Facial recognition-based anti-fake attendance management method, equipment and medium

Abstract

The invention discloses an anti-fake attendance management method and device based on face recognition and a medium, and the method comprises the steps: obtaining attendance face recognition frame data, and obtaining recognition frame data through key frame judgment based on the attendance face recognition frame data; performing facial contour delimiting on the recognition frame data to determine an image recognition boundary; obtaining environment boundary identification data through environment transition identification according to the image identification boundary; based on the environment boundary identification data, determining first attendance identification data through environment real-time state comparison; performing identification material judgment on the identification frame data to determine second attendance identification data; according to the first attendance recognition data and the second attendance recognition data, attendance management data are obtained through attendance parameter matching. According to the method, the technical problem that the behaviors of pretending card punching cannot be efficiently detected and managed is solved.

Description

Technical Field

[0001] The present application relates to the technical field of attendance analysis, and in particular to an anti-impersonation attendance management method, device and medium based on facial recognition. Background Art

[0002] Facial recognition uses a camera as an identification information acquisition device to obtain the facial image of the identification object in a non-contact manner, and completes the identification process through operations such as feature recognition. As the main way for companies or units to clock in and out, facial recognition can meet most of the basic needs of attendance clocking in and out.

[0003] The phenomenon of replacing punch-in and impersonating punch-in in other forms still exists in attendance clocking in, and for corporate clocking in with multiple application scenarios, it is more dependent on ordinary lenses or mobile phones, and it is impossible to effectively identify the impersonated attendance through pre-recorded videos and photos. In the above situation, accurate judgment is generally made through three-dimensional camera and infrared binocular liveness detection, but due to the inherent parameter limitations of attendance equipment, the existing technology cannot achieve efficient detection and management of impersonation of punch-in. Summary of the invention

[0004] The embodiments of the present application provide a facial recognition-based anti-impersonation attendance management method, device and medium, which solve the technical problem of being unable to efficiently detect and manage impersonation punch-in behaviors.

[0005] In a first aspect, an embodiment of the present application provides an anti-impersonation attendance management method based on facial recognition, characterized in that the method includes: acquiring attendance facial recognition frame data, and based on the attendance facial recognition frame data, obtaining recognition frame data through key frame frame judgment; performing facial contour delineation on the recognition frame data to determine the image recognition boundary line; according to the image recognition boundary line, obtaining environmental boundary recognition data through environmental transition recognition; based on the environmental boundary recognition data, determining the first attendance recognition data through real-time environmental status comparison; performing recognition material judgment on the recognition frame data to determine the second attendance recognition data; according to the first attendance recognition data and the second attendance recognition data, obtaining attendance management data through attendance parameter matching.

[0006] In one implementation of the present application, based on the attendance facial recognition frame data, identification frame data is obtained through key frame frame judgment, which specifically includes: performing facial feature recognition on the attendance facial recognition frame data to determine facial feature frame data containing facial features; based on the facial feature frame data, obtaining a key frame feature area threshold through feature area analysis; according to the key frame feature area threshold, threshold screening is performed on the facial feature frame data to obtain identification frame data.

[0007] In one implementation of the present application, facial contours are delineated on recognition frame data to determine an image recognition boundary line, specifically including: based on the recognition frame data, facial feature point data is determined by locating facial feature points; shape fitting is performed on the facial feature point data to obtain facial contour data; and recognition boundary line division is performed on the facial contour data to determine an image recognition boundary line.

[0008] In one implementation of the present application, according to the image recognition boundary line, environmental boundary recognition data is obtained through environmental transition recognition, which specifically includes: obtaining periodic attendance environment data, and performing environmental change analysis on the periodic attendance environment data to obtain attendance surrounding environment transition data; wherein the environmental change analysis includes light intensity change analysis and color block change analysis; defining the recognition range of the image recognition boundary line to determine the environmental transition recognition range; based on the environmental transition recognition range and the attendance surrounding environment transition data, obtaining environmental boundary recognition data through shadow state analysis.

[0009] In one implementation of the present application, based on the environmental boundary identification data, the first attendance identification data is determined by comparing the real-time state of the environment, specifically including: comparing the environmental boundary identification data with the environmental side light intensity to determine the first real-time environmental state; converting the facial side data of the environmental boundary identification data into a grayscale state to obtain edge grayscale data; determining the second real-time environmental state through current brightness analysis based on the edge grayscale data; determining the first attendance identification data based on the first real-time environmental state and the first real-time environmental state by comparing the brightness state.

