Identification method and device, computer device and storage medium

Abstract

The application relates to a recognition method and device, computer equipment, a storage medium and a computer program product, and relates to the technical field of artificial intelligence. The method comprises the following steps: at a first target moment, collecting a first shearing speckle interference graph of an object to be recognized through a shearing speckle interference technology; at a second target moment, collecting a second shearing speckle interference graph of the object to be recognized through the shearing speckle interference technology; determining a change graph of interference light intensity of the object to be recognized from the first target moment to the second target moment according to the first shearing speckle interference graph and the second shearing speckle interference graph; determining a first living body recognition result of the object to be recognized according to the change graph of interference light intensity; in the case that the first living body recognition result indicates that the object to be recognized is a living body, performing image collection on the object to be recognized, obtaining a matching image, and performing identity recognition processing according to the matching image to obtain an identity recognition result of the object to be recognized. The scheme improves the recognition accuracy.

Description

Technical Field

[0001] This application relates to the field of artificial intelligence technology, and in particular to a recognition method, apparatus, computer device, and storage medium. Background Technology

[0002] With the development of artificial intelligence technology, recognition technology has emerged. This technology can identify the identity of an object and obtain a corresponding identity recognition result. This technology is commonly used in the field of facial recognition to determine the identity information or legitimacy of the object to be identified. The identity recognition result includes either a result indicating successful identification or a result indicating failure.

[0003] Traditional identification techniques involve acquiring an image of the object to be identified using an image acquisition device. Then, a target reference image is selected from a pre-set image library to match the object. If no target reference image is found, the identification result indicating a failure is used as the identification result for the object. Alternatively, if a target reference image is found, the identification result indicating a success is used as the identification result for the object.

[0004] However, in real-world identification scenarios, existing identification technologies cannot distinguish whether the object to be identified is the object itself, a photograph of the object, or a spoofed model of the object. This allows others to use the photograph or spoofed model of the object to obtain an identification result indicating successful identification, thereby reducing the accuracy of identification. Summary of the Invention

[0005] Therefore, it is necessary to provide an identification method, apparatus, computer equipment, computer-readable storage medium, and computer program product that can improve identification accuracy in response to the above-mentioned technical problems.

[0006] Firstly, this application provides an identification method. The method includes:

[0007] At the first target moment, the first shear speckle interferogram of the object to be identified is acquired using shear speckle interferometry.

[0008] At the second target time, a second shear speckle interferogram of the object to be identified is acquired using the shear speckle interferometry technique.

[0009] Based on the first shear speckle interferogram and the second shear speckle interferogram, determine the interference light intensity variation diagram of the object to be identified from the first target time to the second target time;

[0010] Based on the interference light intensity variation diagram, the first liveness detection result of the object to be identified is determined;

[0011] If the first liveness detection result indicates that the object to be identified is a live object, an image of the object to be identified is acquired to obtain a matching image, and an identity recognition process is performed based on the matching image to obtain the identity recognition result of the object to be identified.

[0012] In one embodiment, determining the interference intensity variation map of the object to be identified from the first target time to the second target time based on the first shear speckle interferogram and the second shear speckle interferogram includes:

[0013] The absolute value of the difference between the first shear speckle interferogram and the second shear speckle interferogram is used as the interference intensity variation diagram of the object to be identified from the first target time to the second target time.

[0014] In one embodiment, determining the first liveness detection result of the object to be identified based on the interference light intensity variation pattern includes:

[0015] Obtain at least one interference circle center in the interference intensity variation diagram;

[0016] Based on the position information of the interference center, the interference intensity variation map is partitioned to obtain a partitioned interference intensity variation map, wherein the partitioned interference intensity variation map includes at least one interference intensity variation region, and each interference intensity variation region contains one interference center.

[0017] Based on the interference light intensity variation diagram after partitioning, the first liveness detection result of the object to be identified is determined.

[0018] In one embodiment, determining the first liveness detection result of the object to be identified based on the interference intensity variation map after partitioning includes:

[0019] Obtain the number of interference circles and their relative positions in the interference intensity variation diagram;

[0020] By comparing the number of interference circle centers in the interference intensity variation diagram with a preset number, the number comparison result is obtained;

[0021] If the number comparison result indicates that the number of interference centers is the same as the preset number, the relative position of the interference centers is compared with the preset relative position to obtain the position comparison result;

[0022] Based on the location comparison results, the first liveness detection result of the object to be identified is determined.

[0023] In one embodiment, determining the first liveness detection result of the object to be identified based on the interference intensity variation map after partitioning includes:

[0024] Based on the relative positions of the interference circle centers contained within the interference intensity variation regions, the feature category corresponding to each interference intensity variation region is determined;

[0025] For any of the interference light intensity variation regions, the range of the number of interference fringes corresponding to the interference light intensity variation region is determined according to the feature category corresponding to the interference light intensity variation region;

[0026] For any of the interference light intensity change regions, the actual number of interference fringes corresponding to the interference light intensity change region is obtained, and it is determined whether the actual number of interference fringes matches the range of the number of interference fringes, so as to obtain the judgment result corresponding to the interference light intensity change region.

[0027] Based on the judgment result corresponding to at least one of the interference light intensity change regions, the first liveness detection result of the object to be identified is determined.

[0028] In one embodiment, determining the feature category corresponding to each interference intensity variation region based on the relative position of the interference circle centers contained within the interference intensity variation region includes:

[0029] Obtain the number of interference circles and their relative positions in the interference intensity variation diagram;

[0030] If the number of interference centers in the interference intensity variation diagram is the same as the preset number, and the relative positions of the interference centers in the interference intensity variation diagram are the same as the preset relative positions, the feature category corresponding to each interference intensity variation region is determined according to the relative positions of the interference centers contained in the interference intensity variation region.

[0031] In one embodiment, the method further includes:

[0032] If the first liveness detection result indicates that the object to be identified is not a live object, an action guidance prompt message is issued, and an action image of the object to be identified is captured;

[0033] The second liveness detection result is determined based on the motion image and the preset motion feature data corresponding to the preset specified motion contained in the motion guidance prompt message;

[0034] If the second liveness detection result indicates that the object to be identified is a live object, an image of the object to be identified is acquired to obtain a matching image, and identity recognition processing is performed based on the matching image to obtain the identity recognition result of the object to be identified.

[0035] Secondly, this application also provides an identification system. The identification system includes a controller, an image acquisition unit, and a laser generator; wherein:

[0036] The controller is configured to respond to an identification command, control the laser generator to generate sheared coherent light, and send a first image acquisition command to the image acquisition device. The first image acquisition command is configured to instruct the image acquisition device to acquire images at a first target time and a second target time.

[0037] The image acquisition device is configured to, in response to the first image acquisition command, acquire the first shear speckle interferogram of the object to be identified at the first target time, and acquire the second shear speckle interferogram of the object to be identified at the second target time, and feed back the first shear speckle interferogram and the second shear speckle interferogram to the controller.

[0038] The controller is configured to determine the interference intensity variation map of the object to be identified from the first target time to the second target time based on the first shear speckle interferogram and the second shear speckle interferogram, determine the first liveness detection result of the object to be identified based on the interference intensity variation map, and, if the first liveness detection result indicates that the object to be identified is a live body, control the laser generator to generate structured light and send a second image acquisition command to the image acquisition device.

[0039] The image acquisition device is used to acquire an image of the object to be identified in response to the second image acquisition command, obtain an image to be matched, and feed back the image to be matched to the controller;

[0040] The controller is used to perform identity recognition processing based on the image to be matched, and obtain the identity recognition result of the object to be identified.

[0041] In one embodiment, the identification system further includes a first switch and a second switch. The laser generating device includes a laser, a beam splitter, a shearing speckle generation unit, and a structured light generation filter. The first switch is disposed in the first output optical path of the beam splitter, and the second switch is disposed in the second output optical path of the beam splitter, wherein:

[0042] The controller is configured to respond to the identity recognition command by controlling the first switch to open and the second switch to close, and to control the laser to generate target laser.

[0043] The beam splitter is used to split the target laser into a first target laser and a second target laser;

[0044] The first switch is used to allow the first target laser to be incident on the shear speckle generation unit when the first switch is turned on;

[0045] The second switch is used to prevent the second target laser from being incident on the structured light generating filter when the second switch is closed;

[0046] The shear speckle generation unit is used to expand the first target laser beam to obtain the expanded first target laser beam, and to shear the expanded first target laser beam reflected by the object to be identified to obtain the first shear-correlated light and the second shear-correlated light.

[0047] In one embodiment, the identification system includes:

[0048] The controller is configured to, when the first liveness detection result indicates that the object to be identified is a live body, control the first switch to close and the second switch to open, and control the laser to generate target laser;

[0049] The first switch is used to prevent the first target laser from being incident on the shear speckle generation unit when the first switch is closed;

[0050] The second switch is used to allow the second target laser to be incident on the structured light generating filter when the second switch is turned on;

[0051] The structured light generating filter is used to generate the structured light based on the incident second target laser.

[0052] In one embodiment, the laser generating device includes a shear-correlated light generator and a structured light generator, wherein:

[0053] The controller is used to control the shear-correlated light generator to generate expanded target laser in response to the identity recognition command;

[0054] The shearing coherent light generator is used to shear the expanded target laser reflected by the object to be identified to obtain a first shearing coherent light and a second shearing coherent light.

[0055] The controller is further configured to control the structured light generator to generate the structured light when the first liveness detection result indicates that the object to be identified is a live body.

[0056] Thirdly, this application also provides an identification device. The identification device includes:

[0057] The first acquisition module is used to acquire the first shear speckle interferogram of the object to be identified at the first target time using shear speckle interferometry.

[0058] The second acquisition module is used to acquire the second shear speckle interferogram of the object to be identified at the second target time using the shear speckle interferometry technique.

[0059] The determining module is used to determine the interference light intensity change pattern of the object to be identified from the first target time to the second target time based on the first shear speckle interferogram and the second shear speckle interferogram;

[0060] The first liveness detection module is used to determine the first liveness detection result of the object to be identified based on the interference light intensity change diagram;

[0061] The identity recognition module is used to acquire an image of the object to be identified when the first liveness recognition result indicates that the object to be identified is a live object, to obtain a matching image, and to perform identity recognition processing based on the matching image to obtain the identity recognition result of the object to be identified.

[0062] Fourthly, this application also provides a computer device. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the steps described in the first aspect.

[0063] Fifthly, this application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program thereon, which, when executed by a processor, implements the steps described in the first aspect.

[0064] Sixthly, this application also provides a computer program product. The computer program product includes a computer program that, when executed by a processor, performs the steps described in the first aspect.

[0065] The aforementioned identification method, apparatus, computer equipment, storage medium, and computer program product acquire a first shear speckle interferogram of the object to be identified using shear speckle interferometry at a first target time; acquire a second shear speckle interferogram of the object to be identified using shear speckle interferometry at a second target time; determine the interference intensity variation of the object to be identified from the first target time to the second target time based on the first and second shear speckle interferograms; determine a first liveness detection result of the object to be identified based on the interference intensity variation; if the first liveness detection result indicates that the object to be identified is alive, image acquisition is performed on the object to be identified to obtain a matching image, and identity recognition processing is performed on the matching image to obtain the identity recognition result of the object to be identified. In the above method, the interference intensity variation of the object to be identified is determined based on the first shear speckle interferogram acquired at the first target time and the second shear speckle interferogram acquired at the second target time, and then the liveness of the object to be identified is determined based on the interference intensity variation. Only if the object to be identified is alive is the recognition result of the object to be identified determined based on the matching image. Therefore, this method can identify whether the object to be identified is a living person, thereby reducing the possibility of successfully identifying the object by using a photograph or a spurious model of the object to be identified, thus improving the recognition accuracy. Attached Figure Description

[0066] Figure 1 This is a diagram illustrating the application environment of the identification method in one embodiment;

[0067] Figure 2a and Figure 2b This is a diagram illustrating the application environment of the identification method in another embodiment;

[0068] Figure 3 This is a flowchart illustrating the identification method in one embodiment;

[0069] Figure 4 Here is a structural block diagram of the Michelson shear structure in one embodiment;

[0070] Figure 5 This is a flowchart illustrating a method for determining the first liveness detection result in one embodiment;

[0071] Figure 6 This is a flowchart illustrating the method for determining the first liveness detection result in another embodiment;

[0072] Figure 7 This is a flowchart illustrating the method for determining the first liveness detection result in another embodiment;

[0073] Figure 8 This is a flowchart illustrating the identification method in another embodiment;

[0074] Figure 9 This is a diagram illustrating the application environment of the identification method in another embodiment;

[0075] Figure 10a and Figure 10b This is a diagram illustrating the application environment of the identification method in another embodiment;

[0076] Figure 11 This is a structural block diagram of the identification device in one embodiment;

[0077] Figure 12 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0078] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0079] The identification method provided in this application embodiment can be applied to, for example, Figure 1 The application environment shown. Figure 1 The identification system includes a controller 102, an image acquisition unit 104, and a laser generator. The controller 102 is electrically connected to both the image acquisition unit 104 and the laser generator. The controller 102 is a device with control and data processing functions. The laser generator includes a laser 106-1, a beam splitter (referred to as the first beam splitter for easy distinction) 106-2, a shearing speckle generation unit, and a structured light generation filter 106-3. The shearing speckle generation unit includes a beam expander 106-4 and a shearing device 106-5. The identification system also includes a first switch 108, a second switch 110, a first plane mirror 112, and a second beam splitter 114.

[0080] In one embodiment, the identification system further includes a third beam splitter 116, a third switch 118, a fourth switch 120, a second plane mirror 122, a third plane mirror 124, and a fourth beam splitter 126. In another embodiment, as... Figure 2a , Figure 2b As shown, the recognition system also includes a motor 202 and a guide rail 204. The motor drives the shearing device 106-5 to move on the guide rail, which allows the laser speckle to be incident on the shearing device 106-5. The guide rail also allows the structured light reflected from the object to be recognized to be directly incident on the image acquisition unit 104. The laser speckle includes either the expanded target laser reflected from the object to be recognized or the expanded target laser reflected from the object to be recognized. It can be understood that... Figure 2a and Figure 2bThe connection relationship between the shearing device 106-5, the motor 202, and the guide rail 204 is not limited. As long as the shearing device 106-5 is driven to move on the guide rail 204 by the motor 202, thereby causing the laser speckle to be incident on the shearing device 106-5 or the structured light reflected by the object to be identified to be directly incident on the image acquisition device 104, it is within the protection scope of this application.

[0081] In one embodiment, the identification system further includes a system housing, a light-emitting aperture, and a light-in aperture. The light-emitting aperture and the light-in aperture are respectively disposed on the system housing. It can be understood that the laser emitted by the identification system towards the object to be identified is incident on the object to be identified through the light-emitting aperture, while the laser reflected by the object to be identified is incident on the identification system through the light-in aperture.

[0082] by Figure 1 Taking the identification system as an example, the controller 102, in response to the identification command, controls the laser generator to produce sheared coherent light and sends a first image acquisition command to the image acquisition unit 104. The first image acquisition command instructs the image acquisition unit 104 to acquire images at a first target time and a second target time. Specifically, the control unit in the controller 102 sends a laser generation signal to the laser 106-1 through the laser control circuit, and controls the first switch 108 to open, the second switch 110 to close, the third switch 118 to open, and the fourth switch to close through the laser control circuit. In response to the laser generation signal, the laser 106-1 emits a target laser towards the first beam splitter 106-2, so that the target laser is split into two beams (i.e., the first target laser and the second target laser) by the first beam splitter 106-2. The target laser used in this application is a laser that does not stimulate the object to be identified or produces a stimulus less than a preset stimulus level; for example, the target laser is an infrared laser.

[0083] Since the first switch 108 is located in the optical path of the first target laser, when the first switch 108 is open and the second switch 110 is closed, the first target laser is incident on the first plane mirror 112 and reflected by the first plane mirror 112 to the beam expander 106-4. The beam expander 106-4 expands the incident first target laser to generate an expanded first target laser, and emits the expanded first target laser to the second beam splitter 114, which then reflects the expanded first target laser to the object to be identified. The expanded first target laser (i.e., laser speckle) reflected by the object to be identified enters the third beam splitter 116 and is split into two laser speckles. When the third switch 118 is open and the fourth switch 120 is closed, the laser speckle is incident on the shearing device 106-5. The shearing device 106-5 shears the laser speckle to obtain two sheared laser speckles (including a first sheared correlated light and a second sheared coherent light). The first shear-correlated beam and the second shear-coherent beam are coherent beams. The two sheared laser speckle beams are incident on the image acquisition unit 104 and interfere with each other.

[0084] The control unit in controller 102 sends a first image acquisition command to image acquisition unit 104 via the acquisition drive circuit. Responding to the first image acquisition command, image acquisition unit 104 acquires a first shear speckle interferogram of the object to be identified at a first target time, and a second shear speckle interferogram of the object to be identified at a second target time, and feeds back the first and second shear speckle interferograms to the controller. Based on the first and second shear speckle interferograms, controller 102 determines the change in interference light intensity of the object to be identified from the first target time to the second target time. Based on the change in interference light intensity, controller 102 determines a first liveness detection result for the object to be identified. If the first liveness detection result indicates that the object to be identified is alive, controller 102 controls the laser generator to generate structured light and sends a second image acquisition command to image acquisition unit 104.

[0085] Specifically, the control unit in controller 102 sends a laser generation signal to laser 106-1 via a laser control circuit, and controls the first switch 108 to close, the second switch 110 to open, the third switch 118 to close, and the fourth switch to open via the laser control circuit. In response to the laser generation signal, laser 106-1 emits a target laser towards the first beam splitter 106-2, splitting the target laser into two beams (i.e., the first target laser and the second target laser). Since the second switch is located in the optical path of the second target laser, when the first switch 108 is closed and the second switch 110 is open, the second target laser is incident on the structured light filter 106-3. The second target laser passing through the structured light generation filter 106-3 carries the structural information from the structured light generation filter 106-3; therefore, the structured light emitted from the structured light generation filter 106-3 is structured light. The structured light reflected by the object to be identified enters the third beam splitter 116 and is split into two beams of structured light reflected by the object to be identified (for ease of distinction, these are referred to as the reflected structured light). With the third switch 118 closed and the fourth switch 120 open, the reflected structured light is incident on the second plane mirror 122, reflected by the second plane mirror 122 to the third plane mirror 124, then reflected by the third plane mirror 124 to the fourth beam splitter 126, and finally reflected by the fourth beam splitter 126 to the image acquisition unit 104. The control unit in the controller 102 sends a second image acquisition command to the image acquisition unit 104 through the acquisition drive circuit.

[0086] In response to the second image acquisition command, the image acquisition unit 104 acquires an image of the object to be identified, obtains an image to be matched, and sends the image to be matched back to the controller 102. The controller 102 performs identity recognition processing based on the image to be matched to obtain the identity recognition result of the object to be identified.

[0087] by Figure 2a and Figure 2b To illustrate this further, let's take another example of a recognition system, firstly as... Figure 2a As shown, in response to the identification command, the controller 102 controls the laser generator to produce the target laser and sends a first image acquisition command to the image acquisition device. Specifically, the control unit in the controller 102 sends a laser generation signal to the laser 106-1 through the laser control circuit, and controls the first switch 108 to open, the second switch 110 to close, and the shearing device 106-5 to move into the laser speckle optical path through the laser control circuit. In response to the laser generation signal, the laser 106-1 emits the target laser towards the first beam splitter 106-2, so that the target laser is split into two beams (i.e., the first target laser and the second target laser) by the first beam splitter 106-2.

[0088] Since the first switch is located in the optical path of the first target laser, when the first switch 108 is open and the second switch 110 is closed, the first target laser is incident on the first plane mirror 112 and reflected by the first plane mirror 112 to the beam expander 106-4. The beam expander 106-4 expands the incident first target laser to generate an expanded first target laser, and emits the expanded first target laser to the second beam splitter 114, which then reflects the expanded first target laser to the object to be identified. When the shearing device 106-5 is located in the optical path of the expanded first target laser (i.e., laser speckle) reflected by the object to be identified, the shearing device 106-5 shears the laser speckle to obtain two sheared laser speckles (including a first sheared coherent beam and a second sheared coherent beam). The first sheared coherent beam and the second sheared coherent beam are incident on the image acquisition unit 104 and interfere with each other in the image acquisition unit 104.

[0089] The control unit in controller 102 sends a first image acquisition command to image acquisition unit 104 via the acquisition drive circuit. Responding to the first image acquisition command, image acquisition unit 104 acquires a first shear speckle interferogram of the object to be identified at a first target time, and a second shear speckle interferogram of the object to be identified at a second target time, and feeds back the first and second shear speckle interferograms to the controller. Based on the first and second shear speckle interferograms, controller 102 determines the change in interference light intensity of the object to be identified from the first target time to the second target time. Based on the change in interference light intensity, controller 102 determines a first liveness detection result for the object to be identified. If the first liveness detection result indicates that the object to be identified is alive, controller 102 controls the laser generator to generate structured light and sends a second image acquisition command to image acquisition unit 104.

[0090] Specifically, such as Figure 2bAs shown, the control unit in controller 102 sends a laser generation signal to laser 106-1 via a laser control circuit, and controls the first switch 108 to close, the second switch 110 to open, and the shearing device 106-5 to move away from the optical path of the structured light reflected by the object to be identified. In response to the laser generation signal, laser 106-1 emits a target laser towards the first beam splitter 106-2, splitting the target laser into two beams (i.e., the first target laser and the second target laser). Since the second switch is located in the optical path of the second target laser, when the first switch 108 is closed and the second switch 110 is open, the second target laser is incident on the structured light filter 106-3. The second target laser passing through the structured light generation filter 106-3 carries the structural information from the structured light generation filter 106-3; therefore, the structured light emitted from the structured light generation filter 106-3 is structured light. When the shearing device 106-5 is located away from the optical path of the structured light reflected by the object to be identified, the structured light reflected by the object to be identified is directly incident on the image acquisition unit 104. The control unit in the controller 102 sends a second image acquisition command to the image acquisition unit 104 through the acquisition drive circuit.

[0091] In response to the second image acquisition command, the image acquisition unit 104 acquires an image of the object to be identified, obtains an image to be matched, and sends the image to be matched back to the controller 102. The controller 102 performs identity recognition processing based on the image to be matched to obtain the identity recognition result of the object to be identified.

[0092] In one embodiment, such as Figure 3 As shown, an identification method is provided, which is applied to... Figure 1 ,or, Figure 2a and Figure 2b Taking the recognition system in the image as an example, the following steps are included:

[0093] Step 302: At the first target time, acquire the first shear speckle interferogram of the object to be identified using shear speckle interferometry.

[0094] In this embodiment, at a first target time, the image acquisition unit 104 acquires a first shear speckle interferogram of the object to be identified using shear speckle interferometry. The first target time can be the moment the object to be identified (including a face) is detected, or the moment an authentication command is received. Optionally, the first target time is a random moment when the image acquisition unit 104 begins acquiring the first speckle interferogram in response to a first image acquisition command. In one embodiment, the number of first shear speckle interferograms is one. Optionally, the shearing device can be a Michelson shear structure, a Mach-Zehnder structure, an optical wedge structure, or a coated glass structure, etc. Figure 4The Michelson shearing structure shown is an example. The shearing device 106-5 includes a fourth plane mirror 302, a fifth plane mirror 304, and a fifth beam splitter 306. The plane containing the mirror surface of the fourth plane mirror 302 is not perpendicular to the optical axis of the lens of the image acquisition unit 104 (i.e., the fourth plane mirror 302 has a shearing angle with the optical axis of the lens of the image acquisition unit 104; the fourth plane mirror 302 is a shearing mirror). The plane containing the mirror surface of the fifth plane mirror 304 is parallel to the optical axis of the lens of the image acquisition unit 104. Laser speckle is incident on the fifth beam splitter 306 and is then split into two laser speckles. Figure 4 The laser speckle incident on the fourth plane mirror 302 is represented by dashed lines (referred to as laser speckle 1 for easy distinction). The laser speckle incident on the fifth plane mirror 304 is referred to as laser speckle 2 for easy distinction. Laser speckle 1, after being incident on the fourth plane mirror 302, is reflected to the image acquisition unit 104. The laser speckle 1 reflected by the fourth plane mirror 302 is not parallel to the optical axis of the lens of the image acquisition unit 104. Laser speckle 2, after being incident on the fifth plane mirror 304, is reflected to the image acquisition unit 104. The laser speckle 2 reflected by the fifth plane mirror 304 is parallel to the optical axis of the lens of the image acquisition unit 104. This causes the laser speckle 1 and laser speckle 2 incident on the image acquisition unit 104 to interfere, resulting in a sheared speckle interferogram (including a first sheared speckle interferogram or a second sheared speckle interferogram). For example... Figure 4 As shown, an imaging lens 308 can also be set between the fifth beam splitter 306 and the image acquisition unit 104, so as to better converge the laser speckle 1 reflected by the fourth plane mirror 302 and the laser speckle 2 reflected by the fifth plane mirror 304 to the image acquisition unit 104.

[0095] Step 304: At the second target time, acquire the second shear speckle interferogram of the object to be identified using shear speckle interferometry.

[0096] In this embodiment, at the second target time, the image acquisition unit 104 acquires a second shear speckle interferogram of the object to be identified using shear speckle interferometry. In one embodiment, the number of second shear speckle interferograms is one. It is understood that the method for acquiring the second shear speckle interferogram is similar to the method for acquiring the first shear speckle interferogram, and can be referred to step 302, which will not be repeated here. The second target time can be any time after the first target time, for example, a time interval of a preset duration from the first target time.

[0097] Step 306: Based on the first shear speckle interferogram and the second shear speckle interferogram, determine the interference light intensity variation of the object to be identified from the first target time to the second target time.

[0098] In this embodiment, the controller 102 determines the interference intensity variation map of the object to be identified from the first target time to the second target time based on the first shear speckle interferogram and the second shear speckle interferogram. The interference intensity variation map characterizes the change in interference intensity of the object to be identified from the first target time to the second target time. The interference intensity includes the light intensity corresponding to each pixel in the shear speckle interferogram (including the first or second shear speckle interferogram). It can be understood that the interference intensity variation map from the first target time to the second target time refers to a single interference intensity variation map, and the data in this map characterizes the change in laser speckle from the first target time to the second target time (including the change in interference intensity or phase difference). In one embodiment, the controller 102 filters the interference intensity variation map to obtain a filtered interference intensity variation map, and uses the filtered map as a new interference intensity variation map, continuing to execute step 308 based on the new map. It is understandable that the filtered interference intensity variation map can remove some of the errors caused by noise, thereby improving the image accuracy of the interference intensity variation map.

[0099] Step 308: Determine the first liveness detection result of the object to be identified based on the interference light intensity variation diagram.

[0100] The first liveness detection result includes either a first liveness detection result indicating that the object to be identified is a live object, or a first liveness detection result indicating that the object to be identified is a non-live object. The interference intensity variation map includes the position information of any pixel in the interference intensity variation map, and the amount of change in interference intensity at any pixel. For example, the interference intensity variation map is a two-dimensional image, where the horizontal and vertical coordinates of the two-dimensional image represent the position information of the pixels in the interference intensity variation map, and the pixel value corresponding to each pixel represents the amount of change in interference intensity at that pixel.

[0101] In this embodiment, the controller 102 analyzes the change in interference intensity in the interference intensity variation diagram to obtain the analysis result, and determines whether the object to be identified is a living body based on the analysis result. If the object to be identified is a living body, the controller 102 generates a first liveness detection result indicating that the object to be identified is a living body. Alternatively, if the object to be identified is not a living body, the controller 102 generates a first liveness detection result indicating that the object to be identified is not a living body.

[0102] Step 310: If the first liveness detection result indicates that the object to be identified is a live object, the object to be identified is image acquired to obtain a matching image, and identity recognition processing is performed based on the matching image to obtain the identity recognition result of the object to be identified.

[0103] The identity recognition result includes either a successful identity recognition result or a failed identity recognition result.

[0104] In this embodiment of the application, when the first liveness detection result indicates that the object to be identified is a live object, the image acquisition device 104 acquires an image of the object to be identified, obtains a matching image, and sends the matching image to the controller 102. Specifically, as shown... Figure 1 As shown, controller 102 controls a laser generator to generate an infrared structured light beam. The infrared structured light reflected by the object to be identified is incident on image acquisition unit 104, which acquires the matching image of the object to be identified. Controller 102 performs identity recognition processing based on the matching image and a preset image library to obtain the identity recognition result of the object to be identified, and displays the identity recognition result on a display device. The preset image library includes at least one reference image, which is used to determine whether the object to be identified to which the matching image belongs is an object that has completed identification and authentication, or whether it is a whitelisted object. The object corresponding to the reference image can be an object that has completed identification and authentication, or a whitelisted object pre-stored in the preset image library. In one embodiment, controller 102 first calculates the image precision of the matching image. If the image precision of the matching image does not meet the preset precision requirement, controller 102 controls image acquisition unit 104 to acquire a new matching image of the object to be identified. This process continues until the image precision of the new matching image meets the preset precision requirement, at which point identity recognition processing is performed based on the matching image that meets the preset precision requirement.

[0105] In the aforementioned identification method, the interference intensity variation map of the object to be identified is determined based on the first shear speckle interferogram acquired at the first target time and the second shear speckle interferogram acquired at the second target time. Then, the liveness of the object to be identified is determined based on the interference intensity variation map. Only when the object to be identified is a live object is the identification result determined based on the matching image of the object to be identified. Therefore, this method can identify whether the object to be identified is a live object, thereby reducing the possibility of successful identification by using a photograph or a spurious model of the object to impersonate the actual object, thus improving identification accuracy.

[0106] In one embodiment, determining the interference intensity variation map of the object to be identified from the first target time to the second target time based on the first shear speckle interferogram and the second shear speckle interferogram includes:

[0107] The absolute value of the difference between the first shear speckle interferogram and the second shear speckle interferogram is used as the interference intensity variation diagram of the object to be identified from the first target time to the second target time.

[0108] In this embodiment, the controller 102 calculates the absolute value of the difference between the first shear speckle interferogram and the second shear speckle interferogram, and uses the absolute value of the difference between the first shear speckle interferogram and the second shear speckle interferogram as the interference intensity change map of the object to be identified from the first target time to the second target time. Specifically, as shown in the following formula (1).

[0109]

[0110] in, In the diagram showing the change in interference light intensity The change in interference light intensity at each pixel This indicates taking the absolute value. This indicates that the pixel represents the positional information on the interference intensity variation map. In the diagram showing the change in interference light intensity The modulation of background light intensity of pixels. In the diagram showing the change in interference light intensity Background light intensity of pixels, In the diagram showing the change in interference light intensity The phase of the pixel on the first shear speckle interferogram. In the diagram showing the change in interference light intensity The phase difference between the phase of a pixel in the first shear speckle interferogram and its phase in the second shear speckle interferogram. (This includes...) As a high-frequency term, it appears as random speckle in the interference intensity variation diagram. The relatively slow change is a low-frequency term, which appears as fringes in the interference intensity variation diagram. When hour If it is a non-negative integer, it will be displayed as a dark stripe. hour When the value is a non-negative integer, it is displayed as a bright stripe.

[0111] It is understandable that if the object to be identified is a living organism, then because the blood vessels under the skin of a living organism are constantly pulsating in the microscopic world, the object to be identified is dynamic. Consequently, the phase of the light (including laser speckle) reflected by the object to be identified at different times will also change, resulting in different interference events in the image acquisition unit 104. This leads to different shear speckle interferograms acquired by the image acquisition unit 104 at different times. Therefore, the controller 102 can roughly estimate whether the object to be identified is a living organism by measuring the change in interference intensity in the interference intensity variation map of the object to be identified or by checking whether the phase difference of the pixels in the interference intensity variation map is zero.

[0112] In this embodiment, the interference intensity variation map of the object to be identified is obtained by calculating the absolute value of the difference between the first shear speckle interferogram and the second shear speckle interferogram, thereby providing data support for subsequent determination of whether the object to be identified is a living body based on the interference intensity variation map.

[0113] In one embodiment, such as Figure 5 As shown, based on the interference intensity variation diagram, the first liveness detection result of the object to be identified is determined, including:

[0114] Step 502: Obtain at least one interference center in the interference intensity variation diagram.

[0115] In this embodiment, the controller 102 extracts the interference center from the interference intensity variation map of the object to be identified. This application does not limit the method for extracting the interference center; all methods capable of extracting the interference center are within the scope of protection of this application. For example, the controller 102 obtains pixels with the same change in interference intensity from the interference intensity variation map, resulting in at least one pixel group. For any pixel group, the controller 102, based on the position information of each pixel within the pixel group in the interference intensity variation map, groups pixels that fit into the same circular curve into the same target pixel group, resulting in at least one target pixel group. The target pixel group contains multiple target pixels, and the target pixels in the same target pixel group have the same change in interference intensity, and the position information of each target pixel in the same target pixel group can be fitted into a circular curve. For any target pixel group, the controller 102 calculates whether a certain pixel exists in the interference intensity variation map (assuming it is a target pixel) based on the position data of each target pixel within the target pixel group. If the distance to each target pixel in the pixel group is the same, then the controller 102 will... The point is used as the center of the interference circle. Specifically, it is shown in formula (2) below.

[0116] Formula (2)

[0117] in, express The position information (i.e., coordinates) of the point in the interference light intensity variation diagram. express The position information (i.e., coordinates) of the point in the interference light intensity variation diagram. The point represents the first pixel in the target pixel group. Target pixels, It is a positive integer. The maximum value is the number of target pixels included in the target pixel group.

[0118] Step 504: Based on the position information of the interference center, the interference intensity variation map is divided into partitions to obtain the partitioned interference intensity variation map.

[0119] The partitioned interference intensity variation map includes at least one interference intensity variation region, and each interference intensity variation region contains an interference center. It can be understood that the number of interference intensity variation regions is equal to the number of interference centers.

[0120] In this embodiment, the controller 102 partitions each pixel in the interference intensity variation map according to the position information of the interference center in the interference intensity variation map, resulting in a partitioned interference intensity variation map. Each pixel in the partitioned interference intensity variation map has a corresponding interference intensity variation region. For example, for any target pixel group in the interference intensity variation map, the controller 102 divides each target pixel in the target pixel group and the corresponding interference center into the same interference intensity variation region. If there are pixels in the interference intensity variation map that do not have a corresponding target pixel group (for convenience, referred to as ungrouped pixels), then for any ungrouped pixel, the controller 102 takes the target pixel group of the target pixel closest to the ungrouped pixel as the target pixel group of that ungrouped pixel.

[0121] Step 506: Determine the first liveness detection result of the object to be identified based on the interference intensity change diagram after partitioning.

[0122] In this embodiment of the application, the controller 102 determines the first liveness detection result of the object to be identified based on the number of interference circles and / or the position information of the interference circles and / or the feature category corresponding to the interference intensity change area in the partitioned interference light intensity change map.

[0123] In this embodiment, the interference intensity variation map is partitioned based on the position information of the interference center, resulting in a partitioned interference intensity variation map. Then, the first liveness detection result is determined based on this partitioned interference intensity variation map. In other words, this method can not only roughly estimate whether the object to be identified is alive based on the changes in the interference intensity variation map (including changes in interference intensity or phase difference), but also further determine whether the object is alive based on the information contained in the partitioned interference intensity variation map, thus further improving the accuracy of liveness detection.

[0124] In one embodiment, such as Figure 6 As shown, based on the interference intensity variation diagram after partitioning, the first liveness detection result of the object to be identified is determined, including:

[0125] Step 602: Obtain the number of interference circles and their relative positions in the interference intensity variation diagram.

[0126] In this embodiment, the controller 102 counts the number of interference centers in the interference intensity variation diagram and determines the relative positions of the interference centers based on their positions in the diagram. The relative positions of the interference centers are used to characterize the relative positions between them. In one embodiment, the controller 102 can characterize the relative positions of the interference centers by adding relative position markers. These relative positions include, but are not limited to, top left, bottom left, top right, bottom right, top left one (i.e., the first interference center from left to right in the top left region of another interference center (or the interference intensity variation diagram), and bottom right two (i.e., the second interference center from left to right in the bottom right region of another interference center (or the interference intensity variation diagram). For example, assuming the interference centers include interference center 1 (0,0), interference center 2 (10,2), interference center 3 (0,9), and interference center 4 (9,11), then the relative position of interference center 1 is lower left, the relative position of interference center 2 is lower right, the relative position of interference center 3 is upper left, and the relative position of interference center 4 is upper right. If there is only one interference center in the interference intensity variation diagram, the relative position of the interference center is used to characterize the region of the interference center in the interference intensity variation diagram. The region in the interference intensity variation diagram can be divided according to a pre-set image position region division strategy. For example, the controller 102 divides the interference intensity variation diagram into equal parts. There are several regions, among which... The integer is positive. Specifically, if there is only one interference center in the interference intensity variation diagram, the relative position of the interference center is used to characterize the position of the interference center in the interference intensity variation diagram. area.

[0127] Step 604: Compare the number of interference circles in the interference intensity variation diagram with the preset number to obtain the comparison result.

[0128] In this embodiment, the controller 102 compares the number of interference circle centers in the interference intensity variation diagram with a preset number to obtain a comparison result. The preset number is determined based on the number of sample interference circle centers in each sample interference intensity variation diagram. The sample identification object and the object to be identified corresponding to the sample interference intensity variation diagram are of the same object type; for example, both the sample identification object and the object to be identified are people. Optionally, the comparison result can be used to characterize whether the number of interference circle centers is the same as the preset number, or it can be used to characterize the absolute value of the difference between the number of interference circle centers and the preset number. If the comparison result indicates that the number of interference circle centers is different from the preset number, the controller 102 generates a first liveness detection result indicating that the object to be identified is not a living person, and executes step 802.

[0129] Step 606: If the number comparison result indicates that the number of interference centers is the same as the preset number, compare the relative positions of the interference centers with the preset relative positions to obtain the position comparison result.

[0130] In this embodiment, when the number comparison result indicates that the number of interference centers is the same as the preset number, the controller 102 compares the relative positions of each interference center with the preset relative positions to obtain a position comparison result. The preset relative positions are determined based on the relative positions of the sample interference centers in the interference intensity variation diagram of each sample. Optionally, the position comparison result can be used to characterize whether the relative positions of all interference centers are the preset relative positions (i.e., the relative positions of the interference centers are the same as the preset relative positions), or it can be used to characterize how many interference centers have the preset relative positions.

[0131] Step 608: Based on the location comparison results, determine the first liveness detection result of the object to be identified.

[0132] In this embodiment, if the position comparison result indicates that the relative position of the interference circle center is the same as the preset relative position, the controller 102 generates a first liveness detection result indicating that the object to be identified is a living body, and executes step 310. If the position comparison result indicates that the relative position of the interference circle center is not the same as the preset relative position, the controller 102 generates a first liveness detection result indicating that the object to be identified is not a living body, and executes step 802. The first liveness detection result is used to characterize whether the object to be identified is a living body.

[0133] In this embodiment, the liveness of the object to be identified is determined by the number and relative positions of the interference centers in the interference intensity variation diagram. In other words, this method can not only roughly estimate whether the object is alive based on the changes in the interference intensity variation diagram (including changes in interference intensity or phase difference), but also further determine whether the object is alive based on the number and relative positions of the interference centers, thus further improving the accuracy of liveness detection.

[0134] In one embodiment, such as Figure 7 As shown, based on the interference intensity variation diagram after partitioning, the first liveness detection result of the object to be identified is determined, including:

[0135] Step 702: Determine the feature category corresponding to each region of interference intensity variation based on the relative positions of the interference circle centers contained within the region of interference intensity variation.

[0136] In this embodiment, for any region of varying interference intensity, the controller 102 determines the feature category corresponding to the region based on the relative positions of the interference circles contained within the region and a preset correspondence between relative positions and feature categories. The feature category is determined based on the object type corresponding to the object to be identified. For example, when the object type is a person, the feature categories include, but are not limited to, eyes, ears, mouth, and nose. The correspondence between relative positions and feature categories is determined based on the feature categories corresponding to the relative positions in the interference intensity variation maps of each sample.

[0137] Step 704: For any region of varying interference intensity, determine the range of the number of interference fringes corresponding to the region of varying interference intensity based on the characteristic category corresponding to the region of varying interference intensity.

[0138] In this embodiment, for any region of varying interference intensity, the controller 102 determines the range of interference fringe numbers corresponding to that region based on the feature category corresponding to the region and a preset correspondence between the feature category and the range of interference fringe numbers. The correspondence between the feature category and the range of interference fringe numbers is determined based on the number of interference fringes corresponding to the feature category in each sample's interference intensity variation diagram.

[0139] Step 706: For any region of varying interference intensity, obtain the actual number of interference fringes corresponding to the region of varying interference intensity, and determine whether the actual number of interference fringes matches the range of the number of interference fringes, thereby obtaining the judgment result corresponding to the region of varying interference intensity.

[0140] In this embodiment, for any region of varying interference intensity, the controller 102 counts the actual number of interference fringes corresponding to the region of varying interference intensity and determines whether the actual number of interference fringes matches the range of interference fringe numbers, thus obtaining a judgment result corresponding to the region of varying interference intensity. In one embodiment, the controller 102 determines whether the actual number of interference fringes falls within the range of interference fringe numbers. If the actual number of interference fringes falls within the range of interference fringe numbers, the controller 102 generates a judgment result indicating that the actual number of interference fringes matches the range of interference fringe numbers; or, if the actual number of interference fringes does not fall within the range of interference fringe numbers, the controller 102 generates a judgment result indicating that the actual number of interference fringes does not match the range of interference fringe numbers.

[0141] Step 708: Determine the first liveness detection result of the object to be identified based on the judgment result corresponding to at least one region of change in interference light intensity.

[0142] In this embodiment, if there is a judgment result indicating that the actual number of interference fringes does not match the range of interference fringes, the controller 102 generates a first liveness detection result indicating that the object to be identified is not a living body, and executes step 802. Alternatively, if all judgment results indicate that the actual number of interference fringes matches the range of interference fringes, the controller 102 generates a first liveness detection result indicating that the object to be identified is a living body, and executes step 310.

[0143] In this embodiment, the liveness of the object to be identified is determined by whether the actual number of interference fringes corresponding to the region of varying interference intensity matches the range of interference fringe numbers. In other words, this method can not only roughly estimate whether the object is alive based on the changes in interference intensity (including changes in interference intensity or phase difference), but also further determine whether the object is alive based on the actual number of interference fringes corresponding to the region of varying interference intensity, thus further improving the accuracy of liveness detection.

[0144] In one embodiment, the feature category corresponding to each region of varying interference intensity is determined based on the relative positions of the interference circles contained within the regions of varying interference intensity, including:

[0145] Obtain the number of interference centers and their relative positions in the interference intensity variation map; if the number of interference centers in the interference intensity variation map is the same as the preset number and the relative positions of the interference centers in the interference intensity variation map are the same as the preset relative positions, determine the feature category corresponding to each interference intensity variation region based on the relative positions of the interference centers contained in the interference intensity variation region.

[0146] In this embodiment, the controller 102 acquires the number of interference circles and their relative positions in the interference intensity variation diagram. Specifically, refer to step 602. The controller 102 executes step 604. If the number of interference circles in the interference intensity variation diagram is the same as the preset number, it executes step 606. If the relative positions of the interference circles in the interference intensity variation diagram are the same as the preset relative positions, the controller 102 executes step 702. Alternatively, if the relative positions of the interference circles in the interference intensity variation diagram are different from the preset relative positions, the controller 102 generates a first liveness detection result indicating that the object to be identified is not a live body, and executes step 802.

[0147] In this embodiment, the liveness of the object to be identified is determined by analyzing the number of interference centers, their relative positions, and whether the actual number of interference fringes matches the range of interference fringe numbers in the interference intensity variation diagram. In other words, this method can not only roughly estimate whether the object is alive based on the changes in the interference intensity variation diagram (including changes in interference intensity or phase difference), but also further determine whether the object is alive by combining the number of interference centers, their relative positions, and the actual number of interference fringes. Therefore, this method can further improve the accuracy of liveness detection for the object to be identified.

[0148] In one embodiment, such as Figure 8 As shown, the identification method also includes:

[0149] Step 802: If the first liveness detection result indicates that the object to be identified is not a live object, an action guidance prompt message is issued, and an action image of the object to be identified is acquired.

[0150] The control and recognition system also includes a display device.

[0151] In this embodiment, if the first liveness detection result indicates that the object to be identified is not alive, the controller 102 controls the recognition system to generate an action guidance prompt message and displays the action guidance prompt message on the display device. After the action guidance prompt message is displayed on the display device, the controller 102 controls the image acquisition device 104 to acquire an image of the action of the object to be identified.

[0152] Step 804: Determine the second liveness detection result based on the action image and the preset action feature data corresponding to the preset specified action contained in the action guidance prompt message.

[0153] In this embodiment, the controller 102 calculates motion feature data corresponding to the motion image of the object to be identified. The controller 102 determines the motion similarity based on the motion feature data corresponding to the motion image and the preset motion feature data corresponding to a preset specified motion contained in the motion guidance prompt message, and judges the magnitude of the motion similarity compared to a preset similarity threshold. If the motion similarity is greater than or equal to the preset similarity threshold, the controller 102 generates a second liveness detection result indicating that the object to be identified is a live body. Alternatively, if the motion similarity is less than the preset similarity threshold, the controller 102 generates an identity recognition result indicating that the identity recognition of the object to be identified has failed, and displays the identity recognition result to the object to be identified on the display device.

[0154] Step 806: If the second liveness detection result indicates that the object to be identified is a live object, an image of the object to be identified is acquired to obtain a matching image, and identity recognition processing is performed based on the matching image to obtain the identity recognition result of the object to be identified.

[0155] In this embodiment, when the second liveness result indicates that the object to be identified is alive, the controller 102 controls the image acquisition device 104 to acquire an image of the object to be identified, obtaining a matching image of the object. The controller 102 performs identity recognition processing based on the matching image and a preset image library to obtain the identity recognition result of the object to be identified, and displays the identity recognition result to the object to be identified on a display device.

[0156] In this embodiment, if the first liveness detection result indicates that the object to be identified is not alive, the motion image of the object to be identified is used to determine whether the object is alive again, resulting in a second liveness detection result. Then, the identity of the object is further determined based on the second liveness detection result. This reduces the error caused by the first liveness detection result determined based on the interference intensity variation map of the object to be identified, further improving the recognition accuracy.

[0157] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0158] Based on the same inventive concept, this application also provides an identification system for implementing the identification method described above. The solution provided by this system is similar to the implementation scheme described in the above method; therefore, the specific limitations in one or more identification system embodiments provided below can be found in the limitations of the identification method described above, and will not be repeated here.

[0159] In one embodiment, such as Figure 1As shown, an identification system is provided, including a controller 102, an image acquisition unit 104, and a laser generating device. The laser generating device includes a laser 106-1, a beam splitter (referred to as the first beam splitter for easy distinction) 106-2, a shearing speckle generation unit, and a structured light generation filter 106-3. The shearing speckle generation unit includes a beam expander 106-4 and a shearing device 106-5, wherein:

[0160] Controller 102 is used to control the laser generator to generate shear coherent light in response to the identity recognition command, and send a first image acquisition command to image acquisition device 104. The first image acquisition command is used to instruct image acquisition device 104 to perform image acquisition at a first target time and a second target time.

[0161] Image acquisition unit 104 is used to acquire a first shear speckle interferogram of the object to be identified at a first target time in response to a first image acquisition command, and to acquire a second shear speckle interferogram of the object to be identified at a second target time, and to feed back the first shear speckle interferogram and the second shear speckle interferogram to controller 102.

[0162] The controller 102 is used to determine the interference light intensity change map of the object to be identified from the first target time to the second target time based on the first shear speckle interference map and the second shear speckle interference map, determine the first liveness identification result of the object to be identified based on the interference light intensity change map, and control the laser generator to generate structured light and send a second image acquisition command to the image acquisition unit 104 when the first liveness identification result indicates that the object to be identified is a live body.

[0163] Image acquisition unit 104 is used to acquire an image of the object to be identified in response to a second image acquisition command, obtain an image to be matched, and feed back the image to be matched to the controller 102;

[0164] The controller 102 is used to perform identity recognition processing based on the image to be matched, and obtain the identity recognition result of the object to be identified.

[0165] In one embodiment, such as Figure 1 As shown, the identification system also includes a first switch 108 and a second switch 110. The first switch 108 is disposed in the first output light path of the beam splitter (i.e., the first beam splitter) 106-2, and the second switch 110 is disposed in the second output light path of the beam splitter (i.e., the first beam splitter) 106-2. The speckle generation unit includes a beam expander 106-4 and a shearing device 106-5, wherein:

[0166] The controller 102 is used to control the first switch 108 to open and the second switch 110 to close in response to an identification command, and to control the laser 106-2 to generate a target laser.

[0167] The beam splitter (i.e., the first beam splitter) 106-2 is used to split the target laser into the first target laser and the second target laser;

[0168] The first switch 108 is used to allow the first target laser to be incident on the shear speckle generation unit when the first switch 108 is turned on.

[0169] The second switch 110 is used to prevent the second target laser from being incident on the structured light generating filter 106-3 when the second switch 110 is closed.

[0170] The shearing speckle generation unit is used to expand the first target laser beam to obtain the expanded first target laser beam, and to shear the expanded first target laser beam reflected by the object to be identified to obtain the first sheared coherent light and the second sheared coherent light.

[0171] In one embodiment, such as Figure 1 As shown, the identification system includes:

[0172] The controller 102 is used to control the first switch 108 to close and the second switch 110 to open when the first liveness detection result indicates that the object to be identified is a live body, and to control the laser 106-2 to generate target laser.

[0173] The first switch 108 is used to prevent the first target laser from being incident on the shear speckle generation unit when the first switch 108 is closed;

[0174] The second switch 110 is used to allow the second target laser to be incident on the structured light generating filter 106-3 when the second switch 110 is turned on.

[0175] Structured light generation filter is used to generate structured light based on the incident second target laser.

[0176] In one embodiment, such as Figure 9 As shown, or, as Figure 10a and Figure 10b As shown, the laser generating device includes a shear-correlated light generator and a structured light generator 904. The shear-correlated light generator includes a beam-expanding laser generator 902 and a shearing device 106-5, wherein:

[0177] Controller 102 is used to control the shear-related light generator to generate expanded target laser in response to an identification command;

[0178] A shearing coherent light generator is used to shear the expanded target laser beam reflected by the object to be identified, to obtain a first shearing coherent light and a second shearing coherent light.

[0179] The controller 102 is also used to control the structured light generator 904 to generate structured light when the first liveness detection result indicates that the object to be identified is a live body.

[0180] Specifically, with Figure 9 The identification system is illustrated using an example. In response to an identification command, controller 102 controls a shear-correlated light generator to produce shear-coherent light and sends a first image acquisition command to the image acquisition unit. This first image acquisition command instructs the image acquisition unit 104 to acquire images at a first target time and a second target time. The shear-correlated light generator includes a beam expander laser generator 902 and a shearing device 106-5. Specifically, the control unit in controller 102 sends a beam expander laser generation signal to the beam expander laser generator 902 via a laser control circuit, and controls the third switch 118 to open and the fourth switch to close via the same circuit. In response to a laser speckle generation signal, the beam expander laser generator 902 generates a beam expander target laser and emits it towards the object to be identified. The beam expander target laser (i.e., laser speckle) reflected by the object to be identified enters the third beam splitter prism 116 and is split into two laser speckles.

[0181] With the third switch 118 open and the fourth switch 120 closed, the laser speckle is incident on the shearing device 106-5. The shearing device 106-5 shears the laser speckle, resulting in two sheared laser speckles (including a first sheared coherent beam and a second sheared coherent beam). The first and second sheared coherent beams are incident on the image acquisition unit 104 and interfere with each other.

[0182] The control unit in controller 102 sends a first image acquisition command to image acquisition unit 104 via the acquisition drive circuit. Responding to the first image acquisition command, image acquisition unit 104 acquires a first shear speckle interferogram of the object to be identified at a first target time, and a second shear speckle interferogram of the object to be identified at a second target time, and feeds back the first and second shear speckle interferograms to the controller. Based on the first and second shear speckle interferograms, controller 102 determines the change in interference light intensity of the object to be identified from the first target time to the second target time. Based on the change in interference light intensity, controller 102 determines a first liveness detection result for the object to be identified. If the first liveness detection result indicates that the object to be identified is alive, controller 102 controls structured light generator 904 to generate structured light and sends a second image acquisition command to image acquisition unit 104.

[0183] Specifically, the control unit in controller 102 sends a structured light generation signal to the structured light generator 904 via a laser control circuit, and controls the third switch 118 to close and the fourth switch to open via the same laser control circuit. The structured light generator 904 responds to the structured light generation signal, generates structured light, and emits it towards the object to be identified. With the third switch 118 closed and the fourth switch 120 open, the reflected structured light is incident on the second plane mirror 122, reflected by the second plane mirror 122 to the third plane mirror 124, then reflected by the third plane mirror 124 to the fourth beam splitter 126, and finally reflected by the fourth beam splitter 126 to the image acquisition unit 104. The control unit in controller 102 sends a second image acquisition command to the image acquisition unit 104 via an acquisition drive circuit.

[0184] In response to the second image acquisition command, the image acquisition unit 104 acquires an image of the object to be identified, obtains an image to be matched, and sends the image to be matched back to the controller 102. The controller 102 performs identity recognition processing based on the image to be matched to obtain the identity recognition result of the object to be identified.

[0185] by Figure 10a and Figure 10b To illustrate this further, let's take another example of a recognition system, firstly as... Figure 10a As shown, in response to the identification command, the controller 102 controls the shearing coherent light generator to generate shearing coherent light and sends a first image acquisition command to the image acquisition unit. Specifically, the control unit in the controller 102 sends a beam-expanding laser generation signal to the beam-expanding laser generator 902 through the laser control circuit, and controls the shearing device 106-5 to move to the optical path of the laser speckle through the laser control circuit. In response to the beam-expanding laser generation signal, the beam-expanding laser generator 902 generates an expanded target laser and emits the expanded target laser to the object to be identified. When the shearing device 106-5 is located in the optical path of the expanded target laser (i.e., laser speckle) reflected by the object to be identified, the shearing device 106-5 shears the laser speckle, obtaining two beams of sheared laser speckle (including a first shearing coherent light and a second shearing coherent light). The first shearing coherent light and the second shearing coherent light are incident on the image acquisition unit 104 and interfere with each other in the image acquisition unit 104.

[0186] The control unit in controller 102 sends a first image acquisition command to image acquisition unit 104 via the acquisition drive circuit. In response to the first image acquisition command, image acquisition unit 104 acquires a first shear speckle interferogram of the object to be identified at a first target time, and a second shear speckle interferogram of the object to be identified at a second target time, and feeds back the first and second shear speckle interferograms to the controller. Based on the first and second shear speckle interferograms, controller 102 determines the change in interference light intensity of the object to be identified from the first target time to the second target time.

[0187] The controller 102 determines the first liveness detection result of the object to be identified based on the interference light intensity variation diagram. If the first liveness detection result indicates that the object to be identified is alive, the controller controls the structured light generator 904 to generate structured light and sends a second image acquisition command to the image acquisition unit 104. Specifically, as shown... Figure 10b As shown, the control unit in controller 102 sends a structured light generation signal to the structured light generator 904 via the laser control circuit, and controls the third switch 118 to close and the fourth switch to open via the laser control circuit. The structured light generator 904 responds to the structured light generation signal, generates structured light, and emits structured light to the object to be identified. When the shearing device 106-5 is located away from the optical path of the structured light reflected by the object to be identified, the structured light reflected by the object to be identified is directly incident on the image acquisition unit 104. The control unit in controller 102 sends a second image acquisition command to the image acquisition unit 104 via the acquisition drive circuit.

[0188] In response to the second image acquisition command, the image acquisition unit 104 acquires an image of the object to be identified, obtains an image to be matched, and sends the image to be matched back to the controller 102. The controller 102 performs identity recognition processing based on the image to be matched to obtain the identity recognition result of the object to be identified.

[0189] In one embodiment, controller 102 is specifically used for:

[0190] The absolute value of the difference between the first shear speckle interferogram and the second shear speckle interferogram is used as the interference intensity variation diagram of the object to be identified from the first target time to the second target time.

[0191] In one embodiment, controller 102 is specifically used for:

[0192] Obtain at least one interference center in the interference intensity variation diagram;

[0193] Based on the location information of the interference center, the interference intensity variation map is divided into partitions to obtain the partitioned interference intensity variation map. The partitioned interference intensity variation map includes at least one interference intensity variation region, and each interference intensity variation region contains an interference center.

[0194] Based on the interference intensity variation diagram after partitioning, the first liveness detection result of the object to be identified is determined.

[0195] In one embodiment, controller 102 is specifically used for:

[0196] Obtain the number of interference centers and their relative positions in the interference intensity variation diagram;

[0197] By comparing the number of interference circle centers in the interference intensity variation diagram with the preset number, the number comparison results are obtained;

[0198] If the number of interference centers is the same as the preset number, the relative positions of the interference centers are compared with the preset relative positions to obtain the position comparison results.

[0199] Based on the location comparison results, the first liveness detection result of the object to be identified is determined.

[0200] In one embodiment, controller 102 is specifically used for:

[0201] Based on the relative positions of the interference circle centers contained in the regions of varying interference intensity, the feature category corresponding to each region of varying interference intensity is determined.

[0202] For any region of varying interference light intensity, the range of the number of interference fringes corresponding to the region of varying interference light intensity is determined based on the characteristic category corresponding to the region of varying interference light intensity.

[0203] For any region of varying interference light intensity, obtain the actual number of interference fringes corresponding to the region of varying interference light intensity, and determine whether the actual number of interference fringes matches the range of the number of interference fringes, thus obtaining the judgment result corresponding to the region of varying interference light intensity.

[0204] Based on the judgment results corresponding to at least one region of change in interference light intensity, the first liveness detection result of the object to be identified is determined.

[0205] In one embodiment, controller 102 is specifically used for:

[0206] Obtain the number of interference centers and their relative positions in the interference intensity variation diagram;

[0207] If the number of interference centers in the interference intensity variation diagram is the same as the preset number, and the relative positions of the interference centers in the interference intensity variation diagram are the same as the preset relative positions, the feature category corresponding to each interference intensity variation region is determined according to the relative positions of the interference centers contained in the interference intensity variation region.

[0208] In one embodiment, the controller 102 is further configured to:

[0209] If the first liveness detection result indicates that the object to be identified is not a live object, an action guidance prompt message is issued, and an action image of the object to be identified is captured;

[0210] The second liveness detection result is determined based on the motion image and the preset motion feature data corresponding to the preset specified motion contained in the motion guidance prompt message;

[0211] If the second liveness detection result indicates that the object to be identified is a live object, an image of the object to be identified is acquired to obtain a matching image, and identity recognition processing is performed based on the matching image to obtain the identity recognition result of the object to be identified.

[0212] Based on the same inventive concept, this application also provides an identification device for implementing the identification method described above. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations in one or more identification device embodiments provided below can be found in the limitations of the identification method described above, and will not be repeated here.

[0213] In one embodiment, such as Figure 11 As shown, an identification device is provided, comprising:

[0214] The first acquisition module 1102 is used to acquire the first shear speckle interferogram of the object to be identified at the first target time using shear speckle interferometry.

[0215] The second acquisition module 1104 is used to acquire the second shear speckle interferogram of the object to be identified at the second target time using shear speckle interferometry.

[0216] The determination module 1106 is used to determine the interference light intensity change pattern of the object to be identified from the first target time to the second target time based on the first shear speckle interferogram and the second shear speckle interferogram.

[0217] The first liveness detection module 1108 is used to determine the first liveness detection result of the object to be identified based on the interference light intensity change diagram;

[0218] The identity recognition module 1110 is used to acquire an image of the object to be recognized when the first liveness recognition result indicates that the object to be recognized is a live object, to obtain a matching image, and to perform identity recognition processing based on the matching image to obtain the identity recognition result of the object to be recognized.

[0219] In one embodiment, the determining module 1106 is specifically used for:

[0220] The absolute value of the difference between the first shear speckle interferogram and the second shear speckle interferogram is used as the interference intensity variation diagram of the object to be identified from the first target time to the second target time.

[0221] In one embodiment, the first liveness detection module 1108 is specifically used to: acquire at least one interference circle center in the interference intensity variation diagram;

[0222] Based on the location information of the interference center, the interference intensity variation map is divided into partitions to obtain the partitioned interference intensity variation map. The partitioned interference intensity variation map includes at least one interference intensity variation region, and each interference intensity variation region contains an interference center.

[0223] Based on the interference intensity variation diagram after partitioning, the first liveness detection result of the object to be identified is determined.

[0224] In one embodiment, the first liveness detection module 1108 is specifically used to: obtain the number of interference circles and the relative positions of the interference circles in the interference intensity variation diagram;

[0225] By comparing the number of interference circle centers in the interference intensity variation diagram with the preset number, the number comparison results are obtained;

[0226] If the number of interference centers is the same as the preset number, the relative positions of the interference centers are compared with the preset relative positions to obtain the position comparison results.

[0227] Based on the location comparison results, the first liveness detection result of the object to be identified is determined.

[0228] In one embodiment, the first liveness detection module 1108 is specifically used for:

[0229] Based on the relative positions of the interference circle centers contained in the regions of varying interference intensity, the feature category corresponding to each region of varying interference intensity is determined.

[0230] For any region of varying interference light intensity, the range of the number of interference fringes corresponding to the region of varying interference light intensity is determined based on the characteristic category corresponding to the region of varying interference light intensity.

[0231] For any region of varying interference light intensity, obtain the actual number of interference fringes corresponding to the region of varying interference light intensity, and determine whether the actual number of interference fringes matches the range of the number of interference fringes, thus obtaining the judgment result corresponding to the region of varying interference light intensity.

[0232] Based on the judgment results corresponding to at least one region of change in interference light intensity, the first liveness detection result of the object to be identified is determined.

[0233] In one embodiment, the first liveness detection module 1108 is specifically used for:

[0234] Obtain the number of interference centers and their relative positions in the interference intensity variation diagram;

[0235] If the number of interference centers in the interference intensity variation diagram is the same as the preset number, and the relative positions of the interference centers in the interference intensity variation diagram are the same as the preset relative positions, the feature category corresponding to each interference intensity variation region is determined according to the relative positions of the interference centers contained in the interference intensity variation region.

[0236] In one embodiment, the identification device further includes:

[0237] The third acquisition module is used to issue an action guidance prompt message and acquire the action image of the object to be identified when the first liveness recognition result indicates that the object to be identified is not a live body.

[0238] The second liveness detection module is used to determine the second liveness detection result based on the action image and the preset action feature data corresponding to the preset specified action contained in the action guidance prompt message.

[0239] The identity recognition module 1110 is used to acquire an image of the object to be recognized when the second liveness recognition result indicates that the object to be recognized is a live object, to obtain a matching image, and to perform identity recognition processing based on the matching image to obtain the identity recognition result of the object to be recognized.

[0240] Each module in the aforementioned identification device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the operations corresponding to each module.

[0241] In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 12As shown, the computer device includes a processor, memory, input / output interfaces, a communication interface, a display unit, and an input device. The processor, memory, and input / output interfaces are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interfaces. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The input / output interfaces are used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it implements an identification method. The display unit is used to form a visually visible image and can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.

[0242] Those skilled in the art will understand that Figure 12 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0243] In one embodiment, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above method embodiments.

[0244] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the steps in the above method embodiments.

[0245] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0246] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with the relevant laws, regulations and standards of the relevant countries and regions.

[0247] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments described above. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0248] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0249] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A recognition method, characterized in that, The method includes: At the first target moment, the first shear speckle interferogram of the object to be identified is acquired using shear speckle interferometry. At the second target time, a second shear speckle interferogram of the object to be identified is acquired using the shear speckle interferometry technique. Based on the first shear speckle interferogram and the second shear speckle interferogram, determine the interference light intensity variation diagram of the object to be identified from the first target time to the second target time; Based on the interference light intensity variation diagram, the first liveness detection result of the object to be identified is determined; If the first liveness detection result indicates that the object to be identified is a live body, an image of the object to be identified is acquired to obtain a matching image, and an identity recognition process is performed based on the matching image to obtain the identity recognition result of the object to be identified. The step of determining the first liveness detection result of the object to be identified based on the interference light intensity variation diagram includes: Obtain at least one interference circle center in the interference intensity variation diagram; Based on the position information of the interference center, the interference intensity variation map is partitioned to obtain a partitioned interference intensity variation map, wherein the partitioned interference intensity variation map includes at least one interference intensity variation region, and each interference intensity variation region contains one interference center. Based on the interference light intensity variation diagram after partitioning, the first liveness detection result of the object to be identified is determined; Wherein, the interference center The point satisfies the following formula: Official (2) in, express The position information (i.e., coordinates) of the point in the interference light intensity variation diagram. express The position information of the point in the interference light intensity variation diagram. The point represents the first pixel in the target pixel group. Target pixels, It is a positive integer. The maximum value is the number of target pixels included in the target pixel group. The target pixel group contains multiple target pixels, and the change in interference light intensity of the target pixels in the same target pixel group is the same. Furthermore, the position information of each target pixel in the same target pixel group can be fitted into a circular curve.

2. The method according to claim 1, characterized in that, The step of determining the interference intensity variation map of the object to be identified from the first target time to the second target time based on the first shear speckle interferogram and the second shear speckle interferogram includes: The absolute value of the difference between the first shear speckle interferogram and the second shear speckle interferogram is used as the interference intensity variation diagram of the object to be identified from the first target time to the second target time.

3. The method according to claim 1, characterized in that, The step of determining the first liveness detection result of the object to be identified based on the interference intensity variation map after partitioning includes: Obtain the number of interference circles and their relative positions in the interference intensity variation diagram; By comparing the number of interference circle centers in the interference intensity variation diagram with a preset number, the number comparison result is obtained; If the number comparison result indicates that the number of interference centers is the same as the preset number, the relative position of the interference centers is compared with the preset relative position to obtain the position comparison result; Based on the location comparison results, the first liveness detection result of the object to be identified is determined.

4. The method according to claim 1, characterized in that, The step of determining the first liveness detection result of the object to be identified based on the interference intensity variation map after partitioning includes: Based on the relative positions of the interference circle centers contained within the interference intensity variation regions, the feature category corresponding to each interference intensity variation region is determined; For any of the interference light intensity variation regions, the range of the number of interference fringes corresponding to the interference light intensity variation region is determined according to the feature category corresponding to the interference light intensity variation region; For any of the interference light intensity change regions, the actual number of interference fringes corresponding to the interference light intensity change region is obtained, and it is determined whether the actual number of interference fringes matches the range of the number of interference fringes, so as to obtain the judgment result corresponding to the interference light intensity change region. Based on the judgment result corresponding to at least one of the interference light intensity change regions, the first liveness detection result of the object to be identified is determined.

5. The method according to claim 4, characterized in that, The step of determining the feature category corresponding to each interference intensity variation region based on the relative position of the interference circle centers contained within the interference intensity variation region includes: Obtain the number of interference circles and their relative positions in the interference intensity variation diagram; If the number of interference centers in the interference intensity variation diagram is the same as the preset number, and the relative positions of the interference centers in the interference intensity variation diagram are the same as the preset relative positions, the feature category corresponding to each interference intensity variation region is determined according to the relative positions of the interference centers contained in the interference intensity variation region.

6. The method according to claim 1, characterized in that, The method further includes: If the first liveness detection result indicates that the object to be identified is not a live object, an action guidance prompt message is issued, and an action image of the object to be identified is captured; The second liveness detection result is determined based on the motion image and the preset motion feature data corresponding to the preset specified motion contained in the motion guidance prompt message; If the second liveness detection result indicates that the object to be identified is a live object, an image of the object to be identified is acquired to obtain a matching image, and identity recognition processing is performed based on the matching image to obtain the identity recognition result of the object to be identified.

7. An identification system, characterized in that, The system includes a controller, an image acquisition unit, and a laser generator; wherein: The controller is configured to respond to an identification command, control the laser generator to generate sheared coherent light, and send a first image acquisition command to the image acquisition device. The first image acquisition command is configured to instruct the image acquisition device to acquire images at a first target time and a second target time. The image acquisition device is configured to, in response to the first image acquisition command, acquire a first shear speckle interferogram of the object to be identified at the first target time, and acquire a second shear speckle interferogram of the object to be identified at the second target time, and feed back the first shear speckle interferogram and the second shear speckle interferogram to the controller. The controller is configured to determine the interference intensity variation map of the object to be identified from the first target time to the second target time based on the first shear speckle interferogram and the second shear speckle interferogram, determine the first liveness detection result of the object to be identified based on the interference intensity variation map, and, if the first liveness detection result indicates that the object to be identified is a live body, control the laser generator to generate structured light and send a second image acquisition command to the image acquisition device. The image acquisition device is used to acquire an image of the object to be identified in response to the second image acquisition command, obtain an image to be matched, and feed back the image to be matched to the controller; The controller is used to perform identity recognition processing based on the image to be matched, and obtain the identity recognition result of the object to be identified. The controller is specifically used to: acquire at least one interference circle center in the interference intensity variation diagram; Based on the position information of the interference center, the interference intensity variation map is partitioned to obtain a partitioned interference intensity variation map, wherein the partitioned interference intensity variation map includes at least one interference intensity variation region, and each interference intensity variation region contains one interference center. Based on the interference light intensity variation diagram after partitioning, the first liveness detection result of the object to be identified is determined; Wherein, the interference center The point satisfies the following formula: Official (2) in, express The position information (i.e., coordinates) of the point in the interference light intensity variation diagram. express The position information of the point in the interference light intensity variation diagram. The point represents the first pixel in the target pixel group. Target pixels, It is a positive integer. The maximum value is the number of target pixels included in the target pixel group. The target pixel group contains multiple target pixels, and the change in interference light intensity of the target pixels in the same target pixel group is the same. Furthermore, the position information of each target pixel in the same target pixel group can be fitted into a circular curve.

8. The system according to claim 7, characterized in that, The system further includes a first switch and a second switch. The laser generating device includes a laser, a beam splitter, a shearing speckle generation unit, and a structured light generation filter. The first switch is disposed in the first output optical path of the beam splitter, and the second switch is disposed in the second output optical path of the beam splitter, wherein: The controller is configured to respond to the identity recognition command by controlling the first switch to open and the second switch to close, and to control the laser to generate target laser. The beam splitter is used to split the target laser into a first target laser and a second target laser; The first switch is used to allow the first target laser to be incident on the shear speckle generation unit when the first switch is turned on; The second switch is used to prevent the second target laser from being incident on the structured light generating filter when the second switch is closed; The shear speckle generation unit is used to expand the first target laser beam to obtain the expanded first target laser beam, and to shear the expanded first target laser beam reflected by the object to be identified to obtain the first shear-correlated light and the second shear-correlated light.

9. The system according to claim 8, characterized in that, The system includes: The controller is configured to, when the first liveness detection result indicates that the object to be identified is a live body, control the first switch to close and the second switch to open, and control the laser to generate target laser; The first switch is used to prevent the first target laser from being incident on the shear speckle generation unit when the first switch is closed; The second switch is used to allow the second target laser to be incident on the structured light generating filter when the second switch is turned on; The structured light generating filter is used to generate the structured light based on the incident second target laser.

10. The system according to claim 7, characterized in that, The laser generating device includes a shear correlation light generator and a structured light generator, wherein: The controller is used to control the shear-correlated light generator to generate expanded target laser in response to the identity recognition command; The shearing coherent light generator is used to shear the expanded target laser reflected by the object to be identified to obtain a first shearing coherent light and a second shearing coherent light. The controller is further configured to control the structured light generator to generate the structured light when the first liveness detection result indicates that the object to be identified is a live body.

11. An identification device, characterized in that, The device includes: The first acquisition module is used to acquire the first shear speckle interferogram of the object to be identified at the first target time using shear speckle interferometry. The second acquisition module is used to acquire the second shear speckle interferogram of the object to be identified at the second target time using the shear speckle interferometry technique. The determining module is used to determine the interference light intensity change pattern of the object to be identified from the first target time to the second target time based on the first shear speckle interferogram and the second shear speckle interferogram; The first liveness detection module is used to determine the first liveness detection result of the object to be identified based on the interference light intensity change diagram; The identity recognition module is used to acquire an image of the object to be identified when the first liveness recognition result indicates that the object to be identified is a live object, to obtain a matching image, and to perform identity recognition processing based on the matching image to obtain the identity recognition result of the object to be identified. It is the first liveness detection module, specifically used for: Obtain at least one interference circle center in the interference intensity variation diagram; Based on the position information of the interference center, the interference intensity variation map is partitioned to obtain a partitioned interference intensity variation map, wherein the partitioned interference intensity variation map includes at least one interference intensity variation region, and each interference intensity variation region contains one interference center. Based on the interference light intensity variation diagram after partitioning, the first liveness detection result of the object to be identified is determined; Wherein, the interference center The point satisfies the following formula: Official (2) in, express The position information (i.e., coordinates) of the point in the interference light intensity variation diagram. express The position information of the point in the interference light intensity variation diagram. The point represents the first pixel in the target pixel group. Target pixels, It is a positive integer. The maximum value is the number of target pixels included in the target pixel group. The target pixel group contains multiple target pixels, and the change in interference light intensity of the target pixels in the same target pixel group is the same. Furthermore, the position information of each target pixel in the same target pixel group can be fitted into a circular curve.

12. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

13. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

14. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images