Human face liveness detection method and device, processor and electronic device

Abstract

The present application discloses a method and device for detecting liveness of a face, a processor, and an electronic device, and relates to the field of artificial intelligence. The method comprises: receiving a target liveness detection request sent by a target client device; after receiving the target liveness detection request, randomly generating target luminescence information and target coordinate information, and sending the target luminescence information and target coordinate information to the target client device; after sending the target luminescence information and target coordinate information to the target client device, receiving eye image information of the target object returned by the target client device; analyzing the eye image information to determine the result of liveness detection of the target object's face. This application solves the problem in the related art of realizing liveness detection of the face through action instructions and user interaction, which leads to low accuracy of liveness detection of the face.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence, and more specifically, to a method and device for detecting live faces, a processor, and an electronic device. Background Art

[0002] Currently, facial recognition technology has been widely used in various industries and has achieved good results. However, with the increasing threat of various black market attacks and increasingly stringent regulatory requirements, further exploration and improvement of facial recognition's anti-attack detection capabilities are urgently needed.

[0003] Furthermore, the application of facial recognition technology primarily involves two steps: liveness detection and face recognition comparison. Only after a face is identified as a live person through liveness detection can it enter face recognition comparison to confirm the identity of the subject. Furthermore, liveness detection, in the conventional sense, refers to determining whether biometric information obtained from a legitimate user is obtained from a living person. Therefore, liveness detection primarily relies on identifying physiological information from living individuals. It uses physiological information as a vital sign to distinguish biometric features forged using inanimate materials such as flat photos, silicone, and plastic.

[0004] It can be seen that facial liveness detection is a key step in improving the security and reliability of facial recognition systems. Moreover, in recent years, with continuous breakthroughs in fields such as deep learning, big data, and cloud computing, facial recognition has also achieved rapid development, and its application potential has been continuously released. Due to its characteristics such as non-replicability, non-contact, scalability, and convenience, facial recognition has been widely used in various fields, especially in online identity authentication scenarios. For example, in online channel scenarios such as mobile apps, where facial recognition is most widely used, current related technologies mainly achieve liveness detection through interaction with users through motion commands. Users are asked to cooperate with given random motion commands, such as blinking, turning the head, and opening the mouth. The motion information of the facial area is then identified from the captured video, and the liveness is determined by judging whether the motion information is consistent with the given commands.

[0005] However, since mobile online businesses like apps require customers to complete transactions remotely on their own devices, the complex external environment of these devices, coupled with the widespread popularity of various photo activation tools and AI face-changing software, pose an increasingly serious risk of facial impersonation attacks. Current facial motion liveness detection technologies have technical shortcomings in addressing these new attacks. While current motion liveness detection technologies can protect against attacks based on static photos, video playback, and static head models, they lack the ability to generate randomly generated motion commands. With the increasing popularity of various photo activation tools and AI face-changing software, attackers can easily generate corresponding motion commands in advance through video, making attacks increasingly costly and difficult to implement. Furthermore, motion-based liveness detection requires high user interaction, requiring users to make large movements like shaking their heads and opening their mouths, resulting in a poor user experience.

[0006] Currently, no effective solution has been proposed to the problem that face liveness detection is implemented through interaction with users through motion instructions in related technologies, resulting in low accuracy of face liveness detection. Summary of the Invention

[0007] The main purpose of this application is to provide a method and device for detecting human face liveness, a processor and an electronic device to solve the problem in related technologies that human face liveness detection is achieved through action instructions and user interaction, resulting in low accuracy of human face liveness detection.

[0008] To achieve the above-mentioned purpose, according to one aspect of the present application, a method for detecting liveness of a face is provided. The method comprises: receiving a target liveness detection request sent by a target client device, wherein the target liveness detection request is used to perform liveness detection on the face of a target object; after receiving the target liveness detection request, randomly generating target luminescence information and target coordinate information, and sending the target luminescence information and the target coordinate information to the target client device, wherein the target luminescence information at least includes: the luminescence color of a display device in the target client device and the duration corresponding to the luminescence color, and the target coordinate information is used to represent the coordinates of a gaze point in the display device; after sending the target luminescence information and the target coordinate information to the target client device, receiving eye image information of the target object returned by the target client device, wherein the eye image information is image information generated based on the target luminescence information and the target coordinate information; and analyzing the eye image information to determine a result of liveness detection on the face of the target object.

[0009] Furthermore, after randomly generating target luminescence information and target coordinate information, the method also includes: when the target parameters of the target object meet the first preset requirements, controlling the display device to emit light of different colors and display target prompt information at the first coordinate in the display device according to the target luminescence information and the target coordinate information, wherein the target parameters include at least: the angle and distance between the face of the target object and the display device, and the occlusion of the face of the target object, and the target prompt information is used to prompt the gaze point of the target object to move with the prompt content; collecting facial image information of the target object during the change of light and gaze point; extracting the image of the eye area in the facial image information to obtain the eye image information, and sending the eye image information to the target cloud server corresponding to the target client device.

[0010] Further, analyzing the eye image information to determine the result of liveness detection on the face of the target object includes: analyzing the reflective information of the eyeball in the eye image information to obtain first reflective information, wherein the first reflective information includes at least: the reflective color of the eyeball and the duration corresponding to the reflective color; analyzing the gaze point information of the eyeball in the eye image information to obtain coordinate information of the gaze point of the eyeball; determining whether the first reflective information is the same as the target luminous information, and determining whether the coordinate information of the gaze point of the eyeball is the same as the target coordinate information; if the first reflective information is the same as the target luminous information, and the coordinate information of the gaze point of the eyeball is the same as the target coordinate information, determining that the result of liveness detection on the face of the target object is that the face is alive; if the first reflective information is different from the target luminous information, and / or the coordinate information of the gaze point of the eyeball is different from the target coordinate information, determining that the result of liveness detection on the face of the target object is that the face is not alive.

[0011] Furthermore, before analyzing the reflective information of the eyeball in the eye image information, the method also includes: decomposing the eye image information into an illumination component and a reflection component; filtering the illumination component and the reflection component to obtain a Fourier spectrum; determining the difference between planar imaging and stereoscopic imaging based on the Fourier spectrum; detecting whether the eye image information is stereoscopic based on the difference; and if the eye image information is stereoscopic, analyzing the reflective information of the eyeball in the eye image information.

[0012] Furthermore, after analyzing the reflective information of the eyeball in the eye image information to obtain first reflective information, the method also includes: obtaining the reflective characteristics of multiple frames of RGB images of the eyeball in the eye image information under different lighting conditions; verifying the first reflective information based on the reflective characteristics and the target luminescence information to obtain a first verification result; and determining the confidence value of the eyeball's reflection based on the first verification result.

[0013] Furthermore, the eye's gaze point information in the eye image information is analyzed to obtain the coordinate information of the eye's gaze point, including: extracting the outline of the pupil of the target object's eye from the eye image information; obtaining the center position of the pupil based on the outline of the pupil; obtaining the center position of the cornea of ​​the target object's eye based on the eye image information; calculating the offset between the center of the pupil and the center of the cornea based on the center position of the pupil and the center position of the cornea; determining the displacement of the eye in each frame of the eye image information based on the offset between the center of the pupil and the center of the cornea; mapping the eye's gaze point on the display device in combination with the eye model, and obtaining the coordinate information of the eye's gaze point.

[0014] Furthermore, after analyzing the eyeball's gaze point information in the eye image information to obtain the coordinate information of the eyeball's gaze point, the method also includes: verifying the coordinate information of the eyeball's gaze point based on the target coordinate information to obtain a second verification result; determining the confidence value of the eyeball's gaze point based on the second verification result; obtaining the confidence value of the eyeball's reflection; and determining the result of liveness detection on the target object's face based on the confidence value of the eyeball's reflection and the confidence value of the eyeball's gaze point.

[0015] Furthermore, after receiving the target liveness detection request sent by the target client device, the method also includes: obtaining target information in the target liveness detection request, the target information including at least: signature verification information of the target client device and parameter information of the target client device; verifying the target information to obtain a third verification result; if the third verification result meets the second preset requirement, randomly generating the target luminescence information and the target coordinate information; if the third verification result does not meet the second preset requirement, sending an error message to the target client device.

[0016] Furthermore, randomly generating target luminous information and target coordinate information includes: configuring a first parameter of the display device, wherein the first parameter includes at least a dictionary of the luminous color of the display device, the duration corresponding to the luminous color, and the position of the gaze point in the display device; based on the first parameter, combined with a target random algorithm, randomly generating the target luminous information and the target coordinate information.

[0017] Furthermore, before the target parameters of the target object meet the first preset requirements, the method also includes: obtaining a real-time video stream through a camera in the display device; obtaining facial information in the current image from the video stream, and obtaining the target parameters from the facial information; judging whether the target parameters meet the first preset requirements; if the target parameters meet the first preset requirements, controlling the display device to emit light of different colors and display target prompt information at the first coordinate in the display device based on the target luminous information and the target coordinate information; if the target parameters do not meet the first preset requirements, sending a first prompt message to the target object, wherein the first prompt message is used to prompt the target object to change the target parameters.

