Face registration method and device based on 3D structured light camera

Abstract

A face registration method and device based on a 3D structured light camera, the method captures video stream data of a user's face through the 3D structured light camera; pushes the captured video stream data of the user's face into a server of an industrial computer system through an RTMP service; the host computer system acquires the video stream data of the user's face through the server of the industrial computer system, and according to the video stream data of the user's face, performs scanning and recognition processing on the user's face to complete user face registration; the industrial computer system performs live detection and picture quality detection on the registered user's face, and performs screenshot processing on the user's face picture that has passed the detection; the host computer system performs preliminary processing on the received screenshot and sends it to a cloud server; the cloud server registers the user's face according to the screenshot to complete user face registration and cloud backup. The application can adapt the 3D structured light camera to the Kirin system and realize fast and accurate face registration.

Description

Technical Field

[0001] This invention relates to the field of face recognition registration technology, specifically to a face registration method and apparatus based on a 3D structured light camera. Background Technology

[0002] Currently, there is an increasing demand for facial recognition gate access in subways. However, facial registration is generally implemented on self-service or semi-self-service ticket machines. Since these machines typically use the domestic Kylin system, there is a lack of 3D structured light cameras compatible with the Kylin system. Adapting to the Kylin system requires a significant amount of manpower to develop drivers and recognition algorithms, resulting in high efficiency and low cost.

[0003] In addition, traditional mobile phone registration requires the transmission of facial information over the internet, which poses a risk of data leakage. Furthermore, it is impossible to verify whether a person is a real person during mobile phone registration.

[0004] Therefore, how to invent a face registration method that enables 3D structured light cameras to be adapted to the Kylin system and achieve fast and accurate face registration has become an urgent problem to be solved. Summary of the Invention

[0005] Therefore, the present invention provides a face registration method and device based on a 3D structured light camera. This method enables the 3D structured light camera to be adapted to the Kylin system, achieving fast and accurate face registration.

[0006] To achieve the above objectives, the present invention provides the following technical solution: a face registration method based on a 3D structured light camera, comprising:

[0007] The 3D structured light camera is activated via the industrial control computer system; video stream data of the user's face is captured by the 3D structured light camera.

[0008] The industrial control computer system starts the RTMP service and pushes the captured video stream data of the user's face to the server of the industrial control computer system through the RTMP service;

[0009] When the video stream data of the user's face captured by the 3D structured light camera reaches the set requirements, the host computer system obtains the video stream data of the user's face through the server of the industrial control computer system; the host computer system scans and recognizes the user's face based on the video stream data of the user's face to complete the user's face registration.

[0010] The industrial control computer system performs liveness detection and image quality checks on registered users' faces through programmed settings to ensure that the registered users' facial information is authentic and valid.

[0011] The industrial control computer system takes a screenshot of the user's face image after completing the liveness detection and image quality detection, and sends the screenshot to the host computer system.

[0012] The host computer system will perform preliminary processing on the received screenshot and send the pre-processed screenshot to the cloud server;

[0013] The cloud server performs user face registration based on the received, pre-processed screenshot, completing user face registration and cloud backup.

[0014] As a preferred embodiment of a face registration method based on a 3D structured light camera, in the process of capturing the video stream data of a user's face through the 3D structured light camera, the video stream data includes color stream, infrared stream, and depth information stream data.

[0015] As a preferred solution for face registration based on a 3D structured light camera, in the process of the industrial control computer system performing liveness detection and image quality detection on the registered user's face through a set program, the set program is the liveness detection and image quality detection program of Baidu Face Recognition SDK.

[0016] As a preferred solution for a face registration method based on a 3D structured light camera, in the process of the industrial control computer system performing screenshot processing on the user's face image after the completion of the liveness detection and the image quality detection, the screenshot processing involves capturing a frame of color stream image data after the completion of the liveness detection and the image quality detection.

[0017] As a preferred embodiment of a face registration method based on a 3D structured light camera, during the initial processing of the received screenshot by the host computer system, the initial processing includes image cropping and image correction of the screenshot.

[0018] This invention also provides a face registration device based on a 3D structured light camera, and a face registration method based on a 3D structured light camera, comprising:

[0019] The face video data stream acquisition module is used to start the 3D structured light camera through the industrial control computer system; and to capture the video stream data of the user's face through the 3D structured light camera.

