Living body detection method and device and related equipment

Abstract

The invention provides a living body detection method and device and related equipment, and the method comprises the steps: determining the position information of an eye watching position of a target object according to an image sequence of the target object collected by a terminal, and carrying out the living body detection of the target object according to the light spot position information of a light spot and the watching position information; wherein the image sequence is acquired by the terminal in the process of displaying the light spots for multiple times, the light spot position information indicates the positions of the light spots displayed for multiple times on the acquisition interface, one light spot is displayed on the acquisition interface every time, and the positions of the light spots appearing for two adjacent times are different. When living body detection needs to be carried out, the light spots are displayed on the screen of the terminal for multiple times, and whether the target object is a living body or not is determined by analyzing the matching degree of the eyeball watching position of the target object and the light spot display position. The accuracy of living body detection can be improved, verification of counterfeit legal users through methods such as photos or videos is avoided, and the safety of the system is improved.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a living body detection method, device and related equipment. Background Art

[0002] Currently, face recognition technology is widely used in the fields of mobile payment and attendance. In the process of recognizing a face image, it is also necessary to determine whether the face image is a live face image or a face image in a photo or recorded video, so as to prevent attackers from impersonating legitimate users by making fake images of legitimate users (such as photos, videos or high-imitation masks, etc.). Therefore, how to achieve effective liveness detection is a technical problem that needs to be solved urgently. Summary of the invention

[0003] The present application provides a method, device and related equipment for detecting liveness, which can display a light spot on the screen of a terminal multiple times, and determine whether the target object is alive by analyzing the matching degree between the position where the target object's eyeball is looking and the position where the light spot is displayed. It can improve the accuracy of liveness detection, avoid impersonating a legitimate user for verification through methods such as photos or videos, and improve the security of the system.

[0004] In the first aspect, the present application provides a method for liveness detection, which is applied to a server, and the method includes: the server obtains an image sequence of a target object collected by a terminal, determines the gaze position information of the target object in the image sequence by analyzing the image sequence, and then performs liveness detection on the target object based on the light spot position information and the above gaze position information to determine whether the target object is a real live person. Wherein, the gaze position information includes information on one or more positions where the eyes of the target object are gazed; the image sequence is collected by the above terminal in the process of displaying the light spot multiple times, and the image sequence includes multiple images containing the target object; the light spot position information indicates the position of the light spot displayed multiple times on the acquisition interface, and one light spot is displayed on the acquisition interface each time, and the positions of two adjacent light spots are different.

[0005] When liveness detection is required, a light spot is displayed multiple times on the screen of the terminal on the user side. During the display of the light spot, multiple images including the target object are collected, the position of the target object's eye gaze is analyzed based on the image, and the position of the target object's eye gaze is matched with the position of the light spot displayed multiple times, thereby determining whether the target object is a real person. This can improve the accuracy of liveness detection, prevent criminals from impersonating legitimate users for verification through photos, videos or masks, and improve the security of the system.

[0006] In a possible implementation, the server provides the terminal with the acquisition interface, which displays the light spot multiple times. The positions of the light spots displayed multiple times on the acquisition interface are determined according to the light spot position information.

[0007] The server generates a collection interface and provides it to the terminal for display, so that the liveness detection method can be deployed through a cloud service or a browser-server mode, thereby reducing the user's usage cost.

[0008] In a possible implementation, the server provides a configuration interface for setting the detection level to the terminal, and obtains and records the target detection level configured by the user in the configuration interface. Different detection levels correspond to different light spot display modes, and different light spot display modes have different degrees of complexity. For example, different levels of light spot display modes display light spots at different times.

[0009] By providing a configuration interface, users can set the detection level according to actual needs to meet the needs of different users and improve user experience.

[0010] In a possible implementation, before the server provides the acquisition interface to the terminal, in the case where the target object triggers liveness detection, the server generates the spot position information according to the target detection level. Different target detection levels correspond to different spot display modes. After the target object triggers liveness detection, the server will receive a liveness detection request. For example, after the server receives the account and password and passes the verification, the server generates the corresponding spot position information according to the spot display mode configured by the user corresponding to the account.

[0011] In a possible implementation, during the process of displaying the light spot multiple times on the acquisition interface, the duration of each display of the light spot is the same; during the process of displaying the light spot multiple times on the acquisition interface, the duration of each display of the light spot is not completely the same.

[0012] The duration of the light spot displayed on the acquisition interface each time is different. If the target object is a real person, the length of time the target object stares at each position will also be different. This further increases the difficulty of authentication using photos or videos and improves the security of the system.

[0013] In a possible implementation, during the process of displaying the light spot multiple times on the acquisition interface, a background of one or more colors is displayed on the acquisition interface, wherein the color of the background is different from the color of the light spot.

[0014] When the background of the acquisition interface can change color, the probability that the target object is a real person and the probability that the target object is a prosthesis can be determined by analyzing the target object's reflection of different colors of light through facial images, and can be used to assist liveness detection based on light spot position information and the target object's gaze position information.

[0015] In a possible implementation, when the light spot is displayed multiple times on the acquisition interface, the distance between the center points of two adjacent light spots is greater than the distance threshold. In this way, when performing liveness detection later, if the target object is a real live object, it is easier to detect changes in the line of sight or focus position of the target object, thereby improving the accuracy of detection.

[0016] In a possible implementation, the above-mentioned liveness detection of the target object based on the light spot position information of the light spot and the gaze position information includes: matching the light spot position information and the gaze position information, and determining that the target object is a real living person when the matching degree between the light spot position information and the gaze position information is greater than a first threshold.

[0017] The light spot position information obtained above and the gaze position information of the target object are compared and analyzed. Only when the matching degree between the light spot position information and the gaze position information reaches a certain value, it is confirmed that the target object is a real person, and then the subsequent process, such as face recognition, is executed to confirm whether the target object is a legitimate user.

[0018] In a possible implementation, the above-mentioned liveness detection of the target object based on the light spot position information and the gaze position information of the light spot includes: determining the gaze duration information of the target object based on the image sequence, and then performing liveness detection on the target object based on the light spot position information and the duration information of the light spot, as well as the gaze position information and the gaze duration information of the target object; wherein the gaze duration information includes the duration of each of one or more positions gazed by the target object, and each position corresponds to a gaze duration; the duration information includes the duration of each display of the light spot, and the acquisition interface displays a light spot once corresponding to one position and a duration.

[0019] When the server matches the gaze position information with the gaze position of the target object, the server also compares the duration of the light spot displayed at each position with the gaze duration of the target object at that position. When the error between the duration at a position and the gaze duration at that position is less than the error threshold, the server determines that the gaze position of the target object matches the display position of the light spot.

[0020] In a possible implementation, the above-mentioned liveness detection of the target object based on the spot position information and the gaze position information of the light spot includes: determining the matching degree between the spot position information and the gaze position information based on the spot position information and the gaze position information of the light spot; determining the probability that the target object is a real living person based on the image sequence; wherein the images in the image sequence include human faces; and performing liveness detection on the target object based on the matching degree and the probability that the target object is a real living person.

