CN109377614A - A kind of face gate inhibition recognition methods, system, computer storage medium and equipment - Google Patents
A kind of face gate inhibition recognition methods, system, computer storage medium and equipment Download PDFInfo
- Publication number
- CN109377614A CN109377614A CN201811268725.3A CN201811268725A CN109377614A CN 109377614 A CN109377614 A CN 109377614A CN 201811268725 A CN201811268725 A CN 201811268725A CN 109377614 A CN109377614 A CN 109377614A
- Authority
- CN
- China
- Prior art keywords
- face
- gate inhibition
- score
- picture
- human 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C9/00—Individual registration on entry or exit
- G07C9/30—Individual registration on entry or exit not involving the use of a pass
- G07C9/32—Individual registration on entry or exit not involving the use of a pass in combination with an identity check
- G07C9/37—Individual registration on entry or exit not involving the use of a pass in combination with an identity check using biometric data, e.g. fingerprints, iris scans or voice recognition
-
- 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
- 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
Abstract
The present invention provides a kind of face gate inhibition recognition methods, method includes the following steps: picture is captured, obtains picture to be verified；Recognition of face is carried out to obtain human face similarity degree score value to the picture to be verified；According to the human face similarity degree score value Scorelike, popularity coefficient CsafeWith congestion risk factor CcrowdIt calculates safety and divides Score, wherein Score=Scorelike*Ccrowd*Csafe；Divide Score according to the safetylikeGate inhibition is controlled.The present invention allows user when using face gate inhibition, by risk control strategy, dynamically to adjust guard method.The advantages of by combining face gate inhibition and fingerprint, iris etc. to assist guard method, the safety and convenience of gate inhibition are taken into account.
Description
Technical field
The present invention relates to technical field of face recognition, more particularly to a kind of face gate inhibition recognition methods, system and calculating
Machine storage medium.
Background technique
Gate inhibition is to carry out control to exit and entrance, it is developed on the basis of traditional door lock.Due to safety
Property and privacy be primary demand of the mankind in life and work, thus gate inhibition realizes and does not exist in we live, such as silver
Row, hotel, computer room, safe care registry, cubicle, intellectual communityintellectualized village, factory etc..
Gate inhibition can be divided by disengaging identification method: password identification, card recognition, bio-identification.Since bio-identification is natural
It is present in human body, there is anti-lost convenience, and biological characteristic has uniqueness, thus it is continuous with digital technology
Development, biological identification technology have gradually captured the gate inhibition market of the strong safety certification of needs.Among these, face gate inhibition is contactless
Noninductive verifying, be the gate inhibition recognition methods most friendly to user, with continuing to optimize for face recognition algorithms, face gate inhibition's
Using also increasingly wider.
But existing face gate inhibition has certain limitation: face gate inhibition belongs to the inspection of the 1:N face in recognition of face
The application scenarios of rope algorithm are compared in face database one by one according to certain human face photo, as the quantity of face database increases
Add, the calculation amount of algorithm and the time of consumption all linearly increase, and negative is presented in the accuracy of algorithm and the quantity of face database
Pass relationship.Thus, when face database is bigger, then the result of face gate inhibition is more unreliable.
Summary of the invention
In view of the foregoing deficiencies of prior art, the purpose of the present invention is to provide a kind of face gate inhibition recognition methods,
System and computer storage medium, the result to solve the problems, such as face gate inhibition in the prior art are insecure.
In order to achieve the above objects and other related objects, the present invention provides a kind of face gate inhibition recognition methods, this method packet
Include following steps:
Picture is captured, and picture to be verified is obtained；
Recognition of face is carried out to obtain human face similarity degree score value to the picture to be verified；
According to the human face similarity degree score value Scorelike, popularity coefficient CsafeWith congestion risk factor CcrowdCalculate safety
Divide Score, wherein Score=Scorelike*Ccrowd*Csafe；
Divide Score according to the safetylikeGate inhibition is controlled.
Optionally, this method further include:
Score is divided to judge whether to auxiliary verifying according to the safety；
Gate inhibition is controlled according to the auxiliary verification result.
It optionally, further include the mobile object detected in monitored picture before being captured to the picture, when discovery moves
When animal body, picture candid photograph is carried out.
