An identity data recognition detection management system

Abstract

The present invention is applicable to the field of electronic digital data processing technology, and in particular to an identity data recognition detection management system, the system comprising: a video acquisition module for acquiring binocular camera video; a user identification module for determining the front and rear positions of the user and determining the user to be identified; an intention determination module for extracting continuous picture frames, making intention determinations based on the picture frames, and performing identity authentication when it is determined that there is an identity authentication intention; an identity authentication module for performing affine transformation according to the picture frames to obtain a conversion image, performing face recognition on the conversion image, and obtaining an identification result. The present invention uses a binocular camera to collect images of the user, and then uses a binocular depth algorithm to determine the front and rear positions of the user to determine the identified user, and then determines whether the user has the intention to perform identity authentication. Identity authentication is performed only when the identity authentication intention is detected, thereby avoiding the occurrence of misidentification.

Description

Technical Field

[0001] The invention belongs to the technical field of electronic digital data processing, and in particular relates to an identity data recognition detection management system. Background Art

[0002] Face recognition is a biometric technology that identifies people based on their facial features. It uses a camera or camcorder to collect images or video streams containing faces, automatically detects and tracks faces in images, and then performs facial recognition on the detected faces. It is also commonly called portrait recognition or facial recognition.

[0003] The face recognition system mainly consists of four components: face image acquisition and detection, face image preprocessing, face image feature extraction, matching and recognition.

[0004] However, in the current identity recognition system, when a user passes by unintentionally, misidentification is prone to occur, that is, the current identity recognition system cannot determine whether the user has the intention to perform identity recognition. Summary of the invention

[0005] The purpose of the embodiments of the present invention is to provide an identity data recognition detection management system, aiming to solve the problem that the current identity recognition system cannot determine whether the user has the intention to perform identity recognition.

[0006] The embodiment of the present invention is implemented as follows: an identity data recognition detection management system, the system comprising:

[0007] A video acquisition module, used to acquire a binocular camera video, wherein the binocular camera video includes a first camera video and a second camera video;

[0008] A user identification module, used to determine the front and rear positions of the user according to the first camera video and the second camera video, and determine the user to be identified;

[0009] An intention determination module is used to extract continuous picture frames from the first camera video or the second camera video, determine the intention based on the picture frames, and perform identity authentication when it is determined that there is an identity authentication intention;

[0010] The identity authentication module is used to perform affine transformation according to the picture frame to obtain a transformed image, perform face recognition on the transformed image, and obtain a recognition result.

[0011] Preferably, the user identification module includes:

[0012] A picture extraction unit, used for extracting the picture to be identified from the first camera video and the second camera video in a timeline order;

[0013] A binocular distance measurement unit, used to calculate the distance between each user in the first camera video and the second camera video by using a binocular distance measurement method;

[0014] The user selection unit is used to sort the users according to the distance and determine the user with the closest distance as the user to be identified.

[0015] Preferably, the intention determination module includes:

[0016] A picture frame extraction unit, used for randomly selecting the first camera video or the second camera video, and extracting picture frames at a preset time interval;

[0017] A viewing angle determination unit, used to identify the direction of the user's facial swing in the picture frame and determine whether the user's face is facing the video acquisition device;

[0018] The intention recognition unit is used to identify the user's eye position and calculate the time the user looks directly at the video acquisition device. When the preset time is reached, it is determined that there is an identity verification intention.

[0019] Preferably, the identity verification module includes:

[0020] A picture cropping unit, used for cropping the picture frame to retain only the user's facial data;

[0021] An image conversion unit, used to perform affine transformation according to the picture frame, correct the user's face, and obtain a converted image;

[0022] The identity recognition unit is used to recognize the converted image and determine whether there is a match with the preset data based on the recognition result. If so, it is determined that the identity authentication is passed.

[0023] Preferably, when identity verification fails, a prompt voice is issued.

[0024] Preferably, if there are multiple users to be identified, identity verification intention determination is performed on all users to be identified.

[0025] Preferably, when there are multiple users to be identified, the users to be identified are sorted, and identity authentication intentions are determined one by one according to the sorting.

[0026] Preferably, it is determined that there is no identity verification intention, and the user is prompted to look directly at the video acquisition device.

[0027] Preferably, when there are multiple users to be identified, they are sorted from left to right.

