CN110210312A - A kind of method and system verifying certificate and holder - Google Patents
A kind of method and system verifying certificate and holder Download PDFInfo
- Publication number
- CN110210312A CN110210312A CN201910365958.3A CN201910365958A CN110210312A CN 110210312 A CN110210312 A CN 110210312A CN 201910365958 A CN201910365958 A CN 201910365958A CN 110210312 A CN110210312 A CN 110210312A
- Authority
- CN
- China
- Prior art keywords
- certificate
- image
- video
- holder
- face
- 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
- G06V40/172—Classification, e.g. identification
-
- 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
- G06V40/40—Spoof detection, e.g. liveness detection
- G06V40/45—Detection of the body part being alive
Landscapes
- Engineering & Computer Science (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- General Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Analysis (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The present invention discloses a kind of method and system for verifying certificate and holder, this method comprises: acquisition certificate has the video of regulation sequential projection angle in real time；Extract the characteristics of image of certificate under different projection angles in video；According to the characteristics of image of certificate, the true and false of certificate is verified；Acquisition face video in real time；In vivo detection is carried out to face video, extracts the characteristics of image of face；When verifying certificate is very, when In vivo detection is true man, by the image feature comparison of the characteristics of image of certificate and face；Comparison passes through, it was demonstrated that holder is the affiliated people of certificate, and comparison does not pass through, it was demonstrated that the affiliated people of the non-certificate of holder.This method verifies the certificate true and false by different projection angles, whether the verification of face In vivo detection is accredited true man, true man's facial image feature and certificate facial image aspect ratio to verify, whether I am accredited, certificate is fast and accurately verified with holder, and the checking procedure has the characteristics that real-time, accurate, general, robust and expansible.
Description
Technical field
The present invention relates to field of computer technology, in particular to a kind of method and system for verifying certificate and holder.
Background technique
Anti-counterfeiting technology refers to certain means that can play the role of containment to forgery behavior, it can significantly increase the difficulty of forgery
And cost, or reduce the fidelity forged.The anti-fake anti-counterfeiting technology referred to except product of form generally has very strong adaptability
With longer anti-fake life cycle.Since it is by means of the counterfeit protection measures except product, anti-counterfeiting mark must with product or
It, which is packed, is closely linked and forms inseparable entirety.Such as tamper-evident adhesive label, thermoprint label, directly print or
The technologies such as molding.It is anti-fake to belong to form for overwhelming majority anti-counterfeiting technologies and method at present, such as package anti-counterfeiting, cipher counterfeit-proof, various
Anti-counterfeiting mark or trade mark etc..
Image procossing, which refers to, to be analyzed image, processed and is handled, it is made to meet vision, psychology or other requirements
Technology.Image procossing is an application of the signal processing on image domains.Most of image is in digital form at present
Storage, thus image procossing refers to Digital Image Processing in many cases.In addition, the processing method based on optical theory is still occupied
Consequence.Image procossing is the subclass of signal processing, is in addition also had with fields such as computer science, artificial intelligence close
Relationship.
With the popularity of the internet, need the scene of on-line processing business more and more.On-line processing business needs user
Personal certificate image, such as identity card, passport, driver's license etc. are uploaded, but uploads the mode of certificate image, can not be protected
Card user is the true and false that holder cannot guarantee that certificate, brings certain risk for transacting business.
Summary of the invention
In order to solve the above technical problems, the present invention provides a kind of method and system for verifying certificate and holder,
While effectively verifying certificate is true and false, moreover it is possible to further confirm that whether current be my accredited state.
Technical solution provided in an embodiment of the present invention is as follows:
In a first aspect, providing a kind of method for verifying certificate and holder, the method includes at least following steps:
Acquisition certificate has the video under regulation sequential projection angle in real time；
Extract the characteristics of image of certificate under different projection angles in the video；
According to the characteristics of image of the certificate, the true and false of the certificate is verified；
Acquisition face video in real time；
In vivo detection is carried out to the face video, and extracts the characteristics of image of face in the face video；
It is very, when In vivo detection is true man, by the characteristics of image of the certificate and the face when verifying the certificate
Characteristics of image is compared；
When comparison passes through, it was demonstrated that holder is the affiliated people of certificate, obstructed out-of-date when comparing, it was demonstrated that holder is not certificate
Affiliated people.
In some embodiments, the real-time acquisition certificate has the video of regulation sequential projection angle, specifically:
The video that accredited human hand held certificate completes the movement of regulation sequence is acquired, the regulation sequence movement makes certificate have rule
Sequencing column projection angle.
In some embodiments, the characteristics of image according to the certificate, verify the certificate it is true and false before, also wrap
It includes:
According to the characteristics of image of certificate under different projection angles, verify whether the certificate completes regulation sequential projection angle
Under video acquisition, if so, performing the next step rapid；If it is not, then acquiring the video for being directed to certificate again.
In some embodiments, the characteristics of image for extracting certificate under different projection angles in the video, is at least wrapped
Include following sub-step:
The video is split into several pictures by frame；
Extract the characteristics of image of each picture；
The position of certificate in each picture is obtained, and calculates the projection angle of picture；
Record the characteristics of image of the certificate under different projection angles.
