Living body determination device and living body determination method
The biometric determination device uses polarized light to analyze corneal reflections for liveness determination, addressing the challenge of distant subject identification without high-resolution cameras, thereby improving facial recognition security.
Patent Information
- Application Number
- JP2024020685
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2024-02-14
- Publication Date
- 2025-08-26
AI Technical Summary
Existing facial recognition systems struggle to determine whether a subject is a living being from a distance without requiring a high-resolution camera, especially when the subject is wearing a face mask or similar obstructions.
A biometric determination device that uses polarized light to capture and analyze reflections from the cornea of the eye, determining liveness by analyzing specular reflection using a low-resolution camera, which includes a controller, incident and reflected light polarization units, and a camera to capture images for biometric determination.
Enables accurate liveness determination from a distance using a low-resolution camera, effectively distinguishing between living subjects and fake images, enhancing security in facial recognition systems.
Smart Images

Figure 2025124547000001_ABST
Abstract
Description
[Technical Field]
[0001] The present invention relates to a liveness determination device and a liveness determination method. [Background technology]
[0002] In facial recognition devices, security can be improved by determining whether the subject in the camera is a living body to prevent impersonation. Also, if a person is wearing a face mask, it becomes difficult to determine whether they are a living body using the characteristics of the facial skin surface.
[0003] Therefore, there is a method for determining whether a subject is alive by utilizing characteristics of the eyeball. For example, in the method described in Patent Document 1, polarized light is incident on the subject's eye and the liveness is determined based on whether the subject's eye has birefringence. [Prior art documents] [Patent documents]
[0004] [Patent Document 1] Patent Publication No. 2021-157826 Summary of the Invention [Problem to be solved by the invention]
[0005] The technology described in Patent Document 1 can identify a living person by utilizing the birefringence of the eye. However, a high-resolution camera is required to observe the birefringence, and it can only be used when the camera is close to the subject. For a living person determination device to be installed in a face recognition device, a living person determination method that can be performed from a long distance and does not require a high-resolution camera is desired.
[0006] The present invention has been made to solve the above-mentioned problems. That is, one of the objects of the present invention is to provide a living body determination device and a living body determination method that can determine whether or not an object is a living body from an eye image that is not high resolution. [Means for solving the problem]
[0007] In order to solve the above problem, the biometric determination device of the present invention is a biometric determination device comprising a camera that captures an image of a subject to be biometrically determined, a controller that controls the camera, an incident light polarization unit that polarizes a light beam incident from an external light source or an internal light source and emits it toward the subject, and a reflected light polarization unit that is arranged between the subject and the camera, wherein the controller causes the light beam polarized by the incident light polarization unit to be incident on the subject, and the light beam reflected by the subject to be incident on the reflected light polarization unit, and then captures the light from the subject that is emitted from the reflected light polarization unit with the camera, thereby obtaining an image for biometric determination for determining whether the light beam incident on the subject is reflected specularly, and determines whether the light beam incident on the subject is reflected specularly based on the image for biometric determination, thereby determining whether the subject is a living organism.
