CN108446688A - Facial image Sexual discriminating method, apparatus, computer equipment and storage medium - Google Patents
Facial image Sexual discriminating method, apparatus, computer equipment and storage medium Download PDFInfo
- Publication number
- CN108446688A CN108446688A CN201810525407.4A CN201810525407A CN108446688A CN 108446688 A CN108446688 A CN 108446688A CN 201810525407 A CN201810525407 A CN 201810525407A CN 108446688 A CN108446688 A CN 108446688A
- Authority
- CN
- China
- Prior art keywords
- facial image
- gender
- value
- neural network
- classification
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- 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
- G06V40/172—Classification, e.g. identification
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The embodiment of the invention discloses a kind of facial image Sexual discriminating method, apparatus, computer equipment and storage mediums, include the following steps：Obtain facial image to be judged；The facial image is input in preset neural network model；Gender Classification is carried out to the facial image according to the grouped data of neural network model output.When being trained to the neural network model for carrying out face gender judgement, unified expectation processing is carried out to the photo that same person is shot in different space environments, the multiple genders for obtaining same person difference photo it is expected, then the median taken in ranking results is ranked up to gender expectation, gender desired value as same people's difference photo, since training sample concentrates the different photo gender desired values of same people identical, pass through this kind of photo training to convergent neural network model, it is high to the gender of same people scoring output stability in different environments, it is not easily susceptible to the influence of environment.
Description
Technical field
The present embodiments relate to model algorithm field, especially a kind of facial image Sexual discriminating method, apparatus calculates
Machine equipment and storage medium.
Background technology
Higher and higher with the accuracy of face recognition algorithms, an important role of face recognition is, by right
The gender of facial image is classified, and conclusion management is carried out to numerous facial images.
In the prior art, main using the method for deep learning when human body face image being compared and application class
The method flow wanted is：According to preset work purpose, until repetition training convolutional neural networks model to the model is restrained, volume
After the completion of product neural network model training, the facial image for being intended to classify or handle is input to trained convolutional neural networks mould
In type, the weight proportion that convolutional neural networks model learns according to training is classified or is handled to the facial image, thus
, it can be seen that the method for deep learning becomes one by repetition training, by model training has certain identification and judgement
System.
The inventor of the invention has found under study for action, in the prior art by training convolutional neural networks model to figure
As when being handled, same personage the face picture under different scenes obtain the result is that inconsistent, some even phases
Difference is bigger, for example often the Sexual discriminating of people is more accurate under bright illumination condition, under the conditions of illumination is unconspicuous,
Often the Sexual discriminating of people is susceptible to entanglement, and the amplification of data variation is difficult to make e-learning to this consistency, therefore,
The stability of model is relatively low in the prior art, protected from environmental larger.
Invention content
Offer of the embodiment of the present invention is capable of providing a kind of grouped data and more stablizes, smaller face figure protected from environmental
As Sexual discriminating method, apparatus, computer equipment and storage medium.
In order to solve the above technical problems, the technical solution that the embodiment of the invention uses is：A kind of people is provided
Face image Sexual discriminating method, includes the following steps：
Obtain facial image to be judged；
The facial image is input in preset neural network model, wherein when the training neural network model
The gender desired value of the training sample set of multiple images composition of same target source is the median in multiple judgment values；
Gender Classification is carried out to the facial image according to the grouped data of neural network model output.
Optionally, the neural network model is set there are two class categories；It is described to be exported according to the neural network model
Grouped data to the facial image carry out Gender Classification the step of, specifically include following step：
Obtain two classification values of the neural network model output；
Confirm that the class categories in described two classification values corresponding to the maximum classification value of numerical value are Gender Classification result.
Optionally, described the step of obtaining facial image to be judged, include the following steps：
Obtain target video；
The timing extraction frame picture from the target video, and judge to whether there is facial image in the frame picture；
When there are the facial images that when facial image, to confirm the frame picture image be to be judged in the frame picture.
Optionally, the grouped data according to neural network model output carries out gender point to the facial image
Further include following step after the step of class：
Obtain gender classification results；
The facial image is input to preset picture material according to the Gender Classification result and understands that model is corresponding
In input channel, wherein described image content understanding model is set there are two input channel, each input channel corresponds to a kind of property
Other type；
Obtain the content understanding data of described image content understanding model output.
Optionally, described image content understanding model is face value disaggregated model；It is described defeated according to the neural network model
Further include following step after the step of grouped data gone out carries out Gender Classification to the facial image：
Obtain gender classification results；
The facial image is input in the corresponding input channel of face value disaggregated model according to the Gender Classification result,
Wherein, the face value disaggregated model is set there are two input channel, each input channel corresponds to a kind of sex types；
Obtain the face value grouped data of the face value disaggregated model output.
Optionally, the training method of the neural network model includes：
The training sample set is obtained, the training sample set includes multiple facial images of same target；
Multiple described facial images are sequentially inputted in preset first disaggregated model, obtain multiple described faces respectively
The Gender Classification value of image；
The Gender Classification value of multiple facial images is ranked up using numerical value as qualifications；
Confirm that Gender Classification value in an intermediate position in the ranking results is the expectation point of multiple facial images
Class value.
Optionally, described to confirm that Gender Classification value in an intermediate position in the ranking results is multiple described face figures
Further include following step after the step of expectation classification value of picture：
The training sample set is input in the neural network model, swashing for the neural network model output is obtained
Encourage classification value；
Compare whether the distance between the expectation classification value and the excitation classification value are less than or equal to preset first
Threshold value；
When the distance between the expectation classification value and the excitation classification value are more than preset first threshold, follow repeatedly
Ring iterative updates the weight in the neural network model by inverse algorithms, until the expectation classification value swashs with described
Terminate when encouraging the distance between classification value less than or equal to preset first threshold.
In order to solve the above technical problems, the embodiment of the present invention also provides a kind of facial image Sexual discriminating device, including：
Acquisition module, for obtaining facial image to be judged；
Processing module, for the facial image to be input in preset neural network model, wherein the training god
The gender desired value of the training sample set of multiple images composition of same target source is in multiple judgment values when through network model
Median；
Execution module, the grouped data for being exported according to the neural network model carry out gender to the facial image
Classification.
Optionally, the neural network model is set there are two class categories；The facial image Sexual discriminating device also wraps
It includes：
First acquisition submodule, two classification values for obtaining the neural network model output；
First confirms submodule, for confirming the classification class in described two classification values corresponding to the maximum classification value of numerical value
It Wei not Gender Classification result.