[0018] Furthermore, collecting facial image information of the target object during changes in light and gaze point includes: extracting a frontal facial image that meets the target liveness detection request from the video stream according to the frame rate during changes in the color of light on the display device and changes in the gaze point of the target object's eyes; and obtaining facial image information of the target object during changes in light and gaze point based on the frontal facial image.

[0019] To achieve the above-mentioned object, according to another aspect of the present application, a device for detecting liveness of a face is provided. The device comprises: a first receiving unit, configured to receive a target liveness detection request sent by a target client device, wherein the target liveness detection request is used to perform liveness detection on a target face; a first generating unit, configured to randomly generate target luminescence information and target coordinate information after receiving the target liveness detection request, and send the target luminescence information and target coordinate information to the target client device, wherein the target luminescence information includes at least: the luminescence color of a display device in the target client device and the duration corresponding to the luminescence color, and the target coordinate information is used to represent the coordinates of a gaze point in the display device; a second receiving unit, configured to receive eye image information of the target object returned by the target client device after sending the target luminescence information and target coordinate information to the target client device, wherein the eye image information is image information generated based on the target luminescence information and the target coordinate information; and a first analyzing unit, configured to analyze the eye image information to determine a result of liveness detection on the target face.

[0020] Furthermore, the device also includes: a first control unit, which is used to control the display device to emit light of different colors and display target prompt information at the first coordinate in the display device according to the target light information and the target coordinate information after randomly generating target luminescence information and target coordinate information, when the target parameters of the target object meet the first preset requirements, wherein the target parameters include at least: the angle and distance between the face of the target object and the display device, and the occlusion of the face of the target object, and the target prompt information is used to prompt the gaze point of the target object to move with the prompt content; a first acquisition unit, which is used to acquire facial image information of the target object during the change of light and gaze point; a first extraction unit, which is used to extract the image of the eye area in the facial image information, obtain the eye image information, and send the eye image information to the target cloud server corresponding to the target client device.

[0021] Furthermore, the first analysis unit includes: a first analysis subunit, configured to analyze the reflective information of the eyeball in the eye image information to obtain first reflective information, wherein the first reflective information includes at least: the reflective color of the eyeball and the duration corresponding to the reflective color; a second analysis subunit, configured to analyze the gaze point information of the eyeball in the eye image information to obtain coordinate information of the gaze point of the eyeball; a first judgment subunit, configured to judge whether the first reflective information is the same as the target luminous information, and to judge whether the coordinate information of the gaze point of the eyeball is the same as the target coordinate information; a first determination subunit, configured to determine that the result of the liveness detection on the face of the target object is that the face is live if the first reflective information is the same as the target luminous information and the coordinate information of the gaze point of the eyeball is the same as the target coordinate information; and a second determination subunit, configured to determine that the result of the liveness detection on the face of the target object is that the face is not live if the first reflective information is different from the target luminous information and / or the coordinate information of the gaze point of the eyeball is different from the target coordinate information.

[0022] Furthermore, the device also includes: a first decomposition unit, used to decompose the eye image information into an illumination component and a reflection component before analyzing the reflection information of the eyeball in the eye image information; a first filtering unit, used to filter the illumination component and the reflection component to obtain a Fourier spectrum; a first determination unit, used to determine the difference between planar imaging and stereoscopic imaging based on the Fourier spectrum; a first detection unit, used to detect whether the eye image information is stereoscopic based on the difference; and a second analysis unit, used to analyze the reflection information of the eyeball in the eye image information when the eye image information is stereoscopic.

[0023] Furthermore, the device also includes: a first acquisition unit, used to analyze the reflection information of the eyeball in the eye image information to obtain the first reflection information, and then obtain the reflection characteristics of multiple frames of RGB images of the eyeball in the eye image information under different lighting conditions; a first verification unit, used to verify the first reflection information based on the reflection characteristics and the target luminescence information to obtain a first verification result; and a second determination unit, used to determine the confidence value of the eyeball's reflection based on the first verification result.

[0024] Furthermore, the second analysis subunit includes: a first extraction module for extracting the outline of the pupil of the target object's eye from the eye image information; a first determination module for obtaining the center position of the pupil based on the outline of the pupil; a second determination module for obtaining the center position of the cornea of ​​the target object's eye based on the eye image information; a first calculation module for calculating the offset between the center of the pupil and the center of the cornea based on the center position of the pupil and the center position of the cornea; a third determination module for determining the displacement of the eye in each frame of the eye image information based on the offset between the center of the pupil and the center of the cornea; and a first processing module for mapping the gaze point of the eyeball on the display device in combination with the eyeball model and obtaining the coordinate information of the gaze point of the eyeball.

[0025] Furthermore, the device also includes: a second verification unit, which is used to analyze the eyeball's gaze point information in the eye image information to obtain the coordinate information of the eyeball's gaze point, and then verify the coordinate information of the eyeball's gaze point according to the target coordinate information to obtain a second verification result; a third determination unit, which is used to determine the confidence value of the eyeball's gaze point based on the second verification result; a second acquisition unit, which is used to obtain the confidence value of the eyeball's reflection; and a fourth determination unit, which is used to determine the result of liveness detection on the target object's face based on the confidence value of the eyeball's reflection and the confidence value of the eyeball's gaze point.

[0026] Furthermore, the device also includes: a third acquisition unit, used to obtain target information in the target liveness detection request after receiving the target liveness detection request sent by the target client device, and the target information includes at least: signature verification information of the target client device and parameter information of the target client device; a third verification unit, used to verify the target information to obtain a third verification result; a second generation unit, used to randomly generate the target luminescence information and the target coordinate information when the third verification result meets the second preset requirements; a first sending unit, used to send an error message to the target client device when the third verification result does not meet the second preset requirements.

[0027] Furthermore, the first generation unit includes: a first configuration module, used to configure the first parameters of the display device, wherein the first parameters at least include a dictionary of the luminous color of the display device, the duration corresponding to the luminous color, and the position of the gaze point in the display device; a first generation module, used to randomly generate the target luminous information and the target coordinate information based on the first parameters in combination with a target random algorithm.

[0028] Furthermore, the device also includes: a fourth acquisition unit, used to acquire a real-time video stream through the camera in the display device before the target parameters of the target object meet the first preset requirements; a fifth acquisition unit, used to acquire facial information in the current image from the video stream, and acquire the target parameters from the facial information; a first judgment unit, used to judge whether the target parameters meet the first preset requirements; a second control unit, used to control the display device to emit light of different colors and display target prompt information at the first coordinate in the display device according to the target luminous information and the target coordinate information when the target parameters meet the first preset requirements; a second sending unit, used to send a first prompt information to the target object when the target parameters do not meet the first preset requirements, wherein the first prompt information is used to prompt the target object to change the target parameters.

[0029] Furthermore, the first acquisition unit includes: a first extraction module, used to extract a frontal facial image that meets the target liveness detection request from the video stream according to the frame rate during the process of changes in the color of the light of the display device and the change in the gaze point of the target object's eyeball; a second generation module, used to obtain facial image information of the target object during the change of light and gaze point based on the frontal facial image.

[0030] In order to achieve the above-mentioned purpose, according to another aspect of the present application, a processor is provided, which is used to run a program, wherein the program executes any one of the above-mentioned methods for detecting living faces when running.

[0031] In order to achieve the above-mentioned purpose, according to another aspect of the present application, an electronic device is provided, which includes one or more processors and a memory, and the memory is used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement any one of the above-mentioned methods for detecting live faces.