It is optionally, described that recognition of face is carried out to the picture to be verified, comprising:
Detect all human face regions occurred in picture to be verified；
The maximum human face region to be checked of size is extracted from all human face regions；
For calculating the face quality point of the maximum human face region to be checked of the size；
Human face region to be checked maximum to the size carries out face critical point detection；
The feature vector of face to be checked is obtained according to the face key point；
Using 1:N face retrieval algorithm, the spy most like with the feature vector of the face to be checked is searched in face database
Vector is levied, and obtains corresponding human face similarity degree score value.
In order to achieve the above objects and other related objects, the present invention also provides a kind of face gate identification system, the systems
Include:
Picture captures module and obtains picture to be verified for carrying out picture candid photograph；
Face recognition module, for carrying out recognition of face to the picture to be verified to obtain human face similarity degree score value；
Risk control module, for according to the human face similarity degree score value Scorelike, popularity coefficient CsafeWith congestion risk
Coefficient CcrowdIt calculates safety and divides Score, wherein Score=Scorelike*Ccrowd*Csafe；
Access control module, for dividing Score to control gate inhibition according to the safety.
Optionally, which further includes auxiliary authentication module, for dividing Score to carry out auxiliary verifying according to the safety,
The access control module is used to control gate inhibition according to auxiliary verification result.
Optionally, which further includes mobile detection module, for detecting the mobile object in monitored picture, when discovery moves
When animal body, start the candid photograph module.
Optionally, the face recognition module includes:
First face detection module, for detecting all human face regions occurred in picture to be verified；
Face screening module, for extracting the maximum human face region to be checked of size from all human face regions；
Second face detection module, for calculating the face quality point of the maximum human face region to be checked of the size；
First face critical point detection module, the face for extracting the maximum human face region to be checked of the size are crucial
Point；
Second face critical point detection module, for obtaining the feature vector of face to be checked according to the face key point；
Face retrieval module searches the spy with the face to be checked for utilizing 1:N face retrieval algorithm in face database
The most like feature vector of vector is levied, and obtains corresponding human face similarity degree score value.
In order to achieve the above objects and other related objects, the present invention also provides a kind of computer storage medium, storage is calculated
Machine program executes face gate inhibition's recognition methods when the computer program is run by processor.
In order to achieve the above objects and other related objects, the present invention also provides a kind of equipment, comprising:
Memory, for storing computer program；
Processor, for executing the computer program of the memory storage, so that the equipment executes face gate inhibition and knows
Other method.
As described above, a kind of face gate inhibition recognition methods of the invention and system, have the advantages that
The present invention allows user when using face gate inhibition, by risk control strategy, dynamically to adjust guard method.Pass through
The advantages of assisting guard method in conjunction with face gate inhibition and fingerprint, iris etc., has taken into account the safety and convenience of gate inhibition.
The present invention breaches the pregnable limitation of conventional face gate inhibition and remains while having ensured accuracy
Certain ease for use.
Detailed description of the invention
Fig. 1 is a kind of flow chart of face gate inhibition recognition methods of the present invention；
Fig. 2 is that the present invention carries out flow chart of the recognition of face to obtain human face similarity degree score value to the picture to be verified.
Specific embodiment
Embodiments of the present invention are illustrated by particular specific embodiment below, those skilled in the art can be by this explanation
Content disclosed by book is understood other advantages and efficacy of the present invention easily.
Illustrate embodiments of the present invention below by way of specific specific example, those skilled in the art can be by this specification
Other advantages and efficacy of the present invention can be easily understood for disclosed content.The present invention can also pass through in addition different specific realities
The mode of applying is embodied or practiced, the various details in this specification can also based on different viewpoints and application, without departing from
Various modifications or alterations are carried out under spirit of the invention.It should be noted that in the absence of conflict, following embodiment and implementation
Feature in example can be combined with each other.
It should be noted that illustrating the basic structure that only the invention is illustrated in a schematic way provided in following embodiment
Think, only shown in schema then with related component in the present invention rather than component count, shape and size when according to actual implementation
Draw, when actual implementation kenel, quantity and the ratio of each component can arbitrarily change for one kind, and its assembly layout kenel
It is likely more complexity.
