CN110544333A - Access control system and control method thereof - Google Patents
Access control system and control method thereof Download PDFInfo
- Publication number
- CN110544333A CN110544333A CN201910745391.2A CN201910745391A CN110544333A CN 110544333 A CN110544333 A CN 110544333A CN 201910745391 A CN201910745391 A CN 201910745391A CN 110544333 A CN110544333 A CN 110544333A
- Authority
- CN
- China
- Prior art keywords
- face
- module
- living body
- access control
- radio frequency
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L63/00—Network architectures or network communication protocols for network security
- H04L63/08—Network architectures or network communication protocols for network security for authentication of entities
- H04L63/0853—Network architectures or network communication protocols for network security for authentication of entities using an additional device, e.g. smartcard, SIM or a different communication terminal
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L63/00—Network architectures or network communication protocols for network security
- H04L63/08—Network architectures or network communication protocols for network security for authentication of entities
- H04L63/0861—Network architectures or network communication protocols for network security for authentication of entities using biometrical features, e.g. fingerprint, retina-scan
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L63/00—Network architectures or network communication protocols for network security
- H04L63/08—Network architectures or network communication protocols for network security for authentication of entities
- H04L63/0876—Network architectures or network communication protocols for network security for authentication of entities based on the identity of the terminal or configuration, e.g. MAC address, hardware or software configuration or device fingerprint
Abstract
the invention relates to the technical field of entrance guard security, in particular to an entrance guard control system and a control method thereof, which combine a radio frequency technology, a face recognition technology, a WIFI probe technology and a living body detection technology, realize the comparison of face recognition modules 1:1 and effectively solve the problems of unsafe single recognition and low recognition efficiency in the prior art.
Description
Technical Field
The invention relates to the technical field of entrance guard security, in particular to an entrance guard control system and a control method thereof.
background
the safety is a core index of an access system and an access control system, and the core index has clear requirements in national standards and industrial specifications. Currently, most access control systems are based on radio frequency technology, and pass through access control systems by carrying cards, but this method has the following disadvantages: firstly, the card must be carried with the person at any time, which causes inconvenience to the person who can not carry the card due to some reasons (such as loss and movement); secondly, the identity authentication method which does not recognize the card and does not recognize the person cannot effectively inhibit illegal behaviors of counterfeiting the card and entering the card by borrowing the card, and certain potential safety hazards exist.
In the prior art, a chinese patent document with publication number CN107657706A and publication date of 2018, 02/02 is proposed, and the technical scheme disclosed in the patent document is as follows: an entrance guard system and a combined recognition method based on RFID and face recognition comprise a face recognition module, a radio frequency recognition module, an AND gate arithmetic unit and an unlocking module; the output end of the face recognition module and the output end of the radio frequency recognition module are respectively connected with the output end of an AND gate arithmetic unit, and the output end of the AND gate arithmetic unit is connected with the input end of an unlocking module; the joint recognition method comprises a face recognition matching step; a radio frequency identification step and a matching unlocking step. According to the invention, the face image of the user and the identity information stored in the electronic tag carried by the user are simultaneously identified through the face identification module and the radio frequency identification module, and only when the two contents are simultaneously identified and successfully matched, the unlocking module can be controlled to be started, so that the access channel is opened.
In the prior art, a chinese patent document with publication number CN108320359A and publication date of 2018, 07 and 24 is proposed, and the technical scheme disclosed by the patent document is as follows: a city Internet of things intelligent access control and security system comprises a cloud server, a proxy server, a motor vehicle access control system, a non-motor vehicle and personnel access control system, a unit access control system and a building anti-climbing system, wherein the motor vehicle access control system, the non-motor vehicle and personnel access control system, the unit access control system and the building anti-climbing system are all connected with the cloud server, the system also comprises a three-dimensional live-action map and a GIS geographic information system, the unit access control system comprises an IC card access control system, a video telephone access control system, a face recognition access control system, a mobile phone MAC address access control system and a palm vein access control system, the access control and security system displays cells in the city Internet of things in the three-dimensional live-action map, then carries out authority management on personnel, motor vehicles and non-motor vehicles in each cell, realizes the entrance monitoring of the cell and the entrance of the cell, therefore, the intelligent management of the cell is improved, and the public security system is convenient to supervise.
In the actual use process, the following problems can occur in the technical scheme: the personnel identity is determined by utilizing the RFID and the face recognition technology, the single recognition is unsafe, the effect of the system is not ideal, in the face recognition process, the recognition speed is low and the timeliness is poor when M, N is large in the M: N mode, most face recognition systems are not matched with corresponding living body detection technologies, only one color print picture or 3D face mask is needed, the system can be confused, and the cracking cost is even lower than that of a radio frequency card system.
disclosure of Invention
in order to solve the technical problems, the invention provides an access control system and a control method thereof, which can effectively solve the problems of unsafe single identification and low identification efficiency in the prior art.
the invention is realized by adopting the following technical scheme:
an access control system, characterized by: the system comprises a database, a data acquisition module, a face recognition module, a living body detection module and an unlocking module, wherein the output ends of the face recognition module and the living body detection module are in communication connection with the unlocking module; the data acquisition module is in communication connection with the face recognition module; the data acquisition module is used for acquiring a user MAC address, a current user face picture and user radio frequency card information, the face recognition module is used for comparing the face picture acquired by the data acquisition module with face features stored in a database in advance, and the living body detection module is used for detecting whether the face of the current user is a living body.
A control method of an access control system is characterized in that: the method comprises the following steps:
a. The data acquisition module acquires a user MAC address by using a WIFI probe, captures a face picture of a current user by using a camera, and sends the MAC address and the face picture to the face recognition module;
b. The face recognition module receives the MAC address and the face picture, extracts face features in the face picture, searches the face features associated with the MAC address in a database, compares the face feature similarity, informs the unlocking module to open the door if the feature similarity is smaller than a threshold value, and enters the step c if the feature similarity is larger than or equal to the threshold value;
c. The data acquisition module acquires the radio frequency card information of a user and sends the radio frequency card information to the face recognition module;
d. The face recognition module receives the radio frequency card information, searches the face features associated with the radio frequency card information in a database, compares the face features with the face features extracted in the step b for feature similarity, and ends the process if the feature similarity is greater than or equal to a threshold value; if the feature similarity is smaller than the threshold value, entering the step e;
e. and the data acquisition module takes a snapshot of two face pictures again and sends the face pictures to the living body detection module for living body detection, if the detection is successful, the living body detection module informs the unlocking module to open the access control, and if the detection is failed, the process is ended.
The in-vivo detection in the step e specifically comprises the following steps:
e1. The living body detection module divides the two received photos into an eye region, a nose region, a mouth region and a background; and solving the speed magnitude value s and the speed direction numerical value q of the pixel points in each block area, which specifically comprises the following steps:
Wherein u is the velocity component of the pixel in the horizontal direction, and v is the velocity component of the pixel in the vertical direction;
e2. obtaining 4 speed magnitude values s1, s2, s3 and s4 and 4 speed direction values q1, q2, q3 and q 4;
e3. comparing the speed values pairwise, and comparing the speed direction values pairwise to obtain 12 similarity degrees which are respectively a1, a2, a3, a4, a5, a6, b1, b2, b3, b4, b5 and b 6;
e4. calculating a living body coefficient m, specifically:
m＝a*c+a*c+a*c+a*c+a*c+a*c+b*c+b*c+b*c+b*c+b*c+b*c
wherein c1, c2, c3, c4, c5, c6, c7, c8, c9, c10, c11 and c12 are weights of corresponding items respectively;
e5. the biological coefficient m is compared with a threshold value of the biological coefficient value, and if the biological coefficient m is greater than or equal to the threshold value, it is determined as a living body, and if the biological coefficient m is less than the threshold value, it is determined as not a living body.
The step b specifically comprises the following steps:
b1. extracting a face image from the face image through an MTCNN face detection model to obtain a face frame, aligning and then cutting;
b2. Inputting the cut images into an acceptance network, calculating a feature vector of Embedding, wherein the dimension of the feature vector is 512 dimensions, the extracted face feature vector o is (x1, x2, x3, x4..... x512), and the corresponding N face feature vectors p in the database are (yN1, yN2, yN3, yN4.... yN 512);
b3. comparing the face feature vector o with the N face feature vectors p one by one, specifically:
n d are calculated and are d1, d2 and d3..
the database stores user MAC addresses, face features associated with the MAC addresses, radio frequency card information and face features associated with the radio frequency card information in advance.
