Information processing device and information processing method and program

The information processing device enhances spoofing detection in face authentication by using image capture, detection, and size assessment to improve accuracy in identifying fraudulent attempts, addressing the challenge of partially obscured spoofing media.

JP2024158083AInactive Publication Date: 2024-11-08CANON KK
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
JP2023072946
Authority / Receiving Office
JP · JP
Patent Type
Applications
Current Assignee / Owner
Filing Date
2023-04-27
Publication Date
2024-11-08
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

Existing face authentication systems struggle to accurately detect spoofing media when they approach the imaging device, especially when the projected part of the spoofing medium occupies the imaging range, making it difficult to differentiate between legitimate and fraudulent attempts.

Method used

An information processing device that includes an acquisition unit for capturing images, a detection unit to identify spoofing media, a size determination unit to assess the size of the detected spoofing medium, and an impersonation determination unit to determine if spoofing has occurred based on the detection and size analysis.

Benefits of technology

Improves the accuracy of spoofing judgment by accurately determining the presence of spoofing media, even when they are partially or fully outside the imaging range, thereby enhancing security in face authentication systems.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 2024158083000001_ABST
    Figure 2024158083000001_ABST
Patent Text Reader

Abstract

To improve the accuracy of the spoofing detection for spoofing using a spoofing medium.SOLUTION: A processing device comprises an acquisition unit that acquires a picked-up image from an imaging apparatus, a detection unit that detects a spoofing medium used for spoofing from the picked-up image, a size decision unit that determines the size of the spoofing medium detected by the detection unit in the picked-up image, and a spoofing determination unit that determines whether or not spoofing has occurred based on the detection results for the spoofing media and the size determination results for the spoofing media.SELECTED DRAWING: Figure 2
Need to check novelty before this filing date? Find Prior Art

Description

[Technical field]

[0001] The present invention relates to an information processing device, an information processing method, and a program. [Background technology]

[0002] In face recognition devices, there are cases where spoofing attempts are made using face images of registered persons. To combat this, a technique has been proposed for detecting spoofing before the execution of authentication processing.

[0003] As a technique for detecting spoofing, there is a spoofed medium detection technique using machine learning, which detects spoofing by determining whether a spoofed medium is present within the shooting range of an imaging device.

[0004] Patent Document 1 discloses a technique for determining spoofing from an authentication image including an authentication target and a background image displayed behind the authentication target. Patent Document 2 proposes a technique for detecting spoofing by determining whether a frame surrounding the face of a target person exists using face position information from a captured image and frame position information obtained by detecting a linear frame. [Prior art documents] [Patent documents]

[0005] [Patent Document 1] Patent Publication No. 2022-053309 [Patent Document 2] JP 2018-169943 A Summary of the Invention [Problem to be solved by the invention]

[0006] In such a technique, when a spoofing medium used for spoofing approaches an imaging device, the projected portion (the portion where the image is displayed) of the spoofing medium occupies the imaging range of the imaging device, and the spoofing medium cannot be detected. As a result, spoofing judgment is not performed, and authentication of the authentication target may be performed. The technique disclosed in Patent Document 1 may not be able to detect spoofing in an environment where the background changes or an environment where a projector that generates a projected image cannot be installed. Also, the technique disclosed in Patent Document 2 may not be able to detect spoofing because frame detection cannot be performed when a spoofing medium approaches an imaging device as described above.

[0007] Therefore, an object of the present invention is to provide a technique for improving the accuracy of spoofing determination against spoofing using a spoofing medium. [Means for solving the problem]

[0008] One embodiment of the present invention is characterized by comprising an acquisition unit that acquires an image from an imaging device, a detection unit that detects an impersonation medium used for impersonation from the captured image, a size determination unit that determines the size in the captured image of the impersonation medium detected by the detection unit, and an impersonation determination unit that determines whether or not impersonation has occurred based on the detection result of the impersonation medium and the determination result of the size of the impersonation medium. Effect of the Invention

[0009] According to the present invention, it is possible to improve the accuracy of spoofing determination against spoofing using a spoofing medium. [Brief description of the drawings]

[0010] [Figure 1] FIG. 2 is a diagram illustrating an example of a hardware configuration of an information processing device according to an embodiment. [Diagram 2] 1 is a block diagram showing an example of a functional configuration of an information processing device according to an embodiment. [Diagram 3] 10 is a flowchart relating to spoofing determination executed by an information processing device. [Figure 4] FIG. 13 is a state transition diagram of the spoofing determination result updated in S304. [Diagram 5] FIG. 1 is a diagram illustrating an example of a flow of an act of spoofing using a spoofing medium. [Figure 6] FIG. 13 is a diagram showing an example of a spoofed medium. [Figure 7] FIG. 10 is a diagram illustrating spoofing determination according to the present embodiment. [Figure 8] 11A and 11B are diagrams illustrating another example in which the spoofing determination according to the present embodiment is applied. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0011] Preferred embodiments of the present invention will be described in detail below with reference to the accompanying drawings. Note that the present invention is not limited to the following embodiments, which merely show specific examples that are advantageous for carrying out the present invention. Furthermore, not all of the combinations of features described in the following embodiments are necessarily essential for solving the problems of the present invention.

[0012] (Embodiment) 1 is a diagram showing an example of the hardware configuration of an information processing device 100 according to an embodiment. The information processing device 100 is a device that determines whether or not there is spoofing by using a captured image captured for authentication. Note that spoofing is an act of presenting the face of a person registered in an authentication system 108 (described later) on a mobile terminal such as a smartphone or a printed matter such as a photograph, and making an unauthorized use of the system in place of the legitimate registered person.

[0013] A CPU (Central Processing Unit) 101 is a central processing unit that performs calculations and logical determinations for various processes and controls each component connected to a system bus 106. This information processing device 100 is equipped with memories including a program memory and a data memory.

[0014] A ROM (Read-Only Memory) 102 is a program memory that stores programs for control by the CPU, including various processing procedures described later.

[0015] The RAM (Random Access Memory) 103 is a data memory, and has a work area for the above programs of the CPU 101, an area for saving data during error processing, an area for loading the above control programs, etc. Note that a program memory may be realized by loading a program into the RAM 103 from an external storage device connected to the information processing device 100.

[0016] The HDD 104 is a hard disk for storing a plurality of electronic data and programs according to the present embodiment. An external storage device may be used to fulfill a similar role. Here, the external storage device may be realized by, for example, a medium (recording medium) and an external storage drive for realizing access to the medium. Examples of such media include a flexible disk (FD), a CD-ROM, a DVD, a USB memory, an MO, and a flash memory. The external storage device may also be a server device connected via a network. The communication interface (I / F) 105 performs wired or wireless bidirectional communication with other information processing devices, communication devices, external storage devices, and the like using known communication technology.

[0017] In this embodiment, the communication I / F 105 is connected to an image capturing device 107 via a LAN, for example, and receives captured video in real time. The image capturing device 107 is a device that captures video of an authentication target of an authentication system 108 (described later), such as the face of a person entering a room, within the angle of view, and the form of the device is not particularly specified, such as a network camera or a module camera.

[0018] The authentication system 108 is communicatively connected to the information processing device 100, and executes various processes related to authentication depending on the results of the processes performed by the information processing device 100. That is, the authentication system 108 functions as an authentication unit. In this embodiment, the authentication system 108 performs face authentication as an example. The entrance / exit management system 109 is communicatively connected to the authentication system 108, and executes various processes related to unlocking and locking the electric lock depending on the results of the face authentication performed by the authentication system 108.

[0019] 2 is a block diagram showing an example of a functional configuration of the information processing device 100 according to the embodiment. The information processing device 100 includes a control unit 201, an image acquisition unit 202, a detection unit 203, a size determination unit 204, a spoofing determination unit 205, a storage unit 206, and a communication unit 207.

[0020] The control unit 201 includes a CPU 101 and the like, and reads out programs and data stored in a ROM 102 into a RAM 103 to execute various processes.

[0021] The image acquisition unit 202 acquires the image captured by the imaging device 107 .

[0022] The detection unit 203 detects the spoofed medium in the captured image by using an object detection function based on machine learning, and acquires position information of the spoofed medium in the captured image. The detection unit 203 also transmits the area in the captured image where the spoofed medium is detected as the spoofed medium area to the size determination unit 204. In other words, the detection unit 203 transmits the area in the captured image where the spoofed medium exists as the spoofed medium area to the size determination unit 204.

[0023] The size determination unit 204 determines the size of the spoofed medium in the captured image using the detection result of the detection unit 203 and a preset size determination standard. Here, the size of the spoofed medium is determined using the area of ​​the spoofed medium region in the captured image detected by the detection unit 203. Note that the length and width of the spoofed medium region may also be used to determine the size of the spoofed medium.

[0024] The spoofing determination unit 205 updates the spoofing determination result using the result of the determination of the size of the spoofed medium by the size determination unit 204 and the result of the spoofing determination before the update, and determines whether or not there is any spoofing.

[0025] The storage unit 206 stores various types of information.

[0026] The communication unit 207 transmits the captured image and information on the spoofing determination result to the authentication system 108.

[0027] 3 is a flowchart related to spoofing determination executed by information processing device 100. Spoofing determination is continuously executed from the start of processing until the system administrator issues an instruction to end it. Each process (step) will be explained below by adding an S to the beginning of the reference number. Each process shown in this flowchart can be executed by the control of each unit by CPU 101.

[0028] In S301, the image acquisition unit 202 receives (acquires) photographing data (video), that is, a captured image, from the imaging device 107 and inputs the captured image to the detection unit 203.

[0029] In S302, the detection unit 203 detects a spoofed medium. If a spoofed medium is detected in S302, the detection unit 203 transmits the detection result to the size determination unit 204, including the spoofed medium area.

[0030] In S303, the size determination unit 204 determines the size of the detected spoofed medium using the spoofed medium area. If the size of the detected spoofed medium area is equal to or larger than the determination criterion, the size determination unit 204 determines the result as "large", and if it is less than the determination criterion, the size determination unit 204 determines the result as "small". If no spoofed medium is detected, the size determination unit 204 determines the size result as "none". Then, the size determination unit 204 inputs the determination result to the spoofing determination unit 205.

[0031] In S304, the spoofing determination unit 205 determines whether or not there is spoofing based on the result of the detection of the spoofed medium, the result of the size determination, and the spoofing determination result before the update, and updates the spoofing determination result based on the update method described later.

[0032] In S305, the spoofing determination unit 205 transmits the determination result to the authentication system .

[0033] In S306, the control unit 201 ends the process if there is an instruction from the user of the information processing device 100. If not, the process returns to S301, and the processes of S301 to S306 are repeated.

[0034] 4 is a state transition diagram of the spoofing judgment result updated in S304. The initial value of the spoofing judgment result in the information processing device 100 is "not spoofing (no spoofing)". It is assumed that the spoofing judgment result before the update is "not spoofing". In this case, if the judgment result of the size judgment unit 204 is "large (1-1)", it is determined to be "spoofing (spoofing)", and if it is "small (1-2)" or "no (1-3)", it is determined to be "not spoofing". On the other hand, it is assumed that the spoofing judgment result before the update is "spoofing". In this case, if the judgment result of the size judgment unit 204 is "small (2-2)", it is determined to be "not spoofing", and if it is "large (2-1)" or "no (2-3)", it is determined to be "spoofing". That is, if the size of the spoofed medium is not judged to be "small" after the spoofed medium is detected and the spoofed medium is no longer detected (the judgment result becomes "none"), the spoofing judgment unit 205 judges that the medium is "spoofed."

[0035] 5 is a diagram for explaining an example of the flow of a spoofing act using a spoofing medium. In a scene 500 in which normal face authentication is performed, the authentication system 108 unlocks or locks a door 503 by transmitting information to the entrance / exit management system 109 based on the result of face matching of a person 501 captured by the imaging device 107. In addition, the spoofing judgment result is displayed on a display terminal 504 as feedback to the user.

[0036] In a scene 510 in which authentication by spoofing is attempted using a spoofing medium 511, the authentication system 108 displays a warning on the display terminal 504 and does not perform authentication processing. In other words, when a determination result of "spoofing" is transmitted from the information processing device 100, the authentication system 108 displays a warning on the display terminal 504 and does not perform authentication processing.

[0037] Next, the spoofing determination performed in a scene 520 in which the spoofing medium 511 is brought close to the imaging device 107 and is not captured within the imaging range will be specifically described with reference to FIGS. 6 and 7. In S302 of FIG. 3, the detection unit 203 detects the spoofing medium 511 from the input captured image using object detection by machine learning. FIG. 6 is a diagram showing an example of the spoofing medium 511. The spoofing medium 511 is, for example, a mobile terminal such as a tablet terminal or a printed matter such as a photograph. Here, an example is shown in which the spoofing medium 511 is a tablet terminal. The spoofing medium 511 includes a medium part 512 that can display or print an image to be authenticated, that is, an image of a legitimate registered person. For example, when the spoofing medium 511 is a mobile terminal such as a tablet terminal, the medium part 512 is the main body of the mobile terminal, and when the spoofing medium 511 is a printed matter such as a photograph, the medium part 512 is a sheet of paper on which an image is printed. The medium portion 512 includes a display / print area 513 in which an image of the legitimate registrant is displayed or printed on the medium portion 512 .

[0038] The detection unit 203 detects the spoofed medium area from the captured image when detecting a state in which the spoofed medium 511 and the person 501 are holding the spoofed medium 511 toward the imaging device 107. FIG. 7 is a diagram for explaining the spoofing determination according to the present embodiment. In the size determination by the size determination unit 204 in S303, the determination criterion is the minimum size at which the face can be authenticated in the authentication system 108. FIG. 7(A) shows the determination criterion 612 used for the size determination in S303. This is because the size of the spoofed medium 511 is not smaller than the face to be authenticated by the authentication system 108. Therefore, the size determination criterion is the minimum size of the face that can be used for authentication by the authentication system. The size determination criterion is not limited to this, and may be the ratio of the spoofed medium area occupying the captured image, which is set in advance. The ratio of the spoofed medium area occupying the captured image can be calculated by the area of ​​the spoofed medium area / the area of ​​the imaging range. The size determination unit 204 classifies the size of the spoofed medium 511 into "large" or "small" using a preset criterion.

[0039] An example of spoofing determination according to the flowchart of FIG. 3 will be described using the example of FIG. 7(B). FIG. 7(B) is a diagram for explaining spoofing determination according to this embodiment. Specifically, a series of actions is assumed in which an impersonator brings an impersonation medium 511 close to the imaging device 107, and when the impersonator gives up on the act of spoofing, moves the impersonation medium 511 away from the imaging device 107. The dashed line indicates the imaging range 610 of the imaging device 107. Here, the act of spoofing is performed by a person 501 using the impersonation medium 511 on which a face image 611 of the person to be spoofed is displayed. That is, the person 501 corresponds to the impersonator here.

[0040] In scene 601, since no spoofing medium 511 is detected within imaging range 610, spoofing determination unit 205 sets the previous spoofing determination result of "not spoofing" as the current spoofing determination result. In other words, if no spoofing medium 511 is detected, spoofing determination unit 205 does not update the spoofing determination result from the previous spoofing determination result.

[0041] In scene 602, the detection unit 203 detects a spoofed medium 511 within an imaging range 610. Since the size of the detected spoofed medium 511 is less than the judgment criterion 612, the size judgment unit 204 judges the size to be "small", and the spoofing judgment unit 205 judges the spoofing judgment result to be "not spoofed".

[0042] In scene 603, the detection unit 203 detects a spoofed medium 511 within the imaging range 610. Here, since the size of the detected spoofed medium 511 is equal to or larger than the judgment criterion 612, the size judgment unit 204 judges the size to be "large", and the spoofing judgment unit 205 judges the spoofing judgment result to be "spoofed".

[0043] In scene 604, since no spoofing medium 511 is detected within the imaging range 610, the spoofing determination unit 205 sets the previous spoofing determination result, "spoofing", as the current spoofing determination result. In other words, if no spoofing medium 511 is detected, the spoofing determination unit 205 does not update the spoofing determination result. This makes it possible to detect spoofing even when no spoofing medium 511 is detected.

[0044] In scene 605, the detection unit 203 detects a spoofed medium 511 within the imaging range 610. Here, since the size of the detected spoofed medium 511 is equal to or larger than the judgment criterion 612, the size judgment unit 204 judges the size to be "large", and the spoofing judgment unit 205 judges the spoofing judgment result to be "spoofed".

[0045] In scene 606, the detection unit 203 detects a spoofed medium 511 within the imaging range 610. Here, since the size of the spoofed medium 511 is less than the judgment criterion 612, the size judgment unit 204 judges the size to be "small", and the spoofing judgment unit 205 judges the spoofing judgment result to be "not spoofed".

[0046] In scene 607, since no spoofed medium 511 is detected within the imaging range 610, the spoofing determination unit 205 sets the previous spoofing determination result of "not spoofing" as the current spoofing determination result. In other words, since no spoofed medium 511 is detected within the imaging range 610 here, the spoofing determination unit 205 does not update the spoofing determination result.

[0047] It is also possible that the spoofer brings the spoofing medium 511 close to the imaging device, and when he or she gives up on the act of spoofing, moves the spoofing medium 511 out of the imaging range 610 without moving it away from the imaging device 107. Spoofing determination in such a case will be described with reference to Fig. 8. Fig. 8 is a diagram for explaining another example in which the spoofing determination according to this embodiment is applied.

[0048] In scene 605, the detection unit 203 detects a spoofed medium 511 within the imaging range 610. Here, since the size of the detected spoofed medium 511 is equal to or larger than the judgment criterion 612, the size judgment unit 204 judges the size to be "large", and the spoofing judgment unit 205 judges the spoofing judgment result to be "spoofed".

[0049] In scene 701, an impersonator is attempting to move the spoofed medium 511 out of the imaging range 610 of the imaging device 107. The detection unit 203 detects the spoofed medium 511 within the imaging range 610. Here, since the size of the spoofed medium 511 is less than the judgment criterion 612, the size judgment unit 204 judges the size to be "small", and the spoofing judgment unit 205 judges the spoofing judgment result to be "not spoofed".

[0050] In scene 607, the spoofing actor has moved the spoofed medium 511 out of the imaging range 610 of the imaging device 107, and therefore the spoofed medium 511 is not detected within the imaging range 610. Therefore, the spoofing determination unit 205 sets the previous spoofing determination result of "not spoofing" as the current spoofing determination result. In other words, since the spoofed medium 511 has not been detected within the imaging range 610, the spoofing determination unit 205 does not update the spoofing determination result. This allows the spoofing determination to be performed correctly even if the spoofing actor has moved the spoofed medium 511 out of the imaging range 610 without moving it away from the imaging device 107.

[0051] As described above, according to this embodiment, even if the spoofed medium is located outside the imaging range of the imaging device and its presence cannot be detected, the presence or absence of the spoofed medium can be inferred using past judgment results to detect spoofing.

[0052] It should be noted that this spoofing detection method is merely an example, and the spoofing detection method is not limited to this. The target of the authentication system 108 may be an iris authentication using the eyes instead of a face, or an inorganic object.

[0053] As a modified example related to the present invention, there is a process of detecting an attempt to spoof by bringing the spoofing medium 511 close to the imaging device 107 for a long time. If the spoofing medium is not detected for a long time in S304 after the spoofing is determined, the following two situations are considered. The first situation is a situation in which spoofing is attempted and the state in which the spoofing medium 511 in the scene 520 shown in FIG. 5 is brought close to the imaging device 107 continues for a long time. The second situation is a situation in which the information processing device 100 cannot detect the spoofing medium 511 moving away from the imaging device 107 when the spoofing act is given up after detecting the state in which the spoofing medium 511 in the scene 520 shown in FIG. 5 is brought close to the imaging device 107. In this case, the situation is one in which the "spoofing" determination remains. In either case, it can be determined that the system cannot continue, so an error generation process is added, such as notifying the system administrator and stopping the system by determining a timeout. That is, the spoofing determination unit 205 executes an error occurrence process when the spoofing determination result does not change for a predetermined time or more. This increases the number of situations in which suspicious behavior can be detected. The error occurrence process may be to issue an alarm or to reset the determination result to an initial state. When an alarm is issued as the error occurrence process, it increases the number of situations in which suspicious behavior can be detected. When the error occurrence process is to reset the determination result to an initial state, it is possible to automatically return to the spoofing determination process without human intervention.

[0054] Furthermore, when spoofing is attempted by a mobile terminal such as a tablet terminal, the display unit of the mobile terminal may become a mirror surface and the mirror image of the imaging device 107 may be reflected in the imaging range 610. For this reason, the detection unit 203 is given learning so that it can detect the mirror image of the imaging device 107, and when the mirror image of the imaging device 107 is detected, it is possible to perform spoofing determination by going through the same process as for the spoofed medium. That is, the detection unit 203 detects the mirror image of the imaging device 107 reflected on the spoofed medium instead of the spoofed medium. Then, the size determination unit 204 performs size determination of the detected mirror image, and the spoofing determination unit 205 determines the presence or absence of spoofing based on the results.

[0055] Although the preferred embodiments of the present invention have been described above, the present invention is not limited to these embodiments, and various modifications and changes are possible within the scope of the gist of the present invention.

[0056] In the above embodiment, the information processing device 100 is configured separately from the imaging device 107. However, the information processing device 100 may be incorporated in the imaging device 107 as a part of the imaging device 107. Alternatively, the information processing device 100 may be incorporated in an authentication system 108. Furthermore, the authentication system 108 having the functions of the information processing device 100 may be incorporated in an entrance / exit management system 109. Also, the above-mentioned authentication using the spoofing determination can be applied to authentication at the time of logging in to a device or making a payment.

[0057] The present invention can also be realized by a process in which a program for implementing one or more of the functions of the above-described embodiments is supplied to a system or device via a network or a storage medium, and one or more processors in a computer of the system or device read and execute the program. The present invention can also be realized by a circuit (e.g., ASIC) that implements one or more of the functions.

[0058] (Configuration 1) an acquisition unit that acquires a captured image from an imaging device; a detection unit that detects a spoofing medium used for spoofing from the captured image; a size determination unit that determines a size in the captured image of the spoofed medium detected by the detection unit; an information processing device comprising: a spoofing determination unit that determines whether or not there is spoofing based on a result of the detection of the spoofed medium and a result of determining the size of the spoofed medium.

[0059] (Configuration 2) 2. The information processing device according to configuration 1, wherein the spoofing determination unit determines whether or not there is spoofing based further on a result of the spoofing determination before an update.

[0060] (Configuration 3) The information processing device described in configuration 1 or 2, characterized in that the spoofing medium includes a medium portion capable of displaying or printing an image to be authenticated, and a display / print area on the medium portion in which the image is displayed or printed.

[0061] (Configuration 4) The information processing device described in any one of configurations 1 to 3, characterized in that when the detection unit detects the spoofed medium from the captured image and a state in which a person is holding the spoofed medium toward the imaging device, it detects an area in which the spoofed medium exists from the captured image.

[0062] (Configuration 5) The information processing device described in any one of configurations 1 to 4, characterized in that the spoofing determination unit determines the spoofing judgment result to be that spoofing is present if, after the spoofed medium is detected, the area in the captured image in which the spoofed medium is present does not fall below a standard and the spoofed medium is no longer detected.

[0063] (Configuration 6) The information processing device described in any one of configurations 1 to 5, characterized in that the spoofing judgment unit does not update the spoofing judgment result from the previous spoofing judgment result if the spoofed medium is not detected.

[0064] (Configuration 7) 7. The information processing device according to any one of configurations 1 to 6, wherein the spoofing determination unit determines that there is no spoofing when the size of the detected spoofed medium is less than a reference size.

[0065] (Configuration 8) The information processing device of any one of configurations 1 to 7, characterized in that the size determination unit classifies the size of the spoofed medium detected by the detection unit based on the proportion of the spoofed medium that occupies the captured image.

[0066] (Configuration 9) the information processing device is communicably connected to an authentication unit that detects a target to be authenticated; The information processing device described in any one of configurations 1 to 7, characterized in that the size determination unit classifies the size of the spoofed medium detected by the detection unit based on the minimum size of the authentication object that can be authenticated by the authentication unit.

[0067] (Configuration 10) 10. The information processing device according to configuration 9, wherein the object to be authenticated by the authentication unit is a face.

[0068] (Configuration 11) 11. The information processing device according to any one of configurations 1 to 10, wherein the spoofing determination unit executes an error occurrence process when the spoofing determination result does not change for a predetermined time or more.

[0069] (Configuration 12) 12. The information processing device according to any one of configurations 1 to 11, wherein the detection unit detects a mirror image of the imaging device reflected on the spoofed medium instead of the spoofed medium.

[0070] (Configuration 13) 13. The information processing device according to any one of configurations 1 to 12, wherein the captured image is an image for authentication.

[0071] (Method 1) Acquire a captured image from an imaging device; detecting a spoofing medium used for spoofing from the captured image; determining a size of the detected spoofed medium in the captured image; A method for determining whether or not a spoofing has occurred, the method comprising the steps of: determining whether or not a spoofing has occurred based on a result of the detection of the spoofed medium and a result of determining the size of the spoofed medium.

[0072] (program) A program for causing a computer to execute a spoofing determination method, The spoofing determination method includes: Acquire a captured image from an imaging device; detecting a spoofing medium used for spoofing from the captured image; determining a size of the detected spoofed medium in the captured image; A program for determining whether or not a medium has been spoofed based on a result of the detection of the spoofed medium and a result of determining the size of the spoofed medium.

[0073] (storage medium) A computer-readable storage medium storing the program according to claim 14. [Explanation of symbols]

[0074] 100 Information processing device 107 Imaging Device 108 Authentication System 109 Entrance / Exit Control System 201 Control section 202 Image acquisition unit 203 Detection unit 204 Size Judgment Section 205 Spoofing Detection Unit 206 Memory section 207 Communications Department

Claims

1. an acquisition unit that acquires a captured image from an imaging device; a detection unit that detects a spoofing medium used for spoofing from the captured image; a size determination unit that determines a size in the captured image of the spoofed medium detected by the detection unit; an information processing device comprising: a spoofing determination unit that determines whether or not there is spoofing based on a result of the detection of the spoofed medium and a result of determining the size of the spoofed medium.

2. The information processing apparatus according to claim 1 , wherein the spoofing determination unit determines whether or not the spoofing has occurred based on a result of the spoofing determination before an update.

3. 2 . The information processing apparatus according to claim 1 , wherein the spoofing medium includes a medium portion capable of displaying or printing an image to be authenticated, and a display / print area on the medium portion in which the image is displayed or printed.

4. The information processing device according to claim 1, characterized in that the detection unit detects an area in which the spoofed medium exists from the captured image when it detects the spoofed medium from the captured image and a state in which a person is holding the spoofed medium toward the imaging device.

5. The information processing device described in claim 1, characterized in that the spoofing determination unit determines the spoofing judgment result to be that spoofing is present if, after the spoofed medium is detected, the area in which the spoofed medium is present in the captured image does not become smaller than a standard and the spoofed medium is no longer detected.

6. 2 . The information processing apparatus according to claim 1 , wherein the spoofing determination unit, when the spoofed medium is not detected, does not update the spoofing determination result from the previous spoofing determination result.

7. The information processing apparatus according to claim 1 , wherein the spoofing determination unit determines that there is no spoofing when the size of the detected spoofed medium is less than a reference size.

8. The information processing apparatus according to claim 1 , wherein the size determination unit classifies the size of the spoofed medium detected by the detection unit according to a proportion of the captured image that the spoofed medium occupies.

9. the information processing device is communicably connected to an authentication unit that detects a target to be authenticated; 2 . The information processing apparatus according to claim 1 , wherein the size determination unit classifies the size of the spoofed medium detected by the detection unit based on a minimum size of an authentication target that can be authenticated by the authentication unit.

10. 10. The information processing apparatus according to claim 9, wherein the object to be authenticated by the authentication unit is a face.

11. 2 . The information processing apparatus according to claim 1 , wherein the spoofing determination unit executes an error occurrence process when the spoofing determination result does not change for a predetermined period of time or more.

12. The information processing apparatus according to claim 1 , wherein the detection unit detects a mirror image of the imaging device reflected on the spoofed medium instead of the spoofed medium.

13. The information processing apparatus according to claim 1 , wherein the captured image is an image for authentication.

14. Acquire a captured image from an imaging device; detecting a spoofing medium used for spoofing from the captured image; determining a size of the detected spoofed medium in the captured image; A method for determining whether or not a spoofing has occurred, the method comprising the steps of: determining whether or not a spoofing has occurred based on a result of the detection of the spoofed medium and a result of determining the size of the spoofed medium.

15. A program for causing a computer to execute a spoofing determination method, The spoofing determination method includes: Acquire a captured image from an imaging device; detecting a spoofing medium used for spoofing from the captured image; determining a size of the detected spoofed medium in the captured image; A program for determining whether or not a medium has been spoofed based on a result of the detection of the spoofed medium and a result of determining the size of the spoofed medium.

16. A computer-readable storage medium storing the program according to claim 15.

Citation Information

Patent Citations

  • Face authentication processing device, face authentication processing method and face authentication processing system

    JP2018169943A

  • Authentication processing device, authentication processing method and program

    JP2022053309A