[0010] In one implementation of the present application, an identification material judgment is performed on the identification frame data to determine the second attendance identification data, specifically including: performing a shadow change judgment on the identification frame data, and when the shadow change judgment result is normal, performing an identification material judgment on the identification frame data to obtain an identification material judgment result; wherein the identification material judgment includes: photos, videos, and paper; when the identification judgment result is abnormal, marking the identification frame data for an abnormal state to determine the second attendance identification data; when the identification judgment result is normal, marking the identification frame data for a normal state to determine the second attendance identification data; when the shadow change judgment result is abnormal, marking the identification frame data for an abnormal state to determine the second attendance identification data.

[0011] In one implementation of the present application, material identification is performed on identification frame data to obtain a material identification result, specifically including: performing reflected light identification on the identification frame data to determine a first material identification result; based on the first material identification result, obtaining a second material identification result through texture feature identification; based on the second material judgment result, obtaining a third material judgment result through frame rate difference determination; obtaining a material identification result based on the first material identification result or the second material identification result or the third material identification result.

[0012] In one implementation of the present application, after obtaining the attendance management data by matching the attendance parameters according to the first attendance identification data and the second attendance identification data, the method further includes: performing attendance status statistics on the attendance management data to obtain an attendance information table; based on the attendance information table, determining the attendance exception data by attendance exception matching; binding the attendance exception data to the attendance relationship to determine the periodic attendance data; wherein the periodic attendance data includes: the unit to which the attendance personnel belongs, periodic attendance exception data, periodic leave data, and attendance exception change data.

[0013] In a second aspect, an embodiment of the present application also provides an anti-impersonation attendance management device based on facial recognition, characterized in that the device includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can: obtain attendance facial recognition frame data, and based on the attendance facial recognition frame data, obtain recognition frame data through key frame frame determination; perform facial contour delineation on the recognition frame data to determine the image recognition boundary line; according to the image recognition boundary line, obtain environmental boundary recognition data through environmental transition recognition; based on the environmental boundary recognition data, determine the first attendance recognition data through real-time environmental status comparison; perform recognition material determination on the recognition frame data to determine the second attendance recognition data; obtain attendance management data through attendance parameter matching based on the first attendance recognition data and the second attendance recognition data.

[0014] In a third aspect, an embodiment of the present application also provides a non-volatile computer storage medium for anti-impersonation attendance management based on facial recognition, storing computer executable instructions, characterized in that the computer executable instructions are set to: obtain attendance facial recognition frame data, and based on the attendance facial recognition frame data, obtain recognition frame data through key frame frame judgment; perform facial contour delineation on the recognition frame data to determine the image recognition boundary line; according to the image recognition boundary line, obtain environmental boundary recognition data through environmental transition recognition; based on the environmental boundary recognition data, determine the first attendance recognition data through real-time environmental status comparison; perform recognition material judgment on the recognition frame data to determine the second attendance recognition data; according to the first attendance recognition data and the second attendance recognition data, obtain attendance management data through attendance parameter matching.

[0015] The embodiments of the present application provide an anti-impersonation attendance management method, device and medium based on facial recognition. By performing feature analysis on the natural state and the surrounding environment of the facial data of the attendance clock-in, the technical problem of being unable to efficiently detect and manage the impersonation clock-in behavior is solved, and the anti-impersonation of the attendance clock-in in different environments is achieved, thereby improving the accuracy of attendance facial recognition and the wide application of attendance equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0017] Figure 1 A flow chart of an anti-impersonation attendance management method based on facial recognition provided in an embodiment of the present application;

[0018] Figure 2 A schematic diagram of the internal structure of an anti-impersonation attendance management device based on facial recognition provided in an embodiment of the present application. DETAILED DESCRIPTION

[0019] In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution of the present application will be clearly and completely described below in combination with the specific embodiments of the present application and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present application.

[0020] The embodiments of the present application provide an anti-impersonation attendance management method, device and medium based on facial recognition. By performing feature analysis on the natural state and the surrounding environment of the facial data of the attendance clock-in, the technical problem of being unable to efficiently detect and manage the impersonation clock-in behavior is solved, and the anti-impersonation of the attendance clock-in in different environments is achieved, thereby improving the accuracy of attendance facial recognition and the wide application of attendance equipment.

