WO2019134246A1

WO2019134246A1 - Facial recognition-based security monitoring method, device, and storage medium

Info

Publication number: WO2019134246A1
Application number: PCT/CN2018/077623
Authority: WO
Inventors: 杨勇
Original assignee: 平安科技（深圳）有限公司
Priority date: 2018-01-03
Filing date: 2018-02-28
Publication date: 2019-07-11
Also published as: CN108399665A

Abstract

The present application provides a facial recognition-based security monitoring method, a device, and a storage medium. The method comprises: a photography device photographs a real-time image of the current user and obtains a face image thereof; determine whether the face image is shielded; if the face image is not shielded, input the face image into a predetermined and regularly updated facial recognition system to recognize one or more identity card photos in a user information database possibly matching the face image, and the corresponding matching probability; use the identity card photo corresponding to the maximum probability value as the identity card photo of the current user and retrieve identity information of the current user according to the identity card photo; compare the identity information of the current user with that in the blacklist and control, according to the comparison result, whether an access control system to open a door. Face shielding detection and facial recognition of the present application are implemented to prevent a user with the face shielded and a user in the blacklist from entering a monitoring region so as to improve the security of the monitoring region.

Description

Security monitoring method, device and storage medium based on face recognition

This application claims the priority of the Chinese patent application filed on January 3, 2018, the Chinese Patent Office, the application number is 201810003944.2, and the invention name is "face recognition-based security monitoring method, device and storage medium". The citation is incorporated in the application.

Technical field

The present application relates to the field of computer vision processing technologies, and in particular, to a security monitoring method based on face recognition, an electronic device, and a computer readable storage medium.

Background technique

At present, the application field of face recognition is very extensive, and plays a very important role in many fields such as financial payment, access control, and identification, which brings great convenience to people's lives. Now the ATM self-service cash withdrawal room of the bank is basically an open place. As long as the access control button is pressed, or the access control system senses someone, it will automatically open the door, and anyone can enter and exit at will, which makes the ATM self-service withdrawal room have security risks. Therefore, how to use face recognition to block criminals from entering the ATM self-service withdrawal room to maintain bank reputation and security is an urgent problem to be solved.

Summary of the invention

The present invention provides a security monitoring method based on face recognition, an electronic device, and a computer readable storage medium, the main purpose of which is to prevent face occluded users and blacklists by face occlusion detection and face recognition. The user enters the monitoring area to improve the security of the monitoring area.

To achieve the above objective, the present application provides a security monitoring method based on face recognition, which is applied to an electronic device, and the method includes:

S1, receiving a user-initiated door opening request, waking up the camera device to capture a real-time image of the current user, pre-processing the real-time image to obtain a current user's face image;

S2: input the facial image into a predetermined facial occlusion detection system, and determine whether the facial image is occluded;

S3. If the facial image is not occluded, input the facial image into a predetermined regularly updated face recognition system, and identify one or more ID cards in the user information database that may match the facial image. Photo and corresponding matching probability;

S4. In the identified one or more ID card photos, take the photo of the ID card corresponding to the maximum probability as the photo of the ID card of the current user, and retrieve the identity information of the current user according to the photo of the ID card;

S5. Comparing the identity information of the current user with the blacklist. When the user identity information of the current user cannot match the information in the blacklist, the access control system is controlled to open; or, when the identity information of the current user matches the information in the blacklist. Or, when the facial image is occluded, the control access control system does not open the door.

In addition, in order to achieve the above object, the present application further provides an electronic device, including: a memory, a processor, and an imaging device, wherein the memory includes a face recognition-based security monitoring program, and the security monitoring program is processed by the The following steps are implemented when the device is executed:

A. Receiving a user-initiated door opening request, waking up the camera device to take a real-time image of the current user, and pre-processing the real-time image to obtain a current user's face image;

B. input the facial image into a predetermined facial occlusion detection system, and determine whether the facial image is occluded;

C. If the facial image is not occluded, input the facial image into a predetermined regularly updated face recognition system, and identify one or more ID cards in the user information database that may match the facial image. Photo and corresponding matching probability;

D. In the identified one or more ID card photos, take the photo of the ID card corresponding to the maximum probability as the current user's ID card photo, and retrieve the identity information of the current user according to the ID card photo;

E. Comparing the identity information of the current user with the blacklist. When the user identity information of the current user cannot match the information in the blacklist, the access control system is opened; or when the identity information of the current user matches the information in the blacklist. Or, when the facial image is occluded, the control access control system does not open the door.