In the step a, a data acquisition module acquires a specific user MAC address by using a WIFI probe:
a1. the access control system is provided with a WIFI probe and a signal intensity threshold value, and the WIFI probe acquires the MAC address of the user with the signal intensity larger than the signal intensity threshold value;
Ordering the user MAC addresses according to the signal intensity by the WIFI probe;
and a3. the WIFI probe sends the MAC address with the strongest signal intensity to the face recognition module.
Compared with the prior art, the invention has the beneficial effects that:
1. The access control system provided by the invention integrates the radio frequency technology, the face recognition technology, the WIFI probe technology and the living body detection technology, is applied to the access control system, can effectively prevent the defect of single-mode recognition, greatly improves the recognition precision, also ensures the improvement of the recognition speed, and ensures the safety of entrance guard entrance and exit.
2. The control method of the access control system is that people can carry the mobile phone with them when passing through the access control, the WIFI probe can automatically acquire the MAC address of the mobile phone, verification is carried out by combining face recognition, and a user does not need to carry out additional operation when in use. When the WIFI probe and the face recognition technology fail, a user can pass through an entrance guard through the radio frequency card and the living body detection, the user is required to carry and use the radio frequency card, then the living body detection is carried out, and the safety is higher.
in the control method, the MAC address of the user is captured by using a WIFI probe technology, but the privacy information of the user is not influenced, and the 1:1 face recognition is supported during face recognition, so that the problems of low recognition speed and poor timeliness in an M: N mode and when M, N are large in size in face recognition can be effectively solved. And the radio frequency technology, the face recognition technology, the WIFI probe technology and the living body detection technology are integrated, so that the safety of entrance guard exit guard entrance guard exit guard.
3. By using living body detection, the phenomenon that a color printed picture or a 3D face mask can pass through the entrance guard is avoided, and the safety is improved. And the algorithm dependency of the liveness detection is reduced.
4. The face recognition of the invention adopts a 1:1 recognition method, the algorithm dependency is reduced, and a high-precision face recognition algorithm is not needed, so that the face recognition speed is high and the efficiency is high.
5. the database stores the user MAC address, the face characteristics associated with the MAC address, the radio frequency card information and the face characteristics associated with the radio frequency card information in advance, so that 1:1 face recognition is realized in the face recognition process, and the face recognition speed is increased.
6. And a signal intensity threshold value is set, so that the WIFI probe can only acquire the MAC address with the signal intensity greater than the signal intensity threshold value, and the phenomenon that the number of the MAC addresses read at one time is too large is avoided. The MAC addresses are sorted according to the signal intensity, so that the distance of a user can be better distinguished, and the picture of the corresponding user can be accurately captured, so that the face recognition is more efficient.
drawings
The invention will be described in further detail with reference to the following description taken in conjunction with the accompanying drawings and detailed description, in which:
FIG. 1 is a logic sequence diagram of the present invention;
Detailed Description
example 1
As a basic implementation manner of the invention, the invention comprises an access control system, which comprises a database, a data acquisition module, a face recognition module, a living body detection module and an unlocking module, wherein the output ends of the face recognition module and the living body detection module are in communication connection with the unlocking module; the data acquisition module is used for acquiring a user MAC address, a current user face picture and user radio frequency card information, the face recognition module is used for comparing the face picture acquired by the data acquisition module with face features stored in a database in advance, and the living body detection module is used for detecting whether the face of the current user is a living body.
Example 2
as a preferred embodiment of the present invention, the present invention includes a control method of an access control system, the control system includes a database, a data acquisition module, a face recognition module, a living body detection module, and an unlocking module, output ends of the face recognition module and the living body detection module are in communication connection with the unlocking module, and the data acquisition module is in communication connection with the face recognition module; the data acquisition module comprises a WIFI probe, a camera and a radio frequency card identification device and is used for acquiring a user MAC address, a current user face picture and user radio frequency card information, the face identification module is used for comparing the face picture acquired by the data acquisition module with face features stored in a database in advance, and the living body detection module is used for detecting whether the face of the current user is a living body.
with reference to the attached figure 1 of the specification, the control method comprises the following steps:
a. the data acquisition module acquires a user MAC address by using a WIFI probe, captures a face picture of a current user by using a camera, and sends the MAC address and the face picture to the face recognition module;
b. The face recognition module receives the MAC address and the face picture, extracts face features in the face picture, searches the face features associated with the MAC address in a database, compares the face feature similarity, informs the unlocking module to open the door if the feature similarity is smaller than a threshold value, and enters the step c if the feature similarity is larger than or equal to the threshold value;
c. the radio frequency card identification device of the data acquisition module acquires radio frequency card information of a user and sends the radio frequency card information to the face identification module;
d. The face recognition module receives the radio frequency card information, searches the face features associated with the radio frequency card information in a database, compares the face features with the face features extracted in the step b for feature similarity, and ends the process if the feature similarity is greater than or equal to a threshold value; if the feature similarity is smaller than the threshold value, entering the step e;
e. and the data acquisition module takes a snapshot of two face pictures again and sends the face pictures to the living body detection module for living body detection, if the detection is successful, the living body detection module informs the unlocking module to open the access control, and if the detection is failed, the process is ended.
Example 3
As a best implementation mode of the invention, the invention comprises a control method of an access control system, wherein the control system comprises a database, a data acquisition module, a face recognition module, a living body detection module and an unlocking module, the output ends of the face recognition module and the living body detection module are in communication connection with the unlocking module, and the data acquisition module is in communication connection with the face recognition module; the data acquisition module comprises a WIFI probe, a camera and a radio frequency card identification device and is used for acquiring a user MAC address, a current user face picture and user radio frequency card information, the face identification module is used for comparing the face picture acquired by the data acquisition module with face features stored in a database in advance, and the living body detection module is used for detecting whether the face of the current user is a living body.
The control method comprises the following steps:
a. The access control system is provided with a WIFI probe and a camera, and is provided with a signal intensity threshold value, the WIFI probe acquires MAC addresses of users with signal intensity larger than the signal intensity threshold value, sequences the MAC addresses of the users, and sends the MAC address with the strongest signal intensity to the face recognition module; the camera captures a face picture of a current user and sends the face picture to the face recognition module;
b. the database is pre-stored with a user MAC address and face features associated with the MAC address, the face recognition module receives the MAC address and the face picture, extracts the face features in the face picture, searches the face features associated with the MAC address in the database, and performs face feature similarity comparison, specifically:
b1. extracting a face image from the face image through an MTCNN face detection model to obtain a face frame, aligning and then cutting;
b2. inputting the cut images into an increment network, calculating a feature vector of Embedding, wherein the dimension of the feature vector is 512 dimensions, the extracted face feature vector o is (x1, x2, x3, x4... times 512), and the corresponding N face feature vectors p in the database are (yN1, yN2, yN3, yN4.. times.yN 512);
b3. Comparing the face feature vector o with the N face feature vectors p one by one, specifically:
Calculating N d, wherein d is a feature similarity, specifically d1, d2 and d3... dN, if one of the d is smaller than a threshold value, the recognition is successful, the face recognition module informs the unlocking module to open the door control, and if the feature similarity is larger than or equal to the threshold value, the step c is carried out;
c. the radio frequency card identification device of the data acquisition module acquires radio frequency card information of a user and sends the radio frequency card information to the face identification module;
d. b, pre-storing radio frequency card information and face features associated with the radio frequency card information in the database, receiving the radio frequency card information by a face recognition module, searching the face features associated with the radio frequency card information in the database, comparing the face features with the face features extracted in the step b by feature similarity, and ending the process if the feature similarity is greater than or equal to a threshold value; if the feature similarity is smaller than the threshold value, entering the step e;
e. And the data acquisition module takes a snapshot of two face pictures again and sends the face pictures to the living body detection module for living body detection, if the detection is successful, the living body detection module informs the unlocking module to open the access control, and if the detection is failed, the process is ended.
During the detection of the living body in the step e, the method specifically comprises the following steps:
e1. the living body detection module divides the two received photos into an eye region, a nose region, a mouth region and a background; and solving the speed magnitude value s and the speed direction numerical value q of the pixel points in each block area, which specifically comprises the following steps:
Assuming a pixel (x, y) on the image, whose brightness at time t is I (x, y, t), u (x, y) and v (x, y) represent the velocity components of the optical flow of the pixel in the horizontal and vertical directions. Namely, it is
after the time interval Δ t elapses, the luminance of the corresponding point of the point becomes I (x + Δ x, y + Δ y, t + Δ t).