Optionally, the facial image Sexual discriminating device further includes：
Second acquisition submodule, for obtaining target video；
First processing submodule, for the timing extraction frame picture from the target video, and judges in the frame picture
With the presence or absence of facial image；
First implementation sub-module, for when there are when facial image, confirm that the frame picture image is in the frame picture
Facial image to be judged.
Optionally, the facial image Sexual discriminating device further includes：
Third acquisition submodule, for obtaining gender classification results；
Second processing submodule, for the facial image to be input to preset image according to the Gender Classification result
In the corresponding input channel of content understanding model, wherein described image content understanding model is set there are two input channel, each
Input channel corresponds to a kind of sex types；
Second implementation sub-module, the content understanding data for obtaining the output of described image content understanding model.
Optionally, described image content understanding model is face value disaggregated model；The facial image Sexual discriminating device is also
Including：
4th acquisition submodule, for obtaining gender classification results；
Third handles submodule, for the facial image to be input to face value classification mould according to the Gender Classification result
In the corresponding input channel of type, wherein the face value disaggregated model is set there are two input channel, each input channel corresponds to one
Kind sex types；
Third implementation sub-module, the face value grouped data for obtaining the face value disaggregated model output.
Optionally, the facial image Sexual discriminating device further includes：
5th acquisition submodule, for obtaining the training sample set, the training sample set includes the more of same target
Open facial image；
Fourth process submodule, for multiple described facial images to be sequentially inputted in preset first disaggregated model,
The Gender Classification value of multiple facial images is obtained respectively；
First sorting sub-module, for being carried out to the Gender Classification value of multiple facial images using numerical value as qualifications
Sequence；
4th implementation sub-module, for confirming that Gender Classification value in an intermediate position in the ranking results is described more
Open the expectation classification value of facial image.
Optionally, the facial image Sexual discriminating device further includes：
First input submodule, for the training sample set to be input in the neural network model, described in acquisition
The excitation classification value of neural network model output；
Whether first compares submodule, small for comparing the distance between the expectation classification value and the excitation classification value
In or equal to preset first threshold；
5th implementation sub-module, for being preset when the distance between the expectation classification value and the excitation classification value are more than
First threshold when, iterative cycles iteration updates the weight in the neural network model by inverse algorithms, until the institute
Terminate when stating the distance between desired classification value and the excitation classification value less than or equal to preset first threshold.
In order to solve the above technical problems, the embodiment of the present invention also provides a kind of computer equipment, including memory and processing
Device is stored with computer-readable instruction in the memory, when the computer-readable instruction is executed by the processor so that
The processor executes the step of facial image Sexual discriminating method described above.
In order to solve the above technical problems, the embodiment of the present invention also provides a kind of storage Jie being stored with computer-readable instruction
Matter, when the computer-readable instruction is executed by one or more processors so that one or more processors execute above-mentioned institute
The step of stating facial image Sexual discriminating method.
The advantageous effect of the embodiment of the present invention is：It is trained to the neural network model for carrying out face gender judgement
When, unified expectation processing is carried out to the photo that same person is shot in different space environments, obtains same person difference photograph
Multiple genders of piece it is expected, are then ranked up the median taken in ranking results to gender expectation, are shone as same people's difference
The gender desired value of piece, i.e., whether the environment no matter residing photo of same people is is identical, the gender desired value of all photos
All same.Then the facial image for being marked with gender desired value will be input in the neural network model of Sexual discriminating, to god
It is trained through network model, since training sample concentrates the different photo gender desired values of same people identical, passes through this one kind
Photo training is high to the gender of same people scoring output stability in different environments to convergent neural network model, no
It is vulnerable to the influence of environment.
Description of the drawings
To describe the technical solutions in the embodiments of the present invention more clearly, make required in being described below to embodiment
Attached drawing is briefly described, it should be apparent that, drawings in the following description are only some embodiments of the invention, for
For those skilled in the art, without creative efforts, it can also be obtained according to these attached drawings other attached
Figure.
Fig. 1 is the basic procedure schematic diagram of facial image Sexual discriminating method of the embodiment of the present invention；
Fig. 2 is the flow diagram that the embodiment of the present invention judges class categories；
Fig. 3 is the extracting method flow diagram of facial image of the embodiment of the present invention；
Fig. 4 is the flow diagram that the embodiment of the present invention carries out facial image further content understanding；
Fig. 5 is the flow diagram that the embodiment of the present invention carries out facial image face value scoring；
Fig. 6 is the acquisition methods flow diagram that the embodiment of the present invention it is expected classification value；
Fig. 7 is the training method flow diagram of neural network model of the embodiment of the present invention；
Fig. 8 is facial image Sexual discriminating device basic structure schematic diagram of the embodiment of the present invention；
Fig. 9 is computer equipment basic structure block diagram of the embodiment of the present invention.
Specific implementation mode
In order to enable those skilled in the art to better understand the solution of the present invention, below in conjunction in the embodiment of the present invention
Attached drawing, technical scheme in the embodiment of the invention is clearly and completely described.
In some flows of description in description and claims of this specification and above-mentioned attached drawing, contain according to
Multiple operations that particular order occurs, but it should be clearly understood that these operations can not be what appears in this article suitable according to its
Sequence is executed or is executed parallel, and the serial number such as 101,102 etc. of operation is only used for distinguishing each different operation, serial number
It itself does not represent and any executes sequence.In addition, these flows may include more or fewer operations, and these operations can
To execute or execute parallel in order.It should be noted that the descriptions such as " first " herein, " second ", are for distinguishing not
Same message, equipment, module etc., does not represent sequencing, does not also limit " first " and " second " and be different type.
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation describes, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, the every other implementation that those skilled in the art are obtained without creative efforts
Example, shall fall within the protection scope of the present invention.