In addition, in order to achieve the above object, the present application further provides a computer readable storage medium including a face recognition based security monitoring program, which is implemented by a processor, as described above Any of the steps in the security monitoring method based on face recognition.

The face recognition-based security monitoring method, the electronic device and the computer readable storage medium proposed by the present application first perform face occlusion detection on the user's face image to prevent the occluded user from entering the monitoring area; then, the face The unoccluded user determines the user identity through face recognition, compares the user identity information with the blacklist, prevents the user in the blacklist from entering the monitoring area, and periodically updates the face recognition system to improve the accuracy of face recognition; Improve the security of the surveillance area in many ways.

DRAWINGS

1 is a schematic diagram of a preferred embodiment of an electronic device of the present application;

2 is a program block diagram of the face recognition based security monitoring program of FIG. 1;

3 is a flowchart of a preferred embodiment of a security monitoring method based on face recognition according to the present application;

FIG. 4 is a schematic diagram of the refinement process of step S20 in the method for security monitoring based on face recognition according to the present application.

The implementation, functional features and advantages of the present application will be further described with reference to the accompanying drawings.

Detailed ways

It is understood that the specific embodiments described herein are merely illustrative of the application and are not intended to be limiting.

The application provides an electronic device 1 . Referring to FIG. 1 , it is a schematic diagram of a preferred embodiment of the electronic device 1 of the present application. In this embodiment, the electronic device 1 may be a PC (Personal Computer), or may be a terminal device having a computing function, such as a smart phone, a tablet computer, an e-book reader, a portable computer, or a server. In other embodiments, when the electronic device 1 is a server, the server may include: a rack server, a blade server, a tower server, a rack server, or the like.

The electronic device 1 includes a processor 12, a memory 11, an imaging device 13, a network interface 14, and a communication bus 15. The electronic device 1 is connected to the access control system through the network interface 14. Optionally, the network interface 14 may include a standard wired interface and a wireless interface (such as a WI-FI interface). Communication bus 15 is used to implement connection communication between these components.

The memory 11 includes at least one type of readable storage medium. The at least one type of readable storage medium may be a non-volatile storage medium such as a flash memory, a hard disk, a multimedia card, a card type memory, or the like. In some embodiments, the readable storage medium may be an internal storage unit of the electronic device 1, such as a hard disk of the electronic device 1. In other embodiments, the readable storage medium may also be an external memory of the electronic device 1, such as a plug-in hard disk equipped on the electronic device 1, a smart memory card (SMC), Secure Digital (SD) card, Flash Card, etc.

In the embodiment, the readable storage medium of the memory 11 is generally used to store a face recognition-based security monitoring program 10 installed on the electronic device 1, a predetermined face occlusion detection system, and a face recognition system. And the user information database (not shown in the figure). The user information database stores information about all users of a financial institution, including: name, gender, age, ID number, ID card, and the account of the user in the financial institution. The memory 11 can also be used to temporarily store data that has been output or is about to be output.

The processor 12, in some embodiments, may be a Central Processing Unit (CPU), microprocessor or other data processing chip for running program code or processing data stored in the memory 11, such as performing a face-based Identifyed security monitors 10, etc.

The imaging device 13 may be part of the electronic device 1 or may be independent of the electronic device 1. In some embodiments, the electronic device 1 is a terminal device having a camera such as a smartphone, a tablet computer, a portable computer, etc., and the camera device 13 is a camera of the electronic device 1. In other embodiments, the electronic device 1 may be a server, and the camera device 13 is connected to the electronic device 1 via a network.

In this embodiment, the camera device 13 is installed in a security monitoring area, such as an ATM self-service cash withdrawal room door, and real-time images are taken in real time for users who need to enter the ATM self-service cash withdrawal room, and the real-time image is transmitted to the processor 12 through the network, and processed. The device 12 identifies the identity of the current user from the real-time image, and invokes the identity information of the current user from the user information database of the memory 11, and compares the identity information of the current user with the blacklist to determine whether the current user is secure and controls Whether the access control system opens.

Figure 1 shows only the electronic device 1 with components 11-15, but it should be understood that not all illustrated components may be implemented, and more or fewer components may be implemented instead.

Optionally, the electronic device 1 may further include a user interface, and the user interface may include an input unit such as a keyboard, a voice input device such as a microphone, a device with a voice recognition function, a voice output device such as an audio, a headphone, and the like. Optionally, the user interface may also include a standard wired interface and a wireless interface.

Optionally, the electronic device 1 may further include a display, which may also be referred to as a display screen or a display unit. In some embodiments, it may be an LED display, a liquid crystal display, a touch liquid crystal display, and an Organic Light-Emitting Diode (OLED) touch sensor. The display is used to display information processed in the electronic device 1 and a user interface for displaying visualizations.

Optionally, the electronic device 1 further comprises a touch sensor. The area provided by the touch sensor for the user to perform a touch operation is referred to as a touch area. Further, the touch sensor described herein may be a resistive touch sensor, a capacitive touch sensor, or the like. Moreover, the touch sensor includes not only a contact type touch sensor but also a proximity type touch sensor or the like. Furthermore, the touch sensor may be a single sensor or a plurality of sensors arranged, for example, in an array.

In addition, the area of the display of the electronic device 1 may be the same as or different from the area of the touch sensor. Optionally, a display is stacked with the touch sensor to form a touch display. The device detects a user-triggered touch operation based on a touch screen display.

Optionally, the electronic device 1 may further include an access control switch, the access control switch is installed outside the security monitoring area, and the user sends a door opening request to the electronic device 1 by pressing the access control switch.

In the apparatus embodiment shown in FIG. 1, a memory-based security monitoring program 10 is included in the memory 11 as a computer storage medium; the processor 12 executes the face recognition-based security monitoring program 10 stored in the memory 11. The following steps are implemented:

A, receiving a user-initiated door opening request, waking up the camera device 13 to capture a real-time image of the current user, pre-processing the real-time image to obtain a facial image of the current user;

In this embodiment, the ATM self-service withdrawal room of the bank is taken as an example, but not limited to the ATM self-service withdrawal room of the bank, and the specific scheme of the present application is explained. When a user needs to enter the ATM self-service cash withdrawal room, the camera device 13 can be woken up to take a real-time image to the current user by pressing the ATM self-service withdrawal access switch, and the real-time image is sent to the processor 12 through the network. In order to determine the face image corresponding to the current user from the real-time image, the real-time image needs to be pre-processed to facilitate the subsequent face recognition step.

In other embodiments, the pre-processing step includes: recognizing a face region from the real-time image by using a face recognition algorithm; and when the processor 12 receives the real-time image, acquiring a size of the image to establish an same size. Grayscale image; convert the acquired color image into a grayscale image, and create a memory space; equalize the grayscale image histogram, reduce the amount of grayscale image information, speed up the detection, and then detect the person in the image Face, and return an object containing face information, obtain the data of the location of the face, and record the number; finally get the area of the avatar and save it, thus completing the process of face area extraction.

It can be understood that if there are multiple users in the imaging range of the imaging device 13, and the distances of the plurality of users from the imaging device 13 are different, the size of the face of the plurality of users in the real-time image is also different. That is to say, the real-time image captured by the camera device 13 may include a plurality of face images of the user, and the face recognition algorithm extracts a plurality of face regions from the real-time image, and selects the face with the largest size from the plurality of face regions. The area is the face image of the current user. If only one face region is extracted from the live image, the face region is used as the face image of the current user. At the same time, in order to facilitate subsequent face occlusion detection and face recognition, the face image is saved by a preset size (for example, 256*256 pixels). In other embodiments, the face recognition algorithm may also be: a geometric feature based method, a local feature analysis method, a feature face method, an elastic model based method, a neural network method, and the like.

It can be understood that, in order to ensure the security of the ATM self-service cash withdrawal room, the user who blocks the face can be refused to enter. Therefore, it is necessary to determine whether the face image is occluded, including the following steps:

The face image of the current user is input to a predetermined face average model to identify t face feature points from the face image. When t=34, the real-time facial image is aligned with the facial average model, and then the feature extraction algorithm is used to search the real-time facial image for 12 eyelid feature points matching the 34 facial feature points of the facial average model, 2 eye feature points and 20 lip feature points. Then, an eye region can be determined according to 12 eyelid feature points and 2 eyeball feature points, a lip region is determined according to the 20 lip feature points, and the determined eye region and the lip region are input to a predetermined person. The eye part class model of the face and the lip part class model of the face determine the authenticity of the determined eye region and the lip region based on the results obtained by the model. When the results of the output of the eye part model and the lip part model are both false, it means that the eye area and the lip area are not the human eye area and the human lip area, and the current facial image is determined to be occluded. The control access control system does not open the door, and prompts the user to occlude the face through the voice output device; when both the eye part type model and the lip part type model output result are true, it indicates that the eye area and the lip area are human The eye area and the human lip area, that is, the current facial image is not occluded. It should be noted that the facial average model, the lip part model, and the eye part model are pre-trained, and the training steps and the identification steps have mature technologies, which will not be described here.

