WO2019134346A1

WO2019134346A1 - Face recognition method, application server, and computer-readable storage medium

Info

Publication number: WO2019134346A1
Application number: PCT/CN2018/090908
Authority: WO
Inventors: 李影
Original assignee: 平安科技（深圳）有限公司
Priority date: 2018-01-08
Filing date: 2018-06-12
Publication date: 2019-07-11
Also published as: CN108269333A

Abstract

A face recognition method, an application server, and a computer-readable storage medium. The method comprises: extracting a moving object video acquired by at least one camera (400); converting the moving object video into a face image frame (402); comparing the face image frame with a sample in a server to determine whether the image is valid (404); if yes, identity recognition succeeding, and opening the door (406); and if not, the identity recognition failing (408). A moving object video acquired by a camera can be parsed and converted into a face image by means of an execution server, and then the face image is compared with sample data, thereby implementing real-time capture and improving the efficiency of face image acquisition; attendance checking is completed without employees noticing, thereby achieving humanized design and human feeling.

Description

Face recognition method, application server and computer readable storage medium

This application claims priority to Chinese Patent Application No. 201810014831.2, entitled "Face Recognition Method, Application Server, and Computer Readable Storage Media", filed on January 8, 2018, the entire contents of which are hereby incorporated by reference. The citations are incorporated herein by reference.

Technical field

The present application relates to the field of face recognition technologies, and in particular, to a face recognition method, an application server, and a computer readable storage medium.

Background technique

Face recognition technology is a biometric recognition technology based on human facial feature information, which mainly includes face detection and face recognition. In the field of face pattern recognition, face recognition technology has developed rapidly, and there have been corresponding practical applications, such as face recognition based access control systems, attendance machines, face registration and so on. At present, the accuracy of face recognition can reach more than 90%.

At present, many face recognition-based attendances are used to fix face positions by fixing the camera position. However, in the existing face attendance technology, employees are required to collect faces in a specified position. The image, which leads to a poor customer experience, and the recognition efficiency and accuracy of the face is not very high.

Summary of the invention

In view of this, the present application provides a face recognition method, an application server, and a computer readable storage medium to solve the problem of poor customer experience, low recognition rate and accuracy, and lack of intelligence in the existing face recognition technology. problem.

First, in order to achieve the above object, the present application provides a face recognition method, the method comprising the steps of:

Extracting a video of a moving object collected by at least one camera;

Converting the moving object video into a face image frame;

Comparing the face image frame with a sample in the server to determine whether it is a valid image;

If yes, the identification is passed and the access control is opened; and

If no, the identification fails.

In addition, in order to achieve the above object, the present application further provides an application server, including a memory and a processor, where the memory stores a face recognition system operable on the processor, where the face recognition system is The steps of the face recognition method as described above are implemented when the processor is executed.

Further, in order to achieve the above object, the present application further provides a computer readable storage medium storing a face recognition system, the face recognition system being executable by at least one processor to The at least one processor performs the steps of the face recognition method as described above.

Compared with the prior art, the face recognition method, the application server, and the computer readable storage medium provided by the present application may extract a video of a moving object collected by at least one camera, convert the video of the moving object into a face image frame, and The face image frame is compared with the sample in the server to determine whether it is a valid image. If yes, the identity is passed, the access control is opened, and if not, the identity recognition fails. The face recognition method of the present application is to perform a server to parse and convert a video of a moving object collected by a camera into a face image frame, and then compare the sample data with the sample data, thereby realizing real-time capturing and improving the efficiency of face image collection. Completing attendance without the staff's awareness, reflecting the humanized design and feelings.

DRAWINGS

1 is a schematic diagram of an optional hardware architecture of an application server of the present application;

2 is a schematic diagram of a program module of a first embodiment of the present applicant's face recognition system;

3 is a schematic diagram of a program module of a second embodiment of the present applicant's face recognition system;

4 is a schematic flow chart of the first embodiment of the present applicant's face recognition method;

Figure 5 is a schematic diagram of the refinement process of step S400 in Figure 4;

6 is a schematic flow chart of a second embodiment of the present applicant's face recognition method;

7 is a schematic flow chart of a third embodiment of the present applicant's face recognition method;

8 is a schematic flow chart of a fourth embodiment of a face recognition method according to the present invention;

FIG. 9 is a schematic flow chart of a fifth embodiment of a face recognition method according to the present invention.

