CN107133608A - Identity authorization system based on In vivo detection and face verification - Google Patents
Identity authorization system based on In vivo detection and face verification Download PDFInfo
- Publication number
- CN107133608A CN107133608A CN201710395760.0A CN201710395760A CN107133608A CN 107133608 A CN107133608 A CN 107133608A CN 201710395760 A CN201710395760 A CN 201710395760A CN 107133608 A CN107133608 A CN 107133608A
- Authority
- CN
- China
- Prior art keywords
- face
- verification
- identity
- lip
- authenticatee
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/30—Authentication, i.e. establishing the identity or authorisation of security principals
- G06F21/31—User authentication
- G06F21/32—User authentication using biometric data, e.g. fingerprints, iris scans or voiceprints
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/20—Movements or behaviour, e.g. gesture 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
- G06V40/40—Spoof detection, e.g. liveness detection
- G06V40/45—Detection of the body part being alive
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Human Computer Interaction (AREA)
- Oral & Maxillofacial Surgery (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Security & Cryptography (AREA)
- Software Systems (AREA)
- Probability & Statistics with Applications (AREA)
- Computer Hardware Design (AREA)
- Psychiatry (AREA)
- Social Psychology (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
- Collating Specific Patterns (AREA)
Abstract
The invention discloses a kind of identity authorization system based on In vivo detection and face verification, including:Face verification module, face is contrasted on the face and identity card by the authenticatee of acquisition, judges whether matching;Lip reading recognizes authentication module, it is rear for passing through in the face verification module verification, authenticatee is pointed out to read numeral combination providing with the machine, judge whether the outer lip contour action of lip of authenticatee in camera watch region matches with reading lip contour action outside the lip that the numeral is combined, regard as live body if matching and authentication passes through.The problem of being cheated instant invention overcomes molecule agaainst the law using photo and video, it can realize that the identity of testimony of a witness unification differentiates work(, the function of pinpoint accuracy recognition of face and In vivo detection can be reached, with the features such as Detection results are good, accuracy is high, detection speed is fast, available for self-service authentication.
Description
Technical field
The present invention relates to identity identifying technology field, more particularly to a kind of identity based on In vivo detection and face verification
Verification System.
Background technology
Identity identifying technology is the effective workaround for confirming the process of operator's identity in computer systems and producing.
Identity information of all information including user is all represented with one group of specific data in the computer network world, computer
The digital identity of user can only be recognized, all mandates to user are also the mandate for number identity.How to ensure with
The operator that digital identity is operated is exactly this digital identity lawful owner, that is to say, that ensure the physics body of operator
Part is corresponding with digital identity, and identity identifying technology is exactly, in order to solve this problem, to be used as first of protected network assets
Critical point, authentication plays the role of very important.In real world, the authentication basic skills to user can be divided into this
Three kinds:(1) authentication based on information privacy;(2) based on the authentication for trusting object;(3) body based on biological characteristic
Part certification.
As face recognition technology is in the application of field of identity authentication, impersonation attack (or replication attacks) is to face authentication system
System constitutes very big threat.Face In vivo detection technology be one kind prevent attacker using photo or video false impersonation with
A kind of security precautions technology that computer is interacted.In many applications that automated validation is carried out dependent on face, stabilization can
The recognition of face In vivo detection technology leaned on can avoid system from being cheated by attacker.Current face In vivo detection technology is mainly sharp
With the method for man-machine interaction, require that user performs action accordingly in detection process, such as open and close one's eyes, open and shut up, shake the head and nod
Deng.Or addition auxiliary hardware devices, by detecting that the distance of human face is judged.Introduced in CN201310384572.X
Allow user to complete some actions selected at random within the specified time several times, work is determine whether according to performance
Body.This method only carries out simple motion detection to head, and action cooperation and the realtime graphic pair of limbs are not referred to
Compare function.Using the distance between ultrasonic measurement camera and barrier in CN201510300584.9, while utilizing logic
Regression model obtains class probability value f;By calculating the New Set structural for obtaining weighing two images similarity
Similarity index measurement system, abbreviation SSIM values, its value is the bigger the better, and is 1 to the maximum.By SSIM values
With f value linear combinations, final result is obtained, spoofing attack is determine whether by given threshold.But this method requires addition
Auxiliary equipment, greatly limit application scenarios, and not refer to specific testimony of a witness method of calibration.
The content of the invention
In view of the technical drawbacks of the prior art, it is an object of the present invention to provide one kind is based on In vivo detection and people
The identity authorization system of face checking, can carry out In vivo detection and face verification to the face for entering detection zone, improve body
The precision of part Verification System, and then enhance the safety and reliability of identity authorization system.
The present invention is achieved in that a kind of identity authorization system based on In vivo detection and face verification, including:
Face verification module, face is contrasted on the face and identity card by the authenticatee of acquisition, and judgement is
No matching;
Lip reading recognizes authentication module, for by rear, pointed out in the face verification module verification authenticatee read with
Whether the numeral combination that machine is provided, judge the outer lip contour action of lip of authenticatee in camera watch region with reading the digit groups
The outer lip contour action matching of the lip of conjunction, regards as live body if matching and authentication passes through.
The face verification module includes:
Face datection unit, for detecting face in the realtime graphic that photographing module is gathered;
Tip element, it is specified for after Face datection unit detects face, pointing out authenticatee to be placed on identity card
ID card verification region to obtain the image of identity card;
Identity card, is placed on behind the ID card verification region specified, passes through face by face verification unit for authenticatee
Alignment, face characteristic are extracted and the processing sequence of human face similarity degree contrast is examined to contrast face and face on authenticatee's identity card
The image for the face that unit is detected is surveyed, judges whether matching.
Lip reading identification authentication module when carrying out lip reading identification, be by the dynamic detection of lip, shape of the mouth as one speaks feature extraction and
Checking is identified in the sequential steps of lip reading identification.
The ID card verification region is multiple, and the ID card verification region specified is existed at random by the Tip element
Specify in the ID card verification region and on human-computer interaction interface by ejecting square frame and output character is pointed out.
The face verification module carries out second after being proved to be successful first, at least and verified, is proved to be successful for the second time
The checking that lip reading recognizes authentication module is entered back into afterwards.
Lip reading identification authentication module checking at least detects three times, and after repeated detection success prompting authentication into
Work(.
The numeral is combined as the numeral combination randomly generated in 1-9.
The identity authorization system based on In vivo detection and face verification, in addition to result indicating module, the result
Indicating module includes:
Indicated when the first indicator lamp, face for detecting authenticatee in camera watch region;
Second indicator lamp, for being indicated after the match is successful in face verification;
3rd indicator lamp, is pointed out after being proved to be successful for lip reading identification.
The identity authorization system based on In vivo detection and face verification, in addition to photographing module, are tested for obtaining
The realtime graphic and ID Card Image of card person, the photographing module is web camera.
The identity authorization system based on In vivo detection and face verification, including industrial computer, liquid crystal display;The net
Network photographing module is by the network interface of industrial computer described in network connection, and the LCDs passes through HDMI wire and connected with the industrial computer
Connect.
Present system overcomes the problem of molecule agaainst the law is cheated using photo and video, can realize that the testimony of a witness is unified
Identity differentiate work(, the function of pinpoint accuracy recognition of face and In vivo detection can be reached, with Detection results are good, accuracy is high,
The features such as detection speed is fast, available for self-service authentication.
Brief description of the drawings
Fig. 1 show the structure chart of the identity authorization system based on In vivo detection and face verification of the present invention;
Fig. 2 show the schematic diagram of the identity authorization system human-computer interaction interface based on In vivo detection and face verification;
Fig. 3 show the overhaul flow chart of the identity authorization system based on In vivo detection and face verification;
Fig. 4 show the hardware structure diagram of the identity authorization system based on In vivo detection and face verification.
Embodiment
The present invention is described in further detail below in conjunction with the drawings and specific embodiments.It should be appreciated that described herein
Specific embodiment only to explain the present invention, be not intended to limit the present invention.
As shown in figure 1, a kind of identity authorization system based on In vivo detection and face verification, including:
Face verification module, face is contrasted on the face and identity card by the authenticatee of acquisition, and judgement is
No matching;
Lip reading recognizes authentication module, for by rear, pointed out in the face verification module verification authenticatee read with
Whether the numeral combination that machine is provided, judge the outer lip contour action of lip of authenticatee in camera watch region with reading the digit groups
The outer lip contour action matching of the lip of conjunction, regards as live body if matching and authentication passes through.
When implementing, the image and ID Card Image of authenticatee is gathered, to the face in authenticatee's image
After being handled with the face on identity card, compared by extracting feature, judge whether matching.If the match is successful, enter
The step of entering lip reading identification checking, recognizes authentication module by the lip reading, points out authenticatee to read digit groups providing with the machine
Close, then recognize that lip reading, whether with requiring that the numeral read combines information match, carries out lip reading knowledge according to lip reading identification technology
Do not verify, according to the result to whether being that live body is assert and provides the result, and after being proved to be successful, authentication
Pass through.
When carrying out face verification recognition detection, system meeting random display identity card is put into region, in lip reading cognitive phase,
System can allow authenticatee to read random digit combination, therefore can prevent the attack of photo and video, so as to realize face live body
Detection.
The present invention is solved and verified using photo and video by the way that face verification is recognized into checking is combined with lip reading
And the problem of easily cheat, can realize that the identity of testimony of a witness unification differentiates work(, it can reach that pinpoint accuracy recognition of face is examined with live body
The function of survey.
Wherein, the ID card verification region is multiple, can be shown on human-computer interaction interface, specifically described to specify
ID card verification region specified and in human-computer interaction interface in the ID card verification region by the Tip element is random
On pointed out by ejecting square frame and exporting prompting comment.In the present invention, the ID card verification region 1 is preferably 6,
The upper-lower position for the image display area 2 being distributed on the human-computer interaction interface of authenticatee, each three, as shown in Figure 2.
Implement, the numeral is combined as the numeral combination randomly generated in 1-9, such as 1234,3456 or 4367
Deng of coursing, lip reading identification checking can also be language message that spelling words intellectual etc. can be read by authenticatee.
Further, in the present invention, the identity authorization system based on In vivo detection and face verification, in addition to result
Indicating module, realizes the prompting to Face datection result, face verification result and lip reading recognition result, specifically, such as Fig. 2 institutes
Show, can be located at the corresponding position of human-computer interaction interface, the specific result indicating module includes:
Indicated when the first indicator lamp 3, face for detecting authenticatee in camera watch region;
Second indicator lamp 4, for being indicated after the match is successful in face verification;
3rd indicator lamp 5, is pointed out after being proved to be successful for lip reading identification.
The result indicating module is specific when indicating, can be the checking that respective stage is indicated by indicator lamp greening
Success, is otherwise the state of reddening.
Implement, in the present invention, described face verification module includes:
Face datection unit, for detecting face in the realtime graphic that photographing module is gathered;
Tip element, it is specified for after Face datection unit detects face, pointing out authenticatee to be placed on identity card
ID card verification region to obtain the image of identity card;
Identity card, is placed on behind the ID card verification region specified, passes through face by face verification unit for authenticatee
Alignment, face characteristic are extracted and the processing sequence of human face similarity degree contrast is examined to contrast face and face on authenticatee's identity card
The image for the face that unit is detected is surveyed, judges whether matching.
It should be noted that in the present invention, the face verification module and lip reading identification authentication module can be using accordingly
Recognition of face checking and lip reading identification checking software program are realized.
Wherein, the face verification module is when carrying out face verification, including face alignment, face characteristic are extracted and face
Three steps of similarity comparison, during the lip reading identification authentication module checking, including the dynamic detection of lip, feature extraction and lip reading are known
Not.It is specifically described below as follows:
Specifically, the present invention can realize the collection of frame of video, the people developed by QT using the supporting SDK of web camera
Realize image display and human-computer interaction in real time in machine interface.The image that Face datection unit is collected using web camera is input
Obtain face location information.After facial image is detected, the first indicator lamp greening, and point out user will by Tip element
Identity card is placed on the ID card verification region specified, while the face in specified ID card verification region detection identity card.
Wherein, Face datection can utilize opencv haarcascade_frontalface_atl2.xml model inspections,
Face such as is detected in Face datection unit, then identity card is placed on the ID card verification specified by Tip element prompting authenticatee
Verified with obtaining the image of identity card with the face correspondence for carrying out a step in region.
It is same with opencv's after user coordinates limb action that identity card is put into the ID card verification region specified
Face in haarcascade_frontalface_atl2.xml model inspection identity cards, detect the face in identity card with
Afterwards, the face detected to Face datection unit and the identity card face detected carry out feature extraction and real time contrast, to sentence
Whether disconnected identity is consistent.Process is broadly divided into the face for detecting video camera viewing area and identity card viewing area and enters pedestrian
Face alignment, feature extraction and similarity comparison:
1. face aligns
Input picture is retrieved, input picture is translated, scaled etc. and operate, is matched with face template.By right
Neat algorithm obtains matching result.
If the gray matrix of face template is:
T={ tij(i=0,1 ..., m-1;J=0,1 ..., n-1) (1)
Input picture matrix is:
R={ rij(i=0,1 ..., m-1;J=0,1 ..., n-1) (2)
The Euclidean distance of input picture and face template is:
The width of image array is m and height is n, and i, j is pixel coordinate.Got over when being less than predetermined threshold value and d values apart from d
It is small, then it represents that the matching degree between input picture and template is higher.
Symmetry constraint processing is done to image array to be detected.Try to achieve respectively input picture matrix R using vertical central axis as
The left-half image RL and right half part image RR of boundary, seek difference θ=RL-RR of the gray value of two parts image.When θ value
When obtaining minimum value, then it can consider that image of input or so is the most symmetrical, as the optimum position of facial image.It will can ask
The Euclidean distance d obtained is added with symmetry constraint value θ, δ=d+ θ.When δ obtains minimum value, then it is assumed that input picture possesses Euclidean
Distance is minimum with symmetry constraint sum, and picture and the alignment effect of template at this moment is best.δ is end product.The system is adopted
Face template specification is 36 × 36 pixels, if the facial image detected and face template cause not of uniform size, to inspection
The image measured zooms in and out operation, makes it in the same size with face template, and image-region edge is expanded into 8 on this basis
Pixel, is follow-up template matches headspace.
2. feature extraction
The facial image of input is carried out after face alignment, face characteristic is extracted by AlexNet network models, obtained
The characteristic vector and eigentransformation matrix of face.
Convolutional neural networks (CNN) reduce mould as a kind of deep learning framework while characteristics of image is accurately extracted
Type complexity.For advantages of the CNN in terms of image recognition, a kind of facial image feature extracting method based on CNN is proposed.
In CNN, the sub-fraction (local experiences region) of image is as the input of the lowermost layer of hierarchical structure, and information is transferred to successively again
Different layers, every layer is gone to obtain the most significant feature of observation data by a digital filter.This method can be obtained
To translation, scaling and invariable rotary observation data notable feature because image local experiences region permission neuron or
Person's processing unit can have access to most basic feature.The system uses the AlexNet models with 8 layer network structures to fusion
Facial image carry out feature extraction, reuse SVMs (SVM) carry out classification prediction.AlexNet has 8 layers, wherein 5
Individual is convolutional layer, and 2 are full articulamentum, and 1 is output category layer.Wherein:Closelyed follow respectively after (1) first and second convolutional layer
One normalization layer (norm layers);(2) sub-sampling operation is immediately the oneth the second norm layers, and after the 5th convolutional layer;
(3) AlexNet layer second from the bottom can describe the global characteristics of image well, so using the output of its layer second from the bottom
As the feature of image, image can be described well, be well suited for being used for image classification.
3. similarity comparison
The face characteristic of extraction ID Card Image and real-time face image is compared, result is identified.If right
Than success, system, which can randomly select another area requirement user again identity card is put into designated area, to be verified, when
After the result verified twice is all correct, the second indicator lamp greening, face verification passes through.
In the present invention, the lip reading identification authentication module is when carrying out lip reading identification, in order including the dynamic detection of lip, feature
The step of extraction and lip reading are recognized.The dynamic detection of lip is used to position the lip of input picture, and detects whether to exist and open
Shut up action;Feature extraction, effective shape of the mouth as one speaks feature for extracting lip reading;Labiomaney is recognized, is special by effective shape of the mouth as one speaks of extraction
Levy to recognize lip reading content.
Specifically, in the present invention, the lip reading identification authentication module takes algorithm of support vector machine (Support Vector
Machine, SVM) detect that the outer lip contour of lip carries out the extraction of the shape of the mouth as one speaks, eliminating unrelated facial information well
While, it is ensured that its accuracy and speed.Lip is identified using the Dynamic Clustering Algorithm based on K-means algorithms,
And the situation that lip-syncing lockjaw is closed, parts a little and opened is verified, after lip reading identification is verified, the 3rd indicator lamp becomes
It is green, indicate that lip reading identification is verified.
In order to further improve in the reliability of face verification, the present invention, verified in the face verification module first
After success, second of checking is also carried out, after being proved to be successful for the second time, the checking that lip reading recognizes authentication module is entered back into.Such as
Fruit verifies unsuccessful for the second time, then authentication failed, face verification can be re-started, only in desired face verification step success
Lip reading can just be entered afterwards and recognize Qualify Phase.It is of course also possible to be arranged as required to more checking, do not limit specifically.
In order to further improve in the reliability of lip reading identification checking, the present invention, the lip reading identification authentication module checking
At least detect three times, and the prompting authentication success after repeated detection success.Specifically, after being proved to be successful for the first time, system
After there is provided numeral combination for the first time, then second group of numeral combination of random offer, this second group numeral is read by authenticatee
Combination, then verified, if second of lip reading identification is verified, third time checking is carried out, is provided at random again by system
3rd group of numeral combination, the 3rd group of numeral combination is read by authenticatee, then is verified, after three times are proved to be successful, is pointed out
It is verified.It is of course also possible to be arranged as required to more checking, do not limit specifically.
Implement, in the present invention, the identity authorization system based on In vivo detection and face verification, in addition to take the photograph
As module, realtime graphic and ID Card Image for obtaining authenticatee, the photographing module are web camera.The net
Network video camera is after the realtime graphic and ID Card Image of authenticatee is obtained, by the face verification module by foregoing
Method carries out face verification, and carries out lip reading identification checking by lip reading identification authentication module.
During work, from web camera real-time image acquisition;Face is detected in image designated area;Random display identity
Card is put into ID card verification region, points out user to be put into identity card in specified ID card verification region;To the people gathered in real time
Face image and the ID Card Image in the ID card verification region of random display carry out Face datection, face align, feature extraction,
Similarity comparison;Contrast fraction, which reaches, enters lip reading cognitive phase, the instruction that authenticatee sends according to system after predetermined threshold value
The numeral of random display is read, if recognizing successfully, is determined as live body.
Further, the identity authorization system based on In vivo detection and face verification, in addition to industrial computer, can be aobvious
Show the liquid crystal display of image and ID Card Image that the authenticatee gathered in real time is shown on interface;The network shooting mould
Block is connected by the network interface of industrial computer described in network connection, the LCDs by HDMI wire with the industrial computer.It is described
The image and ID Card Image of the real-time authenticatee of network shooting module collection, may be displayed on the liquid crystal display
On display interface, realize and carry out face verification and lip reading identification checking.
The identity authorization system based on In vivo detection and face verification, in addition to keyboard and mouse, respectively with it is described
Industrial computer is connected.
It should be noted that in the present invention, due to system prompt the ID card verification region for being put into identity card and carry
The numeral combination for showing reading is random, and user can not possibly be by way of playing video come by In vivo detection, so this hair
The fraud such as the bright photo that can be better protected from In vivo detection and video clipping mode so that the reliability of In vivo detection
It is higher with security, at the same time, also achieve the recognition of face of pinpoint accuracy.
Compared with prior art, the present invention with the addition of face contrast and In vivo detection technology, targetedly solve existing
There is the problem of identity authorization system is easily attacked by photo and video, using the identity identifying technology, can judge to test exactly
The identity of witness and whether be live body, enhances the reliability and security of identity authorization system.
Described above is only the preferred embodiment of the present invention, it is noted that for the common skill of the art
For art personnel, under the premise without departing from the principles of the invention, some improvements and modifications can also be made, these improvements and modifications
Also it should be regarded as protection scope of the present invention.
Claims (10)
1. a kind of identity authorization system based on In vivo detection and face verification, it is characterised in that including:
Face verification module, face is contrasted on the face and identity card by the authenticatee of acquisition, is judged whether
Match somebody with somebody;
Lip reading recognizes authentication module, for, by rear, pointing out authenticatee to read in the face verification module verification and carrying at random
The numeral combination of confession, judges the outer lip contour of lip of authenticatee in camera watch region acts what is whether combined with reading the numeral
The outer lip contour action matching of lip, regards as live body if matching and authentication passes through.
2. the identity authorization system as claimed in claim 1 based on In vivo detection and face verification, it is characterised in that the face
Authentication module includes:
Face datection unit, for detecting face in the realtime graphic that photographing module is gathered;
Tip element, for after Face datection unit detects face, pointing out authenticatee that identity card is placed on to the body specified
Part demonstrate,proves validation region to obtain the image of identity card;
Identity card, is placed on behind the ID card verification region specified by face verification unit for authenticatee, alignd by face,
The processing sequence that face characteristic is extracted and human face similarity degree is contrasted contrasts face and Face datection list on authenticatee's identity card
The image for the face that member is detected, judges whether matching.
3. the identity authorization system as claimed in claim 1 based on In vivo detection and face verification, it is characterised in that the lip reading
Authentication module is recognized when carrying out lip reading identification, is that the order recognized by the dynamic detection of lip, shape of the mouth as one speaks feature extraction and lip reading is walked
Suddenly checking is identified.
4. the identity authorization system as claimed in claim 2 based on In vivo detection and face verification, it is characterised in that the identity
It is multiple to demonstrate,prove validation region, and the ID card verification region specified is random in the ID card verification area by the Tip element
Specified in domain and on human-computer interaction interface by ejecting square frame and output character is pointed out.
5. the identity authorization system as claimed in claim 1 based on In vivo detection and face verification, it is characterised in that the face
Authentication module carries out second after being proved to be successful first, at least and verified, lip reading identification is entered back into after being proved to be successful for the second time
The checking of authentication module.
6. the identity authorization system as claimed in claim 1 based on In vivo detection and face verification, it is characterised in that the lip reading
Recognize that authentication module checking is at least detected three times, and the prompting authentication success after repeated detection success.
7. the identity authorization system as claimed in claim 1 based on In vivo detection and face verification, it is characterised in that the numeral
It is combined as the numeral combination randomly generated in 1-9.
8. the identity authorization system based on In vivo detection and face verification as described in claim any one of 1-7, it is characterised in that
Also include result indicating module, the result indicating module includes:
Indicated when the first indicator lamp, face for detecting authenticatee in camera watch region;
Second indicator lamp, for being indicated after the match is successful in face verification;
3rd indicator lamp, is pointed out after being proved to be successful for lip reading identification.
9. the identity authorization system as claimed in claim 1 based on In vivo detection and face verification, it is characterised in that also including taking the photograph
As module, realtime graphic and ID Card Image for obtaining authenticatee, the photographing module are web camera.
10. the identity authorization system as claimed in claim 9 based on In vivo detection and face verification, it is characterised in that including work
Control machine, liquid crystal display;The network shooting module is led to by the network interface of industrial computer described in network connection, the LCDs
HDMI wire is crossed to be connected with the industrial computer.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710395760.0A CN107133608A (en) | 2017-05-31 | 2017-05-31 | Identity authorization system based on In vivo detection and face verification |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710395760.0A CN107133608A (en) | 2017-05-31 | 2017-05-31 | Identity authorization system based on In vivo detection and face verification |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107133608A true CN107133608A (en) | 2017-09-05 |
Family
ID=59734159
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710395760.0A Pending CN107133608A (en) | 2017-05-31 | 2017-05-31 | Identity authorization system based on In vivo detection and face verification |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107133608A (en) |
Cited By (29)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108052814A (en) * | 2017-12-07 | 2018-05-18 | 四川大学 | A kind of 3D authentication systems |
CN108319930A (en) * | 2018-03-09 | 2018-07-24 | 百度在线网络技术(北京)有限公司 | Identity identifying method, system, terminal and computer readable storage medium |
CN108428166A (en) * | 2018-02-13 | 2018-08-21 | 东华大学 | The clothes commending system of figure and features feature recognition classification based on convolutional neural networks |
CN108427911A (en) * | 2018-01-30 | 2018-08-21 | 阿里巴巴集团控股有限公司 | A kind of auth method, system, device and equipment |
CN108460266A (en) * | 2018-03-22 | 2018-08-28 | 百度在线网络技术(北京)有限公司 | Method and apparatus for authenticating identity |
CN108470169A (en) * | 2018-05-23 | 2018-08-31 | 国政通科技股份有限公司 | Face identification system and method |
CN108616688A (en) * | 2018-04-12 | 2018-10-02 | Oppo广东移动通信有限公司 | Image processing method, device and mobile terminal, storage medium |
CN108806037A (en) * | 2018-05-17 | 2018-11-13 | 邱宇 | Hotel intelligently moves in the network platform and its implementation |
CN108921071A (en) * | 2018-06-24 | 2018-11-30 | 深圳市中悦科技有限公司 | Human face in-vivo detection method, device, storage medium and processor |
CN108961485A (en) * | 2018-05-07 | 2018-12-07 | 金联汇通信息技术有限公司 | Intelligent door lock, auth method and device |
CN108960103A (en) * | 2018-06-25 | 2018-12-07 | 西安交通大学 | The identity identifying method and system that a kind of face and lip reading blend |
CN109461437A (en) * | 2018-11-28 | 2019-03-12 | 平安科技(深圳)有限公司 | The verifying content generating method and relevant apparatus of lip reading identification |
CN110276230A (en) * | 2018-03-14 | 2019-09-24 | 阿里巴巴集团控股有限公司 | The method, apparatus and electronic equipment that user authentication, lip reading identify |
CN111105539A (en) * | 2018-10-26 | 2020-05-05 | 珠海格力电器股份有限公司 | Access control management method and device |
CN111144277A (en) * | 2019-12-25 | 2020-05-12 | 东南大学 | Face verification method and system with living body detection function |
CN111178157A (en) * | 2019-12-10 | 2020-05-19 | 浙江大学 | Chinese lip language identification method from cascade sequence to sequence model based on tone |
CN111325139A (en) * | 2020-02-18 | 2020-06-23 | 浙江大华技术股份有限公司 | Lip language identification method and device |
CN111383081A (en) * | 2020-03-24 | 2020-07-07 | 东华大学 | Intelligent recommendation method for clothing matching |
CN111886599A (en) * | 2018-05-30 | 2020-11-03 | 居米奥公司 | Machine learning for document authentication |
CN112053160A (en) * | 2020-09-03 | 2020-12-08 | 中国银行股份有限公司 | Intelligent bracelet for lip language recognition, lip language recognition system and method |
CN112200120A (en) * | 2020-10-23 | 2021-01-08 | 支付宝(杭州)信息技术有限公司 | Identity recognition method, living body recognition device and electronic equipment |
CN112395965A (en) * | 2020-11-06 | 2021-02-23 | 山东鲁能软件技术有限公司 | Mobile terminal face recognition system and method based on power intranet |
CN112395580A (en) * | 2020-11-19 | 2021-02-23 | 联通智网科技有限公司 | Authentication method, device, system, storage medium and computer equipment |
CN112437947A (en) * | 2018-07-25 | 2021-03-02 | 日本电气株式会社 | Information processing apparatus, information processing method, and information processing program |
CN113190816A (en) * | 2021-05-08 | 2021-07-30 | 国民认证科技(北京)有限公司 | Man-machine interaction verification method and system using system biological characteristics |
CN113657229A (en) * | 2021-08-06 | 2021-11-16 | 姜政毫 | Face recognition method and system |
CN114297605A (en) * | 2021-12-29 | 2022-04-08 | 江苏方洋智能科技有限公司 | Security authentication method based on security computer |
US11410458B2 (en) | 2018-04-12 | 2022-08-09 | Guangdong Oppo Mobile Telecommunications Corp., Ltd. | Face identification method and apparatus, mobile terminal and storage medium |
CN116152936A (en) * | 2023-02-17 | 2023-05-23 | 深圳市永腾翼科技有限公司 | Face identity authentication system with interactive living body detection and method thereof |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20150113632A1 (en) * | 2013-10-22 | 2015-04-23 | Kabushiki Kaisha Toshiba | Identity authentication system |
CN104636765A (en) * | 2015-01-13 | 2015-05-20 | 王振宇 | Self-service card dispenser for authenticating identity based on third-generation identity card fingerprint and photo information |
CN105335719A (en) * | 2015-10-29 | 2016-02-17 | 北京汉王智远科技有限公司 | Living body detection method and device |
CN105681316A (en) * | 2016-02-02 | 2016-06-15 | 腾讯科技(深圳)有限公司 | Identity verification method and device |
-
2017
- 2017-05-31 CN CN201710395760.0A patent/CN107133608A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20150113632A1 (en) * | 2013-10-22 | 2015-04-23 | Kabushiki Kaisha Toshiba | Identity authentication system |
CN104636765A (en) * | 2015-01-13 | 2015-05-20 | 王振宇 | Self-service card dispenser for authenticating identity based on third-generation identity card fingerprint and photo information |
CN105335719A (en) * | 2015-10-29 | 2016-02-17 | 北京汉王智远科技有限公司 | Living body detection method and device |
CN105681316A (en) * | 2016-02-02 | 2016-06-15 | 腾讯科技(深圳)有限公司 | Identity verification method and device |
Cited By (38)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108052814A (en) * | 2017-12-07 | 2018-05-18 | 四川大学 | A kind of 3D authentication systems |
CN108427911A (en) * | 2018-01-30 | 2018-08-21 | 阿里巴巴集团控股有限公司 | A kind of auth method, system, device and equipment |
US11113514B2 (en) | 2018-01-30 | 2021-09-07 | Advanced New Technologies Co., Ltd. | Identity verification methods, systems, apparatuses, and devices |
CN108427911B (en) * | 2018-01-30 | 2020-06-23 | 阿里巴巴集团控股有限公司 | Identity verification method, system, device and equipment |
CN108428166A (en) * | 2018-02-13 | 2018-08-21 | 东华大学 | The clothes commending system of figure and features feature recognition classification based on convolutional neural networks |
CN108319930A (en) * | 2018-03-09 | 2018-07-24 | 百度在线网络技术(北京)有限公司 | Identity identifying method, system, terminal and computer readable storage medium |
CN108319930B (en) * | 2018-03-09 | 2021-04-06 | 百度在线网络技术(北京)有限公司 | Identity authentication method, system, terminal and computer readable storage medium |
US10740636B2 (en) | 2018-03-09 | 2020-08-11 | Baidu Online Nework Technology (Beijing) Co., Ltd. | Method, system and terminal for identity authentication, and computer readable storage medium |
CN110276230A (en) * | 2018-03-14 | 2019-09-24 | 阿里巴巴集团控股有限公司 | The method, apparatus and electronic equipment that user authentication, lip reading identify |
CN108460266A (en) * | 2018-03-22 | 2018-08-28 | 百度在线网络技术(北京)有限公司 | Method and apparatus for authenticating identity |
US11410458B2 (en) | 2018-04-12 | 2022-08-09 | Guangdong Oppo Mobile Telecommunications Corp., Ltd. | Face identification method and apparatus, mobile terminal and storage medium |
CN108616688A (en) * | 2018-04-12 | 2018-10-02 | Oppo广东移动通信有限公司 | Image processing method, device and mobile terminal, storage medium |
CN108961485A (en) * | 2018-05-07 | 2018-12-07 | 金联汇通信息技术有限公司 | Intelligent door lock, auth method and device |
CN108806037A (en) * | 2018-05-17 | 2018-11-13 | 邱宇 | Hotel intelligently moves in the network platform and its implementation |
CN108470169A (en) * | 2018-05-23 | 2018-08-31 | 国政通科技股份有限公司 | Face identification system and method |
CN111886599A (en) * | 2018-05-30 | 2020-11-03 | 居米奥公司 | Machine learning for document authentication |
CN108921071A (en) * | 2018-06-24 | 2018-11-30 | 深圳市中悦科技有限公司 | Human face in-vivo detection method, device, storage medium and processor |
CN108960103A (en) * | 2018-06-25 | 2018-12-07 | 西安交通大学 | The identity identifying method and system that a kind of face and lip reading blend |
CN108960103B (en) * | 2018-06-25 | 2021-02-19 | 西安交通大学 | Identity authentication method and system with face and lip language integrated |
CN112437947A (en) * | 2018-07-25 | 2021-03-02 | 日本电气株式会社 | Information processing apparatus, information processing method, and information processing program |
CN111105539A (en) * | 2018-10-26 | 2020-05-05 | 珠海格力电器股份有限公司 | Access control management method and device |
CN109461437A (en) * | 2018-11-28 | 2019-03-12 | 平安科技(深圳)有限公司 | The verifying content generating method and relevant apparatus of lip reading identification |
CN109461437B (en) * | 2018-11-28 | 2023-05-09 | 平安科技(深圳)有限公司 | Verification content generation method and related device for lip language identification |
CN111178157A (en) * | 2019-12-10 | 2020-05-19 | 浙江大学 | Chinese lip language identification method from cascade sequence to sequence model based on tone |
CN111144277A (en) * | 2019-12-25 | 2020-05-12 | 东南大学 | Face verification method and system with living body detection function |
CN111144277B (en) * | 2019-12-25 | 2023-09-26 | 东南大学 | Face verification method and system with living body detection function |
CN111325139A (en) * | 2020-02-18 | 2020-06-23 | 浙江大华技术股份有限公司 | Lip language identification method and device |
CN111325139B (en) * | 2020-02-18 | 2023-08-04 | 浙江大华技术股份有限公司 | Lip language identification method and device |
CN111383081A (en) * | 2020-03-24 | 2020-07-07 | 东华大学 | Intelligent recommendation method for clothing matching |
CN112053160B (en) * | 2020-09-03 | 2024-04-23 | 中国银行股份有限公司 | Intelligent bracelet for lip language identification, lip language identification system and method |
CN112053160A (en) * | 2020-09-03 | 2020-12-08 | 中国银行股份有限公司 | Intelligent bracelet for lip language recognition, lip language recognition system and method |
CN112200120A (en) * | 2020-10-23 | 2021-01-08 | 支付宝(杭州)信息技术有限公司 | Identity recognition method, living body recognition device and electronic equipment |
CN112395965A (en) * | 2020-11-06 | 2021-02-23 | 山东鲁能软件技术有限公司 | Mobile terminal face recognition system and method based on power intranet |
CN112395580A (en) * | 2020-11-19 | 2021-02-23 | 联通智网科技有限公司 | Authentication method, device, system, storage medium and computer equipment |
CN113190816A (en) * | 2021-05-08 | 2021-07-30 | 国民认证科技(北京)有限公司 | Man-machine interaction verification method and system using system biological characteristics |
CN113657229A (en) * | 2021-08-06 | 2021-11-16 | 姜政毫 | Face recognition method and system |
CN114297605A (en) * | 2021-12-29 | 2022-04-08 | 江苏方洋智能科技有限公司 | Security authentication method based on security computer |
CN116152936A (en) * | 2023-02-17 | 2023-05-23 | 深圳市永腾翼科技有限公司 | Face identity authentication system with interactive living body detection and method thereof |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107133608A (en) | Identity authorization system based on In vivo detection and face verification | |
CN111709409B (en) | Face living body detection method, device, equipment and medium | |
CN104166841B (en) | The quick detection recognition methods of pedestrian or vehicle is specified in a kind of video surveillance network | |
CN108140123A (en) | Face living body detection method, electronic device and computer program product | |
Geetha et al. | Design of face detection and recognition system to monitor students during online examinations using Machine Learning algorithms | |
CN105335722A (en) | Detection system and detection method based on depth image information | |
Kähm et al. | 2d face liveness detection: An overview | |
CN112215180B (en) | Living body detection method and device | |
CN112052731B (en) | Intelligent portrait identification card punching attendance system and method | |
CN104700094B (en) | A kind of face identification method for intelligent robot and system | |
JP7071991B2 (en) | Methods and equipment for inspecting certificates and bearers | |
EP3642756B1 (en) | Detecting artificial facial images using facial landmarks | |
Lai et al. | Towards gesture-based user authentication | |
CN109376717A (en) | Personal identification method, device, electronic equipment and the storage medium of face comparison | |
Haji et al. | Real time face recognition system (RTFRS) | |
RU2316051C2 (en) | Method and system for automatically checking presence of a living human face in biometric safety systems | |
Boncolmo et al. | Gender Identification Using Keras Model Through Detection of Face | |
Rohini et al. | Attendance monitoring system design based on face segmentation and recognition | |
Firdaus et al. | Masked face recognition using deep learning based on unmasked area | |
US11514715B2 (en) | Deepfake video detection system and method | |
CN108764033A (en) | Auth method and device, electronic equipment, computer program and storage medium | |
Pilania et al. | Implementation of image-based attendance system | |
Singh et al. | Facial Recognition Automation System Using Machine Learning | |
CN110443015A (en) | Electromechanical equipment control method and control equipment | |
Mishra et al. | Integrating State-of-the-Art Face Recognition and Anti-Spoofing Techniques into Enterprise Information Systems |
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 | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20170905 |
|
WD01 | Invention patent application deemed withdrawn after publication |