because the speed of the human face is lower when the human face photo is collected, the change between frames can describe the motion details of the human face, and the displacement amplitude is smaller. We expand using taylor's formula:
wherein epsilon represents a second-order infinite small term which can be ignored, and because the brightness change is very small when the access control system collects the face photos, the brightness change can be regarded as constant, so that
I(x,y,t)＝I(x+Δx,y+Δy,t+Δt)
when the time interval Δ t is sufficiently small to approach 0, it is obtained
i.e., -It is Ixu + Iyv.
because the local areas of the same surface in each scene have similar motion, the projection on the image plane is also in the adjacent area, and the speeds of the adjacent points are consistent, so that all the pixel points in the (x, y) pixel point area do similar motion and have the same optical flow. The velocity (u, v) of (x, y) can be solved by simultaneous equations.
solving the speed magnitude and direction:
e2. the optical flow vector extracted from each block area is divided into two numerical values to be recorded, wherein one is the magnitude and the other is the direction, and 4 speed magnitude values s1, s2, s3 and s4 and 4 speed direction numerical values q1, q2, q3 and q4 are obtained;
e3. and carrying out pairwise comparison between the speed values and the speed direction values, wherein 12 comparison operations are required:
the difference value of each group of (s1, s2) (s1, s3) (s1, s4) (s2, s3) (s2, s4) (s3, s4) (d1, d2) (d1, d3) (d1, d4) (d2, d3) (d2, d4) (d3, d4) represents the similarity of size or direction. Therefore, 12 similarities are obtained in total, the similarity of the first group is a1 ═ s1-s2|, and the similarity of the seventh group is b1 ═ d1-d2|, so that 12 similarities are a1, a2, a3, a4, a5, a6, b1, b2, b3, b4, b5 and b6 respectively;
e4. calculating a living body coefficient m, specifically:
m＝a*c+a*c+a*c+a*c+a*c+a*c+b*c+b*c+b*c+b*c+b*c+b*c
Wherein, c1, c2, c3, c4, c5, c6, c7, c8, c9, c10, c11 and c12 are weights of corresponding items respectively, and it is considered that relative motion between the background and the eye region can reflect whether the acquired human face is a living body. We set the values of c3, c 9a bit larger; it is also possible to set each weight value as 1/12, that is, the relative motion contribution value of each region is the same, and the living coefficient when the relative motion contribution value of each region is the same is specifically:
e5. a higher value of the live coefficient indicates a higher probability that the face in the image is from a real live body. Therefore, the threshold value of the biological coefficient value can be found by a plurality of sets of experiments in advance, the biological coefficient m is compared with the threshold value of the biological coefficient value, and if the biological coefficient m is greater than or equal to the threshold value, it is determined as a living body, and if the biological coefficient m is less than the threshold value, it is determined as not a living body.
In summary, after reading the present disclosure, those skilled in the art should make various other modifications without creative efforts according to the technical solutions and concepts of the present disclosure, which are within the protection scope of the present disclosure.
Claims (6)
1. an access control system, characterized by: the system comprises a database, a data acquisition module, a face recognition module, a living body detection module and an unlocking module, wherein the output ends of the face recognition module and the living body detection module are in communication connection with the unlocking module; the data acquisition module is in communication connection with the face recognition module; the data acquisition module is used for acquiring a user MAC address, a current user face picture and user radio frequency card information, the face recognition module is used for comparing the face picture acquired by the data acquisition module with face features stored in a database in advance, and the living body detection module is used for detecting whether the face of the current user is a living body.
2. The control method of an access control system according to claim 1, characterized in that: the method comprises the following steps:
a. The data acquisition module acquires a user MAC address by using a WIFI probe, captures a face picture of a current user by using a camera, and sends the MAC address and the face picture to the face recognition module;
b. the face recognition module receives the MAC address and the face picture, extracts face features in the face picture, searches the face features associated with the MAC address in a database, compares the face feature similarity, informs the unlocking module to open the door if the feature similarity is smaller than a threshold value, and enters the step c if the feature similarity is larger than or equal to the threshold value;
c. the data acquisition module acquires the radio frequency card information of a user and sends the radio frequency card information to the face recognition module;
d. The face recognition module receives the radio frequency card information, searches the face features associated with the radio frequency card information in a database, compares the face features with the face features extracted in the step b for feature similarity, and ends the process if the feature similarity is greater than or equal to a threshold value; if the feature similarity is smaller than the threshold value, entering the step e;
e. and the data acquisition module takes a snapshot of two face pictures again and sends the face pictures to the living body detection module for living body detection, if the detection is successful, the living body detection module informs the unlocking module to open the access control, and if the detection is failed, the process is ended.