In some embodiments, the characteristics of image for extracting each picture, includes at least following sub-step:
The vision anti-counterfeiting characteristic of certificate in the picture is extracted, the vision anti-counterfeiting characteristic includes static anti-counterfeiting characteristic and moves
State anti-counterfeiting characteristic；
Extract the facial image feature of certificate in the picture.
On the other hand, a kind of system for verifying certificate and holder is provided, the system includes at least:
Video acquisition module: the video that there is regulation sequential projection angle for acquiring certificate in real time, and, for real-time
Acquire face video；
First extraction module: for extracting the characteristics of image of certificate under different projection angles in the video；
First authentication module: for the characteristics of image according to the certificate, the true and false of the certificate is verified；
Second authentication module: for carrying out In vivo detection to the face video；
Second extraction module: for extracting the characteristics of image of face in the face video；
Comparison module: for being true when verifying the certificate, and when In vivo detection is true man, the image of the certificate is special
Sign is compared with the characteristics of image of the face；
Result judgement module: for when comparison passes through, it was demonstrated that holder is the affiliated people of certificate, obstructed out-of-date when comparing,
Prove that holder is not the affiliated people of certificate.
In some embodiments, the video acquisition module is also used to:
The video that accredited human hand held certificate completes the movement of regulation sequence is acquired, the regulation sequence movement makes certificate have rule
Sequencing column projection angle.
In some embodiments, the system also includes:
Third authentication module: for the characteristics of image according to certificate under different projection angles, whether complete the certificate is verified
Video acquisition under established practice sequencing column projection angle, if so, performing the next step rapid；If it is not, then acquisition is directed to certificate again
Video.
In some embodiments, first extraction module includes at least:
Split submodule: for the video to be split into several pictures by frame；
First extracting sub-module: for extracting the characteristics of image of each picture；
First processing submodule: for obtaining the position of certificate in each picture, and the projection angle of picture is calculated.
First record sub module: for recording the characteristics of image of the certificate under different projection angles.
In some embodiments, first extracting sub-module includes at least:
First extraction unit: for extracting the vision anti-counterfeiting characteristic of certificate in the picture, the vision anti-counterfeiting characteristic packet
Include static anti-counterfeiting characteristic and dynamic anti-fake feature；
Second extraction unit: for extracting the facial image feature of certificate in the picture.
The beneficial effect of the present invention compared to existing technologies is:
The present invention provides a kind of method and system for verifying certificate and holder, verifies certificate by different projection angles
Whether the true and false, the verification of face In vivo detection are accredited true man, facial image feature and compare on true man's facial image feature and certificate
To come whether verify be that I am accredited, to fast and accurately be verified for certificate with holder, and checking procedure tool
There is real-time, accurate, general, robust and expansible.
Detailed description of the invention
To describe the technical solutions in the embodiments of the present invention more clearly, make required in being described below to embodiment
Attached drawing is briefly described, it should be apparent that, drawings in the following description are only some embodiments of the invention, for
For those of ordinary skill in the art, without creative efforts, it can also be obtained according to these attached drawings other
Attached drawing.
Fig. 1 is the flow chart of the method for the verification certificate in the embodiment of the present invention one and holder；
Fig. 2 is the flow chart of the method for the verification certificate in the embodiment of the present invention two and holder；
Fig. 3 is the structural schematic diagram of the system of the verification certificate in the embodiment of the present invention three and holder.
Specific embodiment
To make the object, technical solutions and advantages of the present invention clearer, below in conjunction with attached in the embodiment of the present invention
Figure, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is only this
Invention a part of the embodiment, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art exist
Every other embodiment obtained under the premise of creative work is not made, shall fall within the protection scope of the present invention.
Embodiment one
The present embodiment provides a kind of methods for verifying certificate and holder, belong to field of computer technology, are suitable for certificate
Verify scene.
Fig. 1 is the flow chart of the method for a kind of verification certificate that the present embodiment one provides and holder, as shown in Figure 1, should
The method of verification certificate and holder specifically includes:
S1, acquisition certificate has the video of regulation sequential projection angle in real time.
As preferable embodiment, step S1 is specifically as follows:
It acquires accredited human hand held certificate and completes the video of regulation sequence movement, it is specified that sequence movement makes certificate have regulation sequence
Column projection angle；Or,
Acquisition ancillary equipment crawl certificate completes the video of regulation sequence movement, it is specified that sequence movement makes certificate have regulation
Sequential projection angle, wherein ancillary equipment can be manipulator etc..
The purpose of step S1 is the regulation sequential projection angle in order to obtain certificate, can by the accredited operation of holder,
The accredited operation of manipulator of process control, or even the accredited operation of the staff by configuring can be passed through.For ease of description
And manpower, physics cost are reduced, the present embodiment is completed to carry out for the video that regulation sequence acts using holder is accredited
Book.