[0020] The video data stream push module is used by the industrial control computer system to start the RTMP service and push the captured video stream data of the user's face to the server of the industrial control computer system through the RTMP service.

[0021] The host computer system's face registration module is used to obtain the user's face video stream data through the industrial control computer system's server when the 3D structured light camera captures the video stream data of the user's face to the set requirements; the host computer system then scans and recognizes the user's face based on the video stream data of the user's face to complete the user's face registration.

[0022] The face registration information detection module is used by industrial control computer systems to perform liveness detection and image quality detection on the faces of registered users through programmed settings, so as to ensure that the face information of registered users is real and valid.

[0023] The user face screenshot processing module is used by the industrial control computer system to perform screenshot processing on the user face image that has completed the liveness detection and the image quality detection, and send the screenshot to the host computer system;

[0024] The screenshot preliminary processing module is used by the host computer system to perform preliminary processing on the received screenshots and send the pre-processed screenshots to the cloud server.

[0025] The cloud-based face registration module is used by the cloud server to register user faces based on the received, pre-processed screenshots, completing user face registration and cloud backup.

[0026] As a preferred embodiment of a face registration device based on a 3D structured light camera, in the face video data stream acquisition module, during the process of capturing the video stream data of the user's face through the 3D structured light camera, the video stream data includes color stream, infrared stream, and depth information stream data.

[0027] As a preferred embodiment of a face registration device based on a 3D structured light camera, in the face registration information detection module, during the process of the industrial control computer system performing liveness detection and image quality detection on the registered user's face through a set program, the set program is the liveness detection and image quality detection program of Baidu Face Recognition SDK.

[0028] As a preferred embodiment of a face registration device based on a 3D structured light camera, in the user face screenshot processing module, during the process of the industrial control computer system performing screenshot processing on the user face image after the completion of the liveness detection and the image quality detection, the screenshot processing involves capturing a frame of color stream image data after the completion of the liveness detection and the image quality detection.

[0029] As a preferred embodiment of a face registration device based on a 3D structured light camera, the preliminary screenshot processing module includes image cropping and image correction of the screenshot during the preliminary processing of the received screenshot by the host computer system.

[0030] This invention has the following advantages: A 3D structured light camera is started via an industrial control computer system; video stream data of the user's face is captured by the 3D structured light camera; the industrial control computer system starts an RTMP service and pushes the captured video stream data of the user's face to the server of the industrial control computer system via the RTMP service; when the video stream data of the user's face captured by the 3D structured light camera reaches a set requirement, the host computer system obtains the video stream data of the user's face through the server of the industrial control computer system; the host computer system scans the user's face based on the video stream data of the user's face. The system performs facial recognition and processing to complete user face registration. The industrial control computer system uses a programmed procedure to perform liveness detection and image quality checks on the registered user's face to ensure the authenticity and validity of the registered user's facial information. The industrial control computer system then takes a screenshot of the user's face image after liveness detection and image quality checks and sends the screenshot to the host computer system. The host computer system performs preliminary processing on the received screenshot and sends the pre-processed screenshot to the cloud server. The cloud server then performs user face registration based on the received pre-processed screenshot, completing user face registration and cloud backup. This invention enables 3D structured light cameras to be adapted to the Kylin system, achieving fast and accurate face registration and solving the problem of existing technologies requiring significant manpower to develop drivers and recognition algorithms for Kylin system adaptation. Attached Figure Description

[0031] To more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings in the following description are merely exemplary, and those skilled in the art can derive other embodiments based on the provided drawings without creative effort.

[0032] The structures, proportions, sizes, etc. illustrated in this specification are only for the purpose of assisting those skilled in the art in understanding and reading the content disclosed herein, and are not intended to limit the conditions under which the present invention can be implemented. Therefore, they have no substantial technical significance. Any modifications to the structure, changes in the proportions, or adjustments to the size, without affecting the effects and objectives that the present invention can produce, should still fall within the scope of the technical content disclosed in the present invention.