[0008] The biometric determination method of the present invention is a biometric determination method that determines whether or not the subject is a living organism using a camera that captures an image of a subject to be determined to be a living organism, a controller that controls the camera, an incident light polarization unit that polarizes a light beam incident from an external light source or an internal light source and emits it toward the subject, and a reflected light polarization unit that is positioned between the subject and the camera.The controller causes the polarized light beam to be incident on the subject, and the light beam reflected by the subject to be incident on the reflected light polarization unit, and then images the light from the subject that is emitted from the reflected light polarization unit using the camera to obtain a biometric determination image for determining whether or not the light beam incident on the subject is reflected specularly.Based on the biometric determination image, it determines whether or not the light beam incident on the subject is reflected specularly, thereby determining whether or not the subject is a living organism. [Effects of the Invention]
[0009] According to the present invention, it is possible to determine whether a subject is a living organism from an image of an eye that does not have high resolution. Note that the effects described herein are not necessarily limited to those described herein, and may be any of the effects described in this disclosure. [Brief explanation of the drawings]
[0010] [Figure 1] FIG. 1 is a diagram illustrating an example of the hardware configuration of the biometric determination device according to the first embodiment. [Figure 2] FIG. 2 is a diagram showing the positional relationship between the biometric determination device according to the first embodiment and the subject. [Figure 3] FIG. 3 is a functional block diagram showing the configuration of the biometric determination device according to the first embodiment, and its peripheral devices and external devices. [Figure 4] FIG. 4 shows examples of infrared images of a first image and a second image of a real eye and a histogram of pixels within an inscribed rectangle of the iris region. [Figure 5] FIG. 5 shows an example of infrared images of the first and second images of the eye in the print, and a histogram of pixels within the inscribed rectangle of the iris region. [Figure 6] FIG. 6 is a functional block diagram showing the configuration of the biometric determination device according to the second embodiment, and its peripheral devices and external devices. [Figure 7] FIG. 7 is a functional block diagram showing the configuration of a living body determination device according to the third embodiment, and its peripheral devices and external devices. [Figure 8] FIG. 8 is a diagram illustrating an example of the hardware configuration of the biometric determination device according to the fourth embodiment. [Figure 9] FIG. 9 is a diagram showing the positional relationship between the biometric determination device according to the fourth embodiment and the subject. [Figure 10] FIG. 10 is a functional block diagram showing the configuration of a living body determination device according to the fourth embodiment, and its peripheral devices and external devices. [Figure 11] FIG. 11 is a diagram illustrating an example of the hardware configuration of a biometric determination device according to the fifth embodiment. [Figure 12]FIG. 12 is a diagram showing the positional relationship between the biometric determination device according to the fifth embodiment and the subject. [Figure 13] FIG. 13 is a functional block diagram showing the configuration of a living body determination device according to the fifth embodiment, and its peripheral devices and external devices. DETAILED DESCRIPTION OF THE INVENTION
[0011] Hereinafter, each embodiment of the present invention will be described in detail with reference to the drawings. The living body determination device according to each embodiment is intended to be installed in a facility (such as a store or office) where consent has been obtained for imaging the subject for the purpose of determining whether the subject is a living body or not.
[0012] Furthermore, such a biometric determination device can be connected to the face authentication device described above, and adding a biometric determination function to the face authentication device can prevent impersonation of a person. However, the technology is not limited to the above, and the device can be connected to any device other than a face authentication device, particularly a device that needs to determine whether or not a person is a living being (for example, a drowsy driver monitoring system). Alternatively, the biometric determination device can be used alone.
[0013] <<First Embodiment>> First, the configuration of a biometrics determination device according to a first embodiment of the present invention will be described with reference to Figures 1 to 3. The biometrics determination device according to the first embodiment generally has a configuration in which a subject is illuminated with a light source equipped with a polarizing plate and a light source equipped with a polarizing plate perpendicular to the polarizing plate, and the subject is photographed (captured) with a camera equipped with a polarizing plate parallel to one of the polarizing plates to obtain two facial images, and the biometrics are determined by determining whether light is reflected by the cornea of the subject from pixel values of the eye region of one of the facial images.
[0014] 1 is a hardware configuration diagram of a biometric determination device 10 according to a first embodiment of the present invention. The biometric determination device 10 includes a controller 11 as a control unit that controls the entire device. The hardware of the controller 11 includes a CPU (Central Processing Unit) 111H, a ROM (Read Only Memory) 112H, a RAM (Random Access Memory) 113H, a camera control unit 114H, a light source control unit 115H, and an output unit 116H. Specific examples of each of these blocks will be described later.
[0015] As shown in FIG. 1, the biometric determination device 10 is also equipped with a camera 12 connected to the camera control unit 114H in the controller 11 described above and capable of capturing an image of a subject and acquiring image information of the subject, and a light source 13A and a light source 13B connected to the light source control unit 115H and illuminating the subject.
[0016] The camera 12, light source 13A, and light source 13B are preferably capable of capturing and illuminating infrared light. Using infrared light prevents the subject from feeling uncomfortable due to the illumination, improving usability. For example, infrared LEDs (light-emitting diodes) that generate luminous flux can be used for light source 13A and light source 13B. Note that camera 12 may be a visible light camera, and visible light sources (e.g., visible light LEDs) that generate luminous flux can be used for light source 13A and light source 13B.
[0017] In one non-limiting example, the camera 12 converts analog image signals captured through optical elements such as a lens and an aperture (not shown) and an image sensor into digital data, and outputs the digital image data to the camera control unit 114H.