It includes wireless communication that those skilled in the art of the present technique, which are appreciated that " terminal " used herein above, " terminal device " both,
The equipment of number receiver, only has the equipment of the wireless signal receiver of non-emissive ability, and includes receiving and transmitting hardware
Equipment, have on bidirectional communication link, can execute two-way communication reception and emit hardware equipment.This equipment
May include：Honeycomb or other communication equipments are shown with single line display or multi-line display or without multi-line
The honeycomb of device or other communication equipments；PCS (Personal Communications Service, PCS Personal Communications System), can
With combine voice, data processing, fax and/or communication ability；PDA (Personal Digital Assistant, it is personal
Digital assistants), may include radio frequency receiver, pager, the Internet/intranet access, web browser, notepad, day
It goes through and/or GPS (Global Positioning System, global positioning system) receiver；Conventional laptop and/or palm
Type computer or other equipment, have and/or the conventional laptop including radio frequency receiver and/or palmtop computer or its
His equipment." terminal " used herein above, " terminal device " they can be portable, can transport, be mounted on the vehicles (aviation,
Sea-freight and/or land) in, or be suitable for and/or be configured in local runtime, and/or with distribution form, operate in the earth
And/or any other position operation in space." terminal " used herein above, " terminal device " can also be communication terminal, on
Network termination, music/video playback terminal, such as can be PDA, MID (Mobile Internet Device, mobile Internet
Equipment) and/or mobile phone with music/video playing function, can also be the equipment such as smart television, set-top box.
Specifically referring to Fig. 1, Fig. 1 is the basic procedure schematic diagram of the present embodiment facial image Sexual discriminating method.
As shown in Figure 1, a kind of facial image Sexual discriminating method, includes the following steps：
S1100, facial image to be judged is obtained；
The method for obtaining facial image includes two methods of acquisition in real time and extraction storage image/video data.Acquisition in real time
It is mainly used for the real-time application of intelligent terminal (mobile phone, tablet computer and monitoring device), such as judges the application journey of user's gender
Sequence.Extraction storage image/video data is mainly used for that the image and video data of storage is further processed, and also can
Historical photograph is applied for intelligent terminal.
The acquisition of facial image can be extracted by photo, or by the frame picture to video data, obtain
Facial image.
S1200, the facial image is input in preset neural network model, wherein the training neural network
The gender desired value of the training sample set of multiple images composition of same target source is the median in multiple judgment values when model；
The facial image of acquisition has been input to and has been trained in advance to convergent neural network model, in present embodiment
Neural network model can be CNN convolutional neural networks model, VGG convolutional neural networks model or insightface faces
Identification model.
Neural network model is in training in present embodiment, the training sample set of use be by several (such as 100,000
People, but not limited to this) training sample set, each training sample concentration includes multiple facial images such as 10, each trains sample
The number of the facial image of this concentration is not limited to this, in the facial image number that each training sample of present embodiment is concentrated
Amount is not necessarily identical, and the more training results of picture that training sample is concentrated are better.
Since training sample set is made of multiple facial images, and everyone has multiple varying environment states
Facial image, before multiple facial images to same people are trained, need to the gender desired value of facial image into
Row anticipation, anticipation can be carried out by the way of handmarking or using trained to convergent gender is sentenced in the prior art
Disconnected model is judged.
Specifically, gender judge is carried out to the multiple pictures that same people shoots in different environments first, according to gender point
Several magnitude relationships is ranked up the face gender of multiple pictures, and takes median centrally located in sequencing table,
Common gender desired value as same multiple facial images of people.When the facial image of a people is odd number, sequence is obtained
Median in list is as gender desired value；When the facial image of a people is even number, two in sorted lists are obtained
The average value of a median is as gender desired value.
Trained to convergent neural network model by above-mentioned sample training collection, due in training same people in different rings
Gender expectation under border is identical, therefore, the gender test number of the same people that neural network model exports under various circumstances
With higher convergence, the dispersion of data is relatively low.
S1300, Gender Classification is carried out to the facial image according to the grouped data of neural network model output.
It is defeated in response to the input neural network model when facial image is input in training to convergent neural network model
Go out the grouped data to the facial image, the gender score of the facial image is calculated according to the grouped data.For example, after normalization
Gender Classification data value is carried out between 0-1, with 0.5 be Threshold segmentation line, but not limited to this, the Threshold segmentation line of gender
Can accurately it be confirmed according to experimental result.When the numerical value of grouped data is greater than or equal to 0.5, grouped data characterization
The gender of facial image is male, when the numerical value of grouped data is less than 0.5, the gender of the facial image of grouped data characterization
For women.In other embodiments, when the numerical value of grouped data is greater than or equal to 0.5, the people of grouped data characterization
The gender of face image is women, and when the numerical value of grouped data is less than 0.5, the gender of the facial image of grouped data characterization is
Male.
The above embodiment exists to same person when being trained to the neural network model for carrying out face gender judgement
The photo shot in different space environments carries out unified expectation processing, obtains multiple gender phases of same person difference photo
It hopes, the median taken in ranking results then is ranked up to gender expectation, as the gender desired value of same people's difference photo,
Whether the no matter residing environment of the photo of i.e. same people is identical, the gender desired value all same of all photos.Will then by
The facial image for being marked with gender desired value is input in the neural network model of Sexual discriminating, is instructed to neural network model
Practice, since training sample concentrates the different photo gender desired values of same people identical, by this kind of photo training to convergent
Neural network model, it is high to the gender of same people scoring output stability in different environments, it is not easily susceptible to the influence of environment.
In some embodiments, neural network model is set there are two class categories, and two class categories characterize one respectively
Kind gender carries out Gender Classification by judging probability of the grouped data in two class categories to the facial image of input.Tool
Body is referring to Fig. 2, Fig. 2 is the flow diagram that the present embodiment judges class categories.
As described in Figure 2, step S1300 specifically includes following step：
S1311, two classification values for obtaining the neural network model output；
Since convolutional neural networks model is set, there are two class categories, and two class categories correspond to a gender respectively,
Therefore, the grouped data of neural network model output is the probability value that facial image belongs to two class categories.Obtain two points
The corresponding probability value of class classification, i.e. probability value are equal to classification value.
S1312, confirm that the class categories in described two classification values corresponding to the maximum classification value of numerical value are Gender Classification
As a result.
Two classification values are compared, confirm that a maximum classification value in two classification values, the classification value correspond to one
A gender.A more maximum numerical value shows that facial image belongs to the maximum probability of the category, i.e. classification results table in classification value
The gender classification of person of good sense's face image belongs to the corresponding gender classification of the maximum number of classification value.
But mode classification is not limited to this, according to the difference of concrete application environment, in some embodiments, neural network
A classification results are arranged in model.Such as setting classification be respectively male, setting normalization after Gender Classification data 0-1 it
Between carry out value, with 0.5 for Threshold segmentation line, when class probability value is more than or equal to 0.5 gender for characterizing the facial image point
Class is male, and otherwise, then it is women to characterize the facial image.