As shown in Figure 1, the application provides a kind of face gate inhibition recognition methods, this method comprises:
S1. picture is captured, and obtains picture to be verified；
It further include mobile detection before being captured to the picture, effect is detecting monitored picture in an embodiment
In mobile object, when finding mobile object, carry out picture candid photograph.
Specifically, mobile detection refers in the camera coverage using certain mobile detection algorithm automatic monitoring door forbidden zone domain
With the presence or absence of moving object, starts picture if being moved and capture process.
It is the detecting state for being in low-power consumption that this mode, which can allow the video camera most of the time, without most of with processing
There is no personnel to enter the picture in the visual field.
Mobile detection algorithm includes but is not limited to Background difference, frame difference method.Background difference implementation therein are as follows: regarding
Stationary background is chosen as Background in Yezhong, then detects the pixel difference of each frame picture and Background, if a certain frame
The pixel difference of picture has been more than that the threshold value of setting then indicates to enter the object for being not belonging to background in the visual field of present frame, that is, is occurred
Movement.
S2. recognition of face is carried out to obtain human face similarity degree score value, as shown in Fig. 2, to described to the picture to be verified
Picture to be verified carries out recognition of face and is specifically included with obtaining human face similarity degree score value:
S21. all human face regions occurred in picture to be verified are detected；
In this present embodiment, all human face regions occurred in picture to be verified are detected by Face datection algorithm, it is described
Face datection algorithm includes but is not limited to deep neural network, template matching algorithm.
S22. the maximum human face region to be checked of size is extracted from all human face regions
When due to carrying out recognition of face at gate inhibition, it is possible to detect multiple faces, and size maximum face institute's generation
Table be foremost the face for being ready for the people by gate inhibition.Therefore, maximum sized face is extracted.
S23. the face quality point of the maximum human face region to be checked of the size is calculated；
Judged judge whether face quality is qualified by face quality point and threshold value.Face quality point is in [0,1]
Valued space in, value is bigger, and the face quality that represents is better, and general threshold value is 0.8 with worthwhile excellent.
S24. human face region to be checked maximum to the size carries out face critical point detection.
In this present embodiment, since face direction may there are tilt angles with video camera installation direction, thus root is needed
This tilt angle is calculated according to certain face normalization algorithm and is corrected, and could guarantee the accurate of recognition of face in this way
Property.
Face normalization algorithm one of which implementation is as follows:
Using face critical point detection algorithm, the face key point of outlet, nose, mouth is detected.The practical seat put according to these
Mark relationship calculates the pitch angle (pitch), roll angle (roll), yaw angle (yaw) of the face of current shooting.Wherein face
Pitch angle, roll angle, yaw angle be relative to camera coordinates system and define.
Face normalization algorithm includes but is not limited to the algorithm of foregoing description, further includes the side such as correcting using face key point
The algorithm that formula is realized.
S25. the feature vector of face to be checked is obtained according to the corrected face key point；
S26. 1:N face retrieval algorithm is utilized, the feature vector most phase with the face to be detected is searched in face database
As feature vector, and obtain corresponding human face similarity degree score value.
The face database includes personnel ID, human face photo library and their corresponding face feature vectors.
Human face similarity degree value is in the valued space of [0,1], and value is bigger, and the face that represents is more similar, and general threshold value is 0.8
With worthwhile excellent.Face recognition algorithms include but is not limited to deep neural network algorithm, template matching algorithm.
S3. according to the human face similarity degree score value Scorelike, popularity coefficient CsafeWith congestion risk factor CcrowdIt calculates
Safety divides Score, wherein Score=Scorelike*Ccrowd*Csafe。
In this present embodiment, before controlling gate inhibition, need to analyze congestion risk and vacant room risk.Analyze congestion wind
Danger calculates congestion risk factor Ccrowd, analysis congestion risk is to take precautions against by gathering around at gate inhibition caused by gate inhibition's overlong time
It is stifled；It analyzes vacant room risk and calculates popularity coefficient Csafe, analysis vacant room risk is because connecing when gate inhibition enters personnel's less time
It is unattended indoor many regions have been reacted.