[0028] Another object of an embodiment of the present invention is to provide an identity data recognition detection management method, the method comprising:

[0029] Acquire a binocular camera video, where the binocular camera video includes a first camera video and a second camera video;

[0030] Determine the front and rear positions of the user according to the first camera video and the second camera video, and determine the user to be identified;

[0031] Extracting continuous picture frames from the first camera video or the second camera video, determining intent based on the picture frames, and performing identity verification when it is determined that there is an identity verification intent;

[0032] Affine transformation is performed on the picture frame to obtain a transformed image, and face recognition is performed on the transformed image to obtain a recognition result.

[0033] Preferably, the step of determining the front and rear positions of the user according to the first camera video and the second camera video, and determining the user to be identified, specifically includes:

[0034] Extracting the to-be-recognized images from the first camera video and the second camera video in a timeline order;

[0035] Calculate the distance between each user in the first camera video and the second camera video by using a binocular ranging method;

[0036] The users are sorted according to the distance, and the user with the closest distance is determined as the user to be identified.

[0037] Preferably, the step of extracting continuous picture frames from the first camera video or the second camera video and determining the intention based on the picture frames specifically includes:

[0038] Randomly select the first camera video or the second camera video, and extract picture frames according to a preset time interval;

[0039] Identify the direction of the user's facial swing in the picture frame and determine whether the user's face is facing the video acquisition device;

[0040] Identify the user's eye position and calculate the time the user looks directly at the video acquisition device. When the preset time is reached, determine that there is an identity verification intention.

[0041] Preferably, the step of performing affine transformation according to the picture frame to obtain a transformed image, and performing face recognition on the transformed image to obtain a recognition result specifically includes:

[0042] Crop the picture frame to keep only the user's facial data;

[0043] Perform affine transformation according to the picture frame, correct the user's face, and obtain a transformed image;

[0044] The converted image is recognized, and it is determined whether there is a match with the preset data based on the recognition result. If so, the identity verification is determined to be successful.

[0045] An identity data recognition detection and management system provided by an embodiment of the present invention utilizes a binocular camera to capture images of users, and then utilizes a binocular depth algorithm to determine the user's prior and subsequent positions to determine the identified user, and then determine whether the user has the intention to perform identity authentication. Identity authentication is performed only when the intention to perform identity authentication is detected, thereby avoiding the occurrence of misidentification. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 A flowchart of an identity data recognition detection management method provided by an embodiment of the present invention;

[0047] Figure 2 A flowchart of the steps of determining the front and rear positions of a user and determining a user to be identified based on a first camera video and a second camera video provided in an embodiment of the present invention;

[0048] Figure 3 A flowchart of the steps of extracting continuous picture frames from a first camera video or a second camera video and determining intention based on the picture frames provided by an embodiment of the present invention;

[0049] Figure 4 A flowchart of the steps of performing affine transformation according to a picture frame to obtain a transformed image, performing face recognition on the transformed image, and obtaining a recognition result provided by an embodiment of the present invention;

[0050] Figure 5 An architecture diagram of an identity data recognition detection management system provided by an embodiment of the present invention;

[0051] Figure 6 An architectural diagram of a user identification module provided by an embodiment of the present invention;

[0052] Figure 7 An architectural diagram of an intention determination module provided in an embodiment of the present invention;

[0053] Figure 8 An architecture diagram of an identity authentication module provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0054] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0055] The face recognition system mainly consists of four components: face image acquisition and detection, face image preprocessing, face image feature extraction, matching and recognition. However, in the current identity recognition system, when the user passes by unintentionally, it is easy to misidentify, that is, the current identity recognition system cannot determine whether the user has the intention to perform identity recognition.

[0056] The present invention utilizes a binocular camera to capture images of the user, and then utilizes a binocular depth algorithm to determine the user's prior and subsequent positions to determine the identified user, and then determines whether the user has the intention to perform identity authentication. Identity authentication is performed only when the identity authentication intention is detected, thereby avoiding the occurrence of misidentification.

[0057] like Figure 1 FIG. 1 is a flowchart of an identity data recognition detection management method provided by an embodiment of the present invention, the method comprising:

[0058] S100, obtaining a binocular camera video, where the binocular camera video includes a first camera video and a second camera video.