3. the control method of an access control system according to claim 2, characterized in that: the in-vivo detection in the step e specifically comprises the following steps:
e1. the living body detection module divides the two received photos into an eye region, a nose region, a mouth region and a background; and solving the speed magnitude value s and the speed direction numerical value q of the pixel points in each block area, which specifically comprises the following steps:
wherein u is the velocity component of the pixel in the horizontal direction, and v is the velocity component of the pixel in the vertical direction;
e2. obtaining 4 speed magnitude values s1, s2, s3 and s4 and 4 speed direction values q1, q2, q3 and q 4; e3. comparing the speed values pairwise, and comparing the speed direction values pairwise to obtain 12 similarity degrees which are respectively a1, a2, a3, a4, a5, a6, b1, b2, b3, b4, b5 and b 6;
e4. Calculating a living body coefficient m, specifically:
m＝a*c+a*c+a*c+a*c+a*c+a*c+b*c+b*c+b*c+b*c+b*c+b*c
Wherein c1, c2, c3, c4, c5, c6, c7, c8, c9, c10, c11 and c12 are weights of corresponding items respectively;
e5. the biological coefficient m is compared with a threshold value of the biological coefficient value, and if the biological coefficient m is greater than or equal to the threshold value, it is determined as a living body, and if the biological coefficient m is less than the threshold value, it is determined as not a living body.
4. the control method of an access control system according to claim 3, characterized in that: the step b specifically comprises the following steps:
b1. Extracting a face image from the face image through an MTCNN face detection model to obtain a face frame, aligning and then cutting;
b2. inputting the cut images into an increment network, calculating a feature vector of Embedding, wherein the dimension of the feature vector is 512 dimensions, the extracted face feature vector o is (x1, x2, x3, x4... times 512), and the corresponding N face feature vectors p in the database are (yN1, yN2, yN3, yN4.. times.yN 512);
b3. Comparing the face feature vector o with the N face feature vectors p one by one, specifically:
n d are calculated and are d1, d2 and d3..
5. The control method of an access control system according to claim 4, wherein: the database stores user MAC addresses, face features associated with the MAC addresses, radio frequency card information and face features associated with the radio frequency card information in advance.
6. The control method of an access control system according to claim 5, wherein: in the step a, a data acquisition module acquires a specific user MAC address by using a WIFI probe:
a1. the access control system is provided with a WIFI probe and a signal intensity threshold value, and the WIFI probe acquires the MAC address of the user with the signal intensity larger than the signal intensity threshold value;
ordering the user MAC addresses according to the signal intensity by the WIFI probe;
and a3. the WIFI probe sends the MAC address with the strongest signal intensity to the face recognition module.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910745391.2A CN110544333B (en) | 2019-08-13 | 2019-08-13 | Access control system and control method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910745391.2A CN110544333B (en) | 2019-08-13 | 2019-08-13 | Access control system and control method thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110544333A true CN110544333A (en) | 2019-12-06 |
| CN110544333B CN110544333B (en) | 2021-07-16 |
Family
ID=68711488
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910745391.2A Active CN110544333B (en) | 2019-08-13 | 2019-08-13 | Access control system and control method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110544333B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112383571A (en) * | 2021-01-12 | 2021-02-19 | 浙江正元智慧科技股份有限公司 | Login management system based on face recognition big data |
| CN112800886A (en) * | 2021-01-16 | 2021-05-14 | 江苏霆善科技有限公司 | Face recognition system and method based on machine vision |
| CN116259091A (en) * | 2023-01-18 | 2023-06-13 | 北京飞腾时光信息科技有限公司 | Method and device for detecting silent living body |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104143078A (en) * | 2013-05-09 | 2014-11-12 | 腾讯科技（深圳）有限公司 | Living body face recognition method and device and equipment |
| CN205788357U (en) * | 2016-05-13 | 2016-12-07 | 北京旷视科技有限公司 | The checking system identified based on recognition of face and card |
| CN108256459A (en) * | 2018-01-10 | 2018-07-06 | 北京博睿视科技有限责任公司 | Library algorithm is built in detector gate recognition of face and face based on multiple-camera fusion automatically |