Comprehensive congestion risk factor Ccrowd, popularity coefficient CsafeAnd current face's similarity score, for current gate inhibition
Identification calculates safety point.
Wherein, a kind of implementation of congestion risk factor is calculated are as follows:
Because being all by week on life, working law are general is the period, thus enabling current time is t, then it is assumed that the moment
Gate inhibition's degree of crowding t' is similar in the same time with the phase before 7 days, can be predicted with the data before 7 days.
If T is face gate inhibition by the time used, then T can approximation be considered as fixed value, calculation are as follows:
T=Tcap+Tpre+Trec+Tgate
Wherein, TcapFor the time that a picture is captured, TpreFor face pretreated time, TrecFor recognition of face when
Between, TgateFor gate inhibition's primary unlatching+closing time.
If congestion threshold value is Tth, then it is less than T+T when the time difference that continuous two people start to carry out gate inhibition's identificationthWhen, then recognize
For a congestion event has occurred.
Congestion event number in [t'-5T, t'+5T] time window is counted, N is denoted ascrowd, then calculated according to following equation
Congestion risk factor Ccrowd:
Wherein, a kind of implementation of popularity coefficient is calculated are as follows:
The net inflow number for counting current t moment gate inhibition, is denoted as Npeop。NpeopIs defined as:
NpeopThe outgoing number of the entrance number-of=same day gate inhibition
The net inflow number of t' moment gate inhibition, is denoted as N' before statistics 7 dayspeop。
The popularity coefficient C at current time can be then calculated by following equationsafe:
Wherein, a kind of implementation divided safely is calculated are as follows:
The safety for finally obtaining this gate inhibition's behavior divides Score are as follows:
Score=Scorelike*Ccrowd*Csafe
The calculation divided safely includes but is not limited to above-mentioned implementation, can be realized according to actual needs, such as also
Including the use of other statistical values of history gate inhibition's data, in the way of fixed policy that experience is formed etc..
S4. Score is divided to control gate inhibition according to the safety.
Specifically, when obtained safety divides Score to be greater than preset safety point threshold value, then it is assumed that face gate inhibition passes through, no
Then need to carry out auxiliary verifying, auxiliary verification method includes but is not limited to password authentification, fingerprint recognition, Application on Voiceprint Recognition, iris knowledge
Not.
A kind of face gate inhibition recognition methods described herein passes through recognition of face first and identifies as first of gate inhibition,
Again by risk control strategy, carry out automatic dynamic adjustment guard method.
The present invention breaches the pregnable limitation of conventional face gate inhibition, in combination with other fingerprint, password, vocal print,
The verification modes such as iris are identified as second gate inhibition, improve the safety of system；On the other hand, the present invention has also taken into account and has made
The calling frequency of verifying can be assisted with adjust automatically by risk control strategy with convenience, such as in an implementation of the invention
In example, illustrates and a kind of combine indoor occupant quantity, gate inhibition's congestion level dynamically to adjust the mode of control strategy.
The present invention also provides a kind of face gate identification system, the system include picture captures module, face knows another module,
Risk control module and access control module；
The picture captures module and obtains picture to be verified for carrying out picture candid photograph；
The face recognition module, for carrying out recognition of face to the picture to be verified to obtain human face similarity degree point
Value；
In this present embodiment, the face recognition module includes the first face detection module, face screening module, the second people
Face detection module, the first face critical point detection module, the second face critical point detection module and face retrieval module.
First face detection module, for detecting all human face regions occurred in picture to be verified.
Specifically, the first face detection module detects all faces occurred in picture to be verified by Face datection algorithm
Region, the Face datection algorithm include but is not limited to deep neural network, template matching algorithm.
The face screening module, for extracting the maximum human face region to be checked of size from all human face regions.
When due to carrying out recognition of face at gate inhibition, it is possible to detect multiple faces, and size maximum face institute's generation
Table be foremost the face for being ready for the people by gate inhibition.Therefore, maximum sized face is extracted.
Second face detection module, for calculating the face quality point of the maximum human face region to be checked of the size.
Specifically, the second face detection module is judged by face quality point and threshold value, judges that face quality is
No qualification.Face quality is point in the valued space of [0,1], and value is bigger, and the face quality that represents is better, general threshold value 0.8 with
It is worthwhile excellent.