[0033] Figure 1 This is a schematic diagram of a face registration method based on a 3D structured light camera provided in Embodiment 1 of the present invention;

[0034] Figure 2 This is a schematic diagram illustrating the specific implementation process of a face registration method based on a 3D structured light camera provided in Embodiment 1 of the present invention;

[0035] Figure 3 This is a schematic diagram of the architecture of a face registration device based on a 3D structured light camera provided in Embodiment 2 of the present invention. Detailed Implementation

[0036] The following specific embodiments illustrate the implementation of the present invention. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0037] Example 1

[0038] See Figure 1 and Figure 2 Embodiment 1 of the present invention provides a face registration method based on a 3D structured light camera, comprising the following steps:

[0039] S1. Start the 3D structured light camera through the industrial control computer system; capture video stream data of the user's face through the 3D structured light camera;

[0040] S2. The industrial control computer system starts the RTMP service and pushes the captured video stream data of the user's face to the server of the industrial control computer system through the RTMP service.

[0041] S3. When the video stream data of the user's face captured by the 3D structured light camera reaches the set requirements, the host computer system obtains the video stream data of the user's face through the server of the industrial control computer system; the host computer system scans and recognizes the user's face based on the video stream data of the user's face to complete the user's face registration.

[0042] S4. The industrial control computer system performs liveness detection and image quality detection on the registered user's face through a set program to ensure that the registered user's facial information is authentic and valid.

[0043] S5. The industrial control computer system takes a screenshot of the user's face image after completing the liveness detection and image quality detection, and sends the screenshot to the host computer system.

[0044] S6. The host computer system performs preliminary processing on the received screenshot and sends the pre-processed screenshot to the cloud server;

[0045] S7. The cloud server performs user face registration based on the received, pre-processed screenshot, completing user face registration and cloud backup.

[0046] In this embodiment, in step S1, the 3D structured light camera is started through the industrial control computer system; the 3D structured light camera captures video stream data of the user's face;

[0047] The video stream data includes RGB (color) stream, IR (infrared) stream, and Deep (depth information) stream. This video stream data provides a rich and accurate data foundation for subsequent face recognition and liveness detection.

[0048] In this embodiment, in step S2, the industrial control computer system starts the RTMP service and pushes the captured video stream data of the user's face to the server of the industrial control computer system through the RTMP service;

[0049] Specifically, the industrial control computer system enables the RTMP (Real-time Message Transfer Protocol) service and pushes the captured RGB stream to a server started on the local machine, enabling remote users or systems to pull and preview the video stream in real time, thus enhancing the system's remote monitoring and interactive capabilities.

[0050] In this embodiment, in step S3, when the video stream data of the user's face captured by the 3D structured light camera reaches the set requirements, the host computer system obtains the video stream data of the user's face through the server of the industrial control computer system; the host computer system scans and recognizes the user's face based on the video stream data of the user's face to complete the user's face registration.

[0051] In this embodiment, in step S4, the industrial control computer system performs liveness detection and image quality detection on the registered user's face through a set program to ensure that the registered user's face information is authentic and valid.

[0052] Specifically, the industrial control computer system uses the liveness detection and image quality detection programs of Baidu's face recognition SDK to perform liveness detection and image quality detection on the registered user's face.

[0053] Specifically, the core program code for liveness detection is as follows:

[0054] / **

[0055] *Detection - Liveness Detection - Face Retrieval Process

[0056] *OparambdFaceImageConfig / / Visible light YUV data stream

[0057] *@parambaNirFaceImageConfig / / Infrared YUV data stream

[0058] *@parambdDepthFaceImageConfig / / Depth data stream

[0059] *@parambaFaceCheckConfig recognition parameters

[0060] *@param faceDetectCallBacK

[0061] /

[0062] public void onDetectcheck(finatBDFaceImageconfigbaFaceImageconfig,

[0063] final BDFaceInageconfigbaNirFaceImageconfig,

[0064] finatBDFaceImageConfigbdDepthFaceImageConfig,

[0065] final BDFacecheckConfigbdFaceCheckConfig,

[0066] final FaceDetectCalLBack faceDetectCallBack)".

[0067] Among them, faceDetectCallBack will call back the scores of RGB, NIR and Depth detection results;

[0068] Specifically, the core program code for image quality detection is as follows:

[0069] "void initQuality(final Context context,final StringblurModel,finalString occlurModel,final Callback callback)".

[0070] Here, blurModel is the blur detection model path, occlurModel is the occlusion detection model path, and callback is the detection result callback.