Before step S1, further includes: transfer several specification certificate motion pictures at random, generating has sequence movement
Video simultaneously carries out front end displaying, and holder is prompted to complete regulation sequence movement according to signal.Holder completes sequence movement
When, certificate can be made successively to be in different location, and there is different projection angles.
Projection angle in the present embodiment refers to angulation between certificate and camera perspective plane, specifically, in certificate
The line and the so-called angle in camera perspective plane of heart point and camera perspective plane central point.One group of certificate sequential projection number of angles is extremely
Less include 5 or more, is preferred with being set as different directions and different angle range, as often as possible to obtain different directions and difference
Certificate image feature under projection angle, to improve verification reliability.Illustratively, prompt holder completes the rule according to signal
Sequencing column movement, to constitute one group of certificate sequential projection angle are as follows: 45 ° of top, 45 ° of left side, 45 ° of lower section, 45 ° of right side, centre
90 °, i.e., accredited 45 ° of the top for making certificate be sequentially located at camera perspective plane central point, 45 ° of left side, 45 ° of lower section, 45 ° of right side and phase
At immediately ahead of the central point of machine perspective plane.Certainly, the certificate that orderly acts or provide that front end prompts for corresponding holder should be locating
Sequential locations.
S2, the characteristics of image for extracting certificate under different projection angles in video, the step specifically include following sub-step:
S21, video is split into several pictures by frame；
S22, the characteristics of image for extracting each picture；
S23, the position for obtaining certificate in each picture, and calculate the projection angle of picture；
S24, the characteristics of image for recording certificate under different projection angles.
Wherein, S22 further comprises following sub-step:
S221, the vision anti-counterfeiting characteristic for extracting certificate in picture, vision anti-counterfeiting characteristic include static anti-counterfeiting characteristic and dynamic
Anti-counterfeiting characteristic；
S222, the facial image feature for extracting certificate in the picture.
The characteristics of image of every picture is extracted using computer vision the relevant technologies, it is preferable that can be used SIFT, SURF,
BRIEF, ORB scheduling algorithm.
The vision anti-counterfeiting characteristic of certificate includes static anti-counterfeiting characteristic and dynamic anti-fake feature in step S221, and static vision is anti-
Pseudo-characteristic includes texture, color, text etc., will not be changed with the variation of certificate and the projection angle on camera perspective plane,
Feature can be verified by computer vision algorithms make.Dynamic anti-fake feature includes color, shape etc., and meeting is with projected angle
The variation of degree and change, common dynamic anti-fake feature laser anti-counterfeiting code in this way, can by the method for computer vision record not
With the variation of angle laser anti-counterfeiting code, behavioral characteristics are verified.
Step S222 specifically includes following sub-step:
S2221, definition and locating human face's characteristic point utilize the face in the direction definition of image gradient and positioning picture
Characteristic point；
The feature vector of human face characteristic point in S2222, extraction step S2221；
The statistical model of S2223, the feature that human face characteristic point is considered using one and relativeness, using statistical inference
Method, mark human face characteristic point, so that it is determined that need human face characteristic point position.
In general, human face characteristic point may include: the features such as eye, nose.
Step S23 further comprises following sub-step:
S231, the position that certificate in each picture is obtained by Feature Correspondence Algorithm, specifically, by searching for calculating
After homograph (homography matrix), by the specific location for radiating transformation calculations certificate.
S232, it is calculated according to step S231 and obtains in each picture angulation between certificate position and camera perspective plane
Calculate the projection angle of certificate.
As a kind of preferable embodiment, the present embodiment further includes following steps:
S3, it verifies whether to complete the video acquisition of certificate under regulation sequential projection angle, the step specifically:
According to the characteristics of image of certificate under different projection angles, verify whether to complete certificate under regulation sequential projection angle
Video acquisition, if so, performing the next step rapid；If it is not, then acquiring the video for being directed to certificate again.
As a kind of preferable embodiment, in the present embodiment, by verify split by frame after picture in image throwing
Whether shadow angle meets certificate due projection angle under regulation sequential projection, to verify whether to complete regulation sequential projection angle
Spend the acquisition of lower certificate, in the present embodiment, i.e., whether verifying holder completes sequence movement.
S4, the characteristics of image according to certificate, verify the true and false of certificate.The step specifically includes following sub-step:
S41, certificate possessed specification projection angle model under each movement in regulation sequence certificate motion picture is transferred
Enclose and the specification projection angle range in static anti-counterfeiting characteristic and dynamic anti-fake feature authority data range；
S42, will extract in corresponding picture certificate static state anti-counterfeiting characteristic and dynamic anti-fake feature respectively with static anti-fake spy
Sign is compared with the authority data range of dynamic anti-fake feature, when anti-counterfeiting characteristic static in picture belongs to static anti-counterfeiting characteristic rule
Model data area, and when dynamic anti-fake feature belongs to dynamic anti-fake characteristic criterion data area in picture, determine certificate be it is true, into
Enter next step；Otherwise certificate is false, terminates and verifies and holder is prompted further to verify certificate.
Because there are verifier height differences and sense organ to judge difference, holder is completed to provide sequence certificate
When movement, has certain difference and exist, therefore need to be arranged possessed specification projection angle range under each movement.
S5, face video is acquired in real time.
In the present embodiment, the face video for acquiring the video and acquisition holder face of certificate is successively acquired, in certificate school
It tests under the premise of, the verification of further progress holder.
S6, In vivo detection is carried out to face video, and extracts the characteristics of image of face in face video.Step S6 is specific
Including following sub-step:
S61, In vivo detection is carried out to face video by frame.
In vivo detection is the method for determining object real physiological feature in some authentication scenes, can be used for brush face branch
It pays, the scenes such as remote authentication.In face recognition application, In vivo detection can be by blinking, opening one's mouth, shake the head, put first-class group
Conjunction movement verifies whether user is true living body operation using technologies such as the positioning of face key point and face trackings.Can have
Effect resists photo, changes face, mask, blocks and the common attack means such as screen reproduction, to assist to screen fraud, protects
Hinder the interests of user.The detection mode of In vivo detection can be three-dimensional In vivo detection, sub- plane monitoring-network or infrared FMP detection,
The mode of preferred three-dimensional In vivo detection in the present embodiment.
S62, facial image feature is extracted to face video by frame.The facial image characterization method that the step uses can refer to
The specific extracting mode of S222.
S7, when verifying certificate is true, and In vivo detection is true man, by the characteristics of image of the characteristics of image of certificate and face
It is compared.
When being compared, the comparison of the feature vector of identical human face characteristic point and the shape of human face characteristic point can be passed through
The comparison of shape and size carries out.It when specific comparison, can be handled by the method for deep learning image procossing, specifically use image phase
Similarity is calculated like degree algorithm to determine.Since there are the objective condition such as light, clarity, therefore when specifically determining similarity,
Need to set certain similarity threshold, when similarity is located in the threshold value, it is believed that comparison passes through.
S8, when comparison passes through, then prove that holder is the affiliated people of certificate, do not pass through when comparing, then prove that holder is not
The affiliated people of certificate.
If comparison passes through, display end prompt, which compares, to be passed through, and is not passed through if comparing, and shows that comparison does not pass through, prompt is held
Witness compares or exits again.
A kind of method verifying certificate and holder provided in this embodiment, by successively carrying out certificate verification and accredited
The mode of people's verification, while effectively verification certificate is true and false, moreover it is possible to verify true man and hold true card and hold assertive evidence in person, also, should
Method of calibration has the characteristics that real-time, accurate, general, robust and expansible.
Embodiment two
The present embodiment provides a kind of method for verifying certificate and holder, as shown in Fig. 2, the verification certificate and holder
Method specifically includes:
S1, the video that accredited human hand held certificate completes the movement of regulation sequence is acquired in real time；
S2, the characteristics of image of certificate and the characteristics of image of holder face under different projection angles are extracted in video；
S3, the characteristics of image according to certificate, verify the true and false of certificate；
S4, In vivo detection is carried out to face video:
S5, when verifying certificate is true, and In vivo detection is true man, by the characteristics of image of the characteristics of image of certificate and face
It is compared；
S6, pass through when comparison, it was demonstrated that holder is the affiliated people of certificate, is not passed through when comparing, then proving holder not is card
The affiliated people of part.
Further comprising the steps of between step S2 and S3 as a kind of preferable embodiment: whether verifying holder
Complete the video acquisition that the regulation sequence for making certificate have regulation sequential projection angle acts.
In addition, the method for one of the present embodiment verification certificate and holder, with the basic phase of method in embodiment 1
Together, something in common please refers to the specific descriptions in embodiment 1, and this embodiment is not repeated.
In the present embodiment, there is the video of certificate and holder by shooting simultaneously, carry out certificate and holder school respectively
It tests, in this way, not only simple flow, improves user satisfaction, also can be further assured that true man hold true card, hold assertive evidence in person, into one
Step improves verification reliability.
Embodiment three
For the method for verifying certificate and holder for executing above-described embodiment one, two, the present embodiment provides a kind of verification cards
The system of part and holder.
Fig. 3 is the structural schematic diagram of the system of a kind of verification certificate that the present embodiment three provides and holder.Such as Fig. 3 institute
Show, the system 100 of the verification certificate and holder includes at least:
Video acquisition module 1: the video that there is regulation sequential projection angle for acquiring certificate in real time, and, for real
When acquire face video；
First extraction module 2: for extracting the characteristics of image of certificate under different projection angles in video；
First authentication module 3: for the characteristics of image according to certificate, the true and false of certificate is verified；
Second authentication module 4: for carrying out In vivo detection to face video；
Second extraction module 5: for extracting the characteristics of image of face in the face video；
Comparison module 6: if being true for verifying the certificate, and In vivo detection is true man, then by the image of the certificate
Feature is compared with the characteristics of image of the face；
Result judgement module 7: if passing through for comparing, proving that holder is the affiliated people of certificate, do not pass through if comparing,
Prove that holder is not the affiliated people of certificate.
Video acquisition module 1 is also used to:
It acquires accredited human hand held certificate and completes the video of regulation sequence movement, it is specified that sequence movement makes certificate have regulation sequence
Column projection angle.
The system further include:
Third authentication module 8: for the characteristics of image according to certificate under different projection angles, verify whether certificate is completed to advise
Video acquisition under sequencing column projection angle, if so, performing the next step rapid；If it is not, then acquiring the video for being directed to certificate again.
First extraction module 2 includes at least:
Split submodule 21: for video to be split into several pictures by frame；
First extracting sub-module 22: for extracting the characteristics of image of each picture；
First processing submodule 23: for obtaining the position of certificate in each picture, and the projection angle of picture is calculated.
First record sub module 24: for recording the characteristics of image of certificate under different projection angles.
First extracting sub-module 22 includes at least:
First extraction unit 221: for extracting the vision anti-counterfeiting characteristic of certificate in picture, vision anti-counterfeiting characteristic includes static state
Anti-counterfeiting characteristic and dynamic anti-fake feature；
Second extraction unit 222: for extracting the facial image feature of certificate in picture.
It is provided in this embodiment it is a kind of verify certificate and holder system, for execute a kind of verification certificate above-mentioned and
The method of holder, the two belong to same design, repeat no more in corresponding implementation the present embodiment.The verification certificate with hold
The system structure of witness is simple, even can also configure application on the general intelligent terminal of computing capability.
Note that the above is only a better embodiment of the present invention and the applied technical principle.It will be appreciated by those skilled in the art that
The invention is not limited to the specific embodiments described herein, be able to carry out for a person skilled in the art it is various it is apparent variation,
It readjusts and substitutes without departing from protection scope of the present invention.Therefore, although being carried out by above embodiments to the present invention
It is described in further detail, but the present invention is not limited to the above embodiments only, without departing from the inventive concept, also
It may include more other equivalent embodiments, and the scope of the invention is determined by the scope of the appended claims.
Claims (10)
1. a kind of method for verifying certificate and holder, which is characterized in that the method includes at least following steps:
Acquisition certificate has the video of regulation sequential projection angle in real time；
Extract the characteristics of image of certificate under different projection angles in the video；
According to the characteristics of image of the certificate, the true and false of the certificate is verified；
Acquisition face video in real time；
In vivo detection is carried out to the face video, and extracts the characteristics of image of face in the face video；
When the verifying certificate is true, and In vivo detection is true man, by the figure of the characteristics of image of the certificate and the face
As feature is compared；
When comparison passes through, it was demonstrated that holder is the affiliated people of certificate, obstructed out-of-date when comparing, it was demonstrated that holder is not belonging to certificate
People.
2. a kind of method for verifying certificate and holder according to claim 1, which is characterized in that the real-time acquisition card
Part has the video of regulation sequential projection angle, specifically:
The video that accredited human hand held certificate completes the movement of regulation sequence is acquired, the regulation sequence movement makes certificate have regulation sequence
Column projection angle.
3. a kind of method for verifying certificate and holder according to claim 1 or 2, which is characterized in that described according to institute
The characteristics of image for stating certificate, verify the certificate it is true and false before, further includes:
According to the characteristics of image of certificate under different projection angles, the video for completing certificate under regulation sequential projection angle is verified whether
Acquisition, if so, performing the next step rapid；If it is not, then acquiring the video for being directed to certificate again.
4. a kind of method for verifying certificate and holder according to claim 1, which is characterized in that described to extract the view
In frequency under different projection angles certificate characteristics of image, include at least following sub-step:
The video is split into several pictures by frame；
Extract the characteristics of image of each picture；
The position of certificate in each picture is obtained, and calculates the projection angle of picture；
Record the characteristics of image of the certificate under different projection angles.
5. a kind of method for verifying certificate and holder according to claim 4, which is characterized in that described to extract each institute
The characteristics of image of picture is stated, following sub-step is included at least:
The vision anti-counterfeiting characteristic of certificate in the picture is extracted, the vision anti-counterfeiting characteristic includes that static anti-counterfeiting characteristic and dynamic are anti-
Pseudo-characteristic；
Extract the facial image feature of certificate in the picture.
6. a kind of system for verifying certificate and holder, which is characterized in that the system includes at least:
Video acquisition module: the video that there is regulation sequential projection angle for acquiring certificate in real time, and, for acquiring in real time
Face video；；
First extraction module: for extracting the characteristics of image of certificate under different projection angles in the video；
First authentication module: for the characteristics of image according to the certificate, the true and false of the certificate is verified；
Second authentication module: for carrying out In vivo detection to the face video；
Second extraction module: for extracting the characteristics of image of face in the face video；
Comparison module: for being true when verifying the certificate, and when In vivo detection is true man, by the characteristics of image of the certificate with
The characteristics of image of the face is compared；
Result judgement module: for when comparison passes through, it was demonstrated that holder is the affiliated people of certificate, obstructed out-of-date when comparing, it was demonstrated that
Holder is not the affiliated people of certificate.