The first face critical point detection module, the face for extracting the maximum human face region to be checked of the size close
Key point.
In this present embodiment, due to face direction may with video camera installation direction there are tilt angle, thus, the present invention
One facial pretreatment module is set, and the face key point for extracting to the first face critical point detection module is corrected.People
Face correcting algorithm calculates this tilt angle and is corrected, and could guarantee the accuracy of recognition of face in this way.
Face normalization algorithm one of which implementation is as follows:
Using face critical point detection algorithm, the face key point of outlet, nose, mouth is detected.The practical seat put according to these
Mark relationship calculates the pitch angle (pitch), roll angle (roll), yaw angle (yaw) of the face of current shooting.Wherein face
Pitch angle, roll angle, yaw angle be relative to camera coordinates system and define.
Face normalization algorithm includes but is not limited to the algorithm of foregoing description, further includes the side such as correcting using face key point
The algorithm that formula is realized.
The second face critical point detection module, for obtained according to the face key point feature of face to be checked to
Amount.
The face retrieval module is searched and the face to be checked in face database for utilizing 1:N face retrieval algorithm
The most like feature vector of feature vector, and obtain corresponding human face similarity degree score value.
The face database includes personnel ID, human face photo library and their corresponding face feature vectors.
Human face similarity degree value is in the valued space of [0,1], and value is bigger, and the face that represents is more similar, and general threshold value is 0.8
With worthwhile excellent.Face recognition algorithms include but is not limited to deep neural network algorithm, template matching algorithm.
The risk control module, for according to the human face similarity degree score value Scorelike, popularity coefficient CsafeAnd congestion
Risk factor CcrowdIt calculates safety and divides Score, wherein Score=Scorelike*Ccrowd*Csafe。
In this present embodiment, before controlling gate inhibition, need to analyze congestion risk and vacant room risk.Analyze congestion wind
Danger calculates congestion risk factor Ccrowd, analysis congestion risk is to take precautions against by gathering around at gate inhibition caused by gate inhibition's overlong time
It is stifled；It analyzes vacant room risk and calculates popularity coefficient Csafe, analysis vacant room risk is because connecing when gate inhibition enters personnel's less time
It is unattended indoor many regions have been reacted.
Comprehensive congestion risk factor Ccrowd, popularity coefficient CsafeAnd current face's similarity score, for current gate inhibition
Identification calculates safety point.
Wherein, a kind of implementation of congestion risk factor is calculated are as follows:
Because being all by week on life, working law are general is the period, thus enabling current time is t, then it is assumed that the moment
Gate inhibition's degree of crowding t' is similar in the same time with the phase before 7 days, can be predicted with the data before 7 days.
If T is face gate inhibition by the time used, then T can approximation be considered as fixed value, calculation are as follows:
T=Tcap+Tpre+Trec+Tgate
Wherein, TcapFor the time that a picture is captured, TpreFor face pretreated time, TrecFor recognition of face when
Between, TgateFor gate inhibition's primary unlatching+closing time.
If congestion threshold value is Tth, then it is less than T+T when the time difference that continuous two people start to carry out gate inhibition's identificationthWhen, then recognize
For a congestion event has occurred.
Congestion event number in [t'-5T, t'+5T] time window is counted, N is denoted ascrowd, then calculated according to following equation
Congestion risk factor Ccrowd:
Wherein, a kind of implementation of popularity coefficient is calculated are as follows:
The net inflow number for counting current t moment gate inhibition, is denoted as Npeop。NpeopIs defined as:
NpeopThe outgoing number of the entrance number-of=same day gate inhibition
The net inflow number of t' moment gate inhibition, is denoted as N' before statistics 7 dayspeop。
The popularity coefficient C at current time can be then calculated by following equationsafe:
Wherein, a kind of implementation divided safely is calculated are as follows:
The safety for finally obtaining this gate inhibition's behavior divides Score are as follows:
Score=Scorelike*Ccrowd*Csafe
The calculation divided safely includes but is not limited to above-mentioned implementation, can be realized according to actual needs, such as also
Including the use of other statistical values of history gate inhibition's data, in the way of fixed policy that experience is formed etc..