In some embodiments, the neural network model in present embodiment is trained for dividing short-sighted frequency
Class.Therefore, it is necessary to be extracted to the facial image in short-sighted frequency.Specifically, referring to Fig. 3, Fig. 3 is the present embodiment face figure
The extracting method flow diagram of picture.
As shown in figure 3, including the following steps：
S1011, target video is obtained；
Target video is the video data that client uploads, and received server-side is classified to the video data, is classified
The result is that confirm video data in hero gender.
S1012, the timing extraction frame picture from the target video, and judge to whether there is face figure in the frame picture
Picture；
Target video is handled by Video processing software (such as OpenCV), target video is split as several
Frame picture.(such as extracting the mode of a pictures per 0.5s) by way of timing extraction, in several frame pictures successively
Multiple frame pictures are extracted, then frame picture is input in preset human face recognition model, whether there is people in judgment frame picture
Face image.Human face recognition model can be in the prior art it is trained for judge facial image whether there is or not CNN convolutional neural networks
Model, VGG convolutional neural networks model or insightface human face recognition models.
S1013, when there are the face figures that when facial image, to confirm the frame picture image be to be judged in the frame picture
Picture.
When judging that there are the facial images that when facial image, to confirm the frame picture image be to be judged in frame picture.And
The frame picture is input in the neural network model in present embodiment, to one or more of video hero's progressive
It does not calculate.
Due to the environment residing for the facial image of hero in different frame picture in video information be it is changeable, by using
Neural network model in present embodiment can filter the interference of environmental factor to the greatest extent, accurately determine video money
The gender score of hero in material.
In some embodiments, the Gender Classification result in the present embodiment is used as and is more accurately divided facial image
The foundation of analysis.For example, in present embodiment, to facial image into after Gender Classification, facial image is input to other content reason
Further classified in solution model.Referring specifically to Fig. 4, Fig. 4 is that the present embodiment carries out further content to facial image
The flow diagram of understanding.
As shown in figure 4, further including following step after step S1300：
S1321, gender classification results are obtained；
After neural network model exports Gender Classification result, terminal or server system obtain the Gender Classification result.
S1322, the facial image is input to by preset picture material according to the Gender Classification result understands model
In corresponding input channel, wherein described image content understanding model is set there are two input channel, each input channel corresponds to
A kind of sex types；
In present embodiment, content understanding model can be CNN convolutional neural networks model, VGG convolutional neural networks moulds
Type or insightface human face recognition models.
Content understanding model is further classified to facial image, and content understanding can be carried out to facial image
(being not limited to)：A kind of in face value, age or race classifies.
In order to make picture material understand more accurate and more specific aim, in present embodiment, picture material understands mould
Type is set there are two channel, and each channel corresponds to a kind of sex types.Picture material understands that model setting two in training is logical
Road, one of channel is exclusively used in extracting the feature of male's facial image, and another channel is then exclusively used in women
The feature of facial image extracts.Two channels handle the facial image of different sexes respectively, then train to convergent image
Content understanding model difference channel all has gender attribute, and the facial image for capableing of pair gender being adapted to it is made more accurately
Content understanding classification results.In the present embodiment, feature extraction channel that the channel of content understanding model is made of convolutional layer.
S1323, the content understanding data for obtaining the output of described image content understanding model.
After picture material understands that facial image is further processed in model, the content understanding number of its output is obtained
According to.Content understanding data are to (being not limited to)：A kind of classification results in face value, age or race.
It is above-mentioned to be in embodiment, since picture material understands that two channels of model are respectively provided with gender attribute, nerve
After the gender of facial image is identified in network model, facial image is input to by picture material according to recognition result and understands mould
In the other channel of type correspondence, further image procossing is carried out to facial image.Due to the gender attribute in channel, to face
The gender of image is classified, and picture material can be made to understand that the classification results of model are more accurate.
In some embodiments, image understanding model is specially face value disaggregated model.Face value disaggregated model is in nerve net
After network model classifies to facial image, continue to classify to the face value of facial image.Since people are for male and female
Property face value judgment criteria it is inconsistent, using the same model to facial image carry out indifference face value judge, face value can be caused
The relatively low problem of the accuracy rate that scores.It is the flow that the present embodiment carries out facial image face value scoring referring specifically to Fig. 5, Fig. 5
Schematic diagram.
As shown in figure 5, further including following step after step S1300：
S1331, gender classification results are obtained；
After neural network model exports Gender Classification result, terminal or server system obtain the Gender Classification result.
S1332, the facial image is input to by the corresponding input of face value disaggregated model according to the Gender Classification result
In channel, wherein the face value disaggregated model is set there are two input channel, each input channel corresponds to a kind of sex types；
In present embodiment, content understanding model can be CNN convolutional neural networks model, VGG convolutional neural networks moulds
Type or insightface human face recognition models.
In order to make picture material understand more accurate and more specific aim, in present embodiment, face value disaggregated model is set
There are two channels, and each channel corresponds to a kind of sex types.Two channels are arranged in training in face value disaggregated model, wherein one
A channel is exclusively used in extracting the feature of male's facial image, and another channel is then exclusively used in women facial image
Feature extracts.Two channels handle the facial image of different sexes respectively, then train to convergent face value disaggregated model not
Gender attribute is all had with channel, the facial image for capableing of pair gender being adapted to it makes more accurate content understanding classification
As a result.In the present embodiment, feature extraction channel that the channel of content understanding model is made of convolutional layer.
S1333, the face value grouped data for obtaining the face value disaggregated model output.
After facial image is further processed in face value disaggregated model, the face value classification results of its output are obtained.
Above-mentioned is in embodiment, since two channels of face value disaggregated model are respectively provided with gender attribute, neural network
After the gender of facial image is identified in model, facial image is input to by face value disaggregated model correspondence according to recognition result
In other channel, further image procossing is carried out to facial image.Due to the gender attribute in channel, to the property of facial image
Do not classify, the classification results of face value disaggregated model can be made more accurate.
In present embodiment, further includes the training method of neural network model, be the present embodiment referring specifically to Fig. 6, Fig. 6
It is expected that the acquisition methods flow diagram of classification value.
As shown in fig. 6, including the following steps：
S2100, the training sample set is obtained, the training sample set includes multiple facial images of same target；
The training sample set of the present embodiment is obtained by web crawlers or existing image data base.
Neural network model is in training in present embodiment, using several training sample sets (such as 100,000 people),
In, each training sample set includes the multiple facial images of a people.It is trained in multiple facial images to same people
Before, it needs to prejudge the gender desired value of each training sample set, anticipation can use trained in the prior art
Judged to convergent face value judgment models.For example, CNN convolutional neural networks model, VGG convolutional neural networks model or
Insightface human face recognition models.
In present embodiment, the gender expectation for multiple facial images that same training sample is concentrated is identical.
Trained to convergent neural network model by above-mentioned sample training collection, due in training same people in different rings
Gender expectation under border is identical, therefore, the face value test number of the same people that neural network model exports under various circumstances
With higher convergence, the dispersion of data is relatively low.
Same target refers to same person in this reality embodiment.
S2200, multiple described facial images are sequentially inputted in preset first disaggregated model, are obtained respectively described more
Open the Gender Classification value of facial image；
First disaggregated model is already existing all kinds of gender Calculating models in the prior art, first in present embodiment
Disaggregated model can be CNN convolutional neural networks model, VGG convolutional neural networks model or insightface recognitions of face
Model.
Gender judge is carried out to the multiple pictures that same people shoots in different environments first, specifically, by multiple faces
Image is sequentially inputted in the first disaggregated model, obtains the gender score of each facial image.
For example, the Gender Classification data after normalization carry out value between 0-1, with 0.5 for Threshold segmentation line, but it is unlimited
In this, the Threshold segmentation line of gender can accurately be confirmed according to experimental result.When the numerical value of grouped data is greater than or equal to
When 0.5, the gender of the facial image of grouped data characterization is male, when the numerical value of grouped data is less than 0.5, the classification number
Gender according to the facial image of characterization is women.In other embodiments, when the numerical value of grouped data is greater than or equal to 0.5
When, the gender of the facial image of grouped data characterization is women, when the numerical value of grouped data is less than 0.5, the grouped data
The gender of the facial image of characterization is male.
S2300, the Gender Classification value of multiple facial images is ranked up using numerical value as qualifications；
After getting part Sexual discriminating result of the multiple pictures of same people, with the magnitude relationship of gender score, to multiple
The face gender of photo carries out drop power sequence.
S2400, confirm that Gender Classification value in an intermediate position in the ranking results is multiple facial images
It is expected that classification value.
Median centrally located in sequencing table is taken, the common gender as same multiple facial images of people it is expected
Value.When the facial image of a people is odd number, the median in sorted lists is obtained as gender desired value；As a people
Facial image be even number when, obtain sorted lists in two medians average value as gender expectation.
In some embodiments, when training sample concentrates the expectation classification value of everyone multiple facial images unified
After it is expected classification value for gender in an intermediate position in ranking results, neural network model is carried out using above-mentioned facial image
Training.It is the training method flow diagram of the present embodiment neural network model referring specifically to Fig. 7, Fig. 7.
As shown in fig. 7, further including following step after step S2400：
S2500, the training sample set is input in the neural network model, it is defeated obtains the neural network model
The excitation classification value gone out；
The facial image that training sample is concentrated is sequentially inputted in neural network model, neural network model is to face figure
As carrying out feature extraction and classification.
Excitation classification value is the excited data that convolutional neural networks model is exported according to the facial image of input, in nerve
Network model is not trained to before convergence, and excitation classification value is the larger numerical value of discreteness, when neural network model is not instructed
Practice to after restraining, excitation classification value is metastable data.
S2600, the distance between the expectation classification value and the excitation classification value are compared whether less than or equal to default
First threshold；
Judge that the excitation classification value of the full articulamentum output of neural network model and the expectation of setting are classified by loss function
Whether value is consistent, when result is inconsistent, needs to be adjusted the weight in first passage by back-propagation algorithm.
In some embodiments, loss function by calculating encourage classification value and setting it is expected between classification value away from
From (Euclidean distance or space length), whether the expectation classification value to determine excitation classification value and setting is consistent, setting first
Threshold value (for example, 0.05), when the distance between expectation classification value for encouraging classification value and setting is less than or equal to first threshold,
It then determines that excitation classification value is consistent with the expectation classification value of setting, otherwise, then encourages classification value and the expectation classification value of setting not
Unanimously.
S2700, when the distance between the expectation classification value and the excitation classification value be more than preset first threshold when,
Iterative cycles iteration updates the weight in the neural network model by inverse algorithms, until the expectation classification value with
The distance between described excitation classification value terminates when being less than or equal to preset first threshold.
When the expectation classification value of the excitation classification value of neural network model and setting is inconsistent, need to use stochastic gradient
Descent algorithm is corrected the weight in neural network model, so that the output result of convolutional neural networks model is sentenced with classification
The expected result of disconnected information is identical.By several training sample sets (by all training samples when in some embodiments, training
Photo in collection, which is upset, to be trained, with increase model lean on interference performance, enhance the stability of output.) training repeatedly
With correction, when the classification of neural network model output category data and each training sample reaches and (is not limited to) with reference to information comparison
When 99.5%, training terminates.
Trained to convergent neural network model by above-mentioned sample training collection, due in training same people in different rings
Gender desired value under border is identical, therefore, the gender test value of the same people that neural network model exports under various circumstances
With higher convergence, the dispersion of data is relatively low.
In some embodiments, the priority joining relation without setting between step S2500 and S2400, such as when
When the expectation classification value of facial image is by manually being demarcated.
In order to solve the above technical problems, the embodiment of the present invention also provides facial image Sexual discriminating device.
It is the present embodiment facial image Sexual discriminating device basic structure schematic diagram referring specifically to Fig. 8, Fig. 8.
As shown in figure 8, a kind of facial image Sexual discriminating device, which is characterized in that including：Acquisition module 2100, processing
Module 2200 and execution module 2300.Wherein, acquisition module 2100 is for obtaining facial image to be judged；Processing module 2200
For facial image to be input in preset neural network model, wherein same target source when training neural network model
The gender desired value of the training sample set of multiple images composition is the median in multiple judgment values；Execution module 2300 is used for root
Gender Classification is carried out to facial image according to the grouped data of neural network model output.
Facial image Sexual discriminating device is when being trained the neural network model for carrying out face gender judgement, to same
The photo that one people shoots in different space environments carries out unified expectation processing, obtains the multiple of same person difference photo
Gender it is expected, is then ranked up the median taken in ranking results to gender expectation, the gender as same people's difference photo
Desired value, i.e., whether the environment no matter residing photo of same people is is identical, the gender desired value all same of all photos.It will
Then the facial image for being marked with gender desired value is input in the neural network model of Sexual discriminating, to neural network model
It is trained, since training sample concentrates the different photo gender desired values of same people identical, extremely by this kind of photo training
Convergent neural network model, it is high to the gender of same people scoring output stability in different environments, it is not easily susceptible to environment
Influence.
In some embodiments, neural network model is set there are two class categories；Facial image Sexual discriminating device is also
Including：First acquisition submodule and first confirms submodule.Wherein, the first acquisition submodule is defeated for obtaining neural network model
Two classification values gone out；First confirmation submodule is used to confirm the classification in two classification values corresponding to the maximum classification value of numerical value
Classification is Gender Classification result.
In some embodiments, facial image Sexual discriminating device further includes：Second acquisition submodule, the first processing
Module and the first implementation sub-module.Wherein, the second acquisition submodule is for obtaining target video；First processing submodule be used for from
Timing extraction frame picture in target video, and whether there is facial image in judgment frame picture；First implementation sub-module is for working as
There are when facial image in frame picture, acknowledgement frame picture image is facial image to be judged.
In some embodiments, facial image Sexual discriminating device further includes：Third acquisition submodule, second processing
Module and the second implementation sub-module.Wherein, third acquisition submodule is for obtaining gender classification results；Second processing submodule is used
Understand in the corresponding input channel of model in classifying by sex result facial image being input to preset picture material,
In, picture material understands that model is set there are two input channel, each input channel corresponds to a kind of sex types；Second executes son
Module is used to obtain the content understanding data that picture material understands model output.
In some embodiments, picture material understands that model is face value disaggregated model；Facial image Sexual discriminating device
Further include：4th acquisition submodule, third processing submodule and third implementation sub-module.Wherein, the 4th acquisition submodule is used for
Obtain gender classification results；Facial image is input to face value classification mould by third processing submodule for the result that classifies by sex
In the corresponding input channel of type, wherein face value disaggregated model is set there are two input channel, each input channel corresponds to a kind of property
Other type；Third implementation sub-module is used to obtain the face value grouped data of face value disaggregated model output.
In some embodiments, facial image Sexual discriminating device further includes：5th acquisition submodule, fourth process
Module, the first sorting sub-module and the 4th implementation sub-module.Wherein, the 5th acquisition submodule is instructed for obtaining training sample set
Practice multiple facial images that sample set includes same target；Multiple facial images for being sequentially inputted to by fourth process submodule
In preset first disaggregated model, the Gender Classification value of multiple facial images is obtained respectively；First sorting sub-module is used for number
Value is that qualifications are ranked up the Gender Classification value of multiple facial images；4th implementation sub-module is for confirming ranking results
In Gender Classification value in an intermediate position be multiple facial images expectation classification value.
In some embodiments, facial image Sexual discriminating device further includes：First input submodule, the first comparer
Module and the 5th implementation sub-module.Wherein, the first input submodule is used to training sample set being input in neural network model,
Obtain the excitation classification value of neural network model output；First compares submodule it is expected classification value and excitation classification value for comparing
The distance between whether be less than or equal to preset first threshold；5th implementation sub-module is used for when desired classification value and excitation point
When the distance between class value is more than preset first threshold, iterative cycles iteration updates neural network model by inverse algorithms
In weight, terminate when until it is expected classification value with excitation the distance between classification value less than or equal to preset first threshold.
In order to solve the above technical problems, the embodiment of the present invention also provides computer equipment.It is this referring specifically to Fig. 9, Fig. 9
Embodiment computer equipment basic structure block diagram.
As shown in figure 9, the internal structure schematic diagram of computer equipment.As shown in figure 9, the computer equipment includes passing through to be
Processor, non-volatile memory medium, memory and the network interface of bus of uniting connection.Wherein, the computer equipment is non-easy
The property lost storage medium is stored with operating system, database and computer-readable instruction, and control information sequence can be stored in database
Row when the computer-readable instruction is executed by processor, may make processor to realize a kind of facial image Sexual discriminating method.It should
The processor of computer equipment supports the operation of entire computer equipment for providing calculating and control ability.The computer is set
It can be stored with computer-readable instruction in standby memory, when which is executed by processor, may make processing
Device executes a kind of facial image Sexual discriminating method.The network interface of the computer equipment is used for and terminal connection communication.Ability
Field technique personnel are appreciated that structure shown in Fig. 9, only with the block diagram of the relevant part-structure of application scheme, and
The restriction for the computer equipment being applied thereon to application scheme is not constituted, and specific computer equipment may include than figure
Shown in more or fewer components, either combine certain components or arranged with different components.
Processor is for executing acquisition module 2100 in Fig. 8, processing module 2200 and execution module in present embodiment
2300 concrete function, memory are stored with the program code and Various types of data executed needed for above-mentioned module.Network interface is used for
To the data transmission between user terminal or server.Memory in present embodiment is stored with facial image critical point detection
The program code and data needed for all submodules are executed in device, server is capable of the program code and data of invoking server
Execute the function of all submodules.
Computer equipment to carrying out the neural network model that face face value judges when being trained, to same person not
The photo shot in same space environment carries out unified expectation processing, obtains multiple face values expectation of same person difference photo,
Then the median taken in ranking results is ranked up to the expectation of face value, the face value as same people's difference photo it is expected, i.e., together
Whether the no matter residing environment of the photo of one people is identical, and the face value of all photos it is expected all same.It will then will be marked with
Face is worth desired facial image and is input in the neural network model of face value judgement, is trained to neural network model, due to
It is identical that training sample concentrates the different photo face values of same people it is expected, passes through this kind of photo training to convergent neural network mould
Type, it is high to the face value of same people scoring output stability in different environments, it is not easily susceptible to the influence of environment.
The present invention also provides a kind of storage mediums being stored with computer-readable instruction, and the computer-readable instruction is by one
When a or multiple processors execute so that one or more processors execute facial image gender described in any of the above-described embodiment and sentence
The step of disconnected method.
One of ordinary skill in the art will appreciate that realizing all or part of flow in above-described embodiment method, being can be with
Relevant hardware is instructed to complete by computer program, which can be stored in a computer-readable storage and be situated between
In matter, the program is when being executed, it may include such as the flow of the embodiment of above-mentioned each method.Wherein, storage medium above-mentioned can be
The non-volatile memory mediums such as magnetic disc, CD, read-only memory (Read-Only Memory, ROM) or random storage note
Recall body (Random Access Memory, RAM) etc..
It should be understood that although each step in the flow chart of attached drawing is shown successively according to the instruction of arrow,
These steps are not that the inevitable sequence indicated according to arrow executes successively.Unless expressly stating otherwise herein, these steps
Execution there is no stringent sequences to limit, can execute in the other order.Moreover, at least one in the flow chart of attached drawing
Part steps may include that either these sub-steps of multiple stages or stage are not necessarily in synchronization to multiple sub-steps
Completion is executed, but can be executed at different times, execution sequence is also not necessarily to be carried out successively, but can be with other
Either the sub-step of other steps or at least part in stage execute step in turn or alternately.
Claims (10)
1. a kind of facial image Sexual discriminating method, which is characterized in that include the following steps：
Obtain facial image to be judged；
The facial image is input in preset neural network model, wherein same when the training neural network model
The gender desired value of the training sample set of multiple images composition of target source is the median in multiple judgment values；
Gender Classification is carried out to the facial image according to the grouped data of neural network model output.
2. facial image Sexual discriminating method according to claim 1, which is characterized in that the neural network model is equipped with
Two class categories；The grouped data according to neural network model output carries out Gender Classification to the facial image
The step of, specifically include following step：
Obtain two classification values of the neural network model output；
Confirm that the class categories in described two classification values corresponding to the maximum classification value of numerical value are Gender Classification result.
3. facial image Sexual discriminating method according to claim 1, which is characterized in that described to obtain face to be judged
The step of image, includes the following steps：
Obtain target video；
The timing extraction frame picture from the target video, and judge to whether there is facial image in the frame picture；
When there are the facial images that when facial image, to confirm the frame picture image be to be judged in the frame picture.
4. facial image Sexual discriminating method according to claim 1, which is characterized in that described according to the neural network
Further include following step after the step of grouped data of model output carries out Gender Classification to the facial image：
Obtain gender classification results；
The facial image is input to preset picture material according to the Gender Classification result and understands the corresponding input of model
In channel, wherein described image content understanding model is set there are two input channel, each input channel corresponds to a kind of gender class
Type；
Obtain the content understanding data of described image content understanding model output.
5. facial image Sexual discriminating method according to claim 4, which is characterized in that described image content understanding model
For face value disaggregated model；The grouped data according to neural network model output carries out gender point to the facial image
Further include following step after the step of class：
Obtain gender classification results；
The facial image is input in the corresponding input channel of face value disaggregated model according to the Gender Classification result,
In, the face value disaggregated model is set there are two input channel, each input channel corresponds to a kind of sex types；
Obtain the face value grouped data of the face value disaggregated model output.
6. the facial image Sexual discriminating method according to claim 1-5 any one, which is characterized in that the nerve net
The training method of network model includes：
The training sample set is obtained, the training sample set includes multiple facial images of same target；
Multiple described facial images are sequentially inputted in preset first disaggregated model, obtain multiple described facial images respectively
Gender Classification value；
The Gender Classification value of multiple facial images is ranked up using numerical value as qualifications；
Confirm that Gender Classification value in an intermediate position in the ranking results is the expectation classification value of multiple facial images.
7. facial image Sexual discriminating method according to claim 6, which is characterized in that described to confirm the ranking results
In after Gender Classification value in an intermediate position the step of being the expectation classification value of multiple facial images, further include following
Step：
The training sample set is input in the neural network model, the excitation point of the neural network model output is obtained
Class value；
Compare whether the distance between the expectation classification value and the excitation classification value are less than or equal to preset first threshold；
When the distance between the expectation classification value and the excitation classification value are more than preset first threshold, iterative cycles change
In generation, updates the weight in the neural network model by inverse algorithms, until the expectation classification value and the excitation point
The distance between class value terminates when being less than or equal to preset first threshold.
8. a kind of facial image Sexual discriminating device, which is characterized in that including：
Acquisition module, for obtaining facial image to be judged；
Processing module, for the facial image to be input in preset neural network model, wherein the training nerve net
The gender desired value of the training sample set of multiple images composition of same target source is the centre in multiple judgment values when network model
Value；
Execution module, the grouped data for being exported according to the neural network model carry out gender point to the facial image
Class.
9. a kind of computer equipment, including memory and processor, it is stored with computer-readable instruction in the memory, it is described
When computer-readable instruction is executed by the processor so that the processor is executed such as any one of claim 1 to 7 right
It is required that the step of facial image Sexual discriminating method.
10. a kind of storage medium being stored with computer-readable instruction, the computer-readable instruction is handled by one or more
When device executes so that one or more processors execute the facial image as described in any one of claim 1 to 7 claim
The step of other judgment method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810525407.4A CN108446688B (en) | 2018-05-28 | 2018-05-28 | Face image gender judgment method and device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810525407.4A CN108446688B (en) | 2018-05-28 | 2018-05-28 | Face image gender judgment method and device, computer equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108446688A true CN108446688A (en) | 2018-08-24 |
| CN108446688B CN108446688B (en) | 2020-01-07 |
Family
ID=63204771
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810525407.4A Active CN108446688B (en) | 2018-05-28 | 2018-05-28 | Face image gender judgment method and device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108446688B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109360072A (en) * | 2018-11-13 | 2019-02-19 | 平安科技（深圳）有限公司 | Insurance products recommended method, device, computer equipment and storage medium |
| CN111488893A (en) * | 2019-01-25 | 2020-08-04 | 银河水滴科技（北京）有限公司 | Image classification method and device |
| CN112613539A (en) * | 2020-12-11 | 2021-04-06 | 北京迈格威科技有限公司 | Method, device, equipment and medium for constructing classification network and object detection model |
| CN114944000A (en) * | 2022-06-07 | 2022-08-26 | 重庆第二师范学院 | Facial expression recognition model based on multi-scale feature extraction |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104778448A (en) * | 2015-03-24 | 2015-07-15 | 孙建德 | Structure adaptive CNN (Convolutional Neural Network)-based face recognition method |
| CN104915658A (en) * | 2015-06-30 | 2015-09-16 | 东南大学 | Emotion component analyzing method and system based on emotion distribution learning |
| CN105373777A (en) * | 2015-10-30 | 2016-03-02 | 中国科学院自动化研究所 | Face recognition method and device |
| CN106951866A (en) * | 2017-03-21 | 2017-07-14 | 北京深度未来科技有限公司 | A kind of face authentication method and device |
| CN107015993A (en) * | 2016-01-28 | 2017-08-04 | 中国移动通信集团上海有限公司 | A kind of user type recognition methods and device |
| CN107330383A (en) * | 2017-06-18 | 2017-11-07 | 天津大学 | A kind of face identification method based on depth convolutional neural networks |
| CN107679513A (en) * | 2017-10-20 | 2018-02-09 | 北京达佳互联信息技术有限公司 | Image processing method, device and server |
| CN107742107A (en) * | 2017-10-20 | 2018-02-27 | 北京达佳互联信息技术有限公司 | Facial image sorting technique, device and server |
| CN107818314A (en) * | 2017-11-22 | 2018-03-20 | 北京达佳互联信息技术有限公司 | Face image processing method, device and server |
| CN107871106A (en) * | 2016-09-26 | 2018-04-03 | 北京眼神科技有限公司 | Face detection method and device |
-
2018
- 2018-05-28 CN CN201810525407.4A patent/CN108446688B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104778448A (en) * | 2015-03-24 | 2015-07-15 | 孙建德 | Structure adaptive CNN (Convolutional Neural Network)-based face recognition method |
| CN104915658A (en) * | 2015-06-30 | 2015-09-16 | 东南大学 | Emotion component analyzing method and system based on emotion distribution learning |
| CN105373777A (en) * | 2015-10-30 | 2016-03-02 | 中国科学院自动化研究所 | Face recognition method and device |
| CN107015993A (en) * | 2016-01-28 | 2017-08-04 | 中国移动通信集团上海有限公司 | A kind of user type recognition methods and device |
| CN107871106A (en) * | 2016-09-26 | 2018-04-03 | 北京眼神科技有限公司 | Face detection method and device |
| CN106951866A (en) * | 2017-03-21 | 2017-07-14 | 北京深度未来科技有限公司 | A kind of face authentication method and device |
| CN107330383A (en) * | 2017-06-18 | 2017-11-07 | 天津大学 | A kind of face identification method based on depth convolutional neural networks |
| CN107679513A (en) * | 2017-10-20 | 2018-02-09 | 北京达佳互联信息技术有限公司 | Image processing method, device and server |
| CN107742107A (en) * | 2017-10-20 | 2018-02-27 | 北京达佳互联信息技术有限公司 | Facial image sorting technique, device and server |
| CN107818314A (en) * | 2017-11-22 | 2018-03-20 | 北京达佳互联信息技术有限公司 | Face image processing method, device and server |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109360072A (en) * | 2018-11-13 | 2019-02-19 | 平安科技（深圳）有限公司 | Insurance products recommended method, device, computer equipment and storage medium |
| CN111488893A (en) * | 2019-01-25 | 2020-08-04 | 银河水滴科技（北京）有限公司 | Image classification method and device |
| CN111488893B (en) * | 2019-01-25 | 2023-05-30 | 银河水滴科技（北京）有限公司 | Image classification method and device |
| CN112613539A (en) * | 2020-12-11 | 2021-04-06 | 北京迈格威科技有限公司 | Method, device, equipment and medium for constructing classification network and object detection model |
| CN114944000A (en) * | 2022-06-07 | 2022-08-26 | 重庆第二师范学院 | Facial expression recognition model based on multi-scale feature extraction |
| CN114944000B (en) * | 2022-06-07 | 2024-04-19 | 重庆第二师范学院 | Facial expression recognition method based on multi-scale feature extraction |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108446688B (en) | 2020-01-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108734146A (en) | Facial image Age estimation method, apparatus, computer equipment and storage medium | |
| CN108764334A (en) | Facial image face value judgment method, device, computer equipment and storage medium | |
| CN108446688A (en) | Facial image Sexual discriminating method, apparatus, computer equipment and storage medium | |
| CN109284733B (en) | Shopping guide negative behavior monitoring method based on yolo and multitask convolutional neural network | |
| CN110750656B (en) | Multimedia detection method based on knowledge graph | |
| CN112182166B (en) | Text matching method and device, electronic equipment and storage medium | |
| CN109614989B (en) | Training method and device for rapid model, computer equipment and storage medium | |
| CN112508094B (en) | Garbage picture identification method, device and equipment | |
| CN111310026A (en) | Artificial intelligence-based yellow-related terrorism monitoring method | |
| CN101441717B (en) | Method and system for detecting eroticism video | |
| CN107742107A (en) | Facial image sorting technique, device and server | |
| WO2021169347A1 (en) | Method and device for extracting text keywords | |
| CN108074016B (en) | User relationship strength prediction method, device and equipment based on location social network | |
| CN109902912B (en) | Personalized image aesthetic evaluation method based on character features | |
| US11966829B2 (en) | Convolutional artificial neural network based recognition system in which registration, search, and reproduction of image and video are divided between and performed by mobile device and server | |
| CN114550053A (en) | Traffic accident responsibility determination method, device, computer equipment and storage medium | |
| CN109214263A (en) | A kind of face identification method based on feature multiplexing | |
| CN112446337A (en) | Wisdom museum management system based on expression discernment | |
| CN108900905A (en) | A kind of video clipping method and device | |
| CN112395979A (en) | Image-based health state identification method, device, equipment and storage medium | |
| WO2016202132A1 (en) | Method and system for photo management | |
| CN110210550A (en) | Image fine granularity recognition methods based on integrated study strategy | |
| CN111488815A (en) | Basketball game goal event prediction method based on graph convolution network and long-time and short-time memory network | |
| CN113254491A (en) | Information recommendation method and device, computer equipment and storage medium | |
| CN110633624A (en) | Machine vision human body abnormal behavior identification method based on multi-feature fusion |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20211013 Address after: 101d1-10, floor 1, building 1, No. 6, Shangdi West Road, Haidian District, Beijing 100085 Patentee after: Beijing Kwai Technology Co.,Ltd. Patentee after: Beijing Dajia Internet Information Technology Co.,Ltd. Address before: B2201, 20 / F, building 8, yard 1, Zhongguancun East Road, Haidian District, Beijing 100084 Patentee before: Beijing Dajia Internet Information Technology Co.,Ltd. |
|
| TR01 | Transfer of patent right |