After initially determining that the current facial image has not been occluded, the facial image is input into a predetermined facial recognition system, and one or more ID card photos and corresponding matching probabilities that may match the current facial image from the user information database. . The face recognition system is pre-trained by using photos of all users in the user data repository. Currently, the face recognition technology is relatively mature, and will not be described here.

In this embodiment, it is assumed that the face recognition system recognizes three ID card photos P1, P2, and P3, and the matching probabilities corresponding to each ID card photo are 0.6, 0.2, and 0.2, respectively, and the face recognition system default selection probability is the maximum. The corresponding ID photo P1 is taken as the photo of the current user's ID card, and all the information of the current user is retrieved from the user data information base according to P1, including: ID number, name, age, gender, bank card number, mobile phone number, etc. . It can be understood that the greater the matching probability, the greater the possibility that the recognized ID card photo is the current user's ID card photo. Therefore, in other embodiments, in order to improve the accuracy of the face recognition, The probability of identifying one or more ID card photos is filtered. When the probability maximum value is greater than or equal to the first preset threshold (for example, 0.5), the ID card photo corresponding to the maximum value of the retention probability is used as the identity of the current user. The photo is taken; when the probability maximum value is less than the first preset threshold, the current user is prompted to retake the photo by the voice output device.

It can be understood that as the age increases, each person's appearance will change. Therefore, in order to ensure the accuracy of face recognition, the face recognition system needs to be performed every preset time interval (for example, 6 months). Update, and the source of the update data is the photo taken when the user enters the ATM self-service cash withdrawal room, from the face image extracted from the real-time image of each user captured by the camera device 13, when from the user information database according to the face image When the matching probability maximum value of the identified ID card photo is greater than or equal to a second preset threshold (for example, 0.58), the facial image is added to the identity information of the current user in the user information database, and the supplementary users are utilized. The photo is updated periodically on the face recognition system. It should be noted that, in order to ensure that the photo added to the user information database is the current user's own photo, rather than the photos of other users, the second preset threshold should be set to be greater than the first preset threshold.

After confirming the identity information of the current user, the blacklist may be compared with the blacklist. In this embodiment, the blacklist may include: a criminal who is involved in the crime, such as a fugitive criminal, a terrorist, or the like. The identity information, for example, the ID number, compares the current user's ID number with the ID number in the blacklist. When the current user's ID number cannot match the information in the blacklist, the access control system is opened; The identity information of the current user matches the information in the blacklist, and the access control system is not opened.

The electronic device 1 of the above embodiment determines the identity of the user by face recognition, compares the user identity information with the blacklist, prevents the user in the blacklist from entering the security monitoring area, and performs face occlusion detection on the user face image. The user who prevents the face from being occluded enters the security monitoring area, and periodically updates the face recognition system to improve the security of the security monitoring area.

Alternatively, in other embodiments, the face recognition based security monitor 10 may also be partitioned into one or more modules, one or more modules being stored in the memory 11 and executed by the processor 12 to Complete this application. A module as referred to in this application refers to a series of computer program instructions that are capable of performing a particular function. Referring to FIG. 2, it is a program block diagram of the face recognition based security monitoring program 10 of FIG. The face recognition-based security monitoring program 10 can be divided into: an obtaining module 110, a detecting module 120, an identifying module 130, a calling module 140, and a control module 150. The functions or operational steps implemented by the modules 110-150 are similar to the above, and are not described in detail herein, by way of example, for example:

The acquiring module 110 is configured to receive a user-initiated door opening request, wake up the camera device to capture a real-time image of the current user, and perform pre-processing on the real-time image to obtain a facial image of the current user;

The detecting module 120 is configured to input the facial image into a predetermined facial occlusion detecting system, and determine whether the facial image is occluded;

The identification module 130 is configured to: if the facial image is not occluded, input the facial image into a predetermined regularly updated facial recognition system, and identify one of the user information databases that may match the facial image or Multiple ID card photos and corresponding matching probabilities;

The retrieving module 140 is configured to take the photo of the ID card corresponding to the maximum probability as the photo of the current user's ID card in the identified one or more ID card photos, and retrieve the current user's ID card according to the ID card photo Identity information; and

The control module 150 is configured to compare the identity information of the current user with the blacklist, and control the access control system to open when the user identity information of the current user cannot match the information in the blacklist; or, when the identity information of the current user is black The information in the list matches, or when the facial image is occluded, the access control system is not opened.

In addition, the present application also provides a security monitoring method based on face recognition. Referring to FIG. 3, it is a flowchart of a first embodiment of a security monitoring method based on face recognition according to the present application. The method can be performed by a device that can be implemented by software and/or hardware.

In this embodiment, the security monitoring method based on face recognition includes:

S10. Receiving a user-initiated door opening request, waking up the camera device to capture a real-time image of the current user, and pre-processing the real-time image to obtain a current user's face image;

S20: input the facial image into a predetermined facial occlusion detection system, and determine whether the facial image is occluded;

S30. If the facial image is not occluded, input the facial image into a predetermined regularly updated face recognition system, and identify one or more ID cards in the user information database that may match the facial image. Photo and corresponding matching probability;

S40. In the identified one or more ID card photos, take the photo of the ID card corresponding to the maximum probability as the photo of the ID card of the current user, and retrieve the identity information of the current user according to the photo of the ID card;

S50: Comparing the identity information of the current user with the blacklist, and controlling the access control system to open when the current user identity information cannot match the information in the blacklist; or, when the current user identity information matches the information in the blacklist Or, when the facial image is occluded, the control access control system does not open the door.

In this embodiment, the ATM self-service withdrawal room of the bank is taken as an example, but not limited to the ATM self-service withdrawal room of the bank, and the specific scheme of the present application is explained. When a user needs to enter the ATM self-service cash withdrawal room, the camera can be woken up to take a real-time image to the current user by pressing the ATM self-service withdrawal access switch, and the real-time image is sent to the processor through the network. In order to determine the face image corresponding to the current user from the real-time image, the real-time image needs to be pre-processed to facilitate the subsequent face recognition step.

In other embodiments, the pre-processing step in step S10 includes: recognizing a face region from the real-time image by using a face recognition algorithm; after receiving the real-time image, the processor first acquires a size of the image, and establishes A gray image of the same size; convert the acquired color image into a gray image, and create a memory space; equalize the gray image histogram, reduce the amount of gray image information, speed up the detection, and then detect the image The face in the face, and return an object containing the face information, obtain the data of the location of the face, and record the number; finally obtain the area of the avatar and save it, thus completing the process of extracting the face region.

It can be understood that if there are multiple users in the imaging range of the imaging device, and the distances of multiple users from the imaging device are different, the size of the face of the plurality of users in the real-time image is also different. That is to say, the real-time image captured by the camera device may include a plurality of face images of the user, and the face recognition algorithm is used to extract a plurality of face regions from the real-time image, and select the face region with the largest size from the plurality of face regions. As the face image of the current user. If only one face region is extracted from the live image, the face region is used as the face image of the current user. At the same time, in order to facilitate subsequent face occlusion detection and face recognition, the face image is saved by a preset size (for example, 256*256 pixels). In other embodiments, the face recognition algorithm may also be: a geometric feature based method, a local feature analysis method, a feature face method, an elastic model based method, a neural network method, and the like.

It can be understood that in order to ensure the safety of the ATM self-service cash withdrawal room, the user who blocks the face can be refused to enter, so it is necessary to determine whether the facial image has occlusion. After determining that the current facial image has not been occluded, the facial image is input into a predetermined facial recognition system, one or more ID card photos that may match the current facial image in the user information database, and a corresponding matching probability. The face recognition system is pre-trained by using photos of all users in the user data repository. Currently, the face recognition technology is relatively mature, and will not be described here.

It can be understood that as the age increases, each person's appearance will change. Therefore, in order to ensure the accuracy of face recognition, the face recognition system needs to be performed every preset time interval (for example, 6 months). Update, and the source of the updated data is the photo taken when the user enters the ATM self-service cash withdrawal room, and the facial image extracted from the real-time image of each user captured by the camera device is recognized from the user information database according to the facial image. When the maximum matching probability of the ID card photo is greater than or equal to the second preset threshold (for example, 0.58), the facial image is added to the identity information of the current user in the user information database, and the supplementary user is utilized. The photo periodically updates the face recognition system. It should be noted that, in order to ensure that the photo added to the user information database is the current user's own photo, rather than the photos of other users, the second preset threshold should be set to be greater than the first preset threshold.

It should be noted that the parameters that need to be preset in the first preset threshold, the second preset threshold, and the like may be adjusted according to user needs.

The face recognition-based security monitoring method proposed by the foregoing embodiment determines the user identity through face recognition, compares the user identity information with the blacklist, prevents the user in the blacklist from entering the security monitoring area, and periodically recognizes the face. The system is updated to improve the accuracy of face recognition and improve the security of the security monitoring area.

Another preferred embodiment of the face recognition based security monitoring method is proposed based on the above embodiments. Referring to Fig. 4, it is a refinement flow chart of step S20 of the face recognition based security monitoring method of the present application. In this embodiment, the step S20 includes the following steps:

Step S21, identifying t facial feature points from the facial image, and determining an eye region and a lip region according to position information of the t facial feature points;

Step S22, determining the authenticity of the eye region and the lip region, and determining that the facial image is not blocked when the determination result of the eye region and the lip region is true; and

Step S23, when the determination result of the eye region and the lip region includes an unreality, it is determined that the facial image is occluded.

The face image of the current user is input to a predetermined face average model to identify t face feature points from the face image. When t=34, the real-time facial image is aligned with the facial average model, and then the feature extraction algorithm is used to search the real-time facial image for 12 eyelid feature points matching the 34 facial feature points of the facial average model, 2 eye feature points and 20 lip feature points. Then, an eye region can be determined according to 12 eyelid feature points and 2 eyeball feature points, a lip region is determined according to the 20 lip feature points, and the determined eye region and the lip region are input to a predetermined person. The eye part class model of the face and the lip part class model of the face determine the authenticity of the determined eye region and the lip region based on the results obtained by the model. When the results of the output of the eye part model and the lip part model are both false, it means that the eye area and the lip area are not the human eye area and the human lip area, and the current facial image is determined to be occluded. The control access control system does not open the door, and prompts the user to occlude the face through the voice output device; when both the eye part type model and the lip part type model output result are true, it indicates that the eye area and the lip area are human The eye area and the human lip area, that is, the current facial image is not occluded, and the face recognition step is continued. It should be noted that the facial average model, the lip part model, and the eye part model are pre-trained, and the training steps and the identification steps have mature technologies, which will not be described here.

The security monitoring method based on the face recognition proposed by the above embodiment prevents the occluded user from entering the security monitoring area by performing face occlusion detection on the user's face image, thereby improving the security of the security monitoring area.

Another preferred embodiment of the face recognition based security monitoring method is proposed based on the above embodiments. In this embodiment, the step S50 further includes: when the identity information of the current user matches the information in the blacklist, acquiring user information of other users that are performing service processing in the security monitoring area, and sending the information to the other user. Early warning SMS.

When the identity information of the current user matches the information in the blacklist, the user information of other users who are conducting transactions in the ATM self-service withdrawal room, such as a mobile phone number, is sent, and an alert message is sent to other users to inform other users that the ATM self-service withdrawal is involved outdoors. Black is involved in terrorists, please pay attention to personal life and property safety.

The security monitoring method based on the face recognition proposed by the foregoing embodiment sends a short message early warning to the user who is conducting the transaction in the security monitoring area, thereby improving the user experience.

In addition, the present application further provides a computer readable storage medium including a face recognition based security monitoring program, the security monitoring program being executed by the processor to:

The specific implementation manner of the computer readable storage medium of the present application is substantially the same as the specific implementation manner of the foregoing electronic device and the face recognition-based security monitoring method, and details are not described herein again.

It is to be understood that the term "comprises", "comprising", or any other variants thereof, is intended to encompass a non-exclusive inclusion, such that a process, apparatus, article, or method that comprises a series of elements includes those elements. It also includes other elements not explicitly listed, or elements that are inherent to such a process, device, item, or method. An element that is defined by the phrase "comprising a ..." does not exclude the presence of additional equivalent elements in the process, the device, the item, or the method that comprises the element.

The serial numbers of the embodiments of the present application are merely for the description, and do not represent the advantages and disadvantages of the embodiments. Through the description of the above embodiments, those skilled in the art can clearly understand that the foregoing embodiment method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be through hardware, but in many cases, the former is better. Implementation. Based on such understanding, the technical solution of the present application, which is essential or contributes to the prior art, may be embodied in the form of a software product stored in a storage medium (such as ROM/RAM as described above). , a disk, an optical disk, including a number of instructions for causing a terminal device (which may be a mobile phone, a computer, a server, or a network device, etc.) to perform the methods described in the various embodiments of the present application.

The above is only a preferred embodiment of the present application, and is not intended to limit the scope of the patent application, and the equivalent structure or equivalent process transformations made by the specification and the drawings of the present application, or directly or indirectly applied to other related technical fields. The same is included in the scope of patent protection of this application.

Claims

A security monitoring method based on face recognition is applied to an electronic device, and the method comprises:

S1, receiving a user-initiated door opening request, waking up the camera device to capture a real-time image of the current user, pre-processing the real-time image to obtain a current user's face image;

S2: input the facial image into a predetermined facial occlusion detection system, and determine whether the facial image is occluded;

S3. If the facial image is not occluded, input the facial image into a predetermined regularly updated face recognition system, and identify one or more ID cards in the user information database that may match the facial image. Photo and corresponding matching probability;

S4. In the identified one or more ID card photos, take the photo of the ID card corresponding to the maximum probability as the photo of the ID card of the current user, and retrieve the identity information of the current user according to the photo of the ID card;

S5. Comparing the identity information of the current user with the blacklist. When the user identity information of the current user cannot match the information in the blacklist, the access control system is controlled to open; or, when the identity information of the current user matches the information in the blacklist. Or, when the facial image is occluded, the control access control system does not open the door.
The method for security monitoring based on face recognition according to claim 1, wherein the preprocessing in step S1 comprises:

Identifying a face region included in the real-time image by using a face recognition algorithm;

When the real-time image includes a face region, the face region is used as a face image of the current user, and the face image is saved according to a preset size; and

When the real-time image includes multiple face regions, the face region with the largest size is selected as the face image of the current user, and the face image is saved according to a preset size.
The face recognition-based security monitoring method according to claim 1, wherein the step S4 further comprises:

When the maximum value of the probability is greater than or equal to the first preset threshold, the photo of the ID card corresponding to the maximum value of the retention probability is taken as the photo of the ID card of the current user;

When the probability maximum value is less than the first preset threshold, the process returns to step S1.
The face recognition-based security monitoring method according to claim 2, wherein the step S4 further comprises:

When the maximum value of the probability is greater than or equal to the first preset threshold, the photo of the ID card corresponding to the maximum value of the retention probability is taken as the photo of the ID card of the current user;

When the probability maximum value is less than the first preset threshold, the process returns to step S1.
The face recognition-based security monitoring method according to claim 3 or 4, wherein the step S4 further comprises:

When the probability maximum value is greater than or equal to the second preset threshold, the facial image is added to the identity information of the current user in the user information database, and the face recognition system is updated every preset time interval, wherein The second preset threshold is greater than the first preset threshold.
The face recognition-based security monitoring method according to claim 5, wherein the step S2 comprises:

Identifying t facial feature points from the facial image, and determining an eye region and a lip region according to position information of the t facial feature points;

Determining the authenticity of the eye region and the lip region, and determining that the facial image is not occluded when the determination result of the eye region and the lip region is true; and

When the judgment result of the eye region and the lip region includes an unreality, it is determined that the facial image is occluded.
The face recognition-based security monitoring method according to claim 1 or 6, wherein the step S5 further comprises:

When the identity information of the current user matches the information in the blacklist, the user information of other users who are performing service processing in the security monitoring area is obtained, and the alert message is sent to the other users.
An electronic device, comprising: a memory, a processor, and an imaging device, wherein the memory includes a face recognition-based security monitoring program, and the security monitoring program is implemented by the processor to implement the following steps :

A. Receiving a user-initiated door opening request, waking up the camera device to take a real-time image of the current user, and pre-processing the real-time image to obtain a current user's face image;

B. input the facial image into a predetermined facial occlusion detection system, and determine whether the facial image is occluded;

C. If the facial image is not occluded, input the facial image into a predetermined regularly updated face recognition system, and identify one or more ID cards in the user information database that may correspond to the facial image. Photo and corresponding matching probability;

D. In the identified one or more ID card photos, take the photo of the ID card corresponding to the maximum probability as the current user's ID card photo, and retrieve the identity information of the current user according to the ID card photo;

E. Comparing the identity information of the current user with the blacklist. When the user identity information of the current user cannot match the information in the blacklist, the access control system is opened; or when the identity information of the current user matches the information in the blacklist. Or, when the facial image is occluded, the control access control system does not open the door.
The electronic device according to claim 8, wherein the preprocessing in the step A comprises:

Identifying a face region included in the real-time image by using a face recognition algorithm;

When the real-time image includes a face region, the face region is used as a face image of the current user, and the face image is saved according to a preset size; and

When the real-time image includes multiple face regions, the face region with the largest size is selected as the face image of the current user, and the face image is saved according to a preset size.
The electronic device according to claim 8, wherein the step D further comprises:

When the maximum value of the probability is greater than or equal to the first preset threshold, the photo of the ID card corresponding to the maximum value of the retention probability is taken as the photo of the ID card of the current user;

When the probability maximum value is less than the first preset threshold, return to step A.
The electronic device of claim 9, wherein the step D further comprises:

When the maximum value of the probability is greater than or equal to the first preset threshold, the photo of the ID card corresponding to the maximum value of the retention probability is taken as the photo of the ID card of the current user;

When the probability maximum value is less than the first preset threshold, return to step A.
The electronic device according to claim 10 or 11, wherein the step D further comprises:

When the probability maximum value is greater than or equal to the second preset threshold, the facial image is added to the identity information of the current user in the user information database, and the face recognition system is updated every preset time interval, wherein The second preset threshold is greater than the first preset threshold.
The electronic device of claim 12, wherein the step B comprises:

Identifying t facial feature points from the facial image, and determining an eye region and a lip region according to position information of the t facial feature points;

Determining the authenticity of the eye region and the lip region, and determining that the facial image is not occluded when the determination result of the eye region and the lip region is true; and

When the judgment result of the eye region and the lip region includes an unreality, it is determined that the facial image is occluded.
The electronic device according to claim 8 or 13, wherein the step E further comprises:

When the identity information of the current user matches the information in the blacklist, the user information of other users who are performing service processing in the security monitoring area is obtained, and the alert message is sent to the other users.
A computer readable storage medium, characterized in that the computer readable storage medium comprises a face recognition based security monitoring program, and when the security monitoring program is executed by the processor, the following steps are implemented:

A. Receiving a user-initiated door opening request, waking up the camera device to take a real-time image of the current user, and pre-processing the real-time image to obtain a current user's face image;

B. input the facial image into a predetermined facial occlusion detection system, and determine whether the facial image is occluded;

C. If the facial image is not occluded, input the facial image into a predetermined regularly updated face recognition system, and identify one or more ID cards in the user information database that may correspond to the facial image. Photo and corresponding matching probability;

D. In the identified one or more ID card photos, take the photo of the ID card corresponding to the maximum probability as the current user's ID card photo, and retrieve the identity information of the current user according to the ID card photo;

E. Comparing the identity information of the current user with the blacklist. When the user identity information of the current user cannot match the information in the blacklist, the access control system is opened; or when the identity information of the current user matches the information in the blacklist. Or, when the facial image is occluded, the control access control system does not open the door.
The computer readable storage medium of claim 15, wherein the preprocessing in step A comprises:

Identifying a face region included in the real-time image by using a face recognition algorithm;

When the real-time image includes a face region, the face region is used as a face image of the current user, and the face image is saved according to a preset size; and

When the real-time image includes multiple face regions, the face region with the largest size is selected as the face image of the current user, and the face image is saved according to a preset size.
The computer readable storage medium of claim 16, wherein the step D further comprises:

When the maximum value of the probability is greater than or equal to the first preset threshold, the photo of the ID card corresponding to the maximum value of the retention probability is taken as the photo of the ID card of the current user;

When the probability maximum value is less than the first preset threshold, return to step A.
The computer readable storage medium of claim 17, wherein the step D further comprises:

When the maximum value of the probability is greater than or equal to the first preset threshold, the photo of the ID card corresponding to the maximum value of the retention probability is taken as the photo of the ID card of the current user;

When the probability maximum value is less than the first preset threshold, return to step A.
The computer readable storage medium according to claim 17 or 18, wherein the step D further comprises:

When the probability maximum value is greater than or equal to the second preset threshold, the facial image is added to the identity information of the current user in the user information database, and the face recognition system is updated every preset time interval, wherein The second preset threshold is greater than the first preset threshold.
The computer readable storage medium of claim 19, wherein said step B comprises:

Identifying t facial feature points from the facial image, and determining an eye region and a lip region according to position information of the t facial feature points;

Determining the authenticity of the eye region and the lip region, and determining that the facial image is not occluded when the determination result of the eye region and the lip region is true; and

When the judgment result of the eye region and the lip region includes an unreality, it is determined that the facial image is occluded.