[0021] The technical solution proposed in the embodiments of the present application is described in detail below with reference to the accompanying drawings.

[0022] Figure 1 A flowchart of an anti-impersonation attendance management method based on facial recognition is provided in an embodiment of the present application. Figure 1 As shown, an anti-impersonation attendance management method based on facial recognition provided by an embodiment of the present application specifically includes the following steps:

[0023] Step 101, acquiring attendance facial recognition frame data, and obtaining recognition frame data through key frame determination based on the attendance facial recognition frame data.

[0024] Specifically, it includes: performing facial feature recognition on attendance facial recognition frame data to determine facial feature frame data containing facial features; obtaining a key frame feature area threshold through feature area analysis based on the facial feature frame data; and performing threshold screening on the facial feature frame data according to the key frame feature area threshold to obtain recognition frame data.

[0025] The present application obtains attendance facial recognition frame data, and based on the attendance facial recognition frame data, obtains recognition frame data through key frame judgment, thereby realizing image screening of key recognition frames for the facial data obtained from attendance, thereby improving the accuracy and efficiency of attendance status recognition.

[0026] In the examples of the present application, detailed explanation is given by the following Example 1.

[0027] Example 1: Since daily attendance of various departments or units is performed through mobile phone apps or time clocks, in actual applications, high-precision lenses and algorithms are usually not used. This has a great impact on the analysis of attendance data.

[0028] The end of facial recognition is related to the recognition algorithm's determination of face recognition. During this time period or cycle, frame extraction is performed on the facial data within the time period to exclude invalid data or useless data with few facial features, and the frames with the most facial features and pixels (area) are screened to determine the recognition frame data.

[0029] It should be noted that the key frame feature area threshold can be set by the user or technician, or it can be set according to the actual computing power requirements based on real-time analysis of the feature area.

[0030] Step 102: Delineate the facial contour of the recognition frame data to determine the image recognition boundary line.

[0031] Specifically, it includes: based on the recognition frame data, determining the facial feature point data by locating the facial feature points; performing shape fitting on the facial feature point data to obtain the facial contour data; and dividing the facial contour data into recognition demarcation lines to determine the image recognition demarcation lines.

[0032] The present application defines the facial contour of the recognition frame data to determine the image recognition boundary line, thereby achieving the facial contour definition of the recognition frame data in attendance and providing a data basis for subsequent feature analysis thereof.

[0033] In the examples of the present application, detailed explanation is given by the following Example 2.

[0034] Example 2: In order to determine the authenticity of the detected facial image data and meet the limited computing power of the attendance system, analysis is performed based on the range of facial contours.

[0035] The facial detection and feature point location algorithm is used to extract the features of the facial contour from the recognition frame data and determine the facial feature point data; the facial feature point data is divided into recognition demarcation lines through the shape fitting method to obtain the image recognition demarcation line. The demarcation line is used to divide and distinguish the facial recognition area from the remaining surrounding environment area.

[0036] Step 103: Identify the boundary line according to the image and obtain environmental boundary recognition data through environmental transition recognition.

[0037] Specifically, it includes: obtaining periodic attendance environment data, and performing environmental change analysis on the periodic attendance environment data to obtain the transition data of the attendance environment; wherein, the environmental change analysis includes light intensity change analysis and color block change analysis; defining the recognition range of the image recognition boundary line to determine the environmental transition recognition range; based on the environmental transition recognition range and the attendance environment transition data, obtaining the environmental boundary recognition data through shadow state analysis.

[0038] This application obtains environmental boundary recognition data based on image recognition boundary lines through environmental transition recognition, realizes the boundary recognition of the face and the environment in the attendance image, improves the analysis efficiency of the attendance image, and reduces the computing power requirements.

[0039] In the examples of the present application, this is explained in detail through the following Example 3.

[0040] Example 3: Perform environmental change analysis on periodic attendance environment data, which is divided into light intensity change analysis and color block change analysis. Light intensity change analysis is used to detect dynamic changes in light in the image; color block change analysis is used to identify significant color blocks in the background and their change trends.

[0041] Based on the environmental transition recognition range and the transition data of the surrounding environment, shadow status analysis is performed. This includes identifying the shadow area, analyzing the depth, direction and other characteristics of the shadow, and distinguishing facial shadows from background shadows.

[0042] Combined with the analysis results of light intensity changes, color block changes, and shadow status analysis, the boundary between the face and the background environment is further refined to generate environmental boundary recognition data.

[0043] Step 104: Based on the environmental boundary identification data, the first attendance identification data is determined by comparing the real-time status of the environment.

[0044] Specifically, it includes: comparing the light intensity on the environmental side of the environmental boundary recognition data to determine the first real-time environmental state; converting the facial side data of the environmental boundary recognition data into a grayscale state to obtain edge grayscale data; determining the second real-time environmental state through current brightness analysis based on the edge grayscale data; and determining the first attendance recognition data through brightness state comparison based on the first real-time environmental state and the first real-time environmental state.

[0045] This application is based on environmental boundary identification data and determines the first attendance recognition data through real-time environmental status comparison, thereby realizing environmental status analysis on both sides of the contour in the facial data of attendance recognition and reducing the difficulty of identifying the authenticity of facial data.

[0046] In the examples of the present application, a detailed explanation is given by the following Example 4.

[0047] Example 4: Identify the boundary between the facial contour and the environment through environmental boundary recognition and extract environmental side data. Since the other side of the environmental transition recognition range is the range between the environment and the face, the first real-time environmental state is determined by comparing the environmental boundary recognition data with the environmental side light intensity.

[0048] This part is converted into grayscale, and the grayscale image is easier to analyze the brightness. The second real-time environmental state is determined through the current brightness analysis.

[0049] After knowing the relationship between the actual brightness and the image brightness, if the difference between the two is within a reasonable interpolation range, it can be determined whether it is a true attendance facial recognition. Otherwise, it will be identified as other abnormal conditions.

[0050] Step 105: Perform material determination on the recognition frame data to determine the second attendance recognition data.

[0051] Specifically, it includes: judging the shadow change of the recognition frame data, and when the shadow change judgment result is normal, judging the material of the recognition frame data to obtain the recognition material judgment result; wherein, the recognition material judgment includes: photos, videos, and paper; when the recognition judgment result is abnormal, marking the recognition frame data for an abnormal state to determine the second attendance recognition data; when the recognition judgment result is normal, marking the recognition frame data for a normal state to determine the second attendance recognition data; when the shadow change judgment result is abnormal, marking the recognition frame data for an abnormal state to determine the second attendance recognition data.

[0052] In one implementation of the present application, material identification is performed on identification frame data to obtain a material identification result, specifically including: performing reflected light identification on the identification frame data to determine a first material identification result; based on the first material identification result, obtaining a second material identification result through texture feature identification; based on the second material judgment result, obtaining a third material judgment result through frame rate difference determination; obtaining a material identification result based on the first material identification result or the second material identification result or the third material identification result.

[0053] This application realizes the recognition of the material of the recognition frame data to determine the second attendance recognition data.

[0054] Step 106: Obtain attendance management data by matching attendance parameters according to the first attendance identification data and the second attendance identification data.

[0055] After obtaining the attendance management data by matching the attendance parameters according to the first attendance identification data and the second attendance identification data, the method further includes: performing attendance status statistics on the attendance management data to obtain an attendance information table; determining the attendance exception data by attendance exception matching based on the attendance information table; and binding the attendance exception data to the attendance relationship to determine the periodic attendance data; wherein the periodic attendance data includes: the unit to which the attendance personnel belongs, periodic attendance exception data, periodic leave data, and attendance exception change data.

[0056] The present application obtains attendance management data based on the first attendance identification data and the second attendance identification data by matching attendance parameters, and analyzes the attendance management data to determine periodic attendance data, thereby realizing integrated management of the attendance data and improving the processing efficiency and accuracy of the attendance data.

[0057] In the examples of the present application, this is explained in detail through the following Example 5.

[0058] Example 5: Enterprise employees register their personal information in the system, including name, contact number, ID number, gender, employment status, employment form, etc., and upload high-definition facial photos as the basis for attendance comparison. The system supports operations such as adding, modifying, viewing, deleting, reviewing and invalidating employee information.

[0059] Bind employees to units, set employee attendance units and validity periods. If the employee attendance relationship is within the validity period, it is necessary to clock in and out at the unit.

[0060] Set attendance time, location, working days and other parameters; employees submit leave and make-up data, and the attendance is re-settled after approval by the leader.