[0032] Through the present application, the following steps are adopted: receiving a target liveness detection request sent by a target client device, wherein the target liveness detection request is used to perform liveness detection on the face of a target object; after receiving the target liveness detection request, randomly generating target luminescence information and target coordinate information, and sending the target luminescence information and target coordinate information to the target client device, wherein the target luminescence information at least includes: the luminescence color of the display device in the target client device and the duration corresponding to the luminescence color, and the target coordinate information is used to represent the coordinates of the gaze point in the display device; after sending the target luminescence information and target coordinate information to the target client device, receiving eye image information of the target object returned by the target client device, wherein the eye image information is image information generated based on the target luminescence information and target coordinate information; analyzing the eye image information to determine the result of liveness detection on the face of the target object, thereby solving the problem in the related art of realizing face liveness detection through action instructions and user interaction, resulting in low accuracy of face liveness detection. By receiving a target liveness detection request sent by a target client device, randomly generating target luminescence information and target coordinate information, then sending the target luminescence information and target coordinate information to the target client device, and receiving the eye image information of the target object returned by the target client device, and then analyzing the eye image information, the result of liveness detection on the target object's face can be determined, thereby improving the accuracy of face liveness detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] The accompanying drawings, which constitute part of this application, are intended to provide a further understanding of this application. The exemplary embodiments and descriptions of this application are intended to explain this application and do not constitute an improper limitation on this application. In the accompanying drawings:

[0034] Figure 1 This is a flowchart of a method for detecting a living face according to an embodiment of the present application;

[0035] Figure 2 This is a flowchart of an optional method for detecting a living face according to an embodiment of the present application;

[0036] Figure 3 is a schematic diagram of the coordinate setting of the eye position in an embodiment of the present application;

[0037] Figure 4 is a schematic diagram of another eye position coordinate setting in an embodiment of the present application;

[0038] Figure 5 is a schematic diagram of a live face detection system provided according to an embodiment of the present application;

[0039] Figure 6 is a schematic diagram of a client in an embodiment of the present application;

[0040] Figure 7 is a schematic diagram of the cloud in an embodiment of the present application;

[0041] Figure 8 is a schematic diagram of a live face detection device provided according to an embodiment of the present application;

[0042] Figure 9 is a schematic diagram of an electronic device provided according to an embodiment of the present application. DETAILED DESCRIPTION

[0043] It should be noted that, in the absence of conflict, the embodiments and features of the embodiments in this application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0044] In order to enable those skilled in the art to better understand the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of this application.

[0045] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present application described here. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0046] It should be noted that the relevant information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for display and analysis, etc.) involved in this disclosure are all information and data authorized by the user or fully authorized by all parties. For example, an interface is set up between this system and the relevant user or organization. Before obtaining relevant information, it is necessary to send an acquisition request to the aforementioned user or organization through the interface, and obtain the relevant information after receiving the consent information fed back by the aforementioned user or organization.

[0047] The present invention will be described below in conjunction with preferred implementation steps. Figure 1FIG. 1 is a flow chart of a method for detecting a living face according to an embodiment of the present application. Figure 1 As shown, the method includes the following steps:

[0048] Step S101: receiving a target liveness detection request sent by a target client device, wherein the target liveness detection request is used to perform liveness detection on a face of a target object.

[0049] For example, the cloud receives a request from a client to perform liveness detection on a user's face.

[0050] Step S102, after receiving the target liveness detection request, randomly generate target luminescence information and target coordinate information, and send the target luminescence information and target coordinate information to the target client device, wherein the target luminescence information includes at least: the luminescence color of the display device in the target client device and the duration corresponding to the luminescence color, and the target coordinate information is used to represent the coordinates of the gaze point in the display device.

[0051] For example, after receiving a liveness detection request from a client, the cloud randomly generates lighting instructions and gaze point coordinate information and sends them to the client. These randomly generated lighting instructions and gaze point coordinate information are used to control the lighting and display of the client device screen.

[0052] Step S103 , after sending the target luminescence information and the target coordinate information to the target client device, receiving the eye image information of the target object returned by the target client device, wherein the eye image information is image information generated based on the target luminescence information and the target coordinate information.

[0053] For example, after the cloud sends the randomly generated light-emitting instructions and gaze point coordinate information to the client, the cloud receives the user's eye image information data packet sent by the client, and the eye image information data packet is an image generated based on the randomly generated light-emitting instructions and gaze point coordinate information on the cloud.

[0054] Step S104: Analyze the eye image information to determine the result of liveness detection on the target object's face.

[0055] For example, after receiving the eye image information data packet sent by the client, the cloud analyzes and processes the eye reflection and eye gaze point in the image information to determine whether the eye reflection color sequence and eye gaze point position are consistent with the issued instructions and coordinates, thereby completing the user's facial liveness detection.

[0056] Through the above steps S101 to S104, by receiving the target liveness detection request sent by the target client device, and randomly generating target luminescence information and target coordinate information, and then sending the target luminescence information and target coordinate information to the target client device, and receiving the eye image information of the target object returned by the target client device, and then analyzing the eye image information, the result of liveness detection on the face of the target object can be determined, thereby improving the accuracy of face liveness detection.

[0057] Optionally, in the method for detecting live faces provided in an embodiment of the present application, after randomly generating target luminescence information and target coordinate information, the method further includes: when the target parameters of the target object meet the first preset requirements, controlling the display device to emit light of different colors and displaying target prompt information at the first coordinate in the display device according to the target luminescence information and target coordinate information, wherein the target parameters include at least: the angle and distance between the face of the target object and the display device, and the occlusion of the face of the target object, and the target prompt information is used to prompt the target object's gaze point to move with the prompt content; collecting facial image information of the target object during the change of light and gaze point; extracting the image of the eye area in the facial image information to obtain eye image information, and sending the eye image information to the target cloud server corresponding to the target client device.

[0058] Figure 2 is a flowchart of an optional method for detecting a living face according to an embodiment of the present application. Figure 2 As shown, the optional method for detecting living face includes the following steps:

[0059] Step S201: The cloud receives a face liveness detection request initiated by the client;

[0060] Step S202: The cloud randomly generates light-emitting instructions and gaze point coordinate information, and can encrypt the generated information using an asymmetric encryption algorithm to form a ciphertext sequence and send it to the client;

[0061] Step S203: The client receives and decrypts the ciphertext sequence. When the face to be detected is ready, the client controls the device screen to emit different colored lights according to the parsed light emission instructions. Furthermore, the client displays gaze point prompts at the corresponding coordinates on the display screen based on the parsed gaze point coordinates, guiding the user's gaze point to move according to the prompt content.

[0062] In step S204, the client collects facial image information of the user during changes in lighting and gaze, extracts eye area images from the collected facial image information, and finally sends the processed and extracted eye image information to the cloud for liveness determination;

[0063] In step S205, after receiving the image information data packet sent by the client, the cloud analyzes and processes the eye reflection and eye gaze point in the image information to determine whether the eye reflection color sequence and the eye gaze point position are consistent with the issued instructions and coordinates, thereby completing the face liveness detection judgment and finally returning the judgment result to the client.

[0064] In addition, in step S203, the specific process of controlling the client device screen to emit light of different colors and displaying the gaze point prompt information on the corresponding coordinates of the display screen is as follows: (1) controlling the device screen to emit light of different colors according to the parsed light emission instructions, the instructions including the specific light emission colors and durations (such as controlling the screen to display red, blue, and green for 1 second each); (2) displaying the gaze point prompt information on the corresponding coordinates of the display screen according to the parsed gaze point coordinate information, guiding the user's eye gaze point to move along with the prompt content, for example, Figure 3 Schematic diagram of eye position coordinate setting in an embodiment of the present application. Figure 3 As shown, if the eyeball position coordinates are set to upper left, lower left, upper right and lower right, the screen will be divided into four areas for display; Figure 4 This is a schematic diagram of another eyeball coordinate setting in an embodiment of the present application, such as Figure 4 As shown, if the eye position coordinates are set to six categories: upper left, middle left, lower left, upper right, middle right and lower right, the screen is divided into six areas for display.

[0065] In addition, in step S204, the specific process of extracting the eye area image of the collected facial image information is: using the local binary pattern LBP algorithm to locate the eye position of the facial image collected in step S203, intercepting the image of the area where the eye is located, and sending the processed local image information to the cloud to reduce the transmission of redundant information.

[0066] The above solution, without relying on specialized hardware, can be applied on client devices such as mobile phones, eliminating the need for additional user costs and laying the foundation for widespread adoption. By controlling the mobile device screen to emit light of varying colors and intensities, it captures eye reflections while guiding the user to gaze at random points on the screen. Eye tracking determines the direction of gaze, effectively defending against various attacks using photo activation tools and face-swapping software to generate face videos, enhancing the security of online face recognition applications. Furthermore, detecting live faces simply requires the user's eyes to shift as the gaze point displayed on the screen changes. This simple and convenient detection process requires no drastic movements, enhancing the user experience.

[0067] Optionally, in the face liveness detection method provided in the embodiment of the present application, analyzing the eye image information to determine the result of liveness detection on the target object's face includes: analyzing the reflective information of the eyeball in the eye image information to obtain first reflective information, wherein the first reflective information includes at least: the reflective color of the eyeball and the duration corresponding to the reflective color; analyzing the gaze point information of the eyeball in the eye image information to obtain coordinate information of the gaze point of the eyeball; judging whether the first reflective information is the same as the target luminous information, and judging whether the coordinate information of the gaze point of the eyeball is the same as the target coordinate information; when the first reflective information is the same as the target luminous information, and the coordinate information of the gaze point of the eyeball is the same as the target coordinate information, determining that the result of liveness detection on the target object's face is that the face is alive; when the first reflective information is different from the target luminous information, and / or the coordinate information of the gaze point of the eyeball is different from the target coordinate information, determining that the result of liveness detection on the target object's face is that the face is not alive.

[0068] For example, after receiving the eye image information data packet sent by the client, the cloud analyzes and processes the eye reflection and eye gaze point in the image information, that is, by analyzing and processing the eye reflection in the image information, the eye reflection information is detected, and the color and duration sequence of the eye reflection is obtained; then, by analyzing and processing the eye gaze point in the image information, the eye gaze point position is detected, and the eye gaze point coordinate information sequence is obtained; it is determined whether the eye reflection color and duration sequence, and the eye gaze point position are consistent with the issued instructions and coordinates; if the eye reflection color and duration sequence are consistent with the issued instructions, and the eye gaze point position is consistent with the issued coordinates, it means that the object to be identified is a living person; if the eye reflection color and duration sequence are inconsistent with the issued instructions, and / or the eye gaze point position is inconsistent with the issued coordinates, it means that the object to be identified is not a living person.

[0069] Through the above solution, face liveness detection and judgment can be completed quickly and accurately.

[0070] Optionally, in the method for detecting liveness of a face provided in an embodiment of the present application, before analyzing the reflective information of the eyeball in the eye image information, the method also includes: decomposing the eye image information into an illumination component and a reflection component; filtering the illumination component and the reflection component to obtain a Fourier spectrum; determining the difference between planar imaging and stereoscopic imaging based on the Fourier spectrum; detecting whether the eye image information is three-dimensional based on the difference; and if the eye image information is three-dimensional, analyzing the reflective information of the eyeball in the eye image information.

[0071] For example, before analyzing and processing the eyeball reflection in the image information and detecting the eyeball reflection information, a Lambertian reflection model is established and combined with the Logarithmic Total Variation (LTV) method to decompose the eyeball area image into two components: illumination and reflection. The obtained illumination component and reflection component are then filtered using a Differential of Gaussian filter (DoG) to obtain a central Fourier spectrum. The obtained central Fourier spectrum is used to describe the difference between planar and stereoscopic imaging. Based on the difference between planar and stereoscopic imaging, whether the eyeball area image has stereoscopic properties is detected. If the eyeball area image has stereoscopic properties, the eyeball reflection in the image information is analyzed and processed to detect the eyeball reflection information. If the eyeball area image does not have stereoscopic properties, it means that the object to be identified is not a living person, so the eyeball reflection in the image information cannot be analyzed and processed.

[0072] The above solution effectively protects against two-dimensional attacks during liveness detection. Furthermore, by combining triple verification of eye stereoscopic properties, eye reflections, and gaze point, liveness detection is performed based on light color, duration, and gaze point coordinates. This prevents criminals from pre-generating attack videos, thus enhancing the security of liveness detection.

[0073] Optionally, in the method for detecting live faces provided in an embodiment of the present application, after analyzing the reflective information of the eyeball in the eye image information to obtain first reflective information, the method further includes: obtaining the reflective characteristics of multiple frames of RGB images of the eyeball in the eye image information under different lighting conditions; verifying the first reflective information based on the reflective characteristics and the target luminous information to obtain a first verification result; and determining a confidence value of the eyeball's reflection based on the first verification result.

[0074] For example, after analyzing and processing the eye reflection in the image information, detecting the eye reflection information, and obtaining the color and duration sequence of the inverted eye reflection, a light characteristic verification mechanism can be added. That is, by using multiple frames of eye RGB images with different reflection characteristics under different lighting conditions, the eye reflection sequence is verified against the light-emitting instructions randomly generated in the cloud, and the eye reflection confidence value is obtained.

[0075] Through the above solution, the eye reflection confidence value can be obtained quickly and accurately, laying the foundation for subsequent face liveness detection.

[0076] Optionally, in the face liveness detection method provided in the embodiment of the present application, the eyeball gaze point information in the eye image information is analyzed to obtain the coordinate information of the eyeball gaze point, including: extracting the outline of the pupil of the target object's eye from the eye image information; obtaining the center position of the pupil based on the outline of the pupil; obtaining the center position of the cornea of ​​the target object's eye based on the eye image information; calculating the offset between the center of the pupil and the center of the cornea based on the center position of the pupil and the center position of the cornea; determining the displacement of the eye in each frame of the eye image information based on the offset between the center of the pupil and the center of the cornea; mapping the eyeball gaze point on the display device in combination with the eyeball model, and obtaining the coordinate information of the eyeball gaze point.

[0077] For example, through the pupil-corneal reflection method, the pupil contour is extracted from the eyeball image, and the position of the pupil center is calculated. Then, the offset of the line connecting the corneal center and the pupil center is calculated to obtain the displacement of the eye in each frame of the photo. Combined with the eyeball model, the gaze point is mapped on the device screen to obtain the coordinates of the eyeball gaze point (such as upper left, upper right, etc.).

[0078] Through the above solution, the eye gaze points in the image information can be conveniently analyzed and processed, and the coordinate information sequence of the eye gaze points can be conveniently obtained.

[0079] Optionally, in the face liveness detection method provided in the embodiment of the present application, after analyzing the eyeball's gaze point information in the eye image information to obtain the coordinate information of the eyeball's gaze point, the method also includes: verifying the coordinate information of the eyeball's gaze point based on the target coordinate information to obtain a second verification result; determining the confidence value of the eyeball's gaze point based on the second verification result; obtaining the confidence value of the eyeball's reflection; and determining the result of liveness detection on the target object's face based on the confidence value of the eyeball's reflection and the confidence value of the eyeball's gaze point.

[0080] For example, the eye gaze point can be verified by referencing randomly generated gaze point coordinates in the cloud to determine the eye gaze point confidence value. The eye reflection confidence value and the eye gaze point confidence value are then used to determine whether the subject to be identified is alive. Specifically, a passing threshold for the fusion of the eye reflection confidence value and the eye gaze point confidence value can be set based on different security level requirements. Alternatively, a neural network model can be trained using labeled data to generate a liveness determination model, which can then be used to determine whether the subject to be identified is alive.

[0081] Through the above scheme, the confidence value of the eye gaze point can be obtained quickly and accurately. In addition, by using the confidence value and the liveness judgment model, face liveness detection can be completed conveniently.

[0082] Optionally, in the face liveness detection method provided in the embodiment of the present application, after receiving the target liveness detection request sent by the target client device, the method also includes: obtaining target information in the target liveness detection request, the target information including at least: signature verification information of the target client device and parameter information of the target client device; verifying the target information to obtain a third verification result; if the third verification result meets the second preset requirements, randomly generating target luminescence information and target coordinate information; if the third verification result does not meet the second preset requirements, sending an error message to the target client device.

[0083] For example, after the cloud receives a liveness detection request initiated by the client, it can verify the parameters such as the client signature and device information in the request information. If the verification fails, the corresponding error message will be directly returned. If the verification passes, the cloud will randomly generate light-emitting instructions and gaze point coordinate information.

[0084] In summary, by verifying the client, the security of liveness detection can be improved, and liveness detection can be avoided on faces in devices that do not meet the requirements.

[0085] Optionally, in the method for detecting live faces provided in an embodiment of the present application, randomly generating target luminescence information and target coordinate information includes: configuring a first parameter of a display device, wherein the first parameter includes at least a dictionary of the luminescence color of the display device, the duration corresponding to the luminescence color, and the position of the gaze point in the display device; based on the first parameter, combined with a target random algorithm, randomly generating target luminescence information and target coordinate information.

[0086] For example, when the cloud generates random lighting instructions and gaze point coordinate information, it can configure the types of luminous colors (such as red, blue, and green), the lighting duration interval (such as 1 second each for red, blue, and green), and the eye gaze position dictionary (such as upper left, lower left, upper right, and lower right) through parameter settings, and then generate random lighting instructions and gaze point position coordinate sequences through a specific random algorithm.

[0087] Through the above solution, the light emission and display of the client device screen can be controlled, and it can be used for sequence verification during cloud-based liveness detection.

[0088] Optionally, in the method for detecting live faces provided in an embodiment of the present application, before the target parameters of the target object meet the first preset requirements, the method also includes: obtaining a real-time video stream through a camera in a display device; obtaining facial information in the current image from the video stream, and obtaining target parameters from the facial information; judging whether the target parameters meet the first preset requirements; if the target parameters meet the first preset requirements, controlling the display device to emit light of different colors and display target prompt information at the first coordinate in the display device based on the target luminous information and target coordinate information; if the target parameters do not meet the first preset requirements, sending a first prompt information to the target object, wherein the first prompt information is used to prompt the target object to change the target parameters.

[0089] For example, after randomly generating light-emitting instructions and gaze point coordinate information in the cloud, the client detects whether the user's face is ready. Specifically, by encapsulating the face detection SDK, driving the camera device, opening the camera to obtain a real-time video stream, and using the MTCNN network to obtain the face frame in the current image, it determines whether the angle, distance, and occlusion of the face to be recognized meet the requirements. If the detection passes, it means that the user's face is ready. Otherwise, the user is prompted to face the screen, move closer (farther away) from the screen, or remove the occlusion, depending on the angle, distance, and occlusion.

[0090] Through the above solution, before performing liveness detection on the face to be identified, it is possible to conveniently detect whether the user's face is ready.

[0091] Optionally, in the facial liveness detection method provided in an embodiment of the present application, collecting facial image information of the target object during changes in light and gaze point includes: extracting a frontal facial image that meets the target liveness detection request from the video stream according to the frame rate during changes in the color of the light of the display device and changes in the gaze point of the target object's eyeballs; and obtaining facial image information of the target object during changes in light and gaze point based on the frontal facial image.

[0092] For example, the process of collecting facial image information of a user during changes in screen light and gaze point is specifically as follows: driving the camera device, turning on the camera to obtain a real-time video stream, and extracting a frontal facial image that meets the requirements of face liveness detection at a frame rate during changes in screen light color and user eye gaze point.

[0093] Through the above solution, the user's facial image information can be quickly collected during the process of screen light changes and gaze point changes, and the foundation for subsequent face liveness detection can be laid.

[0094] Figure 5 FIG. 1 is a schematic diagram of a live face detection system according to an embodiment of the present application. Figure 5 As shown, the face liveness detection system includes: client terminal (including camera recording equipment and display screen equipment) and cloud server of technical service provider. The local SDK is integrated in the client terminal, and the face recognition liveness detection service is deployed in the cloud server for client program to call. After the client initiates the liveness detection request, it receives and parses the ciphertext sequence returned by the cloud. After detecting that the face is normally aligned with the camera, it controls the device screen to emit different colors of light and displays the gaze point prompt information on the corresponding coordinates of the display screen. Then, it drives the camera device to collect the user's facial image information during the process of light changes and gaze point changes. Finally, it calls the cloud service to send the processed and extracted image information to the cloud for liveness judgment processing. Finally, it receives the liveness judgment result returned by the cloud, thereby collaboratively completing the entire face liveness detection process to ensure the security of face recognition applications.

[0095] Figure 6 This is a schematic diagram of the client in the embodiment of the present application, such as Figure 6 As shown, the client includes a ciphertext sequence parsing unit 21, a face detection unit 22, a device control unit 23, a data acquisition unit 24, and an image extraction unit 25. The ciphertext sequence parsing unit 21 is used to decrypt and restore the ciphertext sequence generated in the cloud; the face detection unit 22 is used to detect whether the user's face is ready; the device control unit 23 is used to control the screen lighting and content display of the client device; the data acquisition unit 24 is used to collect facial image information of the user during changes in screen lighting and gaze point; and the image extraction unit 25 is used to capture key information about the eyeball part of the facial image.

[0096] Figure 7 is a schematic diagram of the cloud in the embodiment of the present application, such as Figure 7 As shown, the cloud-based face liveness detection service includes a random sequence generation unit 31, a reflection detection unit 32, a gaze point detection unit 33, and a liveness determination unit 34. The random sequence generation unit 31 is used to generate random light emission instructions and gaze point coordinate information; the reflection detection unit 32 is used to detect the reflection information of the eyeball to obtain the color and duration sequence of the eyeball reflection; the gaze point detection unit 33 is used to detect the gaze point position of the eyeball to obtain the eyeball gaze point coordinate information sequence; and the liveness determination unit 34 is used to determine whether the object to be identified is alive.

[0097] In summary, the embodiment of the present application provides a method for detecting liveness of a face, which receives a target liveness detection request sent by a target client device, wherein the target liveness detection request is used to perform liveness detection on the face of a target object; after receiving the target liveness detection request, randomly generates target luminescence information and target coordinate information, and sends the target luminescence information and target coordinate information to the target client device, wherein the target luminescence information at least includes: the luminescence color of the display device in the target client device and the duration corresponding to the luminescence color, and the target coordinate information is used to represent the coordinates of the gaze point in the display device; after sending the target luminescence information and target coordinate information to the target client device, receives eye image information of the target object returned by the target client device, wherein the eye image information is image information generated based on the target luminescence information and the target coordinate information; analyzes the eye image information to determine the result of liveness detection on the face of the target object, thereby solving the problem in the related art of realizing face liveness detection through interaction with the user through action instructions, resulting in low accuracy of face liveness detection. By receiving a target liveness detection request sent by a target client device, randomly generating target luminescence information and target coordinate information, then sending the target luminescence information and target coordinate information to the target client device, and receiving the eye image information of the target object returned by the target client device, and then analyzing the eye image information, the result of liveness detection on the target object's face can be determined, thereby improving the accuracy of face liveness detection.

[0098] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0099] The present application also provides a facial liveness detection device. It should be noted that the facial liveness detection device of the present application can be used to execute the facial liveness detection method provided in the present application. The following describes the facial liveness detection device provided in the present application.

[0100] Figure 8 Schematic diagram of a face liveness detection device according to an embodiment of the present application. Figure 8 As shown, the device includes: a first receiving unit 801, a first generating unit 802, a second receiving unit 803 and a first analyzing unit 804.

[0101] Specifically, the first receiving unit 801 is configured to receive a target liveness detection request sent by a target client device, wherein the target liveness detection request is used to perform liveness detection on a face of a target object;

[0102] A first generating unit 802 is configured to randomly generate target luminescence information and target coordinate information after receiving a target liveness detection request, and send the target luminescence information and target coordinate information to a target client device, wherein the target luminescence information includes at least: a luminescence color of a display device in the target client device and a duration corresponding to the luminescence color, and the target coordinate information is used to represent the coordinates of a gaze point in the display device;

[0103] A second receiving unit 803 is configured to receive eye image information of the target object returned by the target client device after sending the target luminescence information and the target coordinate information to the target client device, wherein the eye image information is image information generated based on the target luminescence information and the target coordinate information;

[0104] The first analyzing unit 804 is configured to analyze the eye image information and determine a result of liveness detection on the face of the target object.

[0105] In summary, the face liveness detection device provided by the embodiment of the present application receives a target liveness detection request sent by a target client device through a first receiving unit 801, wherein the target liveness detection request is used to perform liveness detection on the face of the target object; after receiving the target liveness detection request, the first generating unit 802 randomly generates target luminescence information and target coordinate information, and sends the target luminescence information and target coordinate information to the target client device, wherein the target luminescence information at least includes: the luminescence color of the display device in the target client device and the duration corresponding to the luminescence color, and the target coordinate information is used to represent the coordinates of the gaze point in the display device; after sending the target luminescence information and target coordinate information to the target client device, the second receiving unit 803 receives the target object's eye information returned by the target client device. Image information, wherein the eye image information is image information generated based on the target luminescence information and the target coordinate information; the first analysis unit 804 analyzes the eye image information to determine the result of liveness detection on the face of the target object, thereby solving the problem in the related art of realizing face liveness detection through interaction with the user through action instructions, resulting in low accuracy of face liveness detection. By receiving the target liveness detection request sent by the target client device, randomly generating target luminescence information and target coordinate information, and then sending the target luminescence information and target coordinate information to the target client device, and receiving the eye image information of the target object returned by the target client device, and then analyzing the eye image information, the result of liveness detection on the face of the target object can be determined, thereby improving the accuracy of face liveness detection.

[0106] Optionally, in the face liveness detection device provided in the embodiment of the present application, the device also includes: a first control unit, for controlling the display device to emit light of different colors and display target prompt information at the first coordinate in the display device according to the target light-emitting information and target coordinate information after randomly generating target luminescence information and target coordinate information, when the target parameters of the target object meet the first preset requirements, wherein the target parameters include at least: the angle and distance between the face of the target object and the display device, and the occlusion of the face of the target object, and the target prompt information is used to prompt the target object's gaze point to move with the prompt content; a first acquisition unit, for acquiring facial image information of the target object during the change of light and gaze point; a first extraction unit, for extracting the image of the eye area in the facial image information, obtaining eye image information, and sending the eye image information to the target cloud server corresponding to the target client device.

[0107] Optionally, in the face liveness detection device provided in an embodiment of the present application, the first analysis unit includes: a first analysis subunit, configured to analyze the reflective information of the eyeball in the eye image information to obtain first reflective information, wherein the first reflective information includes at least: the reflective color of the eyeball and the duration corresponding to the reflective color; a second analysis subunit, configured to analyze the gaze point information of the eyeball in the eye image information to obtain coordinate information of the gaze point of the eyeball; a first judgment subunit, configured to judge whether the first reflective information is the same as the target luminous information, and to judge whether the coordinate information of the gaze point of the eyeball is the same as the target coordinate information; a first determination subunit, configured to determine that the result of the liveness detection on the face of the target object is that the face is alive when the first reflective information is the same as the target luminous information and the coordinate information of the gaze point of the eyeball is the same as the target coordinate information; a second determination subunit, configured to determine that the result of the liveness detection on the face of the target object is that the face is not alive when the first reflective information is different from the target luminous information and / or the coordinate information of the gaze point of the eyeball is different from the target coordinate information.

[0108] Optionally, in the face liveness detection device provided in the embodiment of the present application, the device also includes: a first decomposition unit, used to decompose the eye image information into an illumination component and a reflection component before analyzing the reflection information of the eyeball in the eye image information; a first filtering unit, used to filter the illumination component and the reflection component to obtain a Fourier spectrum; a first determination unit, used to determine the difference between planar imaging and stereoscopic imaging based on the Fourier spectrum; a first detection unit, used to detect whether the eye image information is three-dimensional based on the difference; and a second analysis unit, used to analyze the reflection information of the eyeball in the eye image information when the eye image information is three-dimensional.

[0109] Optionally, in the face liveness detection device provided in the embodiment of the present application, the device also includes: a first acquisition unit, used to analyze the reflection information of the eyeball in the eye image information to obtain the first reflection information, and then obtain the reflection characteristics of multiple frames of RGB images of the eyeball in the eye image information under different lighting conditions; a first verification unit, used to verify the first reflection information based on the reflection characteristics and the target luminescence information to obtain a first verification result; and a second determination unit, used to determine the confidence value of the eyeball's reflection based on the first verification result.

[0110] Optionally, in the face liveness detection device provided in the embodiment of the present application, the second analysis subunit includes: a first extraction module, used to extract the outline of the pupil of the target object's eye from the eye image information; a first determination module, used to obtain the center position of the pupil based on the outline of the pupil; a second determination module, used to obtain the center position of the cornea of ​​the target object's eye based on the eye image information; a first calculation module, used to calculate the offset between the center of the pupil and the center of the cornea based on the center position of the pupil and the center position of the cornea; a third determination module, used to determine the displacement of the eye in each frame of the eye image information based on the offset between the center of the pupil and the center of the cornea; a first processing module, used to map the eye's gaze point on the display device in combination with the eyeball model, and obtain the coordinate information of the eye's gaze point.

[0111] Optionally, in the face liveness detection device provided in the embodiment of the present application, the device also includes: a second verification unit, which is used to analyze the gaze point information of the eyeball in the eye image information to obtain the coordinate information of the gaze point of the eyeball, and then verify the coordinate information of the gaze point of the eyeball according to the target coordinate information to obtain a second verification result; a third determination unit, which is used to determine the confidence value of the gaze point of the eyeball based on the second verification result; a second acquisition unit, which is used to acquire the confidence value of the reflection of the eyeball; and a fourth determination unit, which is used to determine the result of liveness detection on the face of the target object based on the confidence value of the reflection of the eyeball and the confidence value of the gaze point of the eyeball.

[0112] Optionally, in the face liveness detection device provided in the embodiment of the present application, the device also includes: a third acquisition unit, used to obtain target information in the target liveness detection request after receiving the target liveness detection request sent by the target client device, the target information including at least: signature verification information of the target client device and parameter information of the target client device; a third verification unit, used to verify the target information to obtain a third verification result; a second generation unit, used to randomly generate target luminescence information and target coordinate information when the third verification result meets the second preset requirements; and a first sending unit, used to send an error message to the target client device when the third verification result does not meet the second preset requirements.

[0113] Optionally, in the facial liveness detection device provided in an embodiment of the present application, the first generation unit includes: a first configuration module, used to configure the first parameters of the display device, wherein the first parameters include at least a dictionary of the luminous color of the display device, the duration corresponding to the luminous color, and the position of the gaze point in the display device; a first generation module, used to randomly generate target luminous information and target coordinate information based on the first parameters in combination with a target random algorithm.

[0114] Optionally, in the face liveness detection device provided in the embodiment of the present application, the device also includes: a fourth acquisition unit, used to obtain a real-time video stream through a camera in a display device before the target parameters of the target object meet the first preset requirements; a fifth acquisition unit, used to obtain facial information in the current image from the video stream, and obtain target parameters from the facial information; a first judgment unit, used to judge whether the target parameters meet the first preset requirements; a second control unit, used to control the display device to emit light of different colors and display target prompt information at the first coordinate in the display device according to the target luminous information and target coordinate information when the target parameters meet the first preset requirements; a second sending unit, used to send a first prompt information to the target object when the target parameters do not meet the first preset requirements, wherein the first prompt information is used to prompt the target object to change the target parameters.

[0115] Optionally, in the facial liveness detection device provided in an embodiment of the present application, the first acquisition unit includes: a first extraction module, used to extract a frontal facial image that meets the target liveness detection request from the video stream according to the frame rate during the process of changes in the color of the light of the display device and the change in the gaze point of the target object's eyeball; a second generation module, used to obtain facial image information of the target object during the change of light and gaze point based on the frontal facial image.

[0116] The human face liveness detection device includes a processor and a memory. The above-mentioned first receiving unit 801, first generating unit 802, second receiving unit 803 and first analyzing unit 804 are all stored in the memory as program units, and the processor executes the above-mentioned program units stored in the memory to realize corresponding functions.

[0117] The processor contains a kernel, which calls the corresponding program unit from the memory. One or more kernels can be set, and the accuracy of face liveness detection can be improved by adjusting the kernel parameters.

[0118] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0119] An embodiment of the present invention provides a processor, which is used to run a program, wherein the method for detecting living face is executed when the program is run.

[0120] like Figure 9 As shown, an embodiment of the present invention provides an electronic device, which includes a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, the following steps are implemented: receiving a target liveness detection request sent by a target client device, wherein the target liveness detection request is used to perform liveness detection on the face of a target object; after receiving the target liveness detection request, randomly generating target luminescence information and target coordinate information, and sending the target luminescence information and the target coordinate information to the target client device, wherein the target luminescence information at least includes: the luminescence color of a display device in the target client device and the duration corresponding to the luminescence color, and the target coordinate information is used to represent the coordinates of a gaze point in the display device; after sending the target luminescence information and the target coordinate information to the target client device, receiving eye image information of the target object returned by the target client device, wherein the eye image information is image information generated based on the target luminescence information and the target coordinate information; and analyzing the eye image information to determine a result of liveness detection on the face of the target object.

[0121] When the processor executes the program, the following steps are also implemented: after randomly generating target luminescence information and target coordinate information, the method also includes: when the target parameters of the target object meet the first preset requirements, based on the target luminescence information and the target coordinate information, controlling the display device to emit light of different colors and display target prompt information at the first coordinate in the display device, wherein the target parameters include at least: the angle and distance between the face of the target object and the display device, and the occlusion of the face of the target object, and the target prompt information is used to prompt the target object's gaze point to move with the prompt content; collecting the facial image information of the target object during the change of light and gaze point; extracting the image of the eye area in the facial image information to obtain the eye image information, and sending the eye image information to the target cloud server corresponding to the target client device.

[0122] When the processor executes the program, the following steps are further implemented: analyzing the eye image information to determine a result of liveness detection on the face of the target object, including: analyzing the reflective information of the eyeball in the eye image information to obtain first reflective information, wherein the first reflective information includes at least: a reflective color of the eyeball and a duration corresponding to the reflective color; analyzing the gaze point information of the eyeball in the eye image information to obtain coordinate information of the gaze point of the eyeball; determining whether the first reflective information is the same as the target luminous information, and determining whether the coordinate information of the gaze point of the eyeball is the same as the target coordinate information; if the first reflective information is the same as the target luminous information, and the coordinate information of the gaze point of the eyeball is the same as the target coordinate information, determining that the result of liveness detection on the face of the target object is that the face is live; if the first reflective information is different from the target luminous information, and / or the coordinate information of the gaze point of the eyeball is different from the target coordinate information, determining that the result of liveness detection on the face of the target object is that the face is not live.

[0123] When the processor executes the program, the following steps are also implemented: before analyzing the reflective information of the eyeball in the eye image information, the method also includes: decomposing the eye image information into an illumination component and a reflection component; filtering the illumination component and the reflection component to obtain a Fourier spectrum; determining the difference between planar imaging and stereoscopic imaging based on the Fourier spectrum; detecting whether the eye image information is stereoscopic based on the difference; and if the eye image information is stereoscopic, analyzing the reflective information of the eyeball in the eye image information.

[0124] When the processor executes the program, the following steps are also implemented: after analyzing the reflective information of the eyeball in the eye image information to obtain first reflective information, the method further includes: obtaining the reflective characteristics of multiple frames of RGB images of the eyeball in the eye image information under different lighting conditions; verifying the first reflective information based on the reflective characteristics and the target luminous information to obtain a first verification result; and determining a confidence value of the eyeball's reflection based on the first verification result.

[0125] When the processor executes the program, the following steps are also implemented: analyzing the eye's gaze point information in the eye image information to obtain the coordinate information of the eye's gaze point, including: extracting the outline of the pupil of the target object's eye from the eye image information; obtaining the center position of the pupil based on the pupil outline; obtaining the center position of the cornea of ​​the target object's eye based on the eye image information; calculating the offset between the center of the pupil and the center of the cornea based on the center position of the pupil and the center position of the cornea; determining the displacement of the eye in each frame of the eye image information based on the offset between the center of the pupil and the center of the cornea; mapping the eye's gaze point on the display device in combination with the eye model, and obtaining the coordinate information of the eye's gaze point.

[0126] When the processor executes the program, the following steps are also implemented: after analyzing the eyeball's gaze point information in the eye image information and obtaining the coordinate information of the eyeball's gaze point, the method also includes: verifying the coordinate information of the eyeball's gaze point based on the target coordinate information to obtain a second verification result; determining the confidence value of the eyeball's gaze point based on the second verification result; obtaining the confidence value of the eyeball's reflection; and determining the result of liveness detection on the target object's face based on the confidence value of the eyeball's reflection and the confidence value of the eyeball's gaze point.

[0127] When the processor executes the program, the following steps are also implemented: after receiving the target liveness detection request sent by the target client device, the method also includes: obtaining target information in the target liveness detection request, the target information including at least: signature verification information of the target client device and parameter information of the target client device; verifying the target information to obtain a third verification result; if the third verification result meets the second preset requirement, randomly generating the target luminescence information and the target coordinate information; if the third verification result does not meet the second preset requirement, sending an error message to the target client device.

[0128] When the processor executes the program, the following steps are also implemented: randomly generating target luminous information and target coordinate information includes: configuring the first parameter of the display device, wherein the first parameter at least includes a dictionary of the luminous color of the display device, the duration corresponding to the luminous color, and the position of the gaze point in the display device; based on the first parameter, combined with the target random algorithm, randomly generating the target luminous information and the target coordinate information.

[0129] When the processor executes the program, the following steps are also implemented: before the target parameters of the target object meet the first preset requirements, the method also includes: obtaining a real-time video stream through the camera in the display device; obtaining facial information in the current image from the video stream, and obtaining the target parameters from the facial information; judging whether the target parameters meet the first preset requirements; when the target parameters meet the first preset requirements, controlling the display device to emit light of different colors and display target prompt information at the first coordinate in the display device based on the target luminous information and the target coordinate information; when the target parameters do not meet the first preset requirements, sending a first prompt message to the target object, wherein the first prompt message is used to prompt the target object to change the target parameters.

[0130] When the processor executes the program, it further implements the following steps: collecting facial image information of the target object during changes in lighting and gaze point includes: extracting a frontal facial image that meets the target liveness detection request from the video stream at a frame rate during changes in the color of the display device's lighting and the target object's eye gaze point; and obtaining facial image information of the target object during changes in lighting and gaze point based on the frontal facial image. The device herein may be a server, PC, PAD, mobile phone, etc.

[0131] The present application also provides a computer program product, which, when executed on a data processing device, is suitable for executing a program initialized with the following method steps: receiving a target liveness detection request sent by a target client device, wherein the target liveness detection request is used to perform liveness detection on the face of a target object; after receiving the target liveness detection request, randomly generating target luminescence information and target coordinate information, and sending the target luminescence information and the target coordinate information to the target client device, wherein the target luminescence information at least includes: the luminescence color of a display device in the target client device and the duration corresponding to the luminescence color, and the target coordinate information is used to represent the coordinates of a gaze point in the display device; after sending the target luminescence information and the target coordinate information to the target client device, receiving eye image information of the target object returned by the target client device, wherein the eye image information is image information generated based on the target luminescence information and the target coordinate information; analyzing the eye image information to determine the result of liveness detection on the face of the target object.

[0132] When executed on a data processing device, it is also suitable for executing a program initialized with the following method steps: after randomly generating target luminescence information and target coordinate information, the method also includes: when the target parameters of the target object meet the first preset requirements, according to the target luminescence information and the target coordinate information, controlling the display device to emit light of different colors and display target prompt information at the first coordinate in the display device, wherein the target parameters include at least: the angle and distance between the face of the target object and the display device, and the occlusion of the face of the target object, and the target prompt information is used to prompt the gaze point of the target object to move with the prompt content; collecting the facial image information of the target object during the change of light and gaze point; extracting the image of the eye area in the facial image information to obtain the eye image information, and sending the eye image information to the target cloud server corresponding to the target client device.

[0133] When executed on a data processing device, the program is also suitable for executing initialization with the following method steps: analyzing the eye image information to determine the result of liveness detection on the face of the target object, including: analyzing the reflective information of the eyeball in the eye image information to obtain first reflective information, wherein the first reflective information at least includes: the reflective color of the eyeball and the duration corresponding to the reflective color; analyzing the gaze point information of the eyeball in the eye image information to obtain the coordinate information of the gaze point of the eyeball; judging whether the first reflective information is consistent with the target luminous information The first reflective information is the same as the target luminous information, and the coordinate information of the eyeball's gaze point is the same as the target coordinate information; when the first reflective information is the same as the target luminous information, and the coordinate information of the eyeball's gaze point is the same as the target coordinate information, it is determined that the result of the liveness detection on the target object's face is that the face is alive; when the first reflective information is different from the target luminous information, and / or the coordinate information of the eyeball's gaze point is different from the target coordinate information, it is determined that the result of the liveness detection on the target object's face is that the face is not alive.

[0134] When executed on a data processing device, it is also suitable for executing a program initialized with the following method steps: before analyzing the reflective information of the eyeball in the eye image information, the method also includes: decomposing the eye image information into an illumination component and a reflection component; filtering the illumination component and the reflection component to obtain a Fourier spectrum; determining the difference between planar imaging and stereoscopic imaging based on the Fourier spectrum; detecting whether the eye image information is stereoscopic based on the difference; and analyzing the reflective information of the eyeball in the eye image information when the eye image information is stereoscopic.

[0135] When executed on a data processing device, it is also suitable for executing a program initialized with the following method steps: after analyzing the reflective information of the eyeball in the eye image information to obtain first reflective information, the method also includes: obtaining the reflective characteristics of multiple frames of RGB images of the eyeball in the eye image information under different lighting conditions; verifying the first reflective information based on the reflective characteristics and the target luminescence information to obtain a first verification result; and determining the confidence value of the reflection of the eyeball based on the first verification result.

[0136] When executed on a data processing device, it is also suitable for executing a program initialized with the following method steps: analyzing the gaze point information of the eyeball in the eye image information to obtain the coordinate information of the gaze point of the eyeball, including: extracting the outline of the pupil of the target object's eye from the eye image information; obtaining the center position of the pupil based on the outline of the pupil; obtaining the center position of the cornea of ​​the target object's eye based on the eye image information; calculating the offset between the center of the pupil and the center of the cornea based on the center position of the pupil and the center position of the cornea; determining the displacement of the eye in each frame of the eye image information based on the offset between the center of the pupil and the center of the cornea; mapping the gaze point of the eyeball on the display device in combination with the eyeball model, and obtaining the coordinate information of the gaze point of the eyeball.

[0137] When executed on a data processing device, it is also suitable for executing a program initialized with the following method steps: after analyzing the eyeball's gaze point information in the eye image information to obtain the coordinate information of the eyeball's gaze point, the method also includes: verifying the coordinate information of the eyeball's gaze point based on the target coordinate information to obtain a second verification result; determining the confidence value of the eyeball's gaze point based on the second verification result; obtaining the confidence value of the eyeball's reflection; and determining the result of liveness detection on the target object's face based on the confidence value of the eyeball's reflection and the confidence value of the eyeball's gaze point.

[0138] When executed on a data processing device, it is also suitable for executing a program initialized with the following method steps: after receiving a target liveness detection request sent by a target client device, the method also includes: obtaining target information in the target liveness detection request, the target information at least including: signature verification information of the target client device and parameter information of the target client device; verifying the target information to obtain a third verification result; if the third verification result meets the second preset requirement, randomly generating the target luminescence information and the target coordinate information; if the third verification result does not meet the second preset requirement, sending an error message to the target client device.

[0139] When executed on a data processing device, it is also suitable for executing a program initialized with the following method steps: randomly generating target luminous information and target coordinate information including: configuring a first parameter of the display device, wherein the first parameter includes at least a dictionary of the luminous color of the display device, the duration corresponding to the luminous color, and the position of the gaze point in the display device; based on the first parameter, combined with a target random algorithm, randomly generating the target luminous information and the target coordinate information.

[0140] When executed on a data processing device, it is also suitable for executing a program initialized with the following method steps: before the target parameters of the target object meet the first preset requirements, the method also includes: obtaining a real-time video stream through the camera in the display device; obtaining facial information in the current image from the video stream, and obtaining the target parameters from the facial information; judging whether the target parameters meet the first preset requirements; when the target parameters meet the first preset requirements, controlling the display device to emit light of different colors and display target prompt information at the first coordinate in the display device based on the target luminous information and the target coordinate information; when the target parameters do not meet the first preset requirements, sending a first prompt message to the target object, wherein the first prompt message is used to prompt the target object to change the target parameters.

[0141] When executed on a data processing device, it is also suitable for executing an initialized program having the following method steps: collecting facial image information of the target object during changes in light and gaze point, including: extracting a frontal facial image that meets the target liveness detection request from the video stream according to the frame rate during changes in the color of the light of the display device and changes in the gaze point of the target object's eyeballs; and obtaining facial image information of the target object during changes in light and gaze point based on the frontal facial image.

[0142] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can 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 can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0143] 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 produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the steps in the process. 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.

[0144] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work 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 The function specified in one or more boxes.

[0145] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0146] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0147] The memory may include non-permanent memory 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.

[0148] Computer-readable media includes permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. The information can be computer-readable instructions, data structures, program modules 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 disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, 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 transitory computer-readable media (transitory media), such as modulated data signals and carrier waves.

[0149] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

[0150] 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 take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0151] The above are merely 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 modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should all be included within the scope of the claims of the present application.

Claims

1. A method for detecting a living face, characterized in that: include: Receiving a target liveness detection request sent by a target client device, wherein the target liveness detection request is used to perform liveness detection on a face of a target object; After receiving the target liveness detection request, randomly generating target luminescence information and target coordinate information, and sending the target luminescence information and the target coordinate information to the target client device, wherein the target luminescence information at least includes: the luminescence color of the display device in the target client device and the duration corresponding to the luminescence color, and the target coordinate information is used to represent the coordinates of the gaze point in the display device; After sending the target luminescence information and the target coordinate information to the target client device, receiving eye image information of the target object returned by the target client device, wherein the eye image information is image information generated based on the target luminescence information and the target coordinate information; Analyzing the eye image information to determine a result of liveness detection on the face of the target object; Analyzing the eye image information to determine a result of liveness detection on the face of the target object includes: Analyzing the reflection information of the eyeball in the eye image information to obtain first reflection information, wherein the first reflection information at least includes: the reflection color of the eyeball and the duration corresponding to the reflection color; Before analyzing the light reflection information of the eyeball in the eye image information, the method further includes: Decomposing the eye image information into an illumination component and a reflection component; Filtering the illumination component and the reflection component to obtain a Fourier spectrum; determining the difference between planar imaging and stereoscopic imaging based on the Fourier spectrum; detecting whether the eye image information is stereoscopic according to the difference; In the case where the eye image information has stereoscopic properties, the reflection information of the eyeball in the eye image information is analyzed.

2. The method according to claim 1, characterized in that After randomly generating target luminescence information and target coordinate information, the method further includes: When the target parameters of the target object meet the first preset requirements, the display device is controlled to emit light of different colors and display target prompt information at the first coordinate in the display device according to the target luminescence information and the target coordinate information, wherein the target parameters include at least: the angle and distance between the face of the target object and the display device, and the occlusion of the face of the target object; the target prompt information is used to prompt the target object's gaze point to move along with the prompt content; Collecting facial image information of the target object during changes in light and gaze point; An image of the eye area in the facial image information is extracted to obtain the eye image information, and the eye image information is sent to a target cloud server corresponding to the target client device.

3. The method according to claim 1, characterized in that Analyzing the eye image information to determine a result of liveness detection on the face of the target object includes: Analyzing the gaze point information of the eyeball in the eye image information to obtain coordinate information of the gaze point of the eyeball; determining whether the first reflected light information is the same as the target luminous information, and determining whether the coordinate information of the gaze point of the eyeball is the same as the target coordinate information; When the first light reflection information is identical to the target light emission information, and the coordinate information of the gaze point of the eyeball is identical to the target coordinate information, determining that the result of the liveness detection on the face of the target object is that the face is alive; When the first reflective information is different from the target luminous information, and / or the coordinate information of the eyeball's gaze point is different from the target coordinate information, it is determined that the result of liveness detection on the target object's face is that the face is not alive.

4. The method according to claim 3, characterized in that After analyzing the reflective information of the eyeball in the eye image information to obtain first reflective information, the method further includes: Obtaining reflection characteristics of multiple frames of RGB images of eyeballs under different lighting conditions in the eye image information; Verifying the first reflected light information according to the reflection characteristic and the target luminescence information to obtain a first verification result; Determine a confidence value of the eyeball's reflection based on the first verification result.

5. The method according to claim 3, characterized in that Analyzing the eyeball gaze point information in the eye image information to obtain the coordinate information of the eyeball gaze point includes: extracting the outline of the pupil of the target object's eye from the eye image information; Obtaining the center position of the pupil according to the outline of the pupil; Obtaining the center position of the cornea of ​​the target object's eye based on the eye image information; Calculating an offset between the center of the pupil and the center of the cornea according to the center position of the pupil and the center position of the cornea; determining a displacement of an eye in each frame of the eye image information according to an offset between a center of the pupil and a center of the cornea; The gaze point of the eyeball is mapped onto the display device in combination with the eyeball model, and coordinate information of the gaze point of the eyeball is obtained.

6. The method according to claim 4, characterized in that After analyzing the eye gaze point information in the eye image information to obtain the coordinate information of the eye gaze point, the method further includes: Verifying the coordinate information of the gaze point of the eyeball according to the target coordinate information to obtain a second verification result; Determining a confidence value of the gaze point of the eyeball according to the second verification result; Obtaining a confidence value of the reflection of the eyeball; A result of liveness detection on the face of the target object is determined based on the confidence value of the reflection of the eyeball and the confidence value of the gaze point of the eyeball.

7. The method according to claim 1, characterized in that After receiving the target liveness detection request sent by the target client device, the method further includes: Obtain target information in the target liveness detection request, the target information including at least: signature verification information of the target client device and parameter information of the target client device; Verifying the target information to obtain a third verification result; When the third verification result meets the second preset requirement, randomly generating the target luminescence information and the target coordinate information; If the third verification result does not meet the second preset requirement, an error message is sent to the target client device.

8. The method according to claim 1, characterized in that Randomly generated target luminescence information and target coordinate information include: Configuring first parameters of the display device, wherein the first parameters include at least a dictionary of the luminous color of the display device, a duration corresponding to the luminous color, and a position of a gaze point in the display device; Based on the first parameter and in combination with a target random algorithm, the target luminescence information and the target coordinate information are randomly generated.

9. The method according to claim 2, characterized in that Before the target parameter of the target object meets the first preset requirement, the method further includes: Acquire a real-time video stream through a camera in the display device; Obtaining facial information in a current image from the video stream, and obtaining the target parameters from the facial information; Determining whether the target parameter meets the first preset requirement; When the target parameter meets the first preset requirement, controlling the display device to emit light of different colors and displaying target prompt information at the first coordinate in the display device according to the target light emitting information and the target coordinate information; When the target parameter does not meet the first preset requirement, a first prompt message is sent to the target object, wherein the first prompt message is used to prompt the target object to change the target parameter.

10. The method according to claim 9, characterized in that Collecting facial image information of the target object during changes in light and gaze point includes: Extracting a frontal face image that meets the target living body detection request from the video stream according to a frame rate during a process in which the color of the light on the display device and the gaze point of the target object's eyeball change; Based on the frontal face image, facial image information of the target object during changes in light and gaze point is obtained.

11. A device for detecting human face liveness, characterized in that: include: A first receiving unit is configured to receive a target liveness detection request sent by a target client device, wherein the target liveness detection request is used to perform liveness detection on a face of a target object; a first generating unit, configured to randomly generate target luminescence information and target coordinate information after receiving the target liveness detection request, and send the target luminescence information and the target coordinate information to the target client device, wherein the target luminescence information includes at least: a luminescence color of a display device in the target client device and a duration corresponding to the luminescence color, and the target coordinate information is used to represent the coordinates of a gaze point in the display device; a second receiving unit, configured to receive eye image information of the target object returned by the target client device after sending the target luminescence information and the target coordinate information to the target client device, wherein the eye image information is image information generated based on the target luminescence information and the target coordinate information; a first analyzing unit, configured to analyze the eye image information and determine a result of liveness detection on the face of the target object; The first analysis unit includes: a first analysis subunit, configured to analyze the reflective information of the eyeball in the eye image information to obtain first reflective information, wherein the first reflective information at least includes: the reflective color of the eyeball and the duration corresponding to the reflective color; The device also includes: a first decomposition unit, used to decompose the eye image information into an illumination component and a reflection component before analyzing the reflection information of the eyeball in the eye image information; a first filtering unit, used to filter the illumination component and the reflection component to obtain a Fourier spectrum; a first determination unit, used to determine the difference between planar imaging and stereoscopic imaging based on the Fourier spectrum; a first detection unit, used to detect whether the eye image information has stereoscopic properties based on the difference; and a second analysis unit, used to analyze the reflection information of the eyeball in the eye image information if the eye image information has stereoscopic properties.

12. A processor, characterized in that: The processor is used to run a program, wherein the program, when running, executes the method for detecting a living face according to any one of claims 1 to 10.

13. An electronic device, characterized in that: The device comprises one or more processors and a memory, wherein the memory is used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the method for detecting a living face as described in any one of claims 1 to 10.

Images