7. a kind of system for verifying certificate and holder according to claim 6, which is characterized in that the video acquisition mould
Block is also used to:
The video that accredited human hand held certificate completes the movement of regulation sequence is acquired, the regulation sequence movement makes certificate have regulation sequence
Column projection angle.
8. a kind of system for verifying certificate and holder according to claim 6 or 7, which is characterized in that the system is also
Include:
Third authentication module: for the characteristics of image according to certificate under different projection angles, verify whether the certificate is completed to advise
Video acquisition under sequencing column projection angle, if so, performing the next step rapid；If it is not, then acquiring the video for being directed to certificate again.
9. a kind of system for verifying certificate and holder according to claim 6, which is characterized in that described first extracts mould
Block includes at least:
Split submodule: for the video to be split into several pictures by frame；
First extracting sub-module: for extracting the characteristics of image of each picture；
First processing submodule: for obtaining the position of certificate in each picture, and the projection angle of picture is calculated.
First record sub module: for recording the characteristics of image of the certificate under different projection angles.
10. a kind of system for verifying certificate and holder according to claim 9, which is characterized in that described first extracts
Submodule includes at least:
First extraction unit: for extracting the vision anti-counterfeiting characteristic of certificate in the picture, the vision anti-counterfeiting characteristic includes quiet
State anti-counterfeiting characteristic and dynamic anti-fake feature；
Second extraction unit: for extracting the facial image feature of certificate in the picture.
Priority Applications (5)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910365958.3A CN110210312A (en) | 2019-04-29 | 2019-04-29 | A kind of method and system verifying certificate and holder |
| CN202011462210.4A CN112507889A (en) | 2019-04-29 | 2019-04-29 | Method and system for verifying certificate and certificate holder |
| JP2019547640A JP7071991B2 (en) | 2019-04-29 | 2019-06-26 | Methods and equipment for inspecting certificates and bearers |
| SG11202011107PA SG11202011107PA (en) | 2019-04-29 | 2019-06-26 | Method and apparatus for verifying certificate and certificate holder |
| PCT/CN2019/092928 WO2020220453A1 (en) | 2019-04-29 | 2019-06-26 | Method and device for verifying certificate and certificate holder |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910365958.3A CN110210312A (en) | 2019-04-29 | 2019-04-29 | A kind of method and system verifying certificate and holder |
Related Child Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011462210.4A Division CN112507889A (en) | 2019-04-29 | 2019-04-29 | Method and system for verifying certificate and certificate holder |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110210312A true CN110210312A (en) | 2019-09-06 |
Family
ID=67785383
Family Applications (2)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910365958.3A Pending CN110210312A (en) | 2019-04-29 | 2019-04-29 | A kind of method and system verifying certificate and holder |
| CN202011462210.4A Pending CN112507889A (en) | 2019-04-29 | 2019-04-29 | Method and system for verifying certificate and certificate holder |
Family Applications After (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011462210.4A Pending CN112507889A (en) | 2019-04-29 | 2019-04-29 | Method and system for verifying certificate and certificate holder |
Country Status (4)
| Country | Link |
|---|---|
| JP (1) | JP7071991B2 (en) |
| CN (2) | CN110210312A (en) |
| SG (1) | SG11202011107PA (en) |
| WO (1) | WO2020220453A1 (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111275105A (en) * | 2020-01-19 | 2020-06-12 | 支付宝实验室(新加坡)有限公司 | Certificate verification method and device and electronic equipment |
| CN111275042A (en) * | 2020-01-21 | 2020-06-12 | 支付宝实验室(新加坡)有限公司 | Counterfeit certificate identification method and device and electronic equipment |
| CN111898520A (en) * | 2020-07-28 | 2020-11-06 | 腾讯科技（深圳）有限公司 | Certificate authenticity identification method and device, computer readable medium and electronic equipment |
| CN112507889A (en) * | 2019-04-29 | 2021-03-16 | 众安信息技术服务有限公司 | Method and system for verifying certificate and certificate holder |
| WO2022089124A1 (en) * | 2020-10-29 | 2022-05-05 | 腾讯科技（深圳）有限公司 | Certificate authenticity identification method and apparatus, computer-readable medium, and electronic device |
| CN117237682A (en) * | 2023-10-17 | 2023-12-15 | 支付宝(杭州)信息技术有限公司 | Certificate verification method and device, storage medium and electronic equipment |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113688698B (en) * | 2021-08-09 | 2022-09-16 | 河南职业技术学院 | Face correction recognition method and system based on artificial intelligence |
| CN114333037B (en) * | 2022-02-25 | 2022-05-13 | 北京结慧科技有限公司 | Identification method and system for copied photo containing identity card |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105122314A (en) * | 2013-04-09 | 2015-12-02 | 联邦印刷有限公司 | Image-capturing system for capturing images of a feature of an identification document |
| CN105933280A (en) * | 2016-03-15 | 2016-09-07 | 天地融科技股份有限公司 | Identity authentication method and system |
| CN105989263A (en) * | 2015-01-30 | 2016-10-05 | 阿里巴巴集团控股有限公司 | Method for authenticating identities, method for opening accounts, devices and systems |
| CN106982426A (en) * | 2017-03-30 | 2017-07-25 | 广东微模式软件股份有限公司 | A kind of method and system for remotely realizing old card system of real name |
| CN107341839A (en) * | 2017-07-07 | 2017-11-10 | 成都东软学院 | A kind of certificate image processing method, device and equipment |
| WO2018225391A1 (en) * | 2017-06-05 | 2018-12-13 | 株式会社日立製作所 | Image information verification device |
Family Cites Families (28)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4972476A (en) * | 1989-05-11 | 1990-11-20 | Nathans Robert L | Counterfeit proof ID card having a scrambled facial image |
| JP4011362B2 (en) | 2002-02-15 | 2007-11-21 | 浩 近藤 | Passport forgery prevention information creation system, passport and forgery passport detection system |
| JP2005122395A (en) * | 2003-10-15 | 2005-05-12 | Toshiba Corp | Medium for certification, device for issuing the same, and face collating device |
| JP2008009617A (en) | 2006-06-28 | 2008-01-17 | Glory Ltd | System, program, and method for individual biological information collation |
| NL2010045C2 (en) * | 2012-12-21 | 2014-06-24 | Morpho B V | Identity document comprising a ghost image based on a two- dimensional image. |
| CN103440482A (en) * | 2013-09-02 | 2013-12-11 | 北方工业大学 | Method, system and device for identifying identity document holder based on hidden video |
| CN104361274B (en) * | 2014-10-30 | 2018-02-16 | 深圳市富途网络科技有限公司 | A kind of identity identifying method and its system based on video identification |
| CN105825243A (en) * | 2015-01-07 | 2016-08-03 | 阿里巴巴集团控股有限公司 | Method and device for certificate image detection |
| CN105844206A (en) * | 2015-01-15 | 2016-08-10 | 北京市商汤科技开发有限公司 | Identity authentication method and identity authentication device |
| CN106302330B (en) * | 2015-05-21 | 2021-01-05 | 腾讯科技（深圳）有限公司 | Identity verification method, device and system |
| CN105243357A (en) * | 2015-09-15 | 2016-01-13 | 深圳市环阳通信息技术有限公司 | Identity document-based face recognition method and face recognition device |
| CN105956578B (en) * | 2016-05-23 | 2019-05-14 | 深圳华中科技大学研究院 | A kind of face verification method of identity-based certificate information |
| CN106778525B (en) * | 2016-11-25 | 2021-08-10 | 北京旷视科技有限公司 | Identity authentication method and device |
| CN106650646A (en) * | 2016-12-09 | 2017-05-10 | 南京合荣欣业金融软件有限公司 | Action recognition based living body face recognition method and system |
| CN108573202A (en) * | 2017-03-17 | 2018-09-25 | 北京旷视科技有限公司 | Identity identifying method, device and system and terminal, server and storage medium |
| CN107066983B (en) * | 2017-04-20 | 2022-08-09 | 腾讯科技（上海）有限公司 | Identity verification method and device |
| CN109117688A (en) * | 2017-06-22 | 2019-01-01 | 腾讯科技（深圳）有限公司 | Identity identifying method, device and mobile terminal |
| CN107844748B (en) * | 2017-10-17 | 2019-02-05 | 平安科技（深圳）有限公司 | Auth method, device, storage medium and computer equipment |
| CN107944339B (en) * | 2017-10-20 | 2020-01-21 | 阿里巴巴集团控股有限公司 | Certificate verification and identity verification method and device |
| CN108052814A (en) * | 2017-12-07 | 2018-05-18 | 四川大学 | A kind of 3D authentication systems |
| CN207867529U (en) * | 2018-02-07 | 2018-09-14 | 广东万峯信息科技有限公司 | The testimony of a witness of multi-cam veritifies machine |
| CN108647576A (en) * | 2018-04-10 | 2018-10-12 | 阳光暖果（北京）科技发展有限公司 | A kind of live body identity identifying method based on video sequence recognition of face |
| JP6481073B1 (en) | 2018-07-31 | 2019-03-13 | 株式会社メルカリ | Program, information processing method, information processing apparatus |
| CN109389153B (en) * | 2018-08-31 | 2021-03-02 | 众安信息技术服务有限公司 | Holographic anti-counterfeiting code checking method and device |
| CN109446900A (en) * | 2018-09-21 | 2019-03-08 | 平安科技（深圳）有限公司 | Certificate authenticity verification method, apparatus, computer equipment and storage medium |
| CN109543551A (en) * | 2018-10-26 | 2019-03-29 | 平安科技（深圳）有限公司 | Identity card identifies processing method, device, computer equipment and storage medium |
| CN109684987B (en) * | 2018-12-19 | 2021-02-23 | 南京华科和鼎信息科技有限公司 | Identity verification system and method based on certificate |
| CN110210312A (en) * | 2019-04-29 | 2019-09-06 | 众安信息技术服务有限公司 | A kind of method and system verifying certificate and holder |
-
2019
- 2019-04-29 CN CN201910365958.3A patent/CN110210312A/en active Pending
- 2019-04-29 CN CN202011462210.4A patent/CN112507889A/en active Pending
- 2019-06-26 JP JP2019547640A patent/JP7071991B2/en active Active
- 2019-06-26 WO PCT/CN2019/092928 patent/WO2020220453A1/en active Application Filing
- 2019-06-26 SG SG11202011107PA patent/SG11202011107PA/en unknown
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105122314A (en) * | 2013-04-09 | 2015-12-02 | 联邦印刷有限公司 | Image-capturing system for capturing images of a feature of an identification document |
| CN105989263A (en) * | 2015-01-30 | 2016-10-05 | 阿里巴巴集团控股有限公司 | Method for authenticating identities, method for opening accounts, devices and systems |
| CN105933280A (en) * | 2016-03-15 | 2016-09-07 | 天地融科技股份有限公司 | Identity authentication method and system |
| CN106982426A (en) * | 2017-03-30 | 2017-07-25 | 广东微模式软件股份有限公司 | A kind of method and system for remotely realizing old card system of real name |
| WO2018225391A1 (en) * | 2017-06-05 | 2018-12-13 | 株式会社日立製作所 | Image information verification device |
| CN107341839A (en) * | 2017-07-07 | 2017-11-10 | 成都东软学院 | A kind of certificate image processing method, device and equipment |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112507889A (en) * | 2019-04-29 | 2021-03-16 | 众安信息技术服务有限公司 | Method and system for verifying certificate and certificate holder |
| CN111275105A (en) * | 2020-01-19 | 2020-06-12 | 支付宝实验室(新加坡)有限公司 | Certificate verification method and device and electronic equipment |
| CN111275105B (en) * | 2020-01-19 | 2023-10-20 | 支付宝实验室(新加坡)有限公司 | Certificate verification method and device and electronic equipment |
| CN111275042A (en) * | 2020-01-21 | 2020-06-12 | 支付宝实验室(新加坡)有限公司 | Counterfeit certificate identification method and device and electronic equipment |
| CN111898520A (en) * | 2020-07-28 | 2020-11-06 | 腾讯科技（深圳）有限公司 | Certificate authenticity identification method and device, computer readable medium and electronic equipment |
| WO2022089124A1 (en) * | 2020-10-29 | 2022-05-05 | 腾讯科技（深圳）有限公司 | Certificate authenticity identification method and apparatus, computer-readable medium, and electronic device |
| EP4109332A4 (en) * | 2020-10-29 | 2023-06-21 | Tencent Technology (Shenzhen) Company Limited | Certificate authenticity identification method and apparatus, computer-readable medium, and electronic device |
| CN117237682A (en) * | 2023-10-17 | 2023-12-15 | 支付宝(杭州)信息技术有限公司 | Certificate verification method and device, storage medium and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| JP2021524946A (en) | 2021-09-16 |
| JP7071991B2 (en) | 2022-05-19 |
| WO2020220453A1 (en) | 2020-11-05 |
| SG11202011107PA (en) | 2020-12-30 |
| CN112507889A (en) | 2021-03-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110210312A (en) | A kind of method and system verifying certificate and holder | |
| Liu et al. | A spatio-temporal appearance representation for viceo-based pedestrian re-identification | |
| CN105518708B (en) | For verifying the method for living body faces, equipment and computer program product | |
| Fu et al. | Multiple feature fusion by subspace learning | |
| Wechsler | Reliable Face Recognition Methods: System Design, Impementation and Evaluation | |
| Kollreider et al. | Non-intrusive liveness detection by face images | |
| WO2019152983A2 (en) | System and apparatus for face anti-spoofing via auxiliary supervision | |
| US20070122009A1 (en) | Face recognition method and apparatus | |
| Guo et al. | Improving face anti-spoofing by 3D virtual synthesis | |
| WO2020079741A1 (en) | Iris authentication device, iris authentication method, and recording medium | |
| WO2020065954A1 (en) | Authentication device, authentication method, and storage medium | |
| Gao et al. | Fast face identification under varying pose from a single 2-D model view | |
| Jamil et al. | Face recognition using neural networks | |
| Chen et al. | Sound to visual: Hierarchical cross-modal talking face video generation | |
| Park et al. | 3D face reconstruction from stereo video | |
| Bruce et al. | Comparisons between human and computer recognition of faces | |
| Tin | Robust Algorithm for face detection in color images | |
| Wei et al. | Avatar-mediated face tracking and lip reading for human computer interaction | |
| Parkin et al. | Creating artificial modalities to solve RGB liveness | |
| Liu et al. | Flexible XY patches for face recognition | |
| Kainz et al. | Students’ Attendance Monitoring through the Face Recognition | |
| Rabiha et al. | Face Authentication in E-Learning using Local Binary Pattern and Haar Cascade | |
| Ahlawat et al. | Online invigilation: A holistic approach | |
| CN109146969A (en) | Pedestrian's localization method, device and processing equipment and its storage medium | |
| Beridze | A PCA approach to the object constancy for faces using view-based models of the face |
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: 20190906 |
|
| WD01 | Invention patent application deemed withdrawn after publication |