The access control module, for dividing Score to control gate inhibition according to the safety.
Specifically, when obtained safety divides Score to be greater than preset safety point threshold value, then it is assumed that face gate inhibition passes through, no
Then need to start auxiliary authentication module and carry out auxiliary verifying, auxiliary verification method include but is not limited to password authentification, fingerprint recognition,
Application on Voiceprint Recognition, iris recognition.
In an embodiment, the auxiliary verifying subsystem further includes mobile detection module, for detecting in monitored picture
Mobile object start the candid photograph module when finding mobile object.
Mobile detection refers to whether deposit in the camera coverage using certain mobile detection algorithm automatic monitoring door forbidden zone domain
In moving object, starts picture if being moved and capture process.
It is the detecting state for being in low-power consumption that this mode, which can allow the video camera most of the time, without most of with processing
There is no personnel to enter the picture in the visual field.
Mobile detection algorithm includes but is not limited to Background difference, frame difference method.Background difference implementation therein are as follows: regarding
Stationary background is chosen as Background in Yezhong, then detects the pixel difference of each frame picture and Background, if a certain frame
The pixel difference of picture has been more than that the threshold value of setting then indicates to enter the object for being not belonging to background in the visual field of present frame, that is, is occurred
Movement.
A kind of face gate inhibition recognition methods described herein and system, first by recognition of face as the first sect
Prohibit identification, then by risk control strategy, carrys out automatic dynamic adjustment guard method.
The present invention breaches the pregnable limitation of conventional face gate inhibition, in combination with other fingerprint, password, vocal print,
The verification modes such as iris are identified as second gate inhibition, improve the safety of system；On the other hand, the present invention has also taken into account and has made
The calling frequency of verifying can be assisted with adjust automatically by risk control strategy with convenience, such as in an implementation of the invention
In example, illustrates and a kind of combine indoor occupant quantity, gate inhibition's congestion level dynamically to adjust the mode of control strategy.
The present invention also provides a kind of computer storage mediums, store computer program, the computer program is by processor
Face gate inhibition's recognition methods is executed when operation.
The present invention also provides a kind of computer storage mediums, store computer program, the computer program is by processor
Face gate inhibition's recognition methods is executed when operation.
In order to achieve the above objects and other related objects, the present invention also provides a kind of equipment, comprising:
Memory, for storing computer program；
Processor, for executing the computer program of the memory storage, so that the equipment executes face gate inhibition and knows
Other method.
The above-described embodiments merely illustrate the principles and effects of the present invention, and is not intended to limit the present invention.It is any ripe
The personage for knowing this technology all without departing from the spirit and scope of the present invention, carries out modifications and changes to above-described embodiment.Cause
This, institute is complete without departing from the spirit and technical ideas disclosed in the present invention by those of ordinary skill in the art such as
At all equivalent modifications or change, should be covered by the claims of the present invention.
Claims (10)
1. a kind of face gate inhibition recognition methods, which is characterized in that method includes the following steps:
Picture is captured, and picture to be verified is obtained；
Recognition of face is carried out to obtain human face similarity degree score value to the picture to be verified；
According to the human face similarity degree score value Scorelike, popularity coefficient CsafeWith congestion risk factor CcrowdCalculate safety point
Score, wherein Score=Scorelike*Ccrowd*Csafe；
Divide Score according to the safetylikeGate inhibition is controlled.
2. a kind of face gate inhibition recognition methods according to claim 1, which is characterized in that this method further include:
Score is divided to judge whether to auxiliary verifying according to the safety；
Gate inhibition is controlled according to the auxiliary verification result.
3. a kind of face gate inhibition recognition methods according to claim 1, which is characterized in that captured to the picture
Before, further include the mobile object detected in monitored picture, when finding mobile object, carries out picture candid photograph.
4. a kind of face gate inhibition recognition methods according to claim 1, which is characterized in that described to the picture to be verified
Carry out recognition of face, comprising:
Detect all human face regions occurred in picture to be verified；
The maximum human face region to be checked of size is extracted from all human face regions；
Calculate the face quality point of the maximum human face region to be checked of the size；
Human face region to be checked maximum to the size carries out face critical point detection；
The feature vector of face to be checked is obtained according to the face key point；
Using 1:N face retrieval algorithm, searched in face database the feature most like with the feature vector of the face to be checked to
Amount, and obtain corresponding human face similarity degree score value.