[0071] In this embodiment, in step S5, the industrial control computer system performs screenshot processing on the user's face image that has completed the liveness detection and the image quality detection, and sends the screenshot to the host computer system;

[0072] The screenshot processing involves capturing a frame of color stream image data after the liveness detection and image quality detection are completed.

[0073] Specifically, the screenshot processing captures a frame of RGB image data after liveness detection (including RGB liveness, NIR liveness, and Depth liveness) and RGB image quality detection.

[0074] The principle of liveness detection is to analyze the features of the collected facial information to determine whether the collected face is a real face and filter out photos or videos that are deceptive.

[0075] Specifically, RGB liveness detection analyzes flaws in captured human images, such as moiré patterns, imaging distortion, image quality, and reflectivity, and combines this with analysis of global features and local micro-texture information to effectively filter out fakes.

[0076] Near-infrared (NIR) in vivo detection utilizes the characteristics of near-infrared spectroscopy to detect biological tissues. By irradiating biological tissues with near-infrared light (NIR) and analyzing the reflected or transmitted light signals, structural and functional information about the biological tissues can be obtained.

[0077] Depth liveness detection achieves high-precision 3D face liveness detection by eliminating the influence of strong external interference factors (such as face occlusion, poor lighting, etc.) and multiple facial pose changes (such as side profile, expression, etc.).

[0078] In this embodiment, in step S6, the host computer system performs preliminary processing on the received screenshot and sends the pre-processed screenshot to the cloud server;

[0079] The preliminary processing includes cropping the screenshot and performing image correction.

[0080] Specifically, the preliminary processing involves cropping the RGB data obtained from the screenshot (highlighting facial data) and correcting the image (rotation, translation, scaling, flipping, etc.). The image cropping and correction processes themselves utilize existing technologies and will not be elaborated upon here.

[0081] In this embodiment, in step S7, the cloud server performs user face registration based on the received pre-processed screenshot, completing user face registration and cloud backup.

[0082] Specifically, the face registration process ends when the cloud server successfully receives and processes all registration information. This process not only completes the digital storage of the user's facial information but also achieves deep integration with the cloud system, providing strong technical support and data security for subsequent applications such as face recognition and identity verification.

[0083] In summary, this invention starts a 3D structured light camera via an industrial control computer system; captures video stream data of a user's face through the 3D structured light camera; the industrial control computer system starts an RTMP service and pushes the captured video stream data of the user's face to the server of the industrial control computer system through the RTMP service; when the video stream data of the user's face captured by the 3D structured light camera reaches a set requirement, the host computer system obtains the video stream data of the user's face through the server of the industrial control computer system; the host computer system scans the user's face based on the video stream data of the user's face and... The system performs facial recognition and registration to complete user face registration. An industrial control computer (ICC) system uses a programmed procedure to perform liveness detection and image quality checks on the registered user's face to ensure the authenticity and validity of the registered facial information. The ICC system then takes a screenshot of the user's face image after liveness detection and image quality checks and sends the screenshot to a host computer system. The host computer system performs preliminary processing on the received screenshot and sends it to a cloud server. The cloud server then performs user face registration based on the received preliminary-processed screenshot, completing both user face registration and cloud backup. This invention enables 3D structured light cameras to be adapted to the Kylin system, achieving fast and accurate face registration and solving the problem of existing technologies requiring significant manpower to develop drivers and recognition algorithms for Kylin system adaptation.

[0084] It should be noted that the method of this disclosure embodiment can be executed by a single device, such as a computer or server. The method of this embodiment can also be applied to a distributed scenario, where multiple devices cooperate to complete the task. In such a distributed scenario, one of these devices may execute only one or more steps of the method of this disclosure embodiment, and the multiple devices will interact with each other to complete the method described.

[0085] It should be noted that the above description describes some embodiments of this disclosure. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in a different order than that shown in the above embodiments and still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0086] Example 2

[0087] See Figure 3 Embodiment 2 of the present invention also provides a face registration device based on a 3D structured light camera, comprising:

[0088] The face video data stream acquisition module 001 is used to start the 3D structured light camera through the industrial control computer system; and to capture the video stream data of the user's face through the 3D structured light camera.

[0089] The video data stream push module 002 is used by the industrial control computer system to start the RTMP service and push the captured video stream data of the user's face to the server of the industrial control computer system through the RTMP service.

