A1 (en) * | 2019-05-27 | 2020-12-03 | 北京字节跳动网络技术有限公司 | Method and device for age identification |
| CN114022156A (en) * | 2022-01-05 | 2022-02-08 | 浙江口碑网络技术有限公司 | Easy-to-check mode selection method and device and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2020238321A1 (en) | 2020-12-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110163170A (en) | The method and apparatus at age for identification | |
| CN110162670A (en) | Method and apparatus for generating expression packet | |
| CN110110811A (en) | Method and apparatus for training pattern, the method and apparatus for predictive information | |
| CN109993150A (en) | The method and apparatus at age for identification | |
| CN110245612A (en) | The detection method and device of facial image | |
| CN110210393A (en) | The detection method and device of facial image | |
| CN107644209A (en) | Method for detecting human face and device | |
| CN109859096A (en) | Image Style Transfer method, apparatus, electronic equipment and storage medium | |
| CN109740018A (en) | Method and apparatus for generating video tab model | |
| CN108446390A (en) | Method and apparatus for pushed information | |
| CN109919244A (en) | Method and apparatus for generating scene Recognition model | |
| CN111552888A (en) | Content recommendation method, device, equipment and storage medium | |
| CN109872242A (en) | Information-pushing method and device | |
| CN108345387A (en) | Method and apparatus for output information | |
| CN110163171A (en) | The method and apparatus of face character for identification | |
| CN108595628A (en) | Method and apparatus for pushed information | |
| CN108831505A (en) | The method and apparatus for the usage scenario applied for identification | |
| CN109934191A (en) | Information processing method and device | |
| CN109871834A (en) | Information processing method and device | |
| CN109918530A (en) | Method and apparatus for pushing image | |
| CN109947989A (en) | Method and apparatus for handling video | |
| CN110188660A (en) | The method and apparatus at age for identification | |
| CN110059623A (en) | Method and apparatus for generating information | |
| CN108446658A (en) | The method and apparatus of facial image for identification | |
| CN110046571A (en) | The method and apparatus at age for identification |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190823 |