[0059] In this step, binocular camera video is obtained and video recording is performed using a binocular video acquisition device. The video acquisition device has two cameras with a fixed distance between the two cameras. The two cameras are used to shoot simultaneously to obtain videos of two perspectives, namely the first camera video and the second camera video.

[0060] S200, determining the front and rear positions of the user according to the first camera video and the second camera video, and determining the user to be identified.

[0061] In this step, the front and rear positions of the user are determined based on the first camera video and the second camera video. Since the distance between the cameras is a fixed value, the distance between the user and the camera can be calculated using the binocular ranging algorithm. When performing recognition, the user's eyes or other landmarks are first located, and then the binocular ranging algorithm is called to calculate the approximate distance between the user's eyes and the camera. At this time, the front and rear relationship between the user and the camera can be determined, and the user at the front can be used as the user to be identified.

[0062] S300, extracting continuous picture frames from the first camera video or the second camera video, determining the intention based on the picture frames, and performing identity verification when it is determined that there is an identity verification intention.

[0063] In this step, continuous picture frames are extracted from the first camera video or the second camera video. Since the first camera video or the second camera video shoots the same content but with different shooting angles, a random algorithm is used to determine which of the first camera video and the second camera video to process, and picture frames are extracted therefrom. In order to reduce the amount of data processing, the extraction can be performed in proportion. For example, if the frame rate of the video recording is 30 frames per second, 10 frames are extracted per second, and the extraction is performed at uniform intervals, with one frame extracted every two picture frames, to obtain picture frames. The facial orientation of the user in the picture frames is identified, and it is identified whether the user's eyes are looking directly at the camera. When the user's face is facing the camera and the eyes are looking directly at the camera for a certain period of time, it is determined that there is an identity authentication intention, and the identity authentication is started.

[0064] S400, performing affine transformation according to the picture frame to obtain a transformed image, performing face recognition on the transformed image to obtain a recognition result.

[0065] In this step, an affine transformation is performed based on the picture frame. Since the picture is easily distorted due to the camera and other reasons during the image acquisition process, the user's facial image is adjusted using affine transformation, and then the converted image is recognized using face recognition technology. The portrait database is queried based on the recognition result to determine whether there is a match. If so, it means that the user has permission and the identity verification is successful.

[0066] like Figure 2 As shown, as a preferred embodiment of the present invention, the step of determining the front and rear positions of the user according to the first camera video and the second camera video and determining the user to be identified specifically includes:

[0067] S201, extracting a to-be-recognized frame from the first camera video and the second camera video in a timeline order.

[0068] In this step, the picture to be identified is extracted from the first camera video and the second camera video in chronological order, the frame rates of the first camera video and the second camera video are identified, the frame rate extraction interval comparison table is queried, different picture extraction intervals are determined according to different frame rates, and then the picture is extracted to obtain the picture to be identified.

[0069] S202: Calculate the distance between each user in the first camera video and the second camera video by using a binocular ranging method.

[0070] In this step, the binocular ranging method is used to calculate the distance of each user in the first camera video and the second camera video. First, the position of each user in the first camera video and the second camera video is identified and marked, such as marking the user's eyes, so as to calculate the distance between each user and the camera using the binocular ranging method.

[0071] S203, sorting the users according to the distances, and determining the user with the closest distance as the user to be identified.

[0072] In this step, users are sorted according to distance. When multiple users have the same distance from the camera, they are treated as equal. Then, the relative order of the multiple users is randomly determined, and the user with the closest distance is determined as the user to be identified. If there are multiple users to be identified, the identity authentication intention is determined for all the users to be identified. When there are multiple users to be identified, the users to be identified are sorted, and the identity authentication intention is determined one by one according to the sorting. When there are multiple users to be identified, they are sorted from left to right.

[0073] like Figure 3 As shown, as a preferred embodiment of the present invention, the step of extracting continuous picture frames from the first camera video or the second camera video and determining the intention based on the picture frames specifically includes:

[0074] S301, randomly selecting a first camera video or a second camera video, and extracting picture frames at a preset time interval.

[0075] In this step, the first camera video or the second camera video is randomly selected, a random value is generated using a random algorithm, and the first camera video or the second camera video is selected according to the random value, and then the picture frame is extracted according to its frame rate.

[0076] S302, identifying the direction of the user's facial shaking in the picture frame, and determining whether the user's face is facing the video acquisition device.