[0061] When settling attendance, the employee punch-in data will be settled into four situations: normal, late, early leave, and absenteeism according to the set attendance time and working day, and then the employee attendance rate will be calculated based on the settlement situation.

[0062] Attendance rate (%) = actual number of attendees / number of expected attendees*100%;

[0063] Actual attendance number = number of people clocking in normally + number of people who are late + number of people who leave early + number of people whose leave requests are approved;

[0064] Number of people asking for leave = number of people whose leave requests have been approved. Failure to obtain leave approval is defined as absenteeism.

[0065] The above is an embodiment of the method proposed in this application. Based on the same inventive concept, the embodiment of this application also provides an anti-impersonation attendance management device based on facial recognition, and its structure is as follows: Figure 2 shown.

[0066] Figure 2 The following is a schematic diagram of the internal structure of an anti-impersonation attendance management device based on facial recognition provided in an embodiment of the present application. Figure 2 As shown, the device includes:

[0067] at least one processor 201;

[0068] and, a memory 202 communicatively connected to the at least one processor;

[0069] The memory 202 stores instructions that can be executed by at least one processor, and the instructions are executed by at least one processor 201 to enable at least one processor 201 to:

[0070] Acquire attendance facial recognition frame data, and based on the attendance facial recognition frame data, obtain recognition frame data through key frame judgment; perform facial contour delineation on the recognition frame data to determine the image recognition boundary line; obtain environmental boundary recognition data through environmental transition recognition based on the image recognition boundary line; determine the first attendance recognition data through real-time environmental status comparison based on the environmental boundary recognition data; perform recognition material judgment on the recognition frame data to determine the second attendance recognition data; obtain attendance management data through attendance parameter matching based on the first attendance recognition data and the second attendance recognition data.

[0071] Some embodiments of the present application provide corresponding Figure 1 A non-volatile computer storage medium for anti-impersonation attendance management based on facial recognition, storing computer executable instructions, wherein the computer executable instructions are set as:

[0072] Acquire attendance facial recognition frame data, and based on the attendance facial recognition frame data, obtain recognition frame data through key frame judgment; perform facial contour delineation on the recognition frame data to determine the image recognition boundary line; obtain environmental boundary recognition data through environmental transition recognition based on the image recognition boundary line; determine the first attendance recognition data through real-time environmental status comparison based on the environmental boundary recognition data; perform recognition material judgment on the recognition frame data to determine the second attendance recognition data; obtain attendance management data through attendance parameter matching based on the first attendance recognition data and the second attendance recognition data.

[0073] Each embodiment in this application is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the IoT device and medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiments.

[0074] The system and medium provided in the embodiments of the present application correspond one-to-one to the method. Therefore, the system and medium also have similar beneficial technical effects to the corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the system and medium will not be repeated here.

[0075] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0076] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0077] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0078] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0079] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0080] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0081] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, programs or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0082] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0083] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A facial recognition-based anti-impersonation attendance management method, characterized in that: The method comprises: Acquire attendance facial recognition frame data, and obtain recognition frame data through key frame determination based on the attendance facial recognition frame data; Delineating the facial contour of the recognition frame data to determine an image recognition boundary line; Recognize the boundary line according to the image, and obtain environmental boundary recognition data through environmental transition recognition; Based on the environmental boundary identification data, determining the first attendance identification data by comparing the real-time state of the environment; Performing identification material determination on the identification frame data to determine second attendance identification data; Attendance management data is obtained by matching attendance parameters according to the first attendance identification data and the second attendance identification data.

2. According to claim 1, a facial recognition-based anti-impersonation attendance management method is characterized in that: Based on the attendance facial recognition frame data, the recognition frame data is obtained through key frame determination, specifically including: Performing facial feature recognition on the attendance facial recognition frame data to determine facial feature frame data containing facial features; Based on the facial feature frame data, a key frame feature area threshold is obtained through feature area analysis; According to the key frame feature area threshold, the facial feature frame data is threshold screened to obtain the recognition frame data.

3. The anti-impersonation attendance management method based on facial recognition according to claim 1 is characterized in that: Delineating the facial contour of the recognition frame data to determine the image recognition boundary line specifically includes: Based on the recognition frame data, determine facial feature point data by locating facial feature points; Performing shape fitting on the facial feature point data to obtain facial contour data; The facial contour data is divided into recognition boundary lines to determine the image recognition boundary lines.

4. The anti-impersonation attendance management method based on facial recognition according to claim 1 is characterized in that: According to the image recognition boundary line, environmental boundary recognition data is obtained through environmental transition recognition, which specifically includes: Acquire periodic attendance environment data, and perform environmental change analysis on the periodic attendance environment data to obtain transition data of the attendance surrounding environment; wherein the environmental change analysis includes light intensity change analysis and color block change analysis; Delimiting the recognition range of the image recognition boundary line to determine the environmental transition recognition range; Based on the environment transition identification range and the attendance surrounding environment transition data, the environment boundary identification data is obtained through shadow state analysis.

5. The anti-impersonation attendance management method based on facial recognition according to claim 1 is characterized in that: Based on the environmental boundary identification data, the first attendance identification data is determined by comparing the real-time state of the environment, specifically including: Performing an environment-side light intensity comparison on the environment boundary identification data to determine a first real-time environment state; Converting the facial side data of the environmental boundary recognition data into a grayscale state to obtain edge grayscale data; Determine a second real-time environmental state through current brightness analysis based on the edge grayscale data; Based on the first real-time environmental state and the first real-time environmental state, the first attendance recognition data is determined by comparing the brightness states.

6. The anti-impersonation attendance management method based on facial recognition according to claim 1 is characterized in that: Performing identification material determination on the identification frame data to determine the second attendance identification data specifically includes: Performing shadow change judgment on the recognition frame data, and when the shadow change judgment result is normal, performing material recognition judgment on the recognition frame data to obtain a material recognition judgment result; wherein the material recognition judgment includes: photo, video, paper; In the case where the recognition judgment result is abnormal, marking the recognition frame data as abnormal to determine the second attendance recognition data; In the case where the recognition judgment result is normal, marking the recognition frame data as a normal state to determine the second attendance recognition data; When the shadow change judgment result is abnormal, the recognition frame data is marked as abnormal to determine the second attendance recognition data.

7. The anti-impersonation attendance management method based on facial recognition according to claim 6 is characterized in that: Performing material identification on the identification frame data to obtain a material identification result, specifically including: Performing reflected light recognition on the recognition frame data to determine a first recognition material determination result; Based on the first identified material judgment result, obtain a second material judgment result through texture feature recognition; According to the second material determination result, a third material determination result is obtained by determining the frame rate difference; The material recognition result is obtained based on the first material recognition result, the second material recognition result, or the third material recognition result.

8. The anti-impersonation attendance management method based on facial recognition according to claim 1 is characterized in that: After obtaining attendance management data by matching attendance parameters according to the first attendance identification data and the second attendance identification data, the method further includes: Performing attendance status statistics on the attendance management data to obtain an attendance information table; Based on the attendance information table, determining attendance abnormality data through attendance abnormality matching; The abnormal attendance data is bound to the attendance relationship to determine the periodic attendance data; wherein the periodic attendance data includes: the unit to which the attendance personnel belong, the abnormal periodic attendance data, the periodic leave data, and the abnormal attendance change data. 9.An anti-impersonation attendance management device based on facial recognition, characterized in that: The device comprises: at least one processor; and, a memory communicatively coupled to the at least one processor; The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to: Acquire attendance facial recognition frame data, and obtain recognition frame data through key frame determination based on the attendance facial recognition frame data; Delineating the facial contour of the recognition frame data to determine an image recognition boundary line; Recognize the boundary line according to the image, and obtain environmental boundary recognition data through environmental transition recognition; Based on the environmental boundary identification data, determining the first attendance identification data by comparing the real-time state of the environment; Performing identification material determination on the identification frame data to determine second attendance identification data; Attendance management data is obtained by matching attendance parameters according to the first attendance identification data and the second attendance identification data.

10. A non-volatile computer storage medium for anti-impersonation attendance management based on facial recognition, storing computer executable instructions, characterized in that: The computer executable instructions are configured to: Acquire attendance facial recognition frame data, and obtain recognition frame data through key frame determination based on the attendance facial recognition frame data; Delineating the facial contour of the recognition frame data to determine an image recognition boundary line; Recognize the boundary line according to the image, and obtain environmental boundary recognition data through environmental transition recognition; Based on the environmental boundary identification data, determining the first attendance identification data by comparing the real-time state of the environment; Performing identification material determination on the identification frame data to determine second attendance identification data; Attendance management data is obtained by matching attendance parameters according to the first attendance identification data and the second attendance identification data.

Images