Reference mark:

应用服务器application server	22
存储器Memory	1111
处理器processor	1212
网络接口Network Interface	1313
人脸识别系统 Face recognition system	200200
提取模块 Extraction module	201201
转换模块 Conversion module	202202
判断模块 Judgment module	203203
警报模块 Alarm module	301301

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

Detailed ways

In order to make the objects, technical solutions, and advantages of the present application more comprehensible, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It is understood that the specific embodiments described herein are merely illustrative of the application and are not intended to be limiting. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments of the present application without departing from the inventive scope are the scope of the present application.

It should be noted that the descriptions of "first", "second" and the like in the present application are for the purpose of description only, and are not to be construed as indicating or implying their relative importance or implicitly indicating the number of technical features indicated. . Thus, features defining "first" or "second" may include at least one of the features, either explicitly or implicitly. In addition, the technical solutions between the various embodiments may be combined with each other, but must be based on the realization of those skilled in the art, and when the combination of the technical solutions is contradictory or impossible to implement, it should be considered that the combination of the technical solutions does not exist. Nor is it within the scope of protection required by this application.

Referring to FIG. 1, it is a schematic diagram of an optional hardware architecture of the application server 2 of the present application.

In this embodiment, the application server 2 may include, but is not limited to, the memory 11, the processor 12, and the network interface 13 being communicably connected to each other through a system bus. It is pointed out that Figure 1 only shows the application server 2 with components 11-13, but it should be understood that not all illustrated components may be implemented, and more or fewer components may be implemented instead.

The application server 2 may be a computing device such as a rack server, a blade server, a tower server, or a rack server. The application server 2 may be an independent server or a server cluster composed of multiple servers. .

The memory 11 includes at least one type of readable storage medium including a flash memory, a hard disk, a multimedia card, a card type memory (eg, SD or DX memory, etc.), a random access memory (RAM), a static Random access memory (SRAM), read only memory (ROM), electrically erasable programmable read only memory (EEPROM), programmable read only memory (PROM), magnetic memory, magnetic disk, optical disk, and the like. In some embodiments, the memory 11 may be an internal storage unit of the application server 2, such as a hard disk or memory of the application server 2. In other embodiments, the memory 11 may also be an external storage device of the application server 2, such as a plug-in hard disk equipped on the application server 2, a smart memory card (SMC), and a secure digital number. (Secure Digital, SD) card, flash card, etc. Of course, the memory 11 can also include both the internal storage unit of the application server 2 and its external storage device. In this embodiment, the memory 11 is generally used to store an operating system installed in the application server 2 and various types of application software, such as program codes of the face recognition system 200. Further, the memory 11 can also be used to temporarily store various types of data that have been output or are to be output.

The processor 12 may be a Central Processing Unit (CPU), controller, microcontroller, microprocessor, or other data processing chip in some embodiments. The processor 12 is typically used to control the overall operation of the application server 2. In this embodiment, the processor 12 is configured to run program code or process data stored in the memory 11, such as running the face recognition system 200 and the like.

The network interface 13 may comprise a wireless network interface or a wired network interface, which is typically used to establish a communication connection between the application server 2 and other electronic devices.

So far, the hardware structure and functions of the devices related to this application have been described in detail. Hereinafter, various embodiments of the present application will be made based on the above description.

First, the present application proposes a face recognition system 200.

Referring to FIG. 2, it is a program module diagram of the first embodiment of the applicant's face recognition system 200.

In this embodiment, the face recognition system 200 includes a series of computer program instructions stored in the memory 11, and when the computer program instructions are executed by the processor 12, the face recognition operation of the embodiments of the present application can be implemented. . In some embodiments, the face recognition system 200 can be divided into one or more modules based on the particular operations implemented by the various portions of the computer program instructions. For example, in FIG. 2, the face recognition system 200 can be divided into an extraction module 201, a conversion module 202, and a determination module 203. among them:

The extraction module 201 is configured to extract a video of a moving object collected by at least one camera.

The conversion module 202 is configured to convert the video of the moving object into a face image frame.

Specifically, the extraction module 201 includes a detection unit 2011, an acquisition unit 2012, a determination unit 2013, and a photographing unit 2014 and an identification unit 2015. among them:

The detecting unit 2011 is configured to detect a moving object that appears within a monitoring range of the camera;

The obtaining unit 2012 is configured to acquire the video recognition unit 2014 of the moving object collected by the camera.

That is, when the detecting unit 2011 detects that a moving object appears within the monitoring range of the camera, the acquiring unit 2012 acquires a video of the moving object collected by the camera, and the server acquires the video of the moving object from the camera, and the identifying unit 2014 conversion module 202 The moving object video converts the face image frame.

The determining unit 2013 is configured to determine whether the camera is positioned to the face of the moving object; if yes, the shooting unit 2014 is configured to capture one or more of the face images; if not, the acquiring unit 2012, An overall video for acquiring the moving object collected by the camera;

The conversion module 202 is further configured to convert an entire video of the moving object into an overall image of the moving object;

The recognition unit 2015 is configured to recognize a face image from the entire image of the moving object.

That is to say, when the detecting unit 2011 detects that a moving object appears within the monitoring range of the camera, the face of the moving object is tracked by the camera, and the face range is accurately positioned, and a face image can be directly collected, or multiple pieces can be continuously collected. Face image. If the face is not tracked, the acquisition unit 2012 acquires the overall video of the moving object through the camera, the conversion module 202 converts the overall video of the moving object into an overall image, and the recognition unit 2014 recognizes the face image from the overall image, thereby recognizing the motion. The face of the object.

Optionally, if the face image is recognized from the video of the moving object, the converting module 202 is specifically configured to:

Converting a video of the moving object into a video frame;

Identifying a face in the video frame;

Obtaining a coordinate range of the face in the video frame;

An image of the coordinate range is intercepted.

Optionally, if the face image is recognized from the overall image of the moving object, the identifying unit 2015 is specifically configured to:

Identifying a face in the overall image of the moving object;

Obtaining a coordinate range of the face in the overall image;

An image of the coordinate range is intercepted.

In the present embodiment, when a face is recognized for the captured image, the image having the face is marked as a face image. The face image is collected based on the face detection algorithm, wherein the face detection refers to finding a face in a frame of images acquired by the camera, and obtaining a rectangular coordinate range of the face.

The face detection algorithm includes at least a traditional machine learning algorithm (such as SURF Cascade, etc.) and a deep learning based algorithm (such as Faster RCNN, MTCNN, etc.).

When the scanned face is converted into a face image, the face image is obtained by capturing a rectangular area from the video frame of the camera according to the coordinate range based on the rectangular coordinate range of the face when the face is detected.

Optionally, a plurality of cameras are mounted on the server. The cameras may be access doors or door accesses. The cameras may be located on different floors. The application is not limited herein.

Optionally, the server is further connected to the attendance server to record the attendance data into the attendance database in the attendance server. A sample picture of each employee is stored in the attendance database, and the number of sample pictures may be one or multiple, and multiple sample pictures may record facial image features of each expression of the employee.

Optionally, the server is also connected to the display screen to display the attendance information in real time, and if the employee attendance is successful, the employee's sample picture is also displayed.

Optionally, when the camera captures the video of the moving object, the illumination brightness needs to be lower than a preset threshold, that is, the face needs to be evenly received, and the face contour and the facial features can be recognized by the camera.

Optionally, when a plurality of cameras simultaneously capture video of a moving object, the actuator on the server processes the video of each camera, and within each actuator is an order in which the face image can be correctly captured.

Optionally, the acquisition range of the camera may be set by a parameter, and may be a full screen or a partial screen of the camera. The coverage of the screen is determined by the focal length, resolution, illumination, and the like of the camera lens. As long as the employee enters the collection range of the camera, You can record videos without limiting your employees' expressions, actions, and more. In addition, the present application does not limit the angle of the camera, that is, when acquiring the video of the moving object collected by the camera, the video can be obtained from different directions, from the front, the left side or the right side of the moving object, etc. Get a frontal face image, a left side face image, or a right side face image.

The determining module 203 is configured to compare the face image frame with the sample in the server to determine whether it is a valid image. If yes, the identification is passed, the access control is opened, and if not, the identification fails.

Specifically, the server intercepts the face image frame and compares the sample images in the attendance database, mainly comparing the similarity between the face image frame and the pre-stored sample image of the user, and determining whether the image similarity is greater than a preset. The threshold value, if yes, determines that the face image frame is a valid image, that is, the identity recognition is passed, the access control is opened, and conversely, the face image frame is determined to be an invalid image, that is, the identity recognition fails.

When the determination server intercepts the face image as a valid image, it indicates that the face image is recognized. With the present application, the face recognition can be completed within one second, so the impact on the employee's attendance time is very small.

The image frame of the mobile webcam is captured to compare the sample database with the intercepted face image to verify whether the sample library contains the captured face for identification and access control system shutdown. Obtained remote access control, efficient use of resources, efficient and stable access control identification system services. Achieved the goal of both quality and expansion.

Optionally, when the identification is passed, the employee information corresponding to the valid image is recorded into the attendance server, and the employee information includes: an employee name, an attendance time, a date, and an employee department.

Optionally, the attendance information of the employee can be displayed through the display. As shown in Figure X, in order to display the photo of the employee's attendance information, in Figure X, the top-down shows: employee name, sample photo, attendance time, date, and employee department.

Optionally, while the attendance information is displayed, the attendance information is also saved, and is connected to the attendance system to import the attendance data.

The attendance time can refer to the employee's working hours, off-duty time, lunch break time, overtime hours, and the like.

Optionally, the time that is correctly identified is taken as the attendance time of the employee.

Optionally, when a plurality of cameras capture video or images of the same moving object (employee), the time when the face image is first recognized as the effective image is taken as the attendance time.

When it is determined that the server intercepts the face image as an invalid image, it indicates that the face image is not recognized, and the attendance fails.

The application server provided in this embodiment extracts the video of the moving object collected by the at least one camera through the extraction module 201, and the conversion module 202 converts the video of the moving object into a face image frame, and the determining module 203 performs the image of the face image and the sample in the server. Alignment to determine whether it is a valid image, and if so, the identification is passed, the access control is opened, and if not, the identification fails. The application server of the present application parses and converts the video of the moving object collected by the camera into a face image, and then compares it with the sample data, so that the real-time capture and the efficiency of the face image collection are improved, and the employee is not aware of the state. Completion of attendance, reflecting the human design and feelings.

Referring to FIG. 3, it is a program module diagram of the second embodiment of the applicant's face recognition system 200. In this embodiment, the face system 200 includes an alarm module 301 in addition to the extraction module 201, the conversion module 202, and the determination module 203 in the first embodiment.

In the second embodiment, the determining module 203 is further configured to determine whether the number of times the recognition fails reaches a preset number of times threshold. If not, the trigger extraction module 201 extracts the moving object video collected by the at least one camera, and if so, triggers the alarm module 301 to generate an alarm to prompt the employee to be non-employee.

Specifically, if the determining module 203 determines that the employee identification fails within a preset number of times threshold, the system may be faulty, or the recognition of the sample picture fails due to the video shooting angle, and the motion object is re-extracted. Video, then get the face image and compare it with the sample image. If the judging module 203 determines that the threshold number of times exceeds the preset number of times and fails to identify the employee, it indicates that the employee is not likely to be an employee of the company, and an alarm is generated, which causes the attention of the relevant department.

The application server in this embodiment re-extracts the video of the moving object collected by the at least one camera when it is determined that the number of times the recognition fails does not reach the preset number of times threshold, otherwise, an alarm is generated to further improve the application server to recognize the face image. .

In addition, the present application also proposes a face recognition method.

Referring to FIG. 4, it is a schematic flowchart of the first embodiment of the present applicant's face recognition method. In this embodiment, the order of execution of the steps in the flowchart shown in FIG. 5 may be changed according to different requirements, and some steps may be omitted.

Step S400, extracting a moving object video collected by at least one camera.

Step S402, converting the video of the moving object into a face image frame.

Specifically, as shown in FIG. 5, step S400 further includes:

S501: detecting a moving object that appears within a monitoring range of the camera;

S502. Acquire a video of the moving object collected by a camera.

That is to say, when detecting a moving object appearing within the monitoring range of the camera, the video of the moving object is acquired by the camera, the server acquires the video of the moving object from the camera, and converts the moving object video into the face image frame.

As shown in FIG. 6, step S400 may further include:

S601: detecting a moving object that appears within a monitoring range of the camera;

S602, determining whether the camera is positioned to the face of the moving object; if yes, proceed to S603, and if not, proceed to S604;

S603. Take one or more of the face images;

S604. Acquire an overall video of the moving object collected by the camera.

S605. Convert an entire video of the moving object into an overall image of the moving object.

S606, recognizing a face image from the entire image of the moving object.

That is to say, when detecting a moving object appearing within the monitoring range of the camera, the face of the moving object is tracked by the camera, and the face range is accurately positioned, and a face image can be directly collected, or multiple face images can be continuously collected. . If the face is not tracked, the entire video of the moving object is acquired by the camera, the overall video of the moving object is converted into an overall image, and the face image is recognized from the overall image, thereby identifying the face of the moving object.

As shown in FIG. 7, if a face image is recognized from a video of a moving object, the process is as follows:

S701. Convert a video of the moving object into a video frame.

S702. Identify a human face in the video frame.

S703. Acquire a coordinate range of the face in the video frame.

S704, intercepting an image of the coordinate range.

As shown in FIG. 8, if a face image is recognized from the entire image of the moving object, the process is as follows:

S801, identifying a face in the overall image of the moving object;

S802. Acquire a coordinate range of the face in the overall image.

S803, intercepting an image of the coordinate range.

Step S404, comparing the face image frame with the sample in the server to determine whether it is a valid image. If yes, go to step S406, if no, go to step 408.

Specifically, the server intercepts the face image frame and compares the sample images in the attendance database, mainly comparing the similarity between the face image frame and the pre-stored sample image of the user, and determining whether the image similarity is greater than a preset. The threshold value, if yes, determines that the face image frame is a valid image, and proceeds to step 404, and conversely determines that the face image frame is an invalid image, and proceeds to step 406.

Step S404, the identity recognition is passed, and the access control is opened.

Specifically, when the determination server intercepts the face image as a valid image, it indicates that the face image is recognized. With the present application, the face recognition can be completed within one second, so the impact on the employee's attendance time is very small.

In step S406, the identity recognition fails.

Specifically, when it is determined that the server intercepts the face image as an invalid image, it indicates that the face image is not recognized, and the attendance fails.

As shown in FIG. 9, after step 406, the method further includes:

S901. Determine whether the number of times the recognition fails reaches a preset number of times threshold. If not, the process proceeds to S902, and if so, the process proceeds to S903.

S902. Extract the video of the moving object collected by at least one camera.

S903, an alarm is generated to prompt the employee of the company.

Specifically, if the employee fails to be identified within the preset number of times threshold, the system may be faulty, or the recognition of the sample picture fails due to the video shooting angle, and the video of the moving object is re-extracted, and then acquired. The face image is compared with the sample image. If the employee exceeds the preset number of thresholds and fails to identify the employee, it indicates that the employee is not likely to be a member of the company, and an alarm is generated, which causes the attention of the relevant department.

In the face recognition method provided by the embodiment, the video of the moving object collected by the at least one camera is extracted, the video of the moving object is converted into a face image frame, and the face image frame is compared with the sample in the server to determine whether it is A valid image, if yes, the identity is passed, the access is opened, and if not, the identification fails. The face recognition method of the present application is to perform a server to parse and convert a video of a moving object collected by a camera into a face image, and then compare the sample data with the sample data, thereby realizing real-time capturing and improving the efficiency of face image collection. The employee completed the attendance without being aware of it, reflecting the humanized design and feelings.

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, disk, The optical disc includes a number of instructions for causing a terminal device (which may be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to perform the methods described in 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 face recognition method is applied to an application server, and the method includes the steps of:

Extracting a video of a moving object collected by at least one camera;

Converting the moving object video into a face image frame;

Comparing the face image frame with a sample in the server to determine whether it is a valid image;

If yes, the identification is passed and the access control is opened; and

If no, the identification fails.
The method of claim 1 , wherein the step of extracting the video of the moving object collected by the at least one camera comprises:

Detecting moving objects that appear within the monitoring range of the camera;

Obtaining a video of the moving object collected by the camera.
The face recognition method according to claim 1, wherein the converting the video of the moving object to a face image frame comprises:

Converting a video of the moving object into a video frame;

Identifying a face in the video frame;

Obtaining a coordinate range of the face in the video frame;

An image of the coordinate range is intercepted.
The method of claim 1 , wherein the step of extracting the video of the moving object collected by the at least one camera comprises:

Detecting moving objects that appear within the monitoring range of the camera;

Determining whether the camera is positioned to a face of the moving object;

If yes, take one or more of the face images;

If not, acquiring an overall video of the moving object collected by the camera;

The step of converting the video of the moving object into a face image frame includes:

Converting an overall video of the moving object into an overall image of the moving object;

A face image is recognized from the entire image of the moving object.
The face recognition method according to claim 4, wherein the step of recognizing the face image from the entire image of the moving object comprises:

Identifying a face in the overall image of the moving object;

Obtaining a coordinate range of the face in the overall image;

An image of the coordinate range is intercepted.
The face recognition method according to any one of claims 1 to 5, wherein the face image frame is compared with a sample in the server to determine whether it is a valid image, and specifically includes:

Comparing the face image frame with the pre-stored picture similarity of the sample image of the user, determining whether the picture similarity is greater than a preset threshold.
The face recognition method according to claim 6, wherein the method further comprises the following steps after the identity recognition is passed and the access control is opened:

Entering the employee information corresponding to the valid image into the attendance server;

The employee's attendance information is displayed through the display.
The face recognition method according to claim 6, wherein the method further comprises the following steps after the identity recognition fails:

Determining whether the number of failed recognitions reaches a preset number of times threshold;

If not, the video of the moving object collected by at least one camera is extracted.

If yes, an alert is generated to alert the employee who is not a member of the company.
An application server, comprising: a memory, a processor, wherein the memory stores a face recognition system operable on the processor, the face recognition system being the processor The following steps are implemented during execution:

Extracting a video of a moving object collected by at least one camera;

Converting the moving object video into a face image frame;

Comparing the face image frame with a sample in the server to determine whether it is a valid image;

If yes, the identification is passed and the access control is opened; and

If no, the identification fails.
The application server according to claim 9, wherein the step of extracting the video of the moving object collected by the at least one camera comprises:

Detecting moving objects that appear within the monitoring range of the camera;

Obtaining a video of the moving object collected by the camera.
The application server according to claim 9, wherein the converting the moving object video into a face image frame comprises:

Converting a video of the moving object into a video frame;

Identifying a face in the video frame;

Obtaining a coordinate range of the face in the video frame;

An image of the coordinate range is intercepted.
The application server according to claim 9, wherein the step of extracting the video of the moving object collected by the at least one camera comprises:

Detecting moving objects that appear within the monitoring range of the camera;

Determining whether the camera is positioned to a face of the moving object;

If yes, take one or more of the face images;

If not, acquiring an overall video of the moving object collected by the camera;

The step of converting the video of the moving object into a face image frame includes:

Converting an overall video of the moving object into an overall image of the moving object;

A face image is recognized from the entire image of the moving object.
The application server according to claim 12, wherein the step of recognizing the face image from the entire image of the moving object comprises:

Identifying a face in the overall image of the moving object;

Obtaining a coordinate range of the face in the overall image;

An image of the coordinate range is intercepted.
The application server according to any one of claims 9 to 13, wherein the comparing the face image frame with the sample in the server to determine whether it is a valid image comprises:

Comparing the face image frame with the pre-stored picture similarity of the sample image of the user, determining whether the picture similarity is greater than a preset threshold.
The application server according to claim 14, wherein the method further comprises the following steps after the identity recognition is passed and the access control is opened:

Entering the employee information corresponding to the valid image into the attendance server;

The employee's attendance information is displayed through the display.
The application server according to claim 14, wherein after the identity failure, the method further comprises the steps of:

Determining whether the number of failed recognitions reaches a preset number of times threshold;

If not, the video of the moving object collected by at least one camera is extracted.

If yes, an alert is generated to alert the employee who is not a member of the company.
A computer readable storage medium storing a face recognition system, the face recognition system being executable by at least one processor to cause the at least one processor to perform the following steps:

Extracting a video of a moving object collected by at least one camera;

Converting the moving object video into a face image frame;

Comparing the face image frame with a sample in the server to determine whether it is a valid image;

If yes, the identification is passed and the access control is opened; and

If no, the identification fails.
The computer readable storage medium according to claim 17, wherein the step of extracting the video of the moving object collected by the at least one camera comprises:

Detecting moving objects that appear within the monitoring range of the camera;

Obtaining a video of the moving object collected by the camera.
The computer readable storage medium according to claim 17, wherein the converting the moving object video to a face image frame comprises:

Converting a video of the moving object into a video frame;

Identifying a face in the video frame;

Obtaining a coordinate range of the face in the video frame;

An image of the coordinate range is intercepted.
The computer readable storage medium according to claim 17, wherein the step of extracting the video of the moving object collected by the at least one camera comprises:

Detecting moving objects that appear within the monitoring range of the camera;

Determining whether the camera is positioned to a face of the moving object;

If yes, take one or more of the face images;

If not, acquiring an overall video of the moving object collected by the camera;

The step of converting the video of the moving object into a face image frame includes:

Converting an overall video of the moving object into an overall image of the moving object;

A face image is recognized from the entire image of the moving object.