5. a kind of face gate identification system, which is characterized in that the system includes:
Picture captures module and obtains picture to be verified for carrying out picture candid photograph；
Face recognition module, for carrying out recognition of face to the picture to be verified to obtain human face similarity degree score value；
Risk control module, for according to the human face similarity degree score value Scorelike, popularity coefficient CsafeWith congestion risk factor
CcrowdIt calculates safety and divides Score, wherein Score=Scorelike*Ccrowd*Csafe；
Access control module, for dividing Score to control gate inhibition according to the safety.
6. a kind of face gate identification system according to claim 5, which is characterized in that the system further includes auxiliary verifying
Module, for dividing Score to carry out auxiliary verifying according to the safety, the access control module is used for according to auxiliary verification result
Gate inhibition is controlled.
7. a kind of face gate identification system according to claim 5, which is characterized in that the system further includes mobile detection
Module, when finding mobile object, starts the candid photograph module for detecting the mobile object in monitored picture.
8. a kind of face gate identification system according to claim 5, which is characterized in that the face recognition module packet
It includes:
First face detection module, for detecting all human face regions occurred in picture to be verified；
Face screening module, for extracting the maximum human face region to be checked of size from all human face regions；
Second face detection module, for calculating the face quality point of the maximum human face region to be checked of the size；
First face critical point detection module, for extracting the face key point of the maximum human face region to be checked of the size；
Second face critical point detection module, for obtaining the feature vector of face to be checked according to the face key point；
Face retrieval module, for utilizing 1:N face retrieval algorithm, searched in face database with the feature of the face to be checked to
Most like feature vector is measured, and obtains corresponding human face similarity degree score value.
9. a kind of computer storage medium stores computer program, which is characterized in that the computer program is run by processor
Face gate inhibition recognition methods of the Shi Zhihang as described in Claims 1 to 4 any one.
10. a kind of equipment, which is characterized in that including
Memory, for storing computer program；
Processor, for executing the computer program of the memory storage, so that the equipment executes such as Claims 1 to 4
Face gate inhibition recognition methods described in any one.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811268725.3A CN109377614B (en) | 2018-10-29 | 2018-10-29 | Face access control recognition method, system, computer storage medium and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811268725.3A CN109377614B (en) | 2018-10-29 | 2018-10-29 | Face access control recognition method, system, computer storage medium and equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109377614A true CN109377614A (en) | 2019-02-22 |
| CN109377614B CN109377614B (en) | 2020-02-07 |
Family
ID=65390242
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811268725.3A Active CN109377614B (en) | 2018-10-29 | 2018-10-29 | Face access control recognition method, system, computer storage medium and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109377614B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113034764A (en) * | 2019-12-24 | 2021-06-25 | 深圳云天励飞技术有限公司 | Access control method, device, equipment and access control system |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2006082339A1 (en) * | 2005-02-02 | 2006-08-10 | France Telecom | Method and system for identification by contextual code |
| CN1941080A (en) * | 2005-09-26 | 2007-04-04 | 吴田平 | Soundwave discriminating unlocking module and unlocking method for interactive device at gate of building |
| EP2192560B1 (en) * | 2008-11-25 | 2014-02-12 | Rockwell Automation Limited | Access control |
| CN204926247U (en) * | 2015-09-09 | 2015-12-30 | 国网安徽省电力公司滁州供电公司 | Multistage intelligent entrance guard system that do not to select unblock more based on fingerprint identification |
| CN105513179A (en) * | 2015-12-07 | 2016-04-20 | 小米科技有限责任公司 | Unlocking method and device, as well as intelligent lock |
| CA2908762A1 (en) * | 2015-10-16 | 2017-04-16 | Imperial Parking Canada Corporation | Method and system for managing parking by dual location verification |