[0090] The host computer system face registration module 003 is used to obtain the video stream data of the user's face through the server of the industrial control computer system when the video stream data of the user's face captured by the 3D structured light camera reaches the set requirements; the host computer system scans and recognizes the user's face according to the video stream data of the user's face to complete the user's face registration.

[0091] The face registration information detection module 004 is used by the industrial control computer system to perform liveness detection and image quality detection on the faces of registered users through a set program, so as to ensure that the face information of registered users is real and valid.

[0092] The user face screenshot processing module 005 is used by the industrial control computer system to perform screenshot processing on the user face image that has completed the liveness detection and the image quality detection, and send the screenshot to the host computer system;

[0093] The screenshot preliminary processing module 006 is used by the host computer system to perform preliminary processing on the received screenshot and send the pre-processed screenshot to the cloud server.

[0094] The cloud-based face registration module 007 is used by the cloud server to register the user's face based on the received, pre-processed screenshot, thus completing the user's face registration and cloud backup.

[0095] In this embodiment, in the face video data stream acquisition module 001, during the process of capturing the video stream data of the user's face through the 3D structured light camera, the video stream data includes color stream, infrared stream and depth information stream data.

[0096] In this embodiment, in the face registration information detection module 004, during the process of the industrial control computer system performing liveness detection and image quality detection on the registered user's face through a set program, the set program is the liveness detection and image quality detection program of Baidu Face Recognition SDK.

[0097] In this embodiment, in the user face screenshot processing module 005, during the process of the industrial control computer system performing screenshot processing on the user face image after completing the liveness detection and image quality detection, the screenshot processing involves capturing a frame of color stream image data after the liveness detection and image quality detection are completed.

[0098] In this embodiment, in the screenshot preliminary processing module 006, during the process of the host computer system performing preliminary processing on the received screenshot, the preliminary processing includes image cropping and image correction processing on the screenshot.

[0099] It should be noted that the information interaction and execution process between the modules of the above system are based on the same concept as the method embodiment in Embodiment 1 of this application, and the resulting technical effects are the same as those in the method embodiment of this application. For details, please refer to the description in the method embodiment shown above in this application, and it will not be repeated here.

[0100] Example 3

[0101] Embodiment 3 of the present invention provides a non-transitory computer-readable storage medium storing program code for a face registration method based on a 3D structured light camera. The program code includes instructions for executing the face registration method based on a 3D structured light camera according to Embodiment 1 or any possible implementation thereof.

[0102] Computer-readable storage media can be any available medium that a computer can access, or a data storage device such as a server or data center that integrates one or more available media. The available medium can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., DVDs), or semiconductor media (e.g., solid-state drives, SSDs).

[0103] Example 4

[0104] Embodiment 4 of the present invention provides an electronic device, including: a memory and a processor;

[0105] The processor and the memory communicate with each other via a bus; the memory stores program instructions that can be executed by the processor, and the processor can execute a face registration method based on a 3D structured light camera according to Embodiment 1 or any possible implementation thereof by calling the program instructions.

[0106] Specifically, a processor can be implemented in hardware or software. When implemented in hardware, the processor can be a logic circuit, an integrated circuit, etc. When implemented in software, the processor can be a general-purpose processor that reads software code stored in memory. This memory can be integrated into the processor or located outside the processor and exist independently.

[0107] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of the present invention are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable system. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means.

[0108] It is obvious to those skilled in the art that the modules or steps of the present invention described above can be implemented using general-purpose computing systems. They can be centralized on a single computing system or distributed across a network of multiple computing systems. Optionally, they can be implemented using program code executable by a computing system, thereby storing them in a storage system for execution by the computing system. In some cases, the steps shown or described can be performed in a different order than those presented herein, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, the present invention is not limited to any particular combination of hardware and software.

[0109] Although the present invention has been described in detail above with general descriptions and specific embodiments, modifications or improvements can be made to it, which will be obvious to those skilled in the art. Therefore, all such modifications or improvements made without departing from the spirit of the present invention fall within the scope of protection claimed by the present invention.