[0018] The CPU 111H reads out and executes various programs stored in the ROM 112H or the RAM 113H. Specifically, the functions of the various parts of the biometric determination device 10 are realized by the CPU 111H executing the programs.
[0019] The ROM 112H is a storage medium for storing the programs executed by the CPU 111H and various parameters required for the execution.
[0020] The RAM 113H is a storage medium that serves as a working area for storing various types of information that are temporarily used by the CPU 111H, and also functions as a temporary storage area for data that is used by the CPU 111H.
[0021] The biometric determination device 10 may be configured to include a plurality of CPUs 111H, ROMs 112H, and RAMs 113H.
[0022] The camera control unit 114H includes an input / output interface (not shown) and receives (obtains) image data including two-dimensional information from the camera 12 for each frame, and supplies the data to the CPU 111H and the like.
[0023] The light source control unit 115H includes an input / output interface (not shown) and controls the light source 13A and the light source 13B. In this case, if there are multiple light sources 13A and multiple light sources 13B, the light source control unit 115H may control each light source independently. Data can be transmitted and received between the light source control unit 115H and the light source 13A and the light source 13B using protocols such as USB (Universal Serial Bus), I2C (Inter-Integrated Circuit), SPI (Serial Peripheral Interface), and UART (Universal Asynchronous Receiver Transmitter).
[0024] The output unit 116H outputs the results of processing by the CPU 111H to a peripheral device (for example, a display or a speaker), an external device (for example, a face authentication device), etc. The results of processing by the CPU 111H can be stored in the ROM 112H or the RAM 113H.
[0025] The hardware configuration of the biometric determination device 10 is not limited to the configuration shown in Fig. 1. For example, the CPU 111H, the ROM 112H, and the RAM 113H may be provided as separate entities from the biometric determination device 10. In that case, the biometric determination device 10 may be realized using a general-purpose computer (for example, a server computer, a personal computer, a smartphone, or the like).
[0026] Furthermore, a plurality of computers can be connected via a network, and each computer can share the functions of each part of the biometric determination device 10. On the other hand, one or more of the functions of the biometric determination device 10 can also be realized using dedicated hardware.
[0027] FIG. 2 illustrates the positional relationship between the biometric determination device 10 and the subject. The camera 12 and light source 13 are installed a width WA apart, and the camera 12 and light source 13B are installed a width WB apart. The camera 12 captures an image of the subject from a distance D. The biometric determination device 10 is installed at the height of a person's face, for example, on a stand or a wall. The optical axis ax1 of the camera 12 is different from the optical axis ay1A of the light source 13A, and the optical axis ax1 of the camera 12 is different from the optical axis ay1B of the light source 13B. The optical axis ay1A of the light source 13A and the optical axis ay1B of the light source 13B may be the same. While FIG. 2 illustrates the camera 12, light source 13A, and light source 13B installed inside the biometric determination device 10, they may also be installed outside the biometric determination device 10 via an interface or the like. Although FIG. 2 illustrates only two light sources, the light source 13A and light source 13B may each be configured with multiple light sources.
[0028] Polarizing plate 2A and polarizing plate 2B are provided on optical axis ay1A and optical axis ay1B, respectively. Polarizing plate 2A and polarizing plate 2B are linear polarizing plates, and are arranged so that their polarization axes are perpendicular (so that their polarization axes are orthogonal). Polarizing plate 1 is also provided on optical axis ax1. Polarizing plate 1 is a linear polarizing plate, and is arranged so that its polarization axis angle is the same as that of either polarizing plate 2A or polarizing plate 2B (so that their polarization axes are parallel). In the following example, we will explain an example in which the polarization axis of polarizing plate 1 and that of polarizing plate 2A are at the same angle (so that their polarization axes are parallel). Polarizing plate 1 is sometimes referred to as the "reflected light polarizing unit" or "reflected light polarizing plate." Polarizing plate 2A and polarizing plate 2B are sometimes referred to as the "incident light polarizing unit," polarizing plate 2A is sometimes referred to as the "first incident light polarizing plate," and polarizing plate 2B is sometimes referred to as the "second incident light polarizing plate."