| CN108109233A (en) * | 2017-12-14 | 2018-06-01 | 华南理工大学 | Multilevel security protection system based on biological information of human body |
| CN108364374A (en) * | 2017-12-28 | 2018-08-03 | 武汉烽火众智数字技术有限责任公司 | Face access control device based on deep learning and method |
-
2018
- 2018-10-29 CN CN201811268725.3A patent/CN109377614B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2006082339A1 (en) * | 2005-02-02 | 2006-08-10 | France Telecom | Method and system for identification by contextual code |
| CN1941080A (en) * | 2005-09-26 | 2007-04-04 | 吴田平 | Soundwave discriminating unlocking module and unlocking method for interactive device at gate of building |
| EP2192560B1 (en) * | 2008-11-25 | 2014-02-12 | Rockwell Automation Limited | Access control |
| CN204926247U (en) * | 2015-09-09 | 2015-12-30 | 国网安徽省电力公司滁州供电公司 | Multistage intelligent entrance guard system that do not to select unblock more based on fingerprint identification |
| CA2908762A1 (en) * | 2015-10-16 | 2017-04-16 | Imperial Parking Canada Corporation | Method and system for managing parking by dual location verification |
| CN105513179A (en) * | 2015-12-07 | 2016-04-20 | 小米科技有限责任公司 | Unlocking method and device, as well as intelligent lock |
| CN108109233A (en) * | 2017-12-14 | 2018-06-01 | 华南理工大学 | Multilevel security protection system based on biological information of human body |
| CN108364374A (en) * | 2017-12-28 | 2018-08-03 | 武汉烽火众智数字技术有限责任公司 | Face access control device based on deep learning and method |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113034764A (en) * | 2019-12-24 | 2021-06-25 | 深圳云天励飞技术有限公司 | Access control method, device, equipment and access control system |
| CN113034764B (en) * | 2019-12-24 | 2023-03-03 | 深圳云天励飞技术有限公司 | Access control method, device, equipment and access control system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109377614B (en) | 2020-02-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109446981B (en) | Face living body detection and identity authentication method and device | |
| US20210089754A1 (en) | Face verification method and apparatus | |
| WO2019091012A1 (en) | Security check method based on facial recognition, application server, and computer readable storage medium | |
| US8515124B2 (en) | Method and apparatus for determining fake image | |
| WO2017202169A1 (en) | Access control data processing method, access control method, and electronic apparatus | |
| US20170032182A1 (en) | System for adaptive real-time facial recognition using fixed video and still cameras | |
| Chen et al. | Your face your heart: Secure mobile face authentication with photoplethysmograms | |
| CN206515931U (en) | A kind of face identification system | |
| CN101114909B (en) | Full-automatic video identification authentication system and method | |
| CN105427421A (en) | Entrance guard control method based on face recognition | |
| CN110189447B (en) | Intelligent community gate control system based on face identity recognition | |
| TW201627917A (en) | Method and device for face in-vivo detection | |
| CN112364827B (en) | Face recognition method, device, computer equipment and storage medium | |
| WO2018192448A1 (en) | People-credentials comparison authentication method, system and camera | |
| WO2020248780A1 (en) | Living body testing method and apparatus, electronic device and readable storage medium | |
| CN101751562B (en) | Bank transaction image forensic acquiring method based on face recognition | |
| CN106951846A (en) | A kind of face 3D models typing and recognition methods and device | |
| CN103473564A (en) | Front human face detection method based on sensitive area | |
| CN112562150A (en) | Student apartment management method, device, system and medium based on face recognition | |
| CN110705454A (en) | Face recognition method with living body detection function | |
| CN205644823U (en) | Social security self -service terminal device | |
| CN109377614A (en) | A kind of face gate inhibition recognition methods, system, computer storage medium and equipment | |
| CN114333011A (en) | Network training method, face recognition method, electronic device and storage medium | |
| CN109003367A (en) | Control method and device, storage medium, the terminal of gate inhibition | |
| CN204537273U (en) | A kind of photographing device of swiping the card for gate control system |
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 | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: 401122 5 stories, Block 106, West Jinkai Avenue, Yubei District, Chongqing Applicant after: Chongqing Zhongke Yuncong Technology Co., Ltd. Address before: 401122 5 stories, Block 106, West Jinkai Avenue, Yubei District, Chongqing Applicant before: CHONGQING ZHONGKE YUNCONG TECHNOLOGY CO., LTD. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |