Device, display method, and program

Abstract

To provide a device, display method and program, which enable prevention of an unauthorized access even when spoofing is attempted.SOLUTION: A device is provided, comprising a display capable of displaying first guidance for guiding a target person to be imaged by a camera to maintain his / her line of sight, and second guidance for guiding the target person to change his / her head angle.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present disclosure relates to a device, a display method, and a program for preventing spoofing. [Background technology]

[0002] In recent years, electronic devices and the like have been using biometric data for purposes such as facial recognition to restrict access to data or easily recognize individuals by certain facial characteristics. Personal security, the threat of identity theft, and the like have become major concerns, and malicious actors have attempted to use various techniques to overcome automated identity recognition security methods, particularly to gain unauthorized access to data on or use of electronic devices. Facial recognition is one security method to combat unauthorized access to devices such as smartphones, smart pads, laptops, personal computers, and gaming systems equipped with digital cameras. However, facial recognition may also be performed intentionally to misidentify a person by using a photograph, video, a mask, and the like (hereinafter sometimes referred to as "impersonation").

[0003] To help overcome such deficiencies in face recognition methods, several techniques have been implemented. For example, U.S. Patent No. 6,339,633 teaches taking multiple images from a camera and using threshold comparisons to detect whether one is looking at a still image or a live human face. Another method is known, as described in, for example, U.S. Patent No. 5,339,933, in which stimuli are presented on a screen to elicit a facial response from the subject, the subject's facial movements are tracked by a camera, and compared with a predictive model of the facial response to verify that the subject is human. Also, as described in Patent Document 3, for example, another method is known in which an image is displayed on a screen, the subject's eyes are moved, and the subject's eyes are tracked by a camera to confirm that the subject is a human. Another method described in Patent Document 4 proposes tracking the subject's gaze angle and having the subject respond to challenges such as gazing at numbered locations on a display device in passcode order. However, these methods may still be vulnerable to spoofing attacks, for example where three-dimensional masks are used. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] European Patent Application Publication No. 2546782 [Patent Document 2] European Patent Application Publication No. 3373202 [Patent Document 3] US Patent Application Publication No. 2017 / 0185760 [Patent Document 4] US Patent Application Publication No. 2019 / 0034606 Summary of the Invention [Problem to be solved by the invention]

[0005] What is needed is a technique that overcomes vulnerabilities in facial recognition technology that can properly recognize biometrics even when spoofing methods are attempted.

[0006] Therefore, an exemplary object of the present disclosure is to provide a device, a display method, and a program capable of preventing unauthorized access even when an spoofing method is attempted. [Means for solving the problem]

[0007] A first aspect of the present disclosure provides a device characterized by having a display capable of displaying a first guide that guides a user to maintain a line of sight with a subject being imaged by a camera, and a second guide that guides a user to change the angle of the subject's head relative to the subject.

[0008] A second aspect of the present disclosure provides a display method including displaying a first guide that guides a user to maintain a line of sight toward a subject captured by a camera, and displaying a second guide that guides the user to change the angle of the subject's head.

[0009] A third aspect of the present disclosure provides a program for causing a computer to display a first guide that guides a user to maintain a line of sight toward a subject captured by a camera, and to display a second guide that guides the user to change the angle of the subject's head. [Brief description of the drawings]

[0010] [Figure 1] FIG. 2 illustrates a diagram showing head angle versus gaze angle of a subject when using an exemplary image processing device of the present disclosure. [Diagram 2] 1 is a flowchart of an exemplary method of the present disclosure. [Diagram 3] 4 is another flow chart of an exemplary method of the present disclosure. [Figure 4] 13A-13C illustrate example prompts for a subject on a display of an exemplary image processing device of the present disclosure. [Diagram 5] 13A-13C are diagrams illustrating example prompts for a subject on a display of another exemplary image processing device of the present disclosure. [Figure 6] FIG. 13 shows an experimental example of the difference between gaze angle and head angle of a subject during changes in head angle for a live subject versus a 3D mask. [Figure 7] FIG. 2 is a block diagram of an exemplary image processing device of the present disclosure. [Figure 8] FIG. 1 illustrates an image processing device according to an exemplary embodiment of the present disclosure. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0011] Hereinafter, exemplary embodiments of the present disclosure will be described with reference to the drawings. In the drawings, the same elements are indicated by the same reference numerals, and therefore repeated description will be omitted as appropriate.

[0012] Throughout this specification, references to "one embodiment," "an embodiment," "an example," or "an example" mean that a particular feature, structure, or characteristic described in connection with the embodiment or example is included in at least one embodiment of the present embodiments. Thus, the appearances of the phrases "in one embodiment," "in an embodiment," "an example," or "an example" in various places throughout this specification do not necessarily all refer to the same embodiment or example. Furthermore, the particular features, structures, or characteristics may be combined in any suitable combinations and / or subcombinations in one or more embodiments or examples.

[0013] EXEMPLARY EMBODIMENTS

[0014] Hereinafter, an image processing device will be described as an exemplary embodiment of the present disclosure with reference to the drawings.

[0015] In this example, the image processing device is a mobile phone belonging to an owner (i.e., a subject) whose facial feature points have been previously stored in the storage unit 108. When the subject attempts to unlock or use the mobile phone, the mobile phone may need to identify that the subject is the owner or otherwise authorized user. A facial recognition process is initiated to ensure that the subject can properly use the mobile phone. Alternatively, the image processing device may be a security device that identifies authorized people and allows restricted activities, such as access to sensitive information or entry into restricted areas.

[0016] 7, the image processing device 100 according to this example includes a processor 104, a camera 106, and a storage unit 108. The image processing device may optionally include a display unit 102. First, the camera 106 of the image processing device 100 captures an image of a subject. From the captured image, the processor 104 extracts facial feature points of the subject's face for comparison with facial feature points of targets pre-stored in the storage unit 108. Then, if the comparison determines a match, the image processing device 100 attempts to determine whether the subject is a live person (i.e., check the liveliness of the subject).

[0017] 1 illustrates an example of an image processing device 100 of the present disclosure in which a subject moves the position of their head while directing their gaze toward the image processing device 100. In this example, the image processing device captures an image of the subject and calculates the subject's gaze angle in addition to the subject's head angle. The head angle may be determined, for example, by the distance between the subject's nose relative to the position of the subject's eyes or relative to other facial features of the subject. The gaze angle may be calculated from the position of the pupils of each of the subject's eyes in the captured image.

[0018] When a three-dimensional mask is used to fool an image processing device, the relative angular difference between the head angle and the gaze angle should remain constant as the head angle changes, so that while capturing multiple images of a subject with varying head angles, the subject can be determined to be a live person if the head angles and gaze angles are different.

[0019] An example of observed differences between a real person and a three-dimensional mask during head angle changes is shown in FIG. 6. In this figure, the solid line represents the head pan angle, and the dashed line represents the gaze pan angle. Taking this into account, a predefined threshold difference can be selected to determine whether the subject is a live person. In other words, if the difference between the head angle and the gaze angle is greater than a predefined threshold, the subject is determined to be a live person, and access to the mobile phone (image processing device) can be appropriately granted. Otherwise, access to the mobile phone is appropriately denied, thus realizing improved security and accuracy of face recognition.

[0020] The operational flow chart will be described with reference to FIG. 2 and FIG.

[0021] 2 shows an exemplary flow chart for determining liveliness of a subject. In this method, the gaze angle is calculated (S104) and the head angle is calculated (S105) from the image of the subject captured by the camera 106. The gaze angle calculation (S104) and the head angle calculation (S105) can be performed in any order, as long as they are performed prior to the later step (S106) of calculating the difference between the gaze angle and the head angle. In this step (S106), the difference between the gaze angle and the head angle is calculated and compared with other images captured by the camera. If the difference between the respective images remains constant within a predetermined threshold, it can be determined that the subject is not a live person (S104) and access to the mobile phone can be appropriately denied.

[0022] FIG. 3 shows additional steps of a flow chart to verify the subject's identity and prompt the subject to change head angle so that liveliness determination can be made. First, the subject's face is recognized (S101). This recognition can be done using known face recognition algorithms or known face recognition neural networks. Once the face is recognized, the subject can optionally be instructed via the display unit 102 to change the head angle while maintaining the gaze angle towards the image processing device 100 (S102), for example as shown in FIG. 4. The camera 106 can then capture one or more images and calculate the gaze angle and head angle in the images (S104, S105) so that facial features can be extracted (S103).

[0023] (Other embodiments) In the above exemplary embodiment, the present disclosure has been described with respect to an image processing device and method for achieving anti-spoofing, but the present disclosure should not be considered limited thereto. Other embodiments are possible without going beyond the scope of the present disclosure. Additions, modifications, and other configurations can also be implemented and still fall within the scope of the present disclosure. Some examples are described below.

[0024] The present disclosure may be realized as a non-transitory computer-readable storage medium including instructions for causing at least one computer or a plurality of processors to execute the above-mentioned functions in the image processing device described in the above exemplary embodiment. The program may realize a part of the above-mentioned functions. Furthermore, the program may be a so-called difference file (difference program) capable of realizing the above-mentioned functions in combination with a program already recorded in the computer system.

[0025] Also, the image processing device described above captures the image of the subject using one camera. However, in another exemplary embodiment of the present disclosure, as shown in FIG. 5, multiple cameras can be used to more accurately determine the gaze angle and head angle of the subject, and multiple images obtained from multiple cameras with different viewpoints are used to extract 3D information of the subject. The extracted 3D information of the subject is taken into account in the calculation of the gaze angle and head angle.

[0026] Furthermore, when a three-dimensional mask is used to fool the image processing device 100 and / or image processing method of the present disclosure, a mask with a peephole cut out may be worn by a live person. In such cases, secondary facial features may be detected as a basis for determining whether the subject has the necessary activity to match the target. For example, the subject's blink rate, mouth movement, nostril flare, and / or eyebrow movement may be used to determine whether the subject is a living being, and the subject may be prompted to perform any of these actions via the display unit 102 or speaker in addition to the gaze angle vs. head angle determination taught in this disclosure.

[0027] 8 illustrates an image processing device 1 according to an exemplary embodiment of the present disclosure. The image processing device 1 includes a receiver 10 and a processor 20. The receiver 10 receives a plurality of images of a subject from a camera 2. The processor 20 calculates an angle difference between the gaze angle and head angle of the subject for each of the plurality of images, and determines the authenticity of the subject based on at least the angle difference of each image. [Industrial Applicability]

[0028] This disclosure is applicable to the fields of computers, computer software, and facial recognition. [Explanation of symbols]

[0029] 100 Image Processing Device 102 Display unit 104 processors 106 Camera 108 Storage Unit

Claims

1. a display that displays a first guide to guide a user to maintain a line of sight with respect to a subject captured by a camera, and a second guide to guide a user to change an angle of the subject's head with respect to the subject; A device comprising: a processor that determines whether or not a subject is spoofed using an image including the subject captured by the camera, the image including the subject following the second guidance while following the first guidance.

2. The device according to claim 1 , wherein the second guidance guides the subject to turn the head to the left or right.

3. The device of claim 1 or 2, wherein the processor determines spoofing based on an angular difference between the angle of the subject's gaze and the angle of the subject's head.

4. The device of claim 3 , wherein the processor calculates the angular difference from the images.

5. The device of claim 1 or 2, wherein the processor calculates an angular difference between the angle of the subject's line of sight and the angle of the head for each of a plurality of images captured by the camera to obtain a series of angular differences, and determines spoofing based on at least the series of angular differences.

6. a receiving unit that receives an image including the subject captured by a camera, the image following a first guide that guides the subject to maintain a line of sight and a second guide that guides the subject to change an angle of the subject's head; A processor that uses the image to determine spoofing.

7. The device according to claim 6 , wherein the second guidance guides the subject to turn the head to the left or right.

8. 8. The device of claim 6 or 7, wherein the processor determines spoofing based on an angular difference between the angle of the subject's gaze and the angle of the subject's head.

9. The device of claim 8 , wherein the processor calculates the angular difference from the images.

10. The device of claim 6 or 7, characterized in that the processor calculates an angular difference between the angle of the subject's line of sight and the angle of the head for each of a plurality of images captured by the camera to obtain a series of angular differences, and determines spoofing based on at least the series of angular differences.

11. Displaying a first guide to guide a user to maintain a line of sight with respect to a subject captured by a camera, and a second guide to guide a user to change an angle of a head of the subject with respect to the subject; determining whether or not the subject has been spoofed using an image including the subject captured by the camera, the image including the subject following the second guidance while following the first guidance.

12. On the computer, Displaying a first guide to guide a user to maintain a line of sight with respect to a subject captured by a camera, and a second guide to guide a user to change an angle of a head of the subject with respect to the subject; A program for executing the steps of: determining whether or not an identifiable person has been masqueraded as an identity theft by using an image including the subject captured by the camera, the image including the subject following the second guidance while following the first guidance.

Images