[0021] Whether the target object is a real person is determined by the face information included in the image in the image sequence, and then the matching degree of the light spot position information and the gaze position information is combined to jointly judge whether the target object is a real person, which can improve the accuracy of the judgment and improve the security of the system.

[0022] In a second aspect, the present application provides a liveness detection method, including: a terminal displays a light spot on an acquisition interface multiple times, wherein a light spot is displayed on the acquisition interface each time, and the positions of two adjacent light spots are different; the terminal acquires an image sequence of the target object in the process of displaying the light spot multiple times, and the image sequence includes multiple images containing the target object; wherein the image sequence is used to determine gaze position information of the target object, and the gaze position information and the light spot position information of the light spot are used to perform liveness detection on the target object; the gaze position information includes information on one or more positions where the eyes of the target object are gazed, and the light spot position information includes position information of the light spot that appears multiple times on the acquisition interface.

[0023] When liveness detection is required, a light spot is displayed multiple times on the screen of the terminal. During the display of the light spot, multiple images including the target object are collected, so that the subsequent terminal or server can analyze the position of the target object's eyes based on the image, and match the position of the target object's eyes with the positions of the light spots displayed multiple times, thereby determining whether the target object is a real person. This can improve the accuracy of liveness detection, prevent criminals from impersonating legitimate users for verification through photos, videos or masks, and improve the security of the system.

[0024] In a possible implementation, before the terminal displays the light spot multiple times on the acquisition interface, it also includes: the terminal displays a configuration interface, obtains and records the target detection level configured by the user on the configuration interface; the configuration interface is used to instruct the user to configure the detection level; wherein different detection levels correspond to different light spot display modes; the terminal displays the light spot multiple times on the acquisition interface, including: when the target object triggers liveness detection, the terminal displays the light spot multiple times on the acquisition interface according to the light spot display mode corresponding to the target detection level.

[0025] In a possible implementation, when the terminal displays the light spot multiple times on the acquisition interface, the duration of each display of the light spot is the same, or when the terminal displays the light spot multiple times on the acquisition interface, the duration of each display of the light spot is not exactly the same.

[0026] In a possible implementation, during the process of displaying the light spot multiple times on the acquisition interface, the terminal displays a background of one or more colors on the acquisition interface, wherein the color of the background is different from the color of the light spot.

[0027] In a possible implementation, when the terminal displays the light spot multiple times on the acquisition interface, the distance between the center points of the light spots displayed twice adjacently is greater than a distance threshold.

[0028] In a possible implementation, the method further includes: the terminal matches the light spot position information and the gaze position information, performs liveness detection on the target object, and determines that the target object is a live person when the degree of match between the light spot position information and the gaze position information is greater than a first threshold.

[0029] In a possible implementation, the method further includes: the terminal determines the gaze duration information of the target object based on the image sequence; and performs liveness detection on the target object based on the light spot position information and the duration information of the light spot, as well as the gaze position information and the gaze duration information of the target object; wherein the gaze duration information includes the duration of each of one or more positions of the target object's gaze, and each position corresponds to a gaze duration; the duration information includes the duration of each time the terminal displays the light spot, and the acquisition interface displays a light spot once corresponding to one position and one duration.

[0030] In a possible implementation, the method further includes: the terminal determines the degree of matching between the light spot position information and the gaze position information based on the light spot position information and the gaze position information of the light spot; the terminal determines the probability that the target object is a real living person based on the image sequence; wherein the images in the image sequence include faces; the terminal performs liveness detection on the target object based on the degree of matching and the probability that the target object is a real living person.

[0031] In a possible implementation, the method further includes: the terminal sends the image sequence and the light spot information corresponding to the terminal displaying the light spot multiple times to the server, so that the server performs liveness detection on the target object according to the image sequence and the light spot information; wherein the light spot information includes the light spot position information, or the light spot information includes the light spot position information and duration information, the duration information includes the duration of each time the terminal displays the light spot, and displaying a light spot once on the acquisition interface corresponds to one position and one duration.

[0032] The image sequence is sent to the server, which has more sufficient resources than the terminal. The server can quickly implement liveness detection and improve the efficiency of detection.

[0033] In a third aspect, the present application provides a living body detection device, comprising:

[0034] A communication module, used for acquiring an image sequence of a target object acquired by a terminal, wherein the image sequence is acquired by the terminal in a process of displaying light spots for multiple times, and the image sequence includes multiple images containing the target object;

[0035] A processing module is used to determine the gaze position information of the target object according to the image sequence; the gaze position information includes information on one or more positions where the eyes of the target object are gazed; and then perform liveness detection on the target object according to the light spot position information and the gaze position information of the light spot; wherein the light spot position information includes position information of the light spot appearing in the process of the terminal displaying the light spot multiple times, the terminal displays one light spot on the acquisition interface each time, and the positions of two adjacent light spots appearing are different.

[0036] In a possible implementation, the device further includes an interface providing module, which is used to provide a collection interface to the terminal, and the collection interface will display the light spot multiple times, and the positions of the light spots displayed multiple times on the collection interface are determined according to the light spot position information.

[0037] The above-mentioned liveness detection device is used to implement the operations implemented by the server in the above-mentioned first aspect or any possible implementation method of the first aspect, which will not be repeated here.

[0038] In a fourth aspect, the present application provides a living body detection device, comprising:

[0039] A display module, used to display the light spot on the acquisition interface multiple times, wherein one light spot is displayed on the acquisition interface each time, and the positions where two adjacent light spots appear are different;

[0040] An acquisition module is used to acquire an image sequence of a target object during multiple displays of a light spot, wherein the image sequence includes multiple images containing the target object; wherein the image sequence is used to determine gaze position information of the target object, and the gaze position information and the light spot position information of the light spot are used to perform liveness detection on the target object; the gaze position information includes information on one or more positions where the eyes of the target object are gazed, and the light spot position information includes position information of the light spot that appears multiple times on the acquisition interface.

[0041] In a possible implementation, the device further includes: a processing module for matching the light spot position information and the gaze position information, performing liveness detection on the target object, and determining that the target object is a real live person when the matching degree between the light spot position information and the gaze position information is greater than a first threshold.

[0042] The above-mentioned liveness detection device is used to implement the operations implemented by the terminal in the above-mentioned second aspect or any possible implementation manner of the second aspect, which will not be described in detail here.

[0043] In a fifth aspect, the present application provides a computing device cluster, which includes at least one computing device, each computing device including a processor and a memory, and the processor of the at least one computing device is used to execute instructions stored in the memory of the at least one computing device, so that the computing device cluster performs the method described in the first aspect or any possible implementation of the first aspect.

[0044] In a sixth aspect, the present application provides a terminal device, comprising a processor and a memory, wherein the memory is used to store instructions, and the processor is used to execute the instructions. When the processor executes the instructions, the method described in the second aspect or any possible implementation method of the second aspect is implemented.

[0045] In a seventh aspect, the present application provides a computer-readable storage medium, comprising computer program instructions. When the computer program instructions are executed by a computing device cluster, the computing device cluster executes the method as described in the first aspect or any possible implementation of the first aspect.

[0046] In an eighth aspect, the present application provides a computer-readable storage medium, which stores instructions. When the instructions are executed on a terminal, the terminal executes the method described in the second aspect or any possible implementation of the second aspect.

[0047] In a ninth aspect, the present application provides a computer program product. When the computer program product is run on a computing device cluster, the computing device cluster executes the method described in the first aspect or any possible implementation of the first aspect.

[0048] In a tenth aspect, the present application provides a computer program product. When the computer program product runs on a terminal, the terminal executes the method described in the second aspect or any possible implementation manner of the second aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0050] Figure 1 is a schematic diagram of a liveness detection system provided in an embodiment of the present application;

[0051] Figure 2 It is a flow chart of a living body detection method provided in an embodiment of the present application;

[0052] Figure 3is a schematic diagram of a configuration interface provided in an embodiment of the present application;

[0053] Figure 4 is a schematic diagram of a light spot display mode provided in an embodiment of the present application;

[0054] Figure 5 is a schematic diagram of a liveness detection method provided in an embodiment of the present application;

[0055] Figure 6 It is a flow chart of another living body detection method provided in an embodiment of the present application;

[0056] Figure 7 is a schematic diagram of a living body detection device provided in an embodiment of the present application;

[0057] Figure 8 is a schematic diagram of another living body detection device provided in an embodiment of the present application;

[0058] Fig. 9 is a schematic diagram of a computing device provided in an embodiment of the present application;

[0059] Fig.10 It is a schematic diagram of a computing device cluster provided in an embodiment of the present application. DETAILED DESCRIPTION

[0060] The technical solution in this application will be described below in conjunction with the accompanying drawings.

[0061] At present, face recognition systems face many potential security risks. Attackers can create fakes of the attacked (such as photos, videos, high-imitation masks, etc.) and impersonate the faces of legitimate users for face recognition. In particular, the development of artificial intelligence (AI) technology has not only greatly reduced the time and economic costs of synthesizing photos or videos, but also made it more difficult to identify whether photos or videos are synthesized, resulting in increased security risks for face recognition systems. Therefore, how to achieve effective liveness detection is a technical problem that needs to be solved urgently.

[0062] The present application provides a liveness detection method, in which a terminal can display a light spot on the screen multiple times. In the process of displaying the light spot on the screen multiple times, the terminal collects an image sequence of the target object through an image acquisition device, and the image sequence includes multiple images containing the target object. Among them, the image sequence of the target object can be used to determine the gaze position information of the target object, and the gaze position information includes information on one or more positions where the eyes of the target object are looking. The terminal or computing device performs liveness detection on the target object based on the light spot position information of the light spot and the gaze position information of the target object. Among them, the light spot position information includes the position information of the position where the light spot appears in the process of displaying the light spot multiple times by the terminal. The terminal displays a light spot on the acquisition interface of the screen each time, and the positions of the two adjacent light spots are different. By implementing the above-mentioned liveness detection method, liveness detection can be effectively performed, the accuracy of liveness detection can be improved, and attackers can be prevented from performing face recognition through photos, videos, high-imitation masks and other methods, which can improve the security of the face recognition system.

[0063] like Figure 1 As shown, Figure 1 : is a schematic diagram of a liveness detection system provided in an embodiment of the present application, the system includes a client and a server. The client is an application deployed and installed on a terminal on the user side, such as a browser, a financial application, a payment application, an attendance application, etc. The client displays an acquisition interface on the screen of the terminal, and the acquisition interface displays light spots multiple times; the client is also used to call the image acquisition device of the terminal to acquire an image of the target object during the process of displaying the light spot on the acquisition interface, and obtain an image sequence of the target object, and the image sequence includes multiple images containing the target object. The client then sends the image sequence of the target object to the server through the terminal. Among them, the terminal can be a device with a screen and image acquisition function, such as a smart phone, a tablet computer, a laptop computer, etc.

[0064] The server is a server application deployed on a server or cloud data center. The server is used to receive an image sequence of a target object sent by a client, and determine the gaze position information of the target object based on the image sequence; the gaze position information includes information about one or more positions where the eyes of the target object are looking; then, based on the light spot position information of the light spot and the gaze position information of the target object, a liveness detection is performed on the target object to determine whether the target object is a normal living person. The light spot position information indicates the position of the light spot that is displayed multiple times on the acquisition interface of the client. The client displays a light spot on the acquisition interface each time, and the positions of two adjacent light spots are different.

[0065] The client and server can provide liveness detection services to users in a client-server (C / S) architecture, or in a browser / server (B / S) architecture, or in the form of cloud services. For example, the liveness detection function provided by the present application can be provided to users as an interface of a cloud service, or as an interface of a worldwide web page or a small program interface for users to call, or as a functional module of an application software.

[0066] The following is a detailed description of the liveness detection method provided by the present application in conjunction with the accompanying drawings. It should be understood that the above-mentioned server can be deployed on a physical machine, a virtual machine or a container, and the functions implemented by the server are implemented by using the resources of the computing device where the server is located. The client is deployed on the terminal, and the functions implemented by the client are implemented by using the resources of the terminal where the client is located. For example, when the client needs to collect an image of the target object, the client calls the image acquisition device (such as a camera) of the terminal to realize the acquisition. Figure 2 As shown, Figure 2 1 is a flow chart of a liveness detection method provided in an embodiment of the present application. The method includes S201 to S205.

[0067] S201. The server provides a collection interface to the client, and the light spot is displayed multiple times on the collection interface.

[0068] The server provides a collection interface to the client to display the collection interface on the client's interface, that is, to display the collection interface on the screen of the terminal. When the terminal displays the collection interface on the screen, the collection interface will display the light spot multiple times, and the collection interface will only display one light spot each time, and the positions of the two adjacent light spots are different. In the embodiment of the present application, the purpose of displaying the light spot multiple times in the collection interface is to make the target object being verified always look at the light spot, so that the target object's eyeball follows the movement of the light spot. In one possible implementation, before the light spot is displayed for the first time, a prompt message can also be displayed, and the prompt message is used to prompt the target object that its line of sight should always be fixed on the light spot. For example, the prompt message may be "Please look at the light spot that will be displayed on the screen, and your line of sight moves with the light spot."

[0069] The light spot may be a character, such as Chinese characters, letters, etc., or may be a circular or rectangular light spot. The color of the light spot may be red or green, etc. In the embodiment of the present application, the shape and color of the light spot are not specifically limited.

[0070] In a possible implementation, the server may also provide a configuration interface to the client, which is used to prompt the user to configure the detection level, where different detection levels correspond to different light spot display modes, and different light spot display modes have different levels of complexity. For example, different light spot display modes display light spots at different times, different light spot display modes display light spots at different locations on the acquisition interface, and different light spot display modes display each light spot for different durations in the same detection.

[0071] For example, Figure 3 As shown, Figure 3 is a schematic diagram of a configuration interface provided in an embodiment of the present application. The configuration interface is used for users to set the detection level. The configuration interface provides three detection levels, namely low detection level, medium detection level and high detection level. Users can click "Detailed Introduction" under the detection level to understand the difference between different detection levels. For example, Figure 4 As shown, Figure 4 It is a schematic diagram of a light spot display mode provided in an embodiment of the present application. Figure 4 Taking the light spot as a black circle as an example, the light spot display mode corresponding to the low detection level is: displaying the light spot in the four corners of the acquisition interface in sequence; the light spot display mode corresponding to the medium detection is: randomly displaying the light spot in 6 positions of the acquisition interface in sequence, that is, when two adjacent detections are performed, the 6 positions where the light spot appears for the first time on the acquisition interface are not exactly the same as the 6 positions where the light spot appears for the second time on the acquisition interface; the light spot display mode corresponding to the high detection level is: randomly displaying the light spot in 9 positions of the acquisition interface in sequence, and the duration of each light spot display is not exactly the same.

[0072] Users can choose different detection levels according to specific usage scenarios. For example, if the liveness detection method is used for attendance and the security requirements are low, the user can choose a low detection level; if the liveness detection method is used for security defense of financial services or payment services, the user can choose a high detection level. After selecting the detection level, the user clicks the confirmation button to complete the configuration of the detection level. It should be understood that the above detection level settings are only for example and cannot be understood as specific limitations. For example, more or fewer detection levels can be provided, and there are other forms of different detection levels.

[0073] In one possible implementation, when the target object triggers liveness detection, the server determines the light spot display mode according to the detection level corresponding to the user, and determines the light spot position information according to the light spot display mode. The light spot position information indicates the position of the light spot displayed multiple times on the acquisition interface.

[0074] For example, after the user enters the account and password through the login page of the browser and clicks the OK button, the client sends the account and password to the server through the terminal. When the server determines that the account and password are correct, it triggers liveness detection. The server determines the detection level set by the user according to the account, and determines the spot position information of the spot displayed on the acquisition interface according to the spot display mode corresponding to the detection level. If the spot display mode corresponding to the user is related to the duration of the spot display, the server determines the duration of each spot display. For example, if the spot display mode selected by the user is to randomly display the spot in 9 positions of the acquisition interface in sequence, and the duration of each spot display is not exactly the same, the server randomly generates nine positions and nine durations, and each position and duration is the position and duration of a spot display. Then the server provides the client with a collection interface to display on the screen of the terminal. For another example, the terminal is a terminal for attendance, and the terminal collects images at preset time intervals. When a face is detected in the image, liveness detection is triggered, and the terminal sends a request to the server. After receiving the request, the server provides the collection interface to the terminal.

[0075] Optionally, in the process of displaying the light spot multiple times on the acquisition interface, the duration of each display of the light spot is the same; or the duration of each display of the light spot is not exactly the same.

[0076] In a possible implementation, in the process of displaying the light spot multiple times on the acquisition interface, a background of one or more colors is displayed on the acquisition interface, wherein the color of the background is different from the color of the light spot. For example, the color of the light spot is black, and the display interface will display the light spot four times. When the display interface displays the light spot for the first time, the background of the display interface is red; when the display interface displays the light spot for the second time, the background of the display interface switches to green; when the display interface displays the light spot for the third time, the background of the display interface switches to yellow; when the display interface displays the light spot for the fourth time, the background of the display interface switches to blue. It should be understood that the number of background colors that appear in the process of displaying the light spot on the display interface may be less than the number of light spots, may be equal to the number of light spots, or may be greater than the number of light spots, and the embodiments of the present application do not make specific limitations.

[0077] In one possible implementation, when the light spot is displayed multiple times on the acquisition interface, the distance between the center points of two adjacent displayed light spots is greater than a distance threshold. In this way, when liveness detection is performed subsequently, it is easier to detect changes in the target object's line of sight or focus position when the target object is a real living person.

[0078] S202. The client collects an image sequence of the target image while the light spot is displayed multiple times on the collection interface.

[0079] After receiving the acquisition interface, the terminal displays the acquisition interface on the client's interface. At the same time, the client calls the terminal's image acquisition device, such as the front camera of a mobile phone. In the process of displaying the acquisition interface, the front camera is used to acquire images or videos of the target object. After the light spot is displayed on the acquisition interface, the client stops acquiring images or videos to obtain an image sequence of the target object, which includes multiple images containing the target object. Among them, the image sequence can be all images acquired by the terminal, or it can be a part of the images acquired by sampling from all images acquired by the terminal. For example, the terminal can acquire 30 frames of images in 1 second, but the shortest duration of a light spot display is 1.5 seconds. In this way, the terminal can sample an image every 5 frames in the acquired image to obtain the above image sequence. This can reduce the amount of data that needs to be sent to the server and improve detection efficiency.

[0080] It should be understood that the above-mentioned collection interface is displayed on the client interface, and the collection interface and the client interface are not the same. For example, the client is a browser on a computer, and the collection interface does not necessarily occupy the entire window of the browser.

[0081] S203. The client sends an image sequence of the target object to the server.

[0082] After obtaining the above image sequence, the client sends the image sequence of the above target object to the server.

[0083] S204. After receiving the image sequence of the target object, the server determines the gaze position information of the target object according to the image sequence.

[0084] After receiving the image sequence of the target object, the server locates the face of the target object in the image through the trained face detection model; then locates the left and right eyes of the target object through the face template or the trained eye detection model; and then determines the position of the target object's eye gaze through eye tracking technology to obtain the target object's gaze position information.

[0085] S205. Perform liveness detection on the target object according to the light spot position information of the light spot and the gaze position information of the target object.

[0086] After determining the gaze position information of the target object, the server performs liveness detection on the target object according to the spot position information of the light spot and the gaze position information of the target object. For example, the gaze position information is compared and analyzed with the spot position information of the light spot to determine the matching degree between the gaze position information of the target object and the spot position information of the light spot. When the matching degree is greater than the first threshold, the target object is determined to be a live person.

[0087] Exemplarily, the light spot is displayed in the upper left corner, lower left corner, upper right corner and lower right corner of the acquisition interface in sequence. When the gaze position of the target object determined according to the gaze position information is also these four positions and the order is consistent, the matching degree of the gaze position information and the light spot position information is 100%; if only three of the gaze positions of the target object determined according to the gaze position information match the positions displayed by the above light spots, the matching degree is 75%.

[0088] In a possible implementation, the server can also determine the direction of change of the light spot based on the light spot position information, and determine the direction of change of the target object's gaze position based on the target object's gaze position information, and then determine the degree of match between the gaze position information and the light spot position information based on the direction of change of the light spot and the direction of change of the target object's gaze position. For example, the light spot is displayed in the upper left corner, lower left corner, upper right corner, and lower right corner of the acquisition interface in sequence, and the position where the light spot appears changes three times, corresponding to three change directions: from the upper left to the lower left, from the lower left corner to the upper right corner, and from the upper right corner to the lower right corner. If the number of changes in the target object's gaze position determined by the target object's gaze information is also three times, and the direction of change is the same as the three directions of change of the light spot change, then the degree of match between the gaze position information and the light spot position information is determined to be 100%.

[0089] In a possible implementation, the server can determine the matching degree of the gaze position information and the light spot position information based on the light spot position information and duration information of the light spot, as well as the gaze position information and gaze duration information of the target object, and perform liveness detection on the target object. Among them, the duration information includes the duration of each display of the light spot; the gaze duration information includes the duration of each of the one or more positions that the target object gazes at, and each position corresponds to a gaze duration. For example, the light spot is displayed in the upper left corner, lower left corner, upper right corner and lower right corner of the acquisition interface in sequence. The server determines that the gaze position of the target object is also these four positions and in the same order based on the gaze position information. The server also compares the duration of the light spot displayed at each position with the gaze duration of the target object at the position. When the error between the duration of a position and the gaze duration of the position is less than the error threshold, the server will determine that the gaze position of the target object matches the display position of the light spot.

[0090] In one possible implementation, Figure 5 As shown, Figure 5A schematic diagram of a liveness detection method provided in an embodiment of the present application. In the above S204 and S205, the server only analyzes the image sequence based on the eye tracking technology and then performs liveness detection. In the embodiment of the present application, the server can also perform liveness detection based on the face information of the target image in the image sequence, determine whether the target object is alive based on the face image, and then combine the matching degree obtained in the above S205 and the result obtained by liveness detection based on the face image to determine whether the target object is alive, that is, the liveness detection based on the eye tracking technology and the liveness detection of the face image are combined to obtain the liveness detection result. For example, the face of the target object is detected by the face detection model, and then based on the face image, the trained deep learning classification network model is used to output the probability that the target object is a real live person and the probability that the target object is a prosthesis. For another example, the face image is judged by distortion, moiré, reflection, border and other information in the face image to determine whether the face in the image is a real live person. For another example, when the background of the acquisition interface can change color, the probability that the target object is a real person and the probability that the target object is a fake are determined by analyzing the reflection of different colors of light by the target object through facial image analysis.

[0091] After determining the probability that the target object is a real person and the probability that the target object is a prosthesis, the server determines whether the target object is a real person in combination with the matching degree obtained in S205. The server can determine whether the target object is a real person according to the pre-set judgment rules, the probability that the target object is a real person, the probability that the target object is a prosthesis, and the matching degree. For example, when the matching degree is greater than or equal to the third threshold and the probability that the target object is a real person is greater than the fourth threshold, it is determined that the target object is a real person; when the matching degree is greater than or equal to the third threshold, but the probability that the target object is a prosthesis is greater than the fifth threshold, the detection result that cannot determine whether it is a real person is output; when the matching degree is less than the third threshold, but the probability that the target object is a prosthesis is greater than the sixth threshold, the target object is a prosthesis.

[0092] It should be understood that if the server cannot determine whether the target object is a real person, the target object may be prompted to verify again, that is, the process in the above embodiment is executed again.

[0093] By implementing the liveness detection method provided by the present application, when liveness detection is required, by displaying the light spot on the screen of the terminal multiple times, collecting the facial image of the target object during the display of the light spot, and analyzing the image to determine the degree of match between the position where the target object's eyeball is looking and the position where the light spot is displayed, it is then determined whether the target object is a real live person. This can improve the accuracy of liveness detection, increase the difficulty for criminals to impersonate legitimate users for verification through photos or videos, and improve the security of the system.

[0094] above Figures 2 to 5 The corresponding embodiment introduces in detail the method for detecting a living body in which the client is only responsible for displaying the acquisition interface and acquiring the image sequence corresponding to the target object. In some possible implementations, the client can also generate the light spot position information by itself, and generate the acquisition interface to display the light spot multiple times according to the light spot position information. For example, the client is a payment application or an application provided by a bank. Figure 6 As shown, Figure 6 It is a flow chart of another living body detection method provided in an embodiment of the present application.

[0095] S601. The terminal displays light spots multiple times on the acquisition interface.

[0096] In an embodiment of the present application, when liveness detection is required, the terminal displays a collection interface on the screen. The collection interface will display the light spot multiple times, and the collection interface will only display one light spot each time, and the positions of the two adjacent light spots are different. The purpose of displaying the light spot multiple times on the collection interface is to make the target object being verified always look at the light spot, so that the target object's eyeball follows the movement of the light spot. In a possible implementation, before the light spot is displayed for the first time, a prompt message can also be displayed, and the prompt message is used to prompt the target object that its line of sight should always be fixed on the light spot. For example, the prompt message may be "Please look at the light spot that will be displayed on the screen, and your line of sight moves with the light spot."

[0097] The light spot may be a character, such as Chinese characters, letters, etc., or may be a circular or rectangular light spot. The color of the light spot may be red or green, etc. In the embodiment of the present application, the shape and color of the light spot are not specifically limited.

[0098] In a possible implementation, the client will also provide the user with a configuration interface, which is used to prompt the user to configure the detection level, where different detection levels correspond to different light spot display modes, and different light spot display modes have different levels of complexity. For example, different light spot display modes display light spots at different times, different light spot display modes display light spots at different locations on the acquisition interface, or different light spot display modes display each light spot for different durations in the same detection. For the relevant introduction of user configuration of detection levels and different light spot forms, please refer to the relevant description in S201 above, which will not be repeated here.

[0099] In one possible implementation, when the target object triggers liveness detection, the client determines the light spot display mode according to the detection level corresponding to the user, and determines the light spot position information according to the light spot display mode, and the light spot position information indicates the position of the light spot displayed multiple times on the acquisition interface.

[0100] For example, the user opens the client, and the terminal displays the login interface corresponding to the client on the screen. The user enters the account and password on the login interface, and clicks the OK button. When the account and password are correct, the liveness detection is triggered. The client calls the liveness detection interface, and determines the spot position information of the light spot displayed on the acquisition interface according to the spot display mode corresponding to the detection level set by the user. If the spot display mode corresponding to the user is related to the duration of the light spot display, the client also needs to determine the duration of each light spot display. For example, if the detection level configured by the user is a high detection level, that is, the spot display mode is to randomly display the light spot in 9 positions of the acquisition interface in sequence, and the duration of each light spot display is not exactly the same, then the client randomly generates nine positions and nine durations, and each position and duration is the position and duration of a light spot display. Then the acquisition interface is displayed on the screen of the terminal, and 9 light spots are displayed in sequence.

[0101] Optionally, in the process of displaying the light spot multiple times on the acquisition interface, the duration of each display of the light spot is the same; or the duration of each display of the light spot is not exactly the same.

[0102] In a possible implementation, in the process of displaying the light spot multiple times on the acquisition interface, a background of one or more colors is displayed on the acquisition interface, wherein the color of the background is different from the color of the light spot. For example, the color of the light spot is black, and the display interface will display the light spot four times. When the display interface displays the light spot for the first time, the background of the display interface is red; when the display interface displays the light spot for the second time, the background of the display interface switches to green; when the display interface displays the light spot for the third time, the background of the display interface switches to yellow; when the display interface displays the light spot for the fourth time, the background of the display interface switches to blue. It should be understood that the number of background colors that appear in the process of displaying the light spot on the display interface may be less than the number of light spots, may be equal to the number of light spots, or may be greater than the number of light spots, and the embodiments of the present application do not make specific limitations.

[0103] In a possible implementation, when the light spot is displayed multiple times on the acquisition interface, the distance between the center points of two adjacent light spots is greater than a distance threshold, so that when performing subsequent liveness detection, it is easier to detect changes in the target object when the target object is a real live object.

[0104] S602. The terminal collects an image sequence of the target image while the light spot is displayed multiple times on the collection interface.

[0105] During the process of displaying the light spot on the acquisition interface for multiple times, the client in the terminal calls the image acquisition device of the terminal, such as the front camera of a mobile phone, and during the process of displaying the acquisition interface, the image or video of the target object is acquired through the front camera. After the light spot is displayed on the acquisition interface, the client stops acquiring images or videos to obtain an image sequence of the target object, and the image sequence includes multiple images containing the target object. For a detailed description of how the client acquires images to obtain an image sequence pair, reference can be made to the description in S202 above, which will not be repeated here.

[0106] S603. The terminal determines gaze position information of the target object according to the image sequence.

[0107] After obtaining the image sequence of the target object, the client in the terminal locates the face of the target object in the image through the trained face detection model; then locates the position of the left eye and the right eye of the target object through the face template or the trained eye detection model; then determines the position of the target object's eye gaze through eye tracking technology; and obtains the gaze position information of the target object.

[0108] S604. The terminal performs liveness detection on the target object according to the light spot position information of the light spot and the gaze position information of the target object.

[0109] After determining the gaze position information of the target object, the client performs liveness detection on the target object according to the spot position information of the light spot and the gaze position information of the target object. The method for the client to perform liveness detection on the target object can refer to the above S205 and Figure 5 The relevant descriptions in the corresponding methods will not be repeated here.

[0110] It should be noted that after obtaining the above image sequence, the client can also send the image sequence and the light spot information corresponding to the multiple displayed light spots to the server, and the server performs liveness detection on the target object according to the image sequence and the light spot information. Among them, the light spot information includes the above light spot position information, or the light spot information includes the light spot position information and duration information, and the duration information includes the duration of each display of the light spot by the terminal. Displaying a light spot once on the acquisition interface corresponds to one position and one duration.

[0111] For the above method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should know that the present invention is not limited by the described order of actions. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions involved are not necessarily required by the present invention. Other reasonable step combinations that can be thought of by those skilled in the art based on the above description also fall within the scope of protection of the present invention.

[0112] The liveness detection method provided by the present application is described above in conjunction with the accompanying drawings. The present application also provides a liveness detection device, which is used to implement the functions implemented by the above-mentioned server. Figure 7 As shown, Figure 7 : is a schematic diagram of a liveness detection device provided by an embodiment of the present application. The liveness detection device 700 includes a communication module 710 and a processing module 720, wherein the communication module 710 is used to obtain an image sequence of a target object collected by a terminal, the image sequence is collected by the terminal in the process of displaying a light spot multiple times, and the image sequence includes multiple images containing the target object; the processing module 720 is used to determine the gaze position information of the target object according to the image sequence; the gaze position information includes information on one or more positions where the eyes of the target object are gazed; then, according to the light spot position information and the gaze position information of the light spot, liveness detection is performed on the target object; wherein the light spot position information includes the position information of the light spot appearing in the process of displaying the light spot multiple times by the terminal, and the terminal displays a light spot on the acquisition interface each time, and the positions of the two adjacent light spots are different.

[0113] The above-mentioned living body detection device 700 also includes an interface providing module 730, which is used to provide a collection interface to the terminal. The collection interface will display the light spot multiple times. The positions of the light spots displayed multiple times on the collection interface are determined according to the light spot position information.

[0114] The above-mentioned living body detection device may further include a training module 740 for training a face recognition model and / or a human eye detection model, etc.

[0115] Among them, the communication module 710, the processing module 720, the interface providing module 730 and the training module 740 can all be implemented by software, or can be implemented by hardware. Exemplarily, the implementation of the processing module 720 is introduced below by taking the processing module 720 as an example. Similarly, the implementation of the communication module 710, the interface providing module 730 and the training module 740 can refer to the implementation of the processing module 720.

[0116] As an example of a software functional unit, the processing module 720 may include code running on a computing instance. Among them, the computing instance may include at least one of a physical host (computing device), a virtual machine, and a container. Further, the above-mentioned computing instance may be one or more. For example, the processing module 720 may include code running on multiple hosts / virtual machines / containers. It should be noted that the multiple hosts / virtual machines / containers used to run the code may be distributed in the same region (region) or in different regions. Furthermore, the multiple hosts / virtual machines / containers used to run the code may be distributed in the same availability zone (AZ) or in different AZs, each AZ including one data center or multiple data centers with similar geographical locations. Among them, usually a region may include multiple AZs.

[0117] Similarly, multiple hosts / virtual machines / containers used to run the code can be distributed in the same virtual private cloud (VPC) or in multiple VPCs. Usually, a VPC is set up in a region. For cross-region communication between two VPCs in the same region and between VPCs in different regions, a communication gateway needs to be set up in each VPC to achieve interconnection between VPCs through the communication gateway.

[0118] As an example of a hardware functional unit, the processing module 720 may include at least one processor, such as a central processing unit. Alternatively, the processing module 720 may also be a device implemented using an application-specific integrated circuit (ASIC) or a programmable logic device (PLD). The PLD may be a complex programmable logical device (CPLD), a field-programmable gate array (FPGA), a generic array logic (GAL) or any combination thereof.

[0119] It should be noted that, in other embodiments, the processing module 720 may be used to execute the above Figure 2 The communication module 710 can be used to perform any step implemented by the server in the liveness detection method shown above. Figure 2The steps implemented by the server in the liveness detection method shown in the figure can be specified as needed by the communication module 710, the processing module 720, the interface providing module 730 and the training module 740. Figure 2 The different steps in the liveness detection method shown are used to implement all functions of the server.

[0120] The present application also provides another living body detection device, which is used to implement the functions implemented by the above terminal. Figure 8 As shown, Figure 8 It is a schematic diagram of another living body detection device provided by an embodiment of the present application. The living body detection device 800 includes a display module 810 and an acquisition module 820. Among them, the display module 810 is used to display the light spot on the acquisition interface multiple times, wherein a light spot is displayed on the acquisition interface each time, and the positions of two adjacent light spots are different; the acquisition module 820 is used to collect an image sequence of the target object in the process of displaying the light spot multiple times, and the image sequence includes multiple images containing the target object; wherein the image sequence is used to determine the gaze position information of the target object, and the gaze position information and the light spot position information of the light spot are used to perform living body detection on the target object; the gaze position information includes information on one or more positions where the eyes of the target object are gazed, and the light spot position information includes position information of the light spot that appears multiple times on the acquisition interface.

[0121] The above-mentioned living body detection device 800 also includes a processing module 830, which is used to match the light spot position information and the gaze position information, perform living body detection on the target object, and determine that the target object is a real living person when the matching degree between the light spot position information and the gaze position information is greater than a first threshold.

[0122] The above-mentioned living body detection device 800 also includes a communication module 840, which is used to send the image sequence and the light spot information corresponding to the multiple displayed light spots to the server, and the server performs living body detection on the target object according to the image sequence and the light spot information.

[0123] The operation implemented by the above-mentioned living body detection device 800 can refer to the above-mentioned Figure 2 The operations implemented by the client in the embodiment shown in the figure, or the above Figure 6 The operations implemented by the terminal in the illustrated embodiment will not be described in detail here.

[0124] The present application also provides a computing device, such as Fig. 9 As shown, Fig. 9900 is a schematic diagram of a computing device provided in an embodiment of the present application. The computing device 900 includes: a bus 902, a processor 904, a memory 906, and a communication interface 908. The processor 904, the memory 906, and the communication interface 908 communicate with each other via the bus 902. The computing device 900 may be a server or a terminal device. It should be understood that the present application does not limit the number of processors and memories in the computing device 900.

[0125] The bus 902 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Fig. 9 The bus 902 may include a path for transmitting information between various components of the computing device 900 (eg, the memory 906, the processor 904, and the communication interface 908).

[0126] The processor 904 may include any one or more of a central processing unit (CPU), a graphics processing unit (GPU), a microprocessor (MP), or a digital signal processor (DSP).

[0127] The memory 906 may include a volatile memory, such as a random access memory (RAM). The processor 904 may also include a non-volatile memory, such as a read-only memory (ROM), a flash memory, a hard disk drive (HDD), or a solid state drive (SSD).

[0128] The memory 906 stores executable program codes, and the processor 904 executes the executable program codes to respectively implement the above Figure 7 The communication module 710, the processing module 720, the interface providing module 730 and the training module 740 in the device shown in the figure can realize Figure 2 That is, the memory 906 stores instructions for executing the liveness detection method.

[0129] The communication interface 908 uses a transceiver module such as, but not limited to, a network interface card or a transceiver to implement communication between the computing device 900 and other devices or communication networks.

[0130] The embodiment of the present application also provides a computing device cluster. The computing device cluster includes at least one computing device. The computing device can be a server, such as a central server, an edge server, or a local server in a local data center. In some embodiments, the computing device can also be a terminal device such as a desktop computer, a laptop computer, or a smart phone.

[0131] like Fig.10 As shown, Fig.10 1 is a schematic diagram of a computing device cluster provided in an embodiment of the present application. The computing device cluster includes at least one computing device 900. The memory 906 in one or more computing devices 900 in the computing device cluster may store the same Figure 2 In the illustrated embodiment, the server implements instructions for the liveness detection method.

[0132] In some possible implementations, the memory 906 of one or more computing devices 900 in the computing device cluster may also store a program for executing Figure 2 In the embodiment shown, the server implements some instructions of the liveness detection method. In other words, the combination of one or more computing devices 900 can jointly execute the instructions for executing Figure 2 In the illustrated embodiment, the server implements instructions for the liveness detection method.

[0133] It should be noted that the memory 906 in different computing devices 900 in the computing device cluster can store different instructions, which are respectively used to execute Figure 7 Part of the functions of the living body detection device shown. That is, the instructions stored in the memory 906 in different computing devices 900 can implement the functions of one or more modules in the communication module 710, the processing module 720, the interface providing module 730 and the training module 740.

[0134] In some possible implementations, one or more computing devices in the computing device cluster may be connected via a network. The network may be a wide area network or a local area network, etc. For example, two computing devices 900A and 900B are connected via a network. Specifically, the network is connected via a communication interface in each computing device. In this type of possible implementation, the memory 906 in the computing device 900A stores instructions for executing the functions of the communication module 710 and the interface providing module 730. At the same time, the memory 906 in the computing device 900B stores instructions for executing the functions of the processing module 720 and the training module 740.

[0135] The connection method between the computing device clusters through the network connection can be considered that the liveness detection method provided in the present application requires a training model, and therefore requires a large amount of computing resources and storage resources. Therefore, it is considered to entrust the functions implemented by the processing module 720 and the training module 740 to the computing device 900B for execution.

[0136] It should be understood that the functions of the computing device 900B may also be performed by multiple computing devices 900. Similarly, the functions of the computing device 900A may also be performed by multiple computing devices 900. The distribution mode of each module is not specifically limited in the embodiment of the present application.

[0137] The present application also provides a terminal device. The structure of the terminal device can refer to the above Fig. 9 The computing device shown in the figure is used to implement the above Figure 6 The liveness detection method implemented by the terminal in the corresponding embodiment will not be described in detail here.

[0138] The present application also provides a computer program product including instructions. The computer program product may be software or a program product including instructions that can be run on a computing device or stored in any available medium. When the computer program product is run on at least one computing device, the at least one computing device executes Figure 2 The liveness detection method implemented by the server in the embodiment shown, or Figure 2 In the embodiment shown, the client or Figure 6 The living body detection method implemented by the terminal in the illustrated embodiment.

[0139] The present application also provides a computer-readable storage medium. The computer-readable storage medium may be any available medium that can be stored by a computing device or a data storage device such as a data center that contains one or more available media. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state hard disk). The computer-readable storage medium includes instructions that instruct the computing device to execute Figure 2 The liveness detection method implemented by the server in the embodiment shown, or Figure 2 In the embodiment shown, the client or Figure 6 The living body detection method implemented by the terminal in the illustrated embodiment.

[0140] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the protection scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for detecting a living body, characterized in that: Applied to the server, including: Acquire an image sequence of a target object captured by a terminal, and determine gaze position information of the target object in the image sequence; the gaze position information includes information of one or more positions where the eyes of the target object are gazed, the image sequence is captured by the terminal in a process of displaying light spots for multiple times, and the image sequence includes multiple images containing the target object; According to the spot position information of the light spot and the gaze position information, liveness detection is performed on the target object; wherein the spot position information indicates that the position of the light spot is displayed multiple times on the acquisition interface, one spot is displayed on the acquisition interface each time, and the positions of two adjacent spots are different.

2. The method according to claim 1, characterized in that The method further comprises: The terminal is provided with the acquisition interface, and the acquisition interface displays the light spot multiple times. The positions of the light spots displayed multiple times on the acquisition interface are determined according to the light spot position information.

3. The method according to claim 1 or 2, characterized in that: The method further comprises: Providing a configuration interface to the terminal, the configuration interface is used to instruct a user to configure a detection level; wherein different detection levels correspond to different light spot display modes; Obtain and record the target detection level configured by the user in the configuration interface.

4. The method according to claim 3, characterized in that Before providing the collection interface to the terminal, the method further includes: In the case where the target object triggers liveness detection, the light spot position information is generated according to the target detection level.

5. The method according to any one of claims 1 to 4, characterized in that: In the process of displaying the light spot multiple times on the acquisition interface, the duration of each display of the light spot is the same.

6. The method according to any one of claims 1 to 4, characterized in that: In the process of displaying the light spot multiple times on the acquisition interface, the duration of each display of the light spot is not exactly the same.

7. The method according to any one of claims 1 to 6, characterized in that: In the process of displaying the light spot on the acquisition interface for multiple times, a background of one or more colors is displayed on the acquisition interface, wherein the color of the background is different from the color of the light spot.

8. The method according to any one of claims 1 to 7, characterized in that: When the light spot is displayed multiple times on the acquisition interface, the distance between the center points of the light spots displayed twice adjacently is greater than a distance threshold.

9. The method according to any one of claims 1 to 8, characterized in that: The performing liveness detection on the target object according to the light spot position information of the light spot and the gaze position information includes: The light spot position information and the gaze position information are matched, and when a matching degree between the light spot position information and the gaze position information is greater than a first threshold, it is determined that the target object is a real living person.

10. The method according to any one of claims 1 to 8, characterized in that: The performing liveness detection on the target object according to the light spot position information of the light spot and the gaze position information includes: Determine the gaze duration information of the target object according to the image sequence; wherein the gaze duration information includes the duration of each of the one or more positions that the target object gazes at, and each position corresponds to a gaze duration; Performing liveness detection on the target object according to the light spot position information and the light spot duration information, and the gaze position information and the gaze duration information of the target object; The duration information includes the duration of each display of the light spot, and the acquisition interface displays a light spot once, corresponding to a position and a duration.

11. The method according to any one of claims 1 to 8, characterized in that: The performing liveness detection on the target object according to the light spot position information of the light spot and the gaze position information includes: Determining a matching degree between the light spot position information and the gaze position information according to the light spot position information of the light spot and the gaze position information; Determining the probability that the target object is a real person based on the image sequence; wherein the images in the image sequence include human faces; According to the matching degree and the probability that the target object is a real living person, liveness detection is performed on the target object.

12. A method for detecting a living body, characterized in that: include: The terminal displays the light spot on the collection interface multiple times, wherein one light spot is displayed on the collection interface each time, and the positions where the light spots appear twice are different; The terminal collects an image sequence of the target object during the process of displaying the light spot multiple times, wherein the image sequence includes multiple images containing the target object; Among them, the image sequence is used to determine the gaze position information of the target object, and the gaze position information and the light spot position information of the light spot are used to perform liveness detection on the target object; the gaze position information includes information on one or more positions where the eyes of the target object are gazed, and the light spot position information includes position information of the light spot that appears multiple times on the acquisition interface.

13. The method according to claim 12, characterized in that Before the terminal displays the light spots multiple times on the acquisition interface, the terminal further includes: The terminal displays a configuration interface, and the configuration interface is used to instruct the user to configure the detection level; wherein different detection levels correspond to different light spot display modes; Obtain and record the target detection level configured by the user on the configuration interface; The terminal displays light spots on the acquisition interface multiple times, including: In the case where the target object triggers liveness detection, the terminal displays light spots on the acquisition interface multiple times according to the light spot display mode corresponding to the target detection level.

14. The method according to claim 12 or 13, characterized in that When the terminal displays the light spot multiple times on the acquisition interface, the duration of each display of the light spot is the same.

15. The method according to claim 12 or 13, characterized in that When the terminal displays the light spot multiple times on the acquisition interface, the duration of each display of the light spot is not exactly the same.

16. The method according to any one of claims 12 to 15, characterized in that: In the process of displaying the light spot on the acquisition interface for multiple times, a background of one or more colors is displayed on the acquisition interface, wherein the color of the background is different from the color of the light spot.

17. The method according to any one of claims 12 to 16, characterized in that: When the light spot is displayed multiple times on the acquisition interface, the distance between the center points of the light spots displayed twice adjacently is greater than a distance threshold.

18. The method according to any one of claims 12 to 17, characterized in that: The method further comprises: The terminal matches the light spot position information with the gaze position information, performs liveness detection on the target object, and determines that the target object is a live person when the matching degree between the light spot position information and the gaze position information is greater than a first threshold.

19. The method according to any one of claims 12 to 17, characterized in that: The method further comprises: The terminal determines the gaze duration information of the target object according to the image sequence; wherein the gaze duration information includes the duration of each of the one or more positions that the target object gazes at, and each position corresponds to a gaze duration; Performing liveness detection on the target object according to the light spot position information and the light spot duration information, and the gaze position information and the gaze duration information of the target object; The duration information includes the duration of each time the terminal displays the light spot, and each time the acquisition interface displays the light spot, it corresponds to a position and a duration.

20. The method according to any one of claims 12 to 17, characterized in that: The method further comprises The terminal determines, according to the light spot position information of the light spot and the gaze position information, a matching degree between the light spot position information and the gaze position information; The terminal determines the probability that the target object is a real person according to the image sequence; wherein the images in the image sequence include human faces; The terminal performs liveness detection on the target object according to the matching degree and the probability that the target object is a real live person.

21. The method according to any one of claims 12 to 17, characterized in that: The method further comprises: The terminal sends the image sequence and the light spot information corresponding to the light spots displayed multiple times by the terminal to a server, so that the server performs liveness detection on the target object according to the image sequence and the light spot information; The light spot information includes the light spot position information, or the light spot information includes the light spot position information and duration information, and the duration information includes the duration of each light spot display by the terminal. Displaying a light spot once on the acquisition interface corresponds to one position and one duration.

22. A living body detection device, characterized in that: include: A communication module, used for acquiring an image sequence of a target object acquired by a terminal, wherein the image sequence is acquired by the terminal in a process of displaying light spots for multiple times, and the image sequence includes multiple images containing the target object; A processing module, configured to determine gaze position information of the target object according to the image sequence; the gaze position information includes information of one or more positions where the eyes of the target object gaze; The processing module is also used to perform liveness detection on the target object based on the light spot position information of the light spot and the gaze position information; wherein the light spot position information includes position information of the light spot appearing in the process of the terminal displaying the light spot multiple times, the terminal displays one light spot on the acquisition interface each time, and the positions of two adjacent light spots appearing are different.

23. The device according to claim 22, characterized in that Also includes: The interface providing module is used to provide the acquisition interface to the terminal, the acquisition interface will display the light spot multiple times, and the positions of the light spots displayed multiple times on the acquisition interface are determined according to the light spot position information.

24. A living body detection device, characterized in that: include: A display module, used for displaying light spots on the acquisition interface multiple times, wherein one light spot is displayed on the acquisition interface each time, and positions where two adjacent light spots appear are different; An acquisition module, used for acquiring an image sequence of a target object during a process of displaying the light spot multiple times, wherein the image sequence includes multiple images containing the target object; Among them, the image sequence is used to determine the gaze position information of the target object, and the gaze position information and the light spot position information of the light spot are used to perform liveness detection on the target object; the gaze position information includes information on one or more positions where the eyes of the target object are gazed, and the light spot position information includes position information of the light spot that appears multiple times on the acquisition interface.

25. The device according to claim 24, characterized in that Also includes: A processing module is used to match the light spot position information with the gaze position information, perform liveness detection on the target object, and determine that the target object is a real live person when the matching degree between the light spot position information and the gaze position information is greater than a first threshold.

26. A computing device cluster, characterized in that: The method comprises at least one computing device, each computing device comprises a processor and a memory, and the processor of the at least one computing device is used to execute instructions stored in the memory of the at least one computing device, so that the computing device cluster executes the method according to any one of claims 1 to 11.

27. A terminal device, characterized in that: The method comprises a processor and a memory, wherein the memory is used to store instructions, and the processor is used to execute the instructions. When the processor executes the instructions, the method according to any one of claims 12 to 21 is implemented.

28. A computer-readable storage medium, characterized in that: The method comprises computer program instructions. When the computer program instructions are executed by a computing device cluster, the computing device cluster performs the method according to any one of claims 1 to 11.

29. A computer-readable storage medium, characterized in that: The method comprises computer program instructions, and when the computer program instructions are executed by a computing device cluster, the computing device cluster performs the method as claimed in any one of claims 12 to 21.

Images