Claims

1. A face registration method based on a 3D structured light camera, characterized in that, include: The 3D structured light camera is activated via the industrial control computer system; The 3D structured light camera captures video stream data of the user's face; The industrial control computer system runs on the Android system; The industrial control computer system starts the RTMP service and pushes the captured video stream data of the user's face to the server of the industrial control computer system through the RTMP service; When the video stream data of the user's face captured by the 3D structured light camera reaches the set requirements, the host computer system obtains the video stream data of the user's face through the server of the industrial control computer system. The host computer system scans and recognizes the user's face based on the video stream data of the user's face, and completes the user's face registration; the host computer system runs the domestic Kylin system; The industrial control computer system performs liveness detection and image quality checks on registered users' faces through programmed settings. The industrial control computer system takes a screenshot of the user's face image after completing the liveness detection and image quality detection, and sends the screenshot to the host computer system. The host computer system will perform preliminary processing on the received screenshot and send the pre-processed screenshot to the cloud server; The cloud server performs user face registration based on the received, pre-processed screenshot, completing user face registration and cloud backup; During the process of capturing the video stream data of the user's face through the 3D structured light camera, the video stream data includes color stream, infrared stream and depth information stream data; Liveness detection includes RGB liveness detection, NIR liveness detection, and Depth liveness detection.

2. The face registration method based on a 3D structured light camera according to claim 1, characterized in that, During the process of the industrial control computer system performing liveness detection and image quality detection on the registered user's face through a set program, the set program is the liveness detection and image quality detection program of Baidu Face Recognition SDK.

3. The face registration method based on a 3D structured light camera according to claim 2, characterized in that, During the process of the industrial control computer system taking a screenshot of the user's face image after the completion of the liveness detection and image quality detection, the screenshot process involves capturing a frame of color stream image data after the completion of the liveness detection and image quality detection.

4. The face registration method based on a 3D structured light camera according to claim 3, characterized in that, During the initial processing of the received screenshot by the host computer system, the initial processing includes image cropping and image correction of the screenshot.

5. A face registration device based on a 3D structured light camera, employing the face registration method based on a 3D structured light camera as described in any one of claims 1-4, characterized in that, include: The face video data stream acquisition module is used to start the 3D structured light camera through the industrial control computer system; The 3D structured light camera captures video stream data of the user's face; The industrial control computer system runs on the Android system; The video data stream push module is used by the industrial control computer system to start the RTMP service and push the captured video stream data of the user's face to the server of the industrial control computer system through the RTMP service. The host computer system's face registration module is used to obtain the user's face video stream data through the industrial control computer system's server when the 3D structured light camera captures the video stream data of the user's face to the set requirements. The host computer system scans and recognizes the user's face based on the video stream data of the user's face, and completes the user's face registration; the host computer system runs the domestic Kylin system; The face registration information detection module is used by industrial control computer systems to perform liveness detection and image quality detection on the faces of registered users through programmed settings. The user face screenshot processing module is used by the industrial control computer system to perform screenshot processing on the user face image that has completed the liveness detection and the image quality detection, and send the screenshot to the host computer system; The screenshot preliminary processing module is used by the host computer system to perform preliminary processing on the received screenshots and send the pre-processed screenshots to the cloud server. The cloud-based face registration module is used by the cloud server to register users' faces based on the received screenshots after preliminary processing, thereby completing user face registration and cloud backup. In the face video data stream acquisition module, during the process of capturing the video stream data of the user's face through the 3D structured light camera, the video stream data includes color stream, infrared stream and depth information stream data; Liveness detection includes RGB liveness detection, NIR liveness detection, and Depth liveness detection.

6. A face registration device based on a 3D structured light camera according to claim 5, characterized in that, In the face registration information detection module, during the process of the industrial control computer system performing liveness detection and image quality detection on the registered user's face through a set program, the set program is the liveness detection and image quality detection program of Baidu Face Recognition SDK.

7. A face registration device based on a 3D structured light camera according to claim 6, characterized in that, In the user face screenshot processing module, during the process of the industrial control computer system performing screenshot processing on the user face image after the completion of the liveness detection and the image quality detection, the screenshot processing involves capturing a frame of color stream image data after the completion of the liveness detection and the image quality detection.

8. A face registration device based on a 3D structured light camera according to claim 7, characterized in that, In the screenshot preliminary processing module, during the process of the host computer system performing preliminary processing on the received screenshot, the preliminary processing includes image cropping and image correction processing on the screenshot.

Images