[0077] In this step, the direction of the user's facial swing in the picture frame is identified, and the direction of the user's facial swing is determined by comparing the position of the user's face in two adjacent frames, and it is determined whether the user's face is facing the camera. Specifically, it can be determined by comparing the facial images corresponding to the same moment in the first camera video and the second camera video. For example, when the user's face is facing left, the pixels occupied by the left side of the face will be less than the pixels occupied by the right side of the face. Based on this, the angle between the user's face and the camera is calculated to obtain the first angle.

[0078] S303, identifying the user's eye position, calculating the time the user looks directly at the video acquisition device, and when the preset time is reached, determining that there is an identity verification intention.

[0079] In this step, the user's eye position is identified. Specifically, the user's eye image is extracted, the position distribution of the black and white parts of the user's eyes is identified, and the distribution positions of black pixels and white pixels are counted. When the black part is located in the middle of the white part, it means that the user is looking directly, so as to determine the angle of the user's line of sight according to the positional relationship between the black and white parts, and obtain a second angle. When the sum of the first angle and the second angle is less than a preset value, it is regarded that the user is looking directly at the video acquisition device. For example, if the first angle is 10° and the second angle is -10°, and the sum is 0, it means that the user is facing the camera and looking directly at the camera. Timing is performed, and when the preset time is reached, it is determined that there is an identity verification intention.

[0080] like Figure 4 As shown, as a preferred embodiment of the present invention, the steps of performing affine transformation according to the picture frame to obtain a transformed image, performing face recognition on the transformed image, and obtaining a recognition result specifically include:

[0081] S401, cropping the picture frame to retain only the user's facial data.

[0082] In this step, the picture frame is cropped. Specifically, the binocular positions of the user are identified, and then the size of the cropping frame is determined according to the number of pixels between the binoculars to retain the user's facial data.

[0083] S402, performing affine transformation according to the picture frame, correcting the user's face, and obtaining a transformed image.

[0084] S403, identifying the converted image, and judging whether there is a matching item in the preset data according to the identification result, and if so, judging that the identity authentication is passed.

[0085] In this step, an affine transformation is performed based on the picture frame to correct the user's face, and the converted image is recognized using a preset face recognition model to obtain a recognition result, and whether the verification is successful is determined based on the recognition result; when the identity authentication fails, a prompt voice is issued.

[0086] like Figure 5 As shown, an identity data recognition detection management system provided by an embodiment of the present invention includes:

[0087] The video acquisition module 100 is used to acquire a binocular camera video, where the binocular camera video includes a first camera video and a second camera video.

[0088] In this system, the video acquisition module 100 acquires binocular camera video and uses a binocular structure video acquisition device to record the video. The video acquisition device has two cameras, and the distance between the two cameras is fixed. The two cameras are used to shoot simultaneously to obtain videos from two perspectives, namely the first camera video and the second camera video.

[0089] The user identification module 200 is used to determine the front and rear positions of the user according to the first camera video and the second camera video, and determine the user to be identified.

[0090] In this system, the user identification module 200 determines the front and rear positions of the user based on the first camera video and the second camera video. Since the distance between the cameras is a fixed value, the distance between the user and the camera can be calculated using a binocular ranging algorithm. When performing identification, the user's eyes or other landmarks are first located, and the binocular ranging algorithm is called to calculate the approximate distance between the user's eyes and the camera. At this time, the front and rear relationship between the user and the camera can be determined, and the user at the front can be used as the user to be identified.

[0091] The intention determination module 300 is used to extract continuous picture frames from the first camera video or the second camera video, perform intention determination based on the picture frames, and perform identity verification when it is determined that there is an identity verification intention.

[0092] In the present system, the intention determination module 300 extracts continuous picture frames from the first camera video or the second camera video. Since the first camera video or the second camera video shoots the same content but with different shooting angles, a random algorithm is used to determine which of the first camera video and the second camera video to process and extract picture frames therefrom. In order to reduce the amount of data processing, the extraction can be performed in proportion. For example, if the frame rate of the video recording is 30 frames per second, 10 frames are extracted per second and extracted at uniform intervals, with one frame extracted every two picture frames to obtain a picture frame. The facial orientation of the user in the picture frame is identified, and it is identified whether the user's eyes are looking directly at the camera. When the user's face is facing the camera and the eyes are looking directly at the camera for a certain period of time, it is determined that there is an identity authentication intention and the identity authentication is started.

[0093] The identity authentication module 400 is used to perform affine transformation according to the picture frame to obtain a transformed image, and perform face recognition on the transformed image to obtain a recognition result.

[0094] In this system, the identity authentication module 400 performs an affine transformation based on the picture frame. Since the picture is easily distorted due to the camera and other reasons during the image acquisition process, the user's facial image is adjusted using affine transformation, and then the converted image is recognized using face recognition technology. The portrait database is queried based on the recognition result to determine whether there is a match. If so, it means that the user has the authority and the identity authentication is successful.

[0095] like Figure 6 As shown, as a preferred embodiment of the present invention, the user identification module 200 includes:

[0096] The picture extraction unit 201 is used to extract the pictures to be identified from the first camera video and the second camera video in time sequence.

[0097] In this module, the picture extraction unit 201 extracts the picture to be identified from the first camera video and the second camera video in the timeline order, identifies the frame rate of the first camera video and the second camera video, queries the frame rate extraction interval comparison table, determines different picture extraction intervals according to different frame rates, and then performs picture extraction to obtain the picture to be identified.

[0098] The binocular distance measurement unit 202 is used to calculate the distance between each user in the first camera video and the second camera video by using the binocular distance measurement method.

[0099] In this module, the binocular ranging unit 202 uses the binocular ranging method to calculate the distance of each user in the first camera video and the second camera video. First, the position of each user in the first camera video and the second camera video is identified and marked, such as marking the user's eyes, so as to calculate the distance between each user and the camera using the binocular ranging method.

[0100] The user selection unit 203 is used to sort the users according to the distance and determine the user with the closest distance as the user to be identified.

[0101] In this module, the user selection unit 203 sorts the users according to the distance. When there are multiple users with the same distance from the camera, they are treated as equal, and then the relative order of the multiple users is randomly determined, and the user with the closest distance is determined as the user to be identified; if there are multiple users to be identified, the identity authentication intention is determined for all the users to be identified; when there are multiple users to be identified, the users to be identified are sorted, and the identity authentication intention is determined one by one according to the sorting; when there are multiple users to be identified, they are sorted in order from left to right.

[0102] like Figure 7 As shown, as a preferred embodiment of the present invention, the intention determination module 300 includes:

[0103] The picture frame extraction unit 301 is used to randomly select the first camera video or the second camera video and extract the picture frames at a preset time interval.

[0104] In this module, the picture frame extraction unit 301 randomly selects the first camera video or the second camera video, generates a random value using a random algorithm, determines whether to select the first camera video or the second camera video according to the random value, and then extracts the picture frame according to its frame rate.

[0105] The viewing angle determination unit 302 is used to identify the direction of the user's facial swing in the picture frame and determine whether the user's face is facing the video acquisition device.

[0106] In this module, the viewing angle determination unit 302 identifies the direction of the user's facial swing in the picture frame, and determines the direction of the user's facial swing by comparing the position of the user's face in two adjacent frames, and determines whether the user's face is facing the camera. Specifically, it can be determined by comparing the facial images corresponding to the same moment in the first camera video and the second camera video. For example, when the user's face is facing left, the pixels occupied by the left side of the face will be less than the pixels occupied by the right side of the face. Based on this, the angle between the user's face and the camera is calculated to obtain the first angle.

[0107] The intention recognition unit 303 is used to recognize the user's eye position and calculate the time the user looks directly at the video acquisition device. When the preset time is reached, it is determined that there is an identity verification intention.

[0108] In this module, the intention recognition unit 303 identifies the user's eye position. Specifically, it extracts the user's eye image, identifies the position distribution of the black and white parts of the user's eyes, and counts the distribution positions of black pixels and white pixels. When the black part is located in the middle of the white part, it means that the user is looking directly, so as to determine the angle of the user's line of sight according to the positional relationship between the black and white parts, and obtain a second angle. When the sum of the first angle and the second angle is less than a preset value, it is regarded that the user is looking directly at the video acquisition device. For example, if the first angle is 10° and the second angle is -10°, and the sum is 0, it means that the user is facing the camera and looking directly at the camera. Timing is performed, and when the preset time is reached, it is determined that there is an identity verification intention.

[0109] like Figure 8 As shown, as a preferred embodiment of the present invention, the identity authentication module 400 includes:

[0110] The image cropping unit 401 is used to crop the image frame to retain only the user's facial data.

[0111] The image conversion unit 402 is used to perform affine transformation according to the picture frame, correct the user's face, and obtain a converted image.

[0112] In this module, the picture frame is cropped. Specifically, the binocular positions of the user are identified, and then the size of the cropping frame is determined according to the number of pixels between the binocular eyes to retain the user's facial data.

[0113] The identity recognition unit 403 is used to recognize the converted image and determine whether there is a matching item in the preset data according to the recognition result. If so, it is determined that the identity authentication is passed.

[0114] In this module, the identity recognition unit 403 performs affine transformation according to the picture frame, corrects the user's face, uses a preset face recognition model to perform image recognition on the converted image to obtain a recognition result, and determines whether the verification is passed based on the recognition result; when the identity authentication fails, a prompt voice is issued.

[0115] It should be understood that, although each step in the flow chart of each embodiment of the present invention is shown in sequence according to the indication of the arrow, these steps are not necessarily performed in sequence according to the order indicated by the arrow. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be performed in other orders. Moreover, at least a portion of the steps in each embodiment may include a plurality of sub-steps or a plurality of stages, and these sub-steps or stages are not necessarily performed at the same time, but can be performed at different times, and the execution order of these sub-steps or stages is not necessarily performed in sequence, but can be performed in turn or alternately with at least a portion of other steps or sub-steps or stages of other steps.

[0116] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0117] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0118] The above-mentioned embodiments only express several implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the patent of the present invention. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

[0119] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. An identity data recognition detection management system, characterized in that: The system comprises: A video acquisition module, used to acquire a binocular camera video, wherein the binocular camera video includes a first camera video and a second camera video; A user identification module, used to determine the front and rear positions of the user according to the first camera video and the second camera video, and determine the user to be identified; An intention determination module is used to extract continuous picture frames from the first camera video or the second camera video, determine the intention based on the picture frames, and perform identity authentication when it is determined that there is an identity authentication intention; The identity authentication module is used to perform affine transformation according to the picture frame to obtain a transformed image, perform face recognition on the transformed image, and obtain a recognition result; The intention determination module comprises: A picture frame extraction unit, used for randomly selecting the first camera video or the second camera video, and extracting picture frames at a preset time interval; A viewing angle determination unit, used to identify the direction of the user's facial swing in the picture frame and determine whether the user's face is facing the video acquisition device; The intention recognition unit is used to identify the user's eye position and calculate the time the user looks directly at the video acquisition device. When the preset time is reached, it is determined that there is an identity verification intention.

2. The identity data recognition detection management system according to claim 1, characterized in that: The user identification module comprises: A picture extraction unit, used for extracting the picture to be identified from the first camera video and the second camera video in a timeline order; A binocular distance measurement unit, used to calculate the distance between each user in the first camera video and the second camera video by using a binocular distance measurement method; The user selection unit is used to sort the users according to the distance and determine the user with the closest distance as the user to be identified.

3. The identity data recognition detection management system according to claim 1, characterized in that: The identity verification module comprises: A picture cropping unit, used for cropping the picture frame to retain only the user's facial data; An image conversion unit, used to perform affine transformation according to the picture frame, correct the user's face, and obtain a converted image; The identity recognition unit is used to recognize the converted image and determine whether there is a match with the preset data based on the recognition result. If so, it is determined that the identity authentication is passed.

4. The identity data recognition detection management system according to claim 1, characterized in that: When the identity verification fails, a prompt voice is issued.

5. The identity data recognition detection management system according to claim 1, characterized in that: If there are multiple users to be identified, identity authentication intention determination is performed on all users to be identified.

6. The identity data recognition detection management system according to claim 1, characterized in that: When there are multiple users to be identified, the users to be identified are sorted, and identity authentication intentions are determined one by one according to the sorting.

7. The identity data recognition detection management system according to claim 1, characterized in that: It is determined that there is no identity authentication intention, and the user is prompted to look directly at the video acquisition device.

8. The identity data recognition detection management system according to claim 1, characterized in that: When there are multiple users to be identified, they are sorted from left to right.

Images