| CN109118621A (en) * | 2018-07-24 | 2019-01-01 | 石数字技术成都有限公司 | The face registration system of recognition of face gate inhibition a kind of and application in access control |
| CN109344281A (en) * | 2018-10-12 | 2019-02-15 | 元力云网络有限公司 | A kind of data analysing method based on WIFI probe Yu camera technology |
-
2019
- 2019-08-13 CN CN201910745391.2A patent/CN110544333B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104143078A (en) * | 2013-05-09 | 2014-11-12 | 腾讯科技（深圳）有限公司 | Living body face recognition method and device and equipment |
| CN205788357U (en) * | 2016-05-13 | 2016-12-07 | 北京旷视科技有限公司 | The checking system identified based on recognition of face and card |
| CN108256459A (en) * | 2018-01-10 | 2018-07-06 | 北京博睿视科技有限责任公司 | Library algorithm is built in detector gate recognition of face and face based on multiple-camera fusion automatically |
| CN109118621A (en) * | 2018-07-24 | 2019-01-01 | 石数字技术成都有限公司 | The face registration system of recognition of face gate inhibition a kind of and application in access control |
| CN109344281A (en) * | 2018-10-12 | 2019-02-15 | 元力云网络有限公司 | A kind of data analysing method based on WIFI probe Yu camera technology |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112383571A (en) * | 2021-01-12 | 2021-02-19 | 浙江正元智慧科技股份有限公司 | Login management system based on face recognition big data |
| CN112383571B (en) * | 2021-01-12 | 2021-06-04 | 浙江正元智慧科技股份有限公司 | Login management system based on face recognition big data |
| CN112800886A (en) * | 2021-01-16 | 2021-05-14 | 江苏霆善科技有限公司 | Face recognition system and method based on machine vision |
| CN112800886B (en) * | 2021-01-16 | 2021-09-10 | 江苏霆善科技有限公司 | Face recognition system and method based on machine vision |
| CN116259091A (en) * | 2023-01-18 | 2023-06-13 | 北京飞腾时光信息科技有限公司 | Method and device for detecting silent living body |
| CN116259091B (en) * | 2023-01-18 | 2023-11-10 | 北京飞腾时光信息科技有限公司 | Method and device for detecting silent living body |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110544333B (en) | 2021-07-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP7447978B2 (en) | Face matching system, face matching method, and program | |
| CN109934176B (en) | Pedestrian recognition system, recognition method, and computer-readable storage medium | |
| CN103914686B (en) | A kind of face alignment authentication method and system shone based on certificate photo with collection | |
| CN101142584B (en) | Method for facial features detection | |
| CN110544333B (en) | Access control system and control method thereof | |
| CN102663444B (en) | Method for preventing account number from being stolen and system thereof | |
| KR101710050B1 (en) | Image identification systems and method | |
| CN109344271A (en) | Video portrait records handling method and its system | |
| CN107169458B (en) | Data processing method, device and storage medium | |
| CN102902959A (en) | Face recognition method and system for storing identification photo based on second-generation identity card | |
| US20170228585A1 (en) | Face recognition system and face recognition method | |
| CN101373514A (en) | Method and system for recognizing human face | |
| CN102930243A (en) | Method and system for identifying facial information of special personnel | |
| CN112528706A (en) | Personnel identification system and method thereof | |
| CN103488966A (en) | Intelligent mobile phone capable of identifying real-name ticket information | |
| CN110717428A (en) | Identity recognition method, device, system, medium and equipment fusing multiple features | |
| CN113011544B (en) | Face biological information identification method, system, terminal and medium based on two-dimensional code | |
| CN111385440A (en) | Monitoring camera with face recording and inquiring functions | |
| CN205942742U (en) | Airport identity authentication system based on gait discernment | |
| EP4064218A1 (en) | Vehicle identification profile methods and systems at the edge | |
| JP2012133411A (en) | Face collation system, face collation device and face collation method | |
| CN114783054A (en) | Gait recognition method based on wireless and video feature fusion | |
| AU2024201525B2 (en) | Gate system, gate apparatus, image processing method therefor, program, and arrangement method for gate apparatus | |
| Noel et al. | A Smart IoT based real-time system to Minimize Mishandled Luggage at Airports | |
| CN111291586A (en) | Living body detection method, living body detection device, electronic apparatus, and computer-readable storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |