CN110298246A - Unlocking verification method, device, computer equipment and storage medium - Google Patents
Unlocking verification method, device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN110298246A CN110298246A CN201910431034.9A CN201910431034A CN110298246A CN 110298246 A CN110298246 A CN 110298246A CN 201910431034 A CN201910431034 A CN 201910431034A CN 110298246 A CN110298246 A CN 110298246A
- Authority
- CN
- China
- Prior art keywords
- micro
- expression
- image
- unlocking
- images
- 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
- 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
-
- 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
- G06V40/174—Facial expression recognition
-
- 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
- G06V40/174—Facial expression recognition
- G06V40/176—Dynamic expression
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C9/00—Individual registration on entry or exit
- G07C9/00174—Electronically operated locks; Circuits therefor; Nonmechanical keys therefor, e.g. passive or active electrical keys or other data carriers without mechanical keys
- G07C9/00309—Electronically operated locks; Circuits therefor; Nonmechanical keys therefor, e.g. passive or active electrical keys or other data carriers without mechanical keys operated with bidirectional data transmission between data carrier and locks
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C9/00—Individual registration on entry or exit
- G07C9/30—Individual registration on entry or exit not involving the use of a pass
- G07C9/32—Individual registration on entry or exit not involving the use of a pass in combination with an identity check
- G07C9/37—Individual registration on entry or exit not involving the use of a pass in combination with an identity check using biometric data, e.g. fingerprints, iris scans or voice recognition
Abstract
The invention discloses a kind of unlocking verification method, device, computer equipment and storage mediums, wherein the unlocking verification method includes: the unlocking checking request for obtaining acquisition terminal and sending, and unlocking checking request includes micro- expression video stream;Any frame images to be recognized in micro- expression video stream is extracted, matching is carried out in image data base and obtains images match result;If images match result is successful match, at least two frame target images are extracted by default extracting rule;Each target image is inputted into micro- Expression Recognition tool and carries out micro- expression marking, obtains the micro- expression score table of target;If the corresponding comparison similarity of the micro- expression score table of any two target is greater than micro- expression similarity threshold, identity audit request is sent to monitoring client;Obtain auditing result.The corresponding electronic lock unlocking safety of this method guarantee unlocking checking request, prevents user from carrying out the behavior that unlocking checking request is practised fraud by image.
Description
Technical field
The present invention relates to field of face identification more particularly to a kind of unlocking verification method, device, computer equipment and storages
Medium.
Background technique
With the fast development of information technology and network technology, demand of the people to identity recognizing technology is more and more, right
The requirement of its security reliability is also increasingly stringenter.Identity recognizing technology based on conventional cipher certification is answered in actual information network
Oneself is exposed through out many shortcomings in, and the identity recognizing technology distinguished based on biological characteristic in recent years also it is increasingly mature simultaneously
Show great superiority in practical applications, but the single recognition of face of tradition can only the feature of guarantor can be had
Effect card, it cannot be guaranteed that operator is me, and causes the case for carrying out crime using photo to be often reported in media.How to enhance
The reliability of recognition of face prevents picture cheating from becoming urgent problem to be solved.
Summary of the invention
The embodiment of the present invention provides a kind of unlocking verification method, device, computer equipment and storage medium, to solve to enhance
The reliability of recognition of face, the problem of preventing picture from practising fraud.
A kind of unlocking verification method, comprising:
The unlocking checking request that acquisition terminal is sent is obtained, unlocking checking request includes micro- expression video stream;
Any frame images to be recognized in micro- expression video stream is extracted, is carried out in image data base based on images to be recognized
Match, obtains images match result;
If images match result is successful match, at least two frame target images are extracted by default extracting rule;
Each target image is inputted into micro- Expression Recognition tool and carries out micro- expression marking, is obtained opposite with each target image
The micro- expression score table of the target answered;
The corresponding comparison similarity of the micro- expression score table of any two target is calculated, if comparison similarity is greater than micro- expression phase
Like degree threshold value, then identity audit request is sent to monitoring client;
Obtain the auditing result that the audit request of monitoring client identity-based returns;
If auditing result is that audit passes through, controls Lock-Picking Devices and the corresponding electronic lock of acquisition terminal is carried out at unlocking
Reason.
A kind of unlocking verifying device, comprising:
Checking request module is obtained, for obtaining the unlocking checking request of acquisition terminal transmission, unlocking checking request includes
Micro- expression video stream;
Images to be recognized module is extracted, for extracting any frame images to be recognized in micro- expression video stream, based on to be identified
Image is matched in image data base, obtains images match result;
Extract target image module, if for images match result be successful match, by default extracting rule extract to
Few two frame target images;
Expression score table mould module is obtained, is beaten for each target image to be inputted the micro- expression of micro- Expression Recognition tool progress
Point, obtain the micro- expression score table of target corresponding with each target image;
Comparison similarity module is calculated, for calculating the corresponding comparison similarity of the micro- expression score table of any two target,
If comparing similarity is greater than micro- expression similarity threshold, identity audit request is sent to monitoring client;
Auditing result module is obtained, the auditing result returned for obtaining the audit request of monitoring client identity-based;
Unlocking processing module is controlled, if being that audit passes through for auditing result, controls Lock-Picking Devices to acquisition terminal pair
The electronic lock answered carries out unlocking processing.
A kind of computer equipment, including memory, processor and storage are in the memory and can be in the processing
The computer program run on device, the processor realize above-mentioned unlocking verification method when executing the computer program.
A kind of computer readable storage medium, the computer-readable recording medium storage have computer program, the meter
Calculation machine program realizes above-mentioned unlocking verification method when being executed by processor.
Above-mentioned unlocking verification method, device, computer equipment and storage medium, it is micro- in unlocking checking request by obtaining
Expression video stream, there may be the target image of cheating suspicion is corresponding for acquisition after carrying out micro- expression marking to micro- expression video stream
User to be verified continue by monitoring client to carry out authentication, the last auditing result dual lock verifying returned according to monitoring client is asked
Carry out alignment processing is sought, the corresponding electronic lock unlocking safety of unlocking checking request is ensured, prevents user from opening by image
The behavior that lock checking request is practised fraud;It, can be in people meanwhile only to there are the users to be verified of cheating suspicion to carry out identity audit
When flow is big, the time that each dealing personnel are all carried out with identity audit is saved, improves unlocking verification efficiency.
Detailed description of the invention
In order to illustrate the technical solution of the embodiments of the present invention more clearly, below by institute in the description to the embodiment of the present invention
Attached drawing to be used is needed to be briefly described, it should be apparent that, the accompanying drawings in the following description is only some implementations of the invention
Example, for those of ordinary skill in the art, without any creative labor, can also be according to these attached drawings
Obtain other attached drawings.
Fig. 1 is the application environment schematic diagram of unlocking verification method in one embodiment of the invention;
Fig. 2 is the flow chart of unlocking verification method in one embodiment of the invention;
Fig. 3 is another flow chart of unlocking verification method in one embodiment of the invention;
Fig. 4 is another flow chart of unlocking verification method in one embodiment of the invention;
Fig. 5 is another flow chart of unlocking verification method in one embodiment of the invention;
Fig. 6 is another flow chart of unlocking verification method in one embodiment of the invention;
Fig. 7 is to unlock to verify the schematic diagram of device in one embodiment of the invention;
Fig. 8 is the schematic diagram of computer equipment in one embodiment of the invention.
Specific embodiment
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 description, it is clear that described embodiments are some of the embodiments of the present invention, instead of all the embodiments.Based on this hair
Embodiment in bright, every other implementation obtained by those of ordinary skill in the art without making creative efforts
Example, shall fall within the protection scope of the present invention.
Unlocking verification method provided in an embodiment of the present invention, can be applicable in the application environment such as Fig. 1, the unlocking authentication
Method is applied in unlocking verifying system, the unlocking verify system include client and server, wherein client by network with
Server is communicated.Client is also known as user terminal, refers to corresponding with server, provides the journey of local service for client
Sequence.The client it is mountable but be not limited to various personal computers, laptop, smart phone, tablet computer and portable
In the computer equipments such as formula wearable device.Server can use the service of the either multiple server compositions of independent server
Device cluster is realized.
In one embodiment, as shown in Fig. 2, providing a kind of unlocking verification method, the service in Fig. 1 is applied in this way
It is illustrated, specifically comprises the following steps: for device
S10. the unlocking checking request that acquisition terminal is sent is obtained, unlocking checking request includes micro- expression video stream.
Wherein, unlocking checking request is that the application unlatching acquisition terminal that user is sent by acquisition terminal to server is corresponding
Electronic lock request.Specifically, it can also be entity electronic lock which, which can be virtual electronic lock,.When as virtual electronic
When lock, electronic lock can be rendered as login interface, when locking as entity electronic namely the common electric control lock in market.
Micro- expression video stream be the collected user's face of camera on acquisition terminal it is default shorter when long video
Stream.Because there is also dynamic change namely collected face video stream, that is, micro- expression videos within a short period of time for the micro- expression of face
Stream.
Specifically, collected micro- expression video stream is sent to server by camera by acquisition terminal, to service
Device is based on micro- expression video stream dual lock checking request and is verified.
In step S10, server, which can receive the shorter micro- expression video stream of duration, can carry out unlocking checking request, save
Acquisition time.
S20. extract any frame images to be recognized in micro- expression video stream, based on images to be recognized in image data base into
Row matching, obtains images match result.
Wherein, images to be recognized image is the micro- facial expression image of each frame for constituting micro- expression video stream.Specifically, each frame
Micro- facial expression image is all static image, in extremely rapid succession shows that the micro- facial expression image of every frame forms micro- expression video of movement
Stream, therefore high available more smooth, the more true to nature micro- expression video stream of frame per second.
Image data base is the database for saving each registered user and corresponding standard faces image.
Images match the result is that server by standard faces image each in any frame images to be recognized and image data base
It is matched, whether obtained comparison similarity can be greater than the result of the registered user of similarity threshold.If can obtain pair
Than the registered user that similarity is greater than similarity threshold, then matching result is successful match.If failing to be matched to comparison phase
It is greater than the registered user of similarity threshold like degree, then matching result is that matching is unsuccessful.
Specifically, any frame images to be recognized in the micro- expression video stream obtained in server extraction step S10, preferably
One frame video streaming image is matched the images to be recognized to obtain images match in image data base as images to be recognized
As a result.
In step S20, server can be reduced in video streaming directly using first frame video streaming image as images to be recognized
Extract the time of images to be recognized.
Preferably, after step S20, i.e., after obtaining images match result, unlocking verification method is also specifically included
Following steps:
If S201. images match result is that matching is unsuccessful, the step of sending identity audit request to monitoring client is executed.
In step S201, when server determines image matching result to match unsuccessful, illustrate not deposit in image data base
Similar in legitimate user's image and the images to be recognized height of legitimate user, server should call monitoring client further to adopting at this time
Collect preterminal user to be identified and carry out authentication, ensures the flexibility for starting verifying system.
If S30. images match result is successful match, at least two frame target images are extracted by default extracting rule.
Wherein, to be that server is preassigned extract at least two frame target figures to default extracting rule in micro- expression video stream
The rule of picture, for example extracted, it is specified that pressing designated frame number sequence number, or extracted according to specified extraction time, do not make herein
It is specific to limit.
Target image be include any two field pictures in the video frame of the micro- expression of face.
Specifically, micro- expression is psychology noun, is to cause to hide the of short duration and involuntary quick of certain true emotional
The micro- expression of face.Micro- expression duration of standard between 1/5s to 1/25s, usually only occurs in the privileged site of face.
Micro- expression delicate and be succinctly huge challenge to naked eyes, " micro- expression " flashes across, and typically even awake makees micro- expression
People and observer be all detectable.In experiment, only 10% people can be perceived.
The mankind mainly possess at least six kinds of micro- expressions, and every kind of micro- expression all expresses the different meaning:
Glad: face action when people's happiness includes: that the corners of the mouth tilts, and wrinkle is lifted on cheek, and eyelid is shunk, eyes tail
Portion will form " crow's feet ".
Sad: facial characteristics includes narrowing eye, eyebrow tightening, corners of the mouth drop-down, and chin is lifted or tightened.
Fear: when fearing, mouth and eyes open, and eyebrow raises up, and nostril is magnified.
Indignation: at this moment eyebrow is sagging, and forehead is knitted tightly, and eyelid and lip are nervous.
Detest: micro- expression of detest includes sneering nose, is lifted on upper lip, eyebrow is sagging, narrows eye.
Surprised: when surprised, lower jaw is sagging, and lip and mouth loosen, and eyes magnify, eyelid and the micro- lift of eyebrow.
The principle of micro- expression of the present embodiment based on face always dynamic change can extract at least two Zhang Feitong by server
The target image at one moment, can compare micro- expression shape change on two target images to determine whether user is real user,
The behavior of recognition of face is carried out to exclude user using picture.
In step S30, server can extract at least two target images based on preset rules, carry out for subsequent server micro-
Expression Recognition prepares data basis.
S40. each target image is inputted into micro- Expression Recognition tool and carries out micro- expression marking, obtained and each target image
The corresponding micro- expression score table of target.
Wherein, micro- Expression Recognition tool is target image to be carried out micro- Expression analysis, and export the micro- expression score table of target
Tool.
Specifically, in the present embodiment, micro- Expression Recognition tool should include at least two micro- expression to obtain micro- expression
Identification model, each micro- Expression Recognition model correspond to a kind of micro- expression, for example, glad or sad etc..
The micro- expression score table of target be include all kinds in micro- Expression Recognition tool micro- Expression Recognition model it is right respectively
The micro- expression score answered, for example, glad: 0.6, sad: 0.3 etc., by each micro- corresponding micro- expression label of expression and micro- expression
The corresponding storage of score, can obtain micro- expression score table, as shown in following table one:
Expression | Score value |
It is glad | 0.5 |
It is sad | 0.2 |
Fear | 0.1 |
It is surprised | 0.1 |
Indignation | 0.1 |
Table one
In step S40, each target image is can be obtained by micro- each target image of Expression Recognition tool analysis in server
The corresponding micro- expression score table of target is based on the micro- expression score table of each target to subsequent server and compares preparation
Data basis.
S50. the corresponding comparison similarity of the micro- expression score table of any two target is calculated, if comparison similarity is greater than micro- table
Feelings similarity threshold then sends identity audit request to monitoring client.
Wherein, comparison similarity is that any two carry out phase in the micro- expression score table of all targets obtained in step S40
Like the comparison similarity obtained after degree comparison.Specific way of contrast is the general comparing calculation side for being averaging similarity percentage
Method, such as:
The micro- expression score table of first object: happiness 0.6, sad 0.3;
The micro- expression score table of second target: happiness 0.62, sad 0.27;
The similarity percentage of glad micro- expression is 97%, and sad similarity percentage is 90%, then average similarity
Percentage is 93.5%.
Micro- expression similarity threshold be determine two width target images in corresponding micro- expression be identical micro- expression most
Harmonic(-)mean similarity percentage.In the present embodiment, micro- expression similarity threshold can be set as 90%.Continued with the example above
It is illustrated, in the present embodiment, average similarity percentage is 93.5%, is greater than micro- expression similarity threshold, then can determine that two
Width target image is that micro- expression on identical image namely two width target images does not change.
Monitoring client is the terminal being monitored in real time to the corresponding scene of acquisition terminal for monitoring personnel.
Identity audit request is that server is sent to monitoring client, to confirm that scene sends the user of unlocking checking request
Whether be real user request.Because in step S40, server determine comparison similarity be greater than micro- expression similarity threshold to
Identify user, it is understood that there may be the cheating suspicion identified using photo, in order to which the user to be identified further to scene carries out
Identity validation, server can send identity audit request to corresponding monitoring client at this time.
In step S50, server is greater than the user of micro- expression similarity threshold based on comparison similarity, generates identity audit
Request Concurrency gives corresponding monitoring client, and the flexibility for carrying out authentication to scene user to be identified can be improved, ensure to true
Real user passes through unlocking checking request.
S60. the auditing result that the audit request of monitoring client identity-based returns is obtained.
Wherein, auditing result is to be returned after the audit request of monitoring client identity-based is audited as a result, including that audit is logical
It crosses and audits and do not pass through.
Specifically, monitoring client can by acquisition terminal, it is other can tool of communications or directly reach user where scene it is right
User identity is further confirmed that.For example, monitoring client can call the interface of acquisition terminal and onsite user to carry out remote dialogue,
The identity reality of onsite user is confirmed in dialog procedure.
It, can be to server when monitoring personnel confirmation Field Force is same user with user corresponding in images to be recognized
Return to the auditing result that audit passes through.Unacceptable result is audited conversely, then returning to server.
In step S60, monitoring personnel can carry out identity audit by preset various ways and onsite user, and to service
Device returns to auditing result, ensures the authenticity and accuracy of unlocking checking request.
If S70. auditing result is that audit passes through, controls Lock-Picking Devices and unlock to the corresponding electronic lock of acquisition terminal
Processing.
Specifically, the electronic lock mentioned in the present embodiment includes virtual electronic lock and electric control lock in kind.
When electronic lock is virtual electronic lock, and auditing result is that audit passes through, server can send to acquisition terminal and open
The login interface that beginning checking request passes through.
When electronic lock is virtual electric control lock in kind, and auditing result is that audit passes through, server can be sent out to acquisition terminal
Unlock instruction is sent, so that acquisition terminal unlocks its corresponding electronic lock.
In step S70, server can be that the user that audit passes through automatically turns on electronic lock to auditing result, improve automation
Unlock efficiency.
The unlocking verification method that the present embodiment proposes, server is by obtaining micro- expression video in unlocking checking request
Stream, there may be the target image of cheating suspicion is corresponding to be verified for acquisition after carrying out micro- expression marking to micro- expression video stream
User continues by monitoring client to carry out authentication, and the last auditing result dual lock checking request returned according to monitoring client carries out pair
It should handle, ensure the corresponding electronic lock unlocking safety of unlocking checking request, prevent user from carrying out unlocking verifying by image and ask
Ask the behavior practised fraud;It, can be big in flow of the people meanwhile only to there are the users to be verified of cheating suspicion to carry out identity audit
When, the time that each dealing personnel are all carried out with identity audit is saved, unlocking verification efficiency is improved.
In one embodiment, it as shown in figure 3, in step S20, i.e., is carried out in image data base based on images to be recognized
Matching obtains images match as a result, specifically comprising the following steps:
S21. the image similarity of each legitimate user's image in images to be recognized and image data base is calculated.
Wherein, image similarity is that each legitimate user's image carries out image comparison in images to be recognized and image data base
Obtained percent similarity.
Specifically, server can be used perceptual hash algorithm and obtain the similar of images to be recognized and each legitimate user's image
Percentage realizes that process is as follows:
1. input picture (images to be recognized and each legitimate user's image);
2. gray processing;
3. by image size normalization to 8*8 size;
4. simplifying gray scale to reduce calculation amount, such as all gray scales divided by 5;
5. calculating average gray value avg;
6. compare the size of 8*8=64 pixel Yu average gray value avg, it is denoted as 1 if big, it is small to be denoted as 0, by certain
Sequence is arranged in the finger-print codes of 64 2 systems;
7. comparing the finger-print codes of images to be recognized and each legitimate user's image, percent similarity namely image phase are calculated
Like degree.
In step S21, server can obtain the image similarity of images to be recognized and each legitimate user's image, be subsequent
Determine whether the corresponding user of the images to be recognized is that legitimate user prepares data basis.
If S22. image similarity is greater than the first image similarity threshold value, and image similarity is similar no more than the second image
Threshold value is spent, then legitimate user's image is updated using images to be recognized, and obtaining images match result is successful match.
Wherein, the first image similarity threshold value is that the minimum image that two images of satisfaction are same legitimate user is similar
Degree.
Second image similarity threshold value is to ensure legitimate user's image for saving in image data base of legitimate user and work as
The most like image similarity of preceding legitimate user.It is to be appreciated that legitimate user is likely to occur hair-cutting in daily life or wears
Situations such as glasses, legitimate user's image and the current reality of legitimate user before the legitimate user saved in image data base at this time
Interphase looks are likely to occur slight change.In order to accelerate the speed that server determines image similarity, server should timely update conjunction
Legitimate user's image that method user stores in image data base.
In step S22, when the image similarity of server judgement images to be recognized and legitimate user's image is between the first figure
When as between similarity and the second image similarity, Ying Caiyong images to be recognized updates legitimate user's image, ensures figure to be identified
While as corresponding legitimate user himself, the real-time of legitimate user image of the legitimate user in image data base can be also ensured
Property.
If S23. image similarity be not more than the first image similarity threshold value, obtain images match result for matching not at
Function.
In step S23, server determine the image similarity of images to be recognized and each eligible users image no more than
It is unsuccessful to match that first image similarity threshold value can determine that images match result, and matching process is quick and easy.
Step S21 is into S23, when server determines the image similarity of images to be recognized and legitimate user's image between the
When between one image similarity and the second image similarity, Ying Caiyong images to be recognized updates legitimate user's image, ensures wait know
While other image corresponds to legitimate user himself, the reality of legitimate user image of the legitimate user in image data base can be also ensured
Shi Xing.The image similarity of server judgement images to be recognized and each eligible users image is no more than the first image similarity
It is unsuccessful to match that threshold value can determine that images match result, and matching process is quick and easy.
In one embodiment, micro- Expression Recognition tool includes at least two micro- Expression Recognition models, each micro- Expression Recognition
Model corresponds to a micro- expression label.As shown in figure 4, in step s 40, i.e., each target image is inputted micro- Expression Recognition tool
Micro- expression marking is carried out, the micro- expression score table of target corresponding with each target image is obtained, specifically comprises the following steps:
S41. each target image is inputted each micro- Expression Recognition model to identify, is obtained opposite with micro- expression label
The micro- expression score value of the classification answered.
Wherein, micro- Expression Recognition model be obtained after carrying out Expression analysis to target image to belong to the model corresponding micro-
The expression score value of expression label.
Specifically, the micro- Expression Recognition model of training includes following four step: 1) preparing data set: including and micro- expression mark
Sign video clip acquisition, video image normalized and training/verifying/test set segmentation etc. of corresponding micro- expression;2) it sets
Meter learning model: it selects basic model frame for convolutional neural networks CNN+ Recognition with Recurrent Neural Network RNN, adjust the network number of plies, true
Determine the hyper parameters such as loss function, design learning rate;3) model output error training pattern: is passed through into BP algorithm backpropagation, benefit
With stochastic gradient descent SGD or Adam algorithm optimization model parameter;4) it verifies model: utilizing untrained data verification model
Generalization ability needs to redesign model if prediction result is undesirable, carries out the training of a new round, finally obtains prediction
As a result micro- Expression Recognition model of micro- expression label is preferably had.
In step S41, each target image can be inputted each micro- Expression Recognition model and identified by server, obtain with
The corresponding micro- expression score value of classifying of micro- expression label, is based on the micro- expression score value of the classification for subsequent server and obtains the micro- table of target
Feelings score table prepares data basis.
S42. association saves each micro- expression label and corresponding tag along sort score value, is formed opposite with each target image
The micro- expression score table of the target answered.
In step S42, server, which can be associated with, saves each micro- expression label and corresponding tag along sort score value, is formed and every
It is corresponding to be directly based upon at least two frame target images for server for the micro- expression score table of the corresponding target of one target image
The micro- expression score table of target compares preparation data basis.
Into S42, each target image can be inputted each micro- Expression Recognition model and identified step S41 by server,
The micro- expression score value of classification corresponding with micro- expression label is obtained, the micro- expression score value of the classification is based on for subsequent server and obtains mesh
It marks micro- expression score table and prepares data basis.Server, which can be associated with, saves each micro- expression label and corresponding tag along sort point
Value forms the micro- expression score table of target corresponding with each target image, is directly based upon at least two frame target figures for server
As the micro- expression score table of corresponding target compares preparation data basis.
In one embodiment, as shown in figure 5, after step S50, i.e., it is greater than micro- expression similarity threshold in comparison similarity
After value, unlocking verification method also specifically comprises the following steps:
S501. In vivo detection request is sent to acquisition terminal.
Wherein, In vivo detection request is that requirement user that server is sent to acquisition terminal is made before camera to taking on service jobs
The request of body movement.
In step S501, when server determines that the comparison similarity of at least two width target images is greater than micro- expression similarity threshold
When value, illustrate that the corresponding image of at least two width target images is identical image, there are users to carry out recognition of face using image
Cheating risk, at this point, server further should confirm user identity by In vivo detection, to improve the true of unlocking checking request
Property.
S502. the living body video flowing that acquisition terminal is returned based on In vivo detection request is obtained, using In vivo detection standard pair
Living body video flowing is verified, and In vivo detection result is obtained.
Living body video flowing be include that user makes the video flowing that corresponding movement is requested with In vivo detection before camera, than
Such as, blink or put head etc..
In vivo detection standard is standard as defined in the preset index that should meet to the movement of each living body of server, for example,
For blink movement, it should be maintained in the image at assigned timeslot interval, the eye of face should be kept closed.
In vivo detection result is the detection knot obtained after server is detected living body video flowing by In vivo detection standard
Fruit, including detect to pass through and detect and not pass through.It is to be appreciated that detection is by illustrating that living body video flowing meets In vivo detection standard
In specified requirement.
In step S502, server meets the verifying that the designated user in step S51 carries out living body video flowing by screening,
It carries out face to user further to be detected, to improve the reliability of unlocking checking request;Meanwhile only to comparison similarity
Corresponding greater than micro- expression similarity threshold user carries out In vivo detection, can reduce all carrying out In vivo detection to each user and open
The verification time is locked, verification efficiency is improved.
S503. based on In vivo detection as a result, dual lock checking request is handled.
Specifically, server can be based on the In vivo detection that step S502 is obtained as a result, the corresponding electricity of dual lock checking request
The operation such as locking is unlocked or kept to son lock, for example, when In vivo detection result is that detection passes through, the controllable acquisition of server
The corresponding electronic lock of terminal is unlocked operation, on the contrary then keep electronic locking conjunction state etc..
In step S503, server can carry out respective handling to electronic lock on the basis of In vivo detection result, ensure electricity
The safety in sub- lock control region.
Step S501 is into S503, when server determines that the comparison similarity of at least two width target images is greater than micro- expression phase
When like degree threshold value, illustrate that the corresponding image of at least two width target images is identical image, there are users to carry out face using image
The cheating risk of identification, at this point, server further should confirm user identity by In vivo detection, to improve unlocking checking request
Authenticity.Server meets the verifying that the designated user in step S51 carries out living body video flowing by screening, carries out to user
Face is further detected, to improve the reliability of unlocking checking request;Meanwhile micro- expression only is greater than to comparison similarity
The corresponding user of similarity threshold carries out In vivo detection, when can reduce the unlocking verifying for all carrying out In vivo detection to each user
Between, improve verification efficiency.Server can carry out respective handling to electronic lock on the basis of In vivo detection result, ensure electronic lock
The safety of control area.
In one embodiment, it as shown in fig. 6, after step S60, i.e., is returned in acquisition monitoring client identity-based audit request
After the auditing result returned, unlocking verification method also specifically comprises the following steps:
If S601. auditing result is that audit does not pass through, refuse unlocking checking request.
In step S601, when server receive audit transmission auditing result be audit it is obstructed out-of-date, that is, be rejected by out
Checking request is locked, ensures the safety of unlocking verifying system.
S602. verification tip information is generated, verification tip information is sent to User ID corresponding with images to be recognized
Corresponding user terminal.
Wherein, User ID is the corresponding user's mark of legitimate user that images to be recognized matches in image data base
Know.
Verification tip information, which is server, which sends its image to the corresponding user terminal of User ID, may be stolen into opening
Lock the prompt information of verifying system.It is to be appreciated that the safety and legitimate user in order to ensure unlocking verifying system enter and leave and open
The authenticity of verifying system is locked, the corresponding user terminal of User ID that server should will likely have security risk, which sends to generate, to be tested
Information is demonstrate,proved, carries out identity registration etc. to prompt the eligible users whether to need to log in unlocking verifying system again.
Step S601 is into S602, when the auditing result that server receives the transmission of audit is that audit is obstructed out-of-date
Refuse unlocking checking request, ensures the safety of unlocking verifying system.Server is in order to ensure the safety of unlocking verifying system
The authenticity that unlocking verifying system is entered and left with legitimate user, should will likely have the corresponding user terminal of User ID of security risk
It sends and generates verification information, carry out identity registration etc. to prompt the eligible users whether to need to log in unlocking verifying system again.
The unlocking verification method that the present embodiment proposes, server is by obtaining micro- expression video in unlocking checking request
Stream, there may be the target image of cheating suspicion is corresponding to be verified for acquisition after carrying out micro- expression marking to micro- expression video stream
User continues by monitoring client to carry out authentication, and the last auditing result dual lock checking request returned according to monitoring client carries out pair
It should handle, ensure the corresponding electronic lock unlocking safety of unlocking checking request, prevent user from carrying out unlocking verifying by image and ask
Ask the behavior practised fraud;It, can be big in flow of the people meanwhile only to there are the users to be verified of cheating suspicion to carry out identity audit
When, the time that each dealing personnel are all carried out with identity audit is saved, unlocking verification efficiency is improved.
Further, when the image similarity of server judgement images to be recognized and legitimate user's image is between the first image
When between similarity and the second image similarity, Ying Caiyong images to be recognized updates legitimate user's image, ensures images to be recognized
While corresponding legitimate user himself, the real-time of legitimate user image of the legitimate user in image data base can be also ensured.
The image similarity of server judgement images to be recognized and each eligible users image is no more than the first image similarity threshold value
It is unsuccessful to match to can determine that images match result, and matching process is quick and easy.
Further, each target image can be inputted each micro- Expression Recognition model and identified by server, obtain with
The corresponding micro- expression score value of classifying of micro- expression label, is based on the micro- expression score value of the classification for subsequent server and obtains the micro- table of target
Feelings score table prepares data basis.Server, which can be associated with, saves each micro- expression label and corresponding tag along sort score value, is formed
It is right respectively to be directly based upon at least two frame target images for server for the micro- expression score table of target corresponding with each target image
The micro- expression score table of the target answered compares preparation data basis.
Further, when server determines that the comparison similarity of at least two width target images is greater than micro- expression similarity threshold
When, illustrate that the corresponding image of at least two width target images is identical image, there are users using the work of image progress recognition of face
Disadvantage risk, at this point, server further should confirm user identity by In vivo detection, to improve the true of unlocking checking request
Property.Server meets the verifying that the designated user in step S51 carries out living body video flowing by screening, carries out face to user
It is further detected, to improve the reliability of unlocking checking request;Meanwhile micro- expression similarity only is greater than to comparison similarity
The corresponding user of threshold value carries out In vivo detection, can reduce the unlocking verification time that In vivo detection is all carried out to each user, improves
Verification efficiency.Server can carry out respective handling to electronic lock on the basis of In vivo detection result, ensure electronic lock control zone
The safety in domain.
Further, the auditing result for the transmission audited when server reception is that audit is obstructed out-of-date, that is, is rejected by unlocking
Checking request ensures the safety of unlocking verifying system.Server is in order to ensure the safety and legal use of unlocking verifying system
Family enters and leaves the authenticity of unlocking verifying system, and the corresponding user terminal of User ID that should will likely have security risk, which is sent, to be generated
Verification information carries out identity registration etc. to prompt the eligible users whether to need to log in unlocking verifying system again.
It should be understood that the size of the serial number of each step is not meant that the order of the execution order in above-described embodiment, each process
Execution sequence should be determined by its function and internal logic, the implementation process without coping with the embodiment of the present invention constitutes any limit
It is fixed.
In one embodiment, a kind of unlocking verifying device is provided, which verifies device and test with unlocking in above-described embodiment
Card method corresponds.As shown in fig. 7, unlocking verifying device includes obtaining checking request module 10, extracting images to be recognized
Module 20 extracts target image module 30, obtains expression score table mould module 40, calculate comparison similarity module 50, obtain and examine
Core object module 60 and control unlocking processing module 70.Detailed description are as follows for each functional module:
Checking request module 10 is obtained, for obtaining the unlocking checking request of acquisition terminal transmission, unlocking checking request packet
Include micro- expression video stream.
Images to be recognized module 20 is extracted, for extracting any frame images to be recognized in micro- expression video stream, based on wait know
Other image is matched in image data base, obtains images match result.
Target image module 30 is extracted, if being successful match for images match result, is extracted by default extracting rule
At least two frame target images.
Expression score table mould module 40 is obtained, carries out micro- expression for each target image to be inputted micro- Expression Recognition tool
Marking obtains the micro- expression score table of target corresponding with each target image.
Comparison similarity module 50 is calculated, it is similar for calculating the corresponding comparison of the micro- expression score table of any two target
Degree sends identity audit request to monitoring client if comparison similarity is greater than micro- expression similarity threshold.
Auditing result module 60 is obtained, the auditing result returned for obtaining the audit request of monitoring client identity-based.
Unlocking processing module 70 is controlled, if being that audit passes through for auditing result, controls Lock-Picking Devices to acquisition terminal
Corresponding electronic lock carries out unlocking processing.
Preferably, the extraction images to be recognized module 20, including calculate image similarity unit 21, obtain successful match list
Member 22 and the unsuccessful matching unit 23 of acquisition.
Image similarity unit 21 is calculated, for calculating each legitimate user's image in images to be recognized and image data base
Image similarity.
Successful match unit 22 is obtained, if being greater than the first image similarity threshold value for image similarity, and image is similar
Degree is not more than the second image similarity threshold value, then updates legitimate user's image using images to be recognized, and obtain images match knot
Fruit is successful match.
Unsuccessful matching unit 23 is obtained, if being not more than the first image similarity threshold value for image similarity, is obtained
Images match result is that matching is unsuccessful.
Preferably, unlocking verifying device further includes executing identity auditing module.
Identity auditing module is executed, if being that matching is unsuccessful for images match result, executes to monitoring client and sends body
The step of part audit request.
Preferably, which includes obtaining micro- expression score value unit and formation expression score value list
Member.
Micro- expression score value unit is obtained, is identified for each target image to be inputted each micro- Expression Recognition model,
Obtain the micro- expression score value of classification corresponding with micro- expression label.
Expression score value table unit is formed, saves each micro- expression label and corresponding tag along sort score value, shape for being associated with
At the micro- expression score table of target corresponding with each target image.
Preferably, unlocking verifying device further includes sending In vivo detection module, obtaining living body video stream module and processing
Checking request module.
In vivo detection module is sent, for sending In vivo detection request to acquisition terminal.
Living body video stream module is obtained, the living body video flowing returned for obtaining acquisition terminal based on In vivo detection request,
Living body video flowing is verified using In vivo detection standard, obtains In vivo detection result.
Checking request module is handled, for being based on In vivo detection as a result, dual lock checking request is handled.
Preferably, unlocking verifying device further includes refuse inspection of books request module and generation prompt information module.
Refuse inspection of books request module, if being that audit does not pass through for auditing result, refuses unlocking checking request.
Prompt information module is generated to be sent to verification tip information and figure to be identified for generating verification tip information
As the corresponding user terminal of corresponding User ID.
About unlocking, the specific of verifying device limits the restriction that may refer to above for unlocking verification method, herein not
It repeats again.Modules in above-mentioned unlocking verifying device can be realized fully or partially through software, hardware and combinations thereof.On
Stating each module can be embedded in the form of hardware or independently of in the processor in computer equipment, can also store in a software form
In memory in computer equipment, the corresponding operation of the above modules is executed in order to which processor calls.
In one embodiment, a kind of computer equipment is provided, which can be server, internal structure
Figure can be as shown in Figure 8.The computer equipment includes processor, the memory, network interface sum number connected by system bus
According to library.Wherein, the processor of the computer equipment is for providing calculating and control ability.The memory of the computer equipment includes
Non-volatile memory medium, built-in storage.The non-volatile memory medium is stored with operating system, computer program and data
Library.The built-in storage provides environment for the operation of operating system and computer program in non-volatile memory medium.The calculating
The database of machine equipment is for the relevant data of verification method of unlocking.The network interface of the computer equipment is used for and external end
End passes through network connection communication.To realize a kind of unlocking verification method when the computer program is executed by processor.
In one embodiment, a kind of computer equipment is provided, including memory, processor and storage are on a memory and can
The computer program run on a processor, processor realize above-described embodiment unlocking verification method when executing computer program,
Such as S10 shown in Fig. 2 to step S70.Alternatively, processor realizes verifying dress of unlocking in above-described embodiment when executing computer program
The function for each module/unit set, such as module 10 shown in Fig. 7 is to the function of module 70.It is no longer superfluous herein to avoid repeating
It states.
In one embodiment, a kind of computer readable storage medium is provided, computer program, computer journey are stored thereon with
Above-described embodiment unlocking verification method, such as S10 shown in Fig. 2 to step S70 are realized when sequence is executed by processor.Alternatively, the meter
The function of each module/unit in verifying device of unlocking in above-mentioned apparatus embodiment, example are realized when calculation machine program is executed by processor
Module 10 as shown in Figure 7 to module 70 function.To avoid repeating, details are not described herein again.
Those of ordinary skill in the art will appreciate that realizing all or part of the process in above-described embodiment method, being can be with
Relevant hardware is instructed to complete by computer program, it is readable which can be stored in a non-volatile computer
It takes in storage medium, the computer program is when being executed, it may include such as the process of the embodiment of above-mentioned each method.Wherein, this Shen
Please any reference used in each embodiment to memory, storage, database or other media, may each comprise non-volatile
And/or volatile memory.Nonvolatile memory may include that read-only memory (ROM), programming ROM (PROM), electricity can be compiled
Journey ROM (EPROM), electrically erasable ROM (EEPROM) or flash memory.Volatile memory may include random access memory
(RAM) or external cache.By way of illustration and not limitation, RAM is available in many forms, such as static state RAM
(SRAM), dynamic ram (DRAM), synchronous dram (SDRAM), double data rate sdram (DDRSDRAM), enhanced SDRAM
(ESDRAM), synchronization link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) directly RAM (RDRAM), straight
Connect memory bus dynamic ram (DRDRAM) and memory bus dynamic ram (RDRAM) etc..
It is apparent to those skilled in the art that for convenience of description and succinctly, only with above-mentioned each function
Can unit, module division progress for example, in practical application, can according to need and by above-mentioned function distribution by different
Functional unit, module are completed, i.e., the internal structure of described device is divided into different functional unit or module, more than completing
The all or part of function of description.
The above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations;Although with reference to the foregoing embodiments
Invention is explained in detail, those skilled in the art should understand that: it still can be to aforementioned each implementation
Technical solution documented by example is modified or equivalent replacement of some of the technical features;And these modification or
Replacement, the spirit and scope for technical solution of various embodiments of the present invention that it does not separate the essence of the corresponding technical solution should all include
Within protection scope of the present invention.
Claims (10)
1. a kind of unlocking verification method characterized by comprising
The unlocking checking request that acquisition terminal is sent is obtained, the unlocking checking request includes micro- expression video stream;
Extract any frame images to be recognized in micro- expression video stream, based on the images to be recognized in image data base into
Row matching, obtains images match result;
If described image matching result is successful match, at least two frame target images are extracted by default extracting rule;
Each target image is inputted into micro- Expression Recognition tool and carries out micro- expression marking, is obtained and each target image
The corresponding micro- expression score table of target;
The corresponding comparison similarity of the micro- expression score table of target described in any two is calculated, if the comparison similarity is greater than micro- table
Feelings similarity threshold then sends identity audit request to monitoring client;
It obtains the monitoring client and the auditing result that request returns is audited based on the identity;
If the auditing result is that audit passes through, controls Lock-Picking Devices and unlock to the corresponding electronic lock of the acquisition terminal
Processing.
2. unlocking verification method as described in claim 1, which is characterized in that described to be based on the images to be recognized in picture number
According to being matched in library, images match result is obtained, comprising:
Calculate the image similarity of each legitimate user's image in the images to be recognized and described image database;
If described image similarity is greater than the first image similarity threshold value, and described image similarity is similar no more than the second image
Threshold value is spent, then legitimate user's image is updated using the images to be recognized, and obtaining images match result is successful match;
If described image similarity is not more than the first image similarity threshold value, it is unsuccessful to match to obtain images match result.
3. unlocking verification method as described in claim 1, which is characterized in that described image matching result include matching not at
Function;
After the acquisition images match result, the unlocking verification method further include:
If described image matching result is that matching is unsuccessful, the step of sending identity audit request to monitoring client is executed.
4. unlocking verification method as described in claim 1, which is characterized in that micro- Expression Recognition tool includes at least two
Micro- Expression Recognition model, each corresponding micro- expression label of micro- Expression Recognition model;
It is described that each target image is inputted into the micro- expression marking of micro- Expression Recognition tool progress, it obtains and each target
The micro- expression score table of the corresponding target of image, comprising:
Each target image is inputted each micro- Expression Recognition model to identify, is obtained and micro- expression label
The corresponding micro- expression score value of classification;
Association saves each micro- expression label and corresponding tag along sort score value, is formed opposite with each target image
The micro- expression score table of the target answered.
5. unlocking verification method as described in claim 1, which is characterized in that it is similar to be greater than micro- expression in the comparison similarity
It spends after threshold value, the unlocking verification method further include:
In vivo detection request is sent to the acquisition terminal;
The living body video flowing that the acquisition terminal is returned based on In vivo detection request is obtained, using In vivo detection standard to institute
It states living body video flowing to be verified, obtains In vivo detection result;
Based on the In vivo detection as a result, handling the unlocking checking request.
6. unlocking verification method as described in claim 1, which is characterized in that obtain the monitoring client based on the body described
After the auditing result that part audit request returns, the unlocking verification method further include:
If the auditing result is that audit does not pass through, refuse the unlocking checking request;
Verification tip information is generated, the verification tip information is sent to User ID pair corresponding with the images to be recognized
The user terminal answered.
7. device is verified in a kind of unlocking characterized by comprising
Checking request module is obtained, for obtaining the unlocking checking request of acquisition terminal transmission, the unlocking checking request includes
Micro- expression video stream;
Extract images to be recognized module, for extracting any frame images to be recognized in micro- expression video stream, based on it is described to
Identification image is matched in image data base, obtains images match result;
Extract target image module, if for described image matching result be successful match, by default extracting rule extract to
Few two frame target images;
Expression score table mould module is obtained, is beaten for each target image to be inputted the micro- expression of micro- Expression Recognition tool progress
Point, obtain the micro- expression score table of target corresponding with each target image;
Comparison similarity module is calculated, for calculating the corresponding comparison similarity of the micro- expression score table of target described in any two,
If the comparison similarity is greater than micro- expression similarity threshold, identity audit request is sent to monitoring client;
Auditing result module is obtained, the auditing result that request returns is audited based on the identity for obtaining the monitoring client;
Unlocking processing module is controlled, if being that audit passes through for the auditing result, it is whole to the acquisition to control Lock-Picking Devices
Corresponding electronic lock is held to carry out unlocking processing.
8. verifying device as claimed in claim 7 of unlocking, which is characterized in that the extraction images to be recognized module, comprising:
Image similarity unit is calculated, is schemed for calculating each legitimate user in the images to be recognized and described image database
The image similarity of picture;
Successful match unit is obtained, if being greater than the first image similarity threshold value, and described image phase for described image similarity
It is not more than the second image similarity threshold value like degree, then legitimate user's image is updated using the images to be recognized, and obtain
Images match result is successful match;
Unsuccessful matching unit is obtained, if being not more than the first image similarity threshold value for described image similarity, obtains figure
As matching result is that matching is unsuccessful.
9. a kind of computer equipment, including memory, processor and storage are in the memory and can be in the processor
The computer program of upper operation, which is characterized in that the processor realized when executing the computer program as claim 1 to
Any one of 6 unlocking verification methods.
10. a kind of computer readable storage medium, the computer-readable recording medium storage has computer program, and feature exists
In realizing and unlock as described in any one of claim 1 to 6 verification method when the computer program is executed by processor.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910431034.9A CN110298246A (en) | 2019-05-22 | 2019-05-22 | Unlocking verification method, device, computer equipment and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910431034.9A CN110298246A (en) | 2019-05-22 | 2019-05-22 | Unlocking verification method, device, computer equipment and storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110298246A true CN110298246A (en) | 2019-10-01 |
Family
ID=68026950
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910431034.9A Pending CN110298246A (en) | 2019-05-22 | 2019-05-22 | Unlocking verification method, device, computer equipment and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110298246A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111126244A (en) * | 2019-12-20 | 2020-05-08 | 南京邮电大学 | Security authentication system and method based on facial expressions |
CN111861240A (en) * | 2020-07-27 | 2020-10-30 | 深圳前海微众银行股份有限公司 | Suspicious user identification method, device, equipment and readable storage medium |
CN114006921A (en) * | 2021-10-15 | 2022-02-01 | 厦门狄耐克物联智慧科技有限公司 | Nurse station supervisor with intelligent control |
CN115277661A (en) * | 2022-07-21 | 2022-11-01 | 平安壹钱包电子商务有限公司 | Method and device for judging illegal operation based on Web page and storage medium |
WO2023134080A1 (en) * | 2022-01-12 | 2023-07-20 | 平安科技(深圳)有限公司 | Method and apparatus for identifying camera spoofing, device, and storage medium |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107045744A (en) * | 2017-04-14 | 2017-08-15 | 特斯联(北京)科技有限公司 | A kind of intelligent villa entrance guard authentication method and system |
CN108288165A (en) * | 2018-03-28 | 2018-07-17 | 成都信达智胜科技有限公司 | A kind of high-precision confirming face method |
CN108830975A (en) * | 2018-04-27 | 2018-11-16 | 安徽继远软件有限公司 | A kind of Intelligent human-face identification gate control system and control method |
WO2019075840A1 (en) * | 2017-10-17 | 2019-04-25 | 平安科技(深圳)有限公司 | Identity verification method and apparatus, storage medium and computer device |
-
2019
- 2019-05-22 CN CN201910431034.9A patent/CN110298246A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107045744A (en) * | 2017-04-14 | 2017-08-15 | 特斯联(北京)科技有限公司 | A kind of intelligent villa entrance guard authentication method and system |
WO2019075840A1 (en) * | 2017-10-17 | 2019-04-25 | 平安科技(深圳)有限公司 | Identity verification method and apparatus, storage medium and computer device |
CN108288165A (en) * | 2018-03-28 | 2018-07-17 | 成都信达智胜科技有限公司 | A kind of high-precision confirming face method |
CN108830975A (en) * | 2018-04-27 | 2018-11-16 | 安徽继远软件有限公司 | A kind of Intelligent human-face identification gate control system and control method |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111126244A (en) * | 2019-12-20 | 2020-05-08 | 南京邮电大学 | Security authentication system and method based on facial expressions |
CN111861240A (en) * | 2020-07-27 | 2020-10-30 | 深圳前海微众银行股份有限公司 | Suspicious user identification method, device, equipment and readable storage medium |
CN114006921A (en) * | 2021-10-15 | 2022-02-01 | 厦门狄耐克物联智慧科技有限公司 | Nurse station supervisor with intelligent control |
WO2023134080A1 (en) * | 2022-01-12 | 2023-07-20 | 平安科技(深圳)有限公司 | Method and apparatus for identifying camera spoofing, device, and storage medium |
CN115277661A (en) * | 2022-07-21 | 2022-11-01 | 平安壹钱包电子商务有限公司 | Method and device for judging illegal operation based on Web page and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110298246A (en) | Unlocking verification method, device, computer equipment and storage medium | |
CN101661557B (en) | Face recognition system and face recognition method based on intelligent card | |
AU2019219813A1 (en) | Transaction verification system | |
WO2019062080A1 (en) | Identity recognition method, electronic device, and computer readable storage medium | |
CN102890776B (en) | The method that expression figure explanation is transferred by facial expression | |
CN108573202A (en) | Identity identifying method, device and system and terminal, server and storage medium | |
Azzini et al. | A fuzzy approach to multimodal biometric continuous authentication | |
CN112528259A (en) | Identity authentication method, identity authentication device, computer equipment and storage medium | |
WO2018082011A1 (en) | Living fingerprint recognition method and device | |
CN109756458A (en) | Identity identifying method and system | |
CN103514440A (en) | Facial recognition | |
CN104169933A (en) | Method, apparatus, and computer-readable recording medium for authenticating a user | |
US10922399B2 (en) | Authentication verification using soft biometric traits | |
CN109472269A (en) | Characteristics of image configuration and method of calibration, device, computer equipment and medium | |
CA3195818A1 (en) | Intelligent gallery management for biometrics | |
KR20200029659A (en) | Method and apparatus for face recognition | |
CN109389028A (en) | Face identification method, device, equipment and storage medium based on motion analysis | |
Yin et al. | Fusion of face recognition and facial expression detection for authentication: a proposed model | |
CN109544384A (en) | Subsidy distribution method, device, terminal, storage medium based on bio-identification | |
Boncolmo et al. | Gender Identification Using Keras Model Through Detection of Face | |
Anand et al. | Enhancing the performance of multimodal automated border control systems | |
CN116758643A (en) | Method and device for detecting deeply forged face image | |
Agbinya et al. | Design and implementation of multimodal digital identity management system using fingerprint matching and face recognition | |
Azzini et al. | Impostor users discovery using a multimodal biometric continuous authentication fuzzy system | |
CN112309025B (en) | Information display method and device, electronic equipment and storage medium |
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 |