[0029] As another example, circularly polarized light can also be used. When circularly polarized light is used, polarizer 2A can be a right-handed circular polarizer, polarizer 2B can be a left-handed circular polarizer, and polarizer 1 can be a left-handed circular polarizer.
[0030] As yet another example, it is possible not to provide polarizing plate 2A. In the case of a method using linearly polarized light without providing polarizing plate 2A, polarizing plate 1 and polarizing plate 2B are arranged so that their polarization axes are perpendicular to each other. In the case of a method using circularly polarized light without providing polarizing plate 2A, polarizing plate 1 and polarizing plate 2B are left-handed circular polarizing plates. In the following example, an example using a linear polarizing plate with polarizing plate 2A will be described.
[0031] 3 is a block diagram showing the functional configuration of the biometric determination device 10 and its peripherals. The biometric determination device 10 is connected to a peripheral device 20 and an external device 3.
[0032] The biometric determination device 10 includes the camera 12, light source 13A, and light source 13B described above in FIG. 1, and an imaging control unit 101, an eye detection unit 102, a corneal reflex determination unit 103, a biometric determination unit 104, a communication unit 105, and an external interface 106 as functions of the controller 11 (CPU 111H, etc.) in FIG. 1.
[0033] The photographing control unit 101 controls the timing of photographing by the camera 12 and the timing of illumination by the light sources 13A and 13B. The photographing control unit 101 starts photographing by receiving a photographing timing input from the peripheral device 20, for example, via the external interface 106 described below. The photographing control unit 101 first illuminates the light source 13A and photographs a first image with the camera while the light source is illuminated, then illuminates the light source 13B and photographs a second image with the camera while the light source is illuminated. Photographing may be performed continuously over multiple frames, or only one frame may be photographed. In this example, an example of continuous photographing at, for example, 30 frames per second will be described. When photographing only one frame, the illumination of the light source 13A and the light source 13B only needs to be for one frame each.
[0034] The timing of shooting that the shooting control unit 101 receives from the peripheral device 20 is input by a desired operation of the user, such as a touch button arranged on a display 21 equipped with a touch panel or a button on a remote control 23. As another example, the device can automatically start shooting when a sound is detected by the microphone 24 or when the presence of a human is detected by the human sensor 25.
[0035] Alternatively, instead of using a motion sensor, the camera 12 can constantly capture images, and when it detects a human in the image captured by the camera 12, the camera 12 can output the image. The process of detecting a human in the image captured by the camera 12 may be performed by the camera 12 or by the image capture control unit 101. Deep learning can be used as a method for detecting a human in the image captured by the camera 12. When using deep learning, this can be achieved by training a deep neural network in advance with, for example, facial images of multiple people. Additionally, when the biometric determination device 10 is used in a fixed environment, a human can also be detected using the difference between the image of the previous frame and the image of the current frame. For example, by subtracting each pixel from the previous frame and the current frame, it can be determined that a human has appeared in the image if the subtraction result contains a certain number of pixels above a certain value.
[0036] The camera 12 photographs the subject according to the photographing timing received from the photographing control unit 101, and outputs the photographed first and second images to the eye detection unit 102. At this time, all photographed images may be output to the eye detection unit 102, or only when a human is detected in the image as described above may the photographed images be output to the eye detection unit 102. The photographed images may also be subjected to processing such as normalization or standardization before being output to the eye detection unit 102. At this time, the entire image may be subjected to processing such as normalization or standardization so that the pixel values of the iris region excluding the pupil region fall within a certain pixel value range. The first and second images may also be referred to as "images for biometric determination."
[0037] The eye detection unit 102 detects the eyes of the subject from each of the first and second images input from the camera 12. For example, deep learning can be used to detect the eyes. When using deep learning, this can be achieved by having a deep neural network learn the eyes of multiple people in advance. Pattern matching can also be used. As another method, if the position and direction of the subject's eyes and the position and direction of the camera 12 are fixed, it is also possible to detect specific positions in the images captured by the camera 12 as eyes without performing the eye detection process described above.
[0038] Furthermore, the eye detection unit 102 outputs images obtained by cutting out the eye regions detected from each of the first image and the second image input from the camera 12 to the corneal reflex determination unit 103. At this time, both the left and right eyes may be detected and images obtained by cutting out the regions of both eyes may be output, or only one of the left and right eyes may be detected and an image obtained by cutting out the region of one of the eyes may be output.
[0039] The eye detection unit 102 cuts out the image so as to include at least the iris and pupil. The cutout may be a circumscribing rectangle or an inscribing rectangle of the iris region as shown in FIG. 4, or a circle that fits the iris region. When cutting out a circumscribing rectangle or an inscribing rectangle, for example, the width and height of the cutout region may be a certain percentage of the distance between the eyes, with the detected eye position as the center. When cutting out a circle, the radius may be a certain percentage of the distance between the eyes, with the detected eye position as the center.
[0040] Alternatively, an edge filter such as a Laplacian filter may be used to obtain the outline of the iris region, and the inscribed rectangle or circumscribed rectangle of the outline, or the inside of the outline, may be cut out.
[0041] The corneal reflex determination unit 103 determines whether or not light is reflected (specularly reflected) by the cornea and outputs the determination result. The corneal reflex determination unit 103 receives the image of the eye output by the eye detection unit 102 as input and determines whether or not light is specularly reflected by the image of the eye.
[0042] Whether the cornea reflects light specularly can be determined by the presence of bright pixels (bright pixels indicating luminous flux) in the image. Figure 4 shows examples of first and second images of the vicinity of a real human eye, along with their respective inscribed rectangle histograms of the iris region. Figure 5 also shows examples of first and second images of the vicinity of a real human eye on a printout, along with their respective inscribed rectangle histograms of the iris region. In the case of a real eye, the cornea specularly reflects light. The specularly reflected light from the eye maintains the polarization state of the linearly polarized incident light. Therefore, in the first image, polarizer 1 and polarizer 2A have the same polarization axis angle (parallel polarization axes), allowing the specularly reflected light to be observed. In the second image, polarizer 1's polarization axis is perpendicular to that of polarizer 2B, blocking the specularly reflected light from the eye, making it difficult to observe. Due to this phenomenon, the histogram of the first image of the real eye contains many bright pixels, while the histogram of the second image of the real eye contains fewer bright pixels.
[0043] In contrast, in the case of a printed material, there is no specular reflection like in a Purkinje image, but rather diffusely reflected light. Diffusely reflected light does not maintain the polarization state of the incident light and is unpolarized. Therefore, there is almost no difference in the histograms of the first and second images. In Figure 5, the printed material has white dots printed on it, so there are bright pixels in both the first and second images. If the printed material does not have white dots printed on it, there will be no bright pixels in either the first or second image.
[0044] The corneal reflex determination unit 107 scans the pixels in the eye area, and can determine that the cornea is reflecting light if there are a certain number of pixels with a certain value or more.
[0045] Another method for determining whether the cornea is reflecting light is to determine it from the shape of the histogram. Specifically, for example, first, the moving average of the histogram is calculated, and the resulting moving average is differentiated to determine the maximum value. Whether the cornea is reflecting light can be determined based on the number and positions of the determined maximum values. For example, this can be determined based on conditions such as whether there is at least one maximum value between pixel values 100 and 200 and at least one maximum value above pixel value 230.
[0046] Another method is to calculate the gradient, kurtosis, skewness, and half-width of the graph and use a predictive model such as a decision tree to determine whether the cornea is reflecting light. In this case, the gradient and other parameters may be calculated multiple times by dividing the horizontal axis of the graph. Yet another method is to use deep learning. When using deep learning, this can be achieved by having a deep neural network learn the inscribed rectangle of the iris area of a real person in advance.
[0047] When the eye detection unit 102 detects both eyes, the corneal reflex determination unit 103 may determine whether or not light is regularly reflected by the cornea of each eye independently, and output the determination results independently.
[0048] The living body determination unit 104 determines whether the subject is a living body or not based on the determination result output by the corneal reflex determination unit 103, and outputs the determination result.
[0049] When the corneal reflex determination unit 103 detects light indicating a light beam (light beam reflected by the cornea) in the first image but does not detect light indicating a light beam (light beam reflected by the cornea) in the second image, the living body determination unit 104 can determine that the cornea is specularly reflecting a polarized light beam, and can therefore determine that the subject is a living body. On the other hand, when the corneal reflex determination unit 103 detects light indicating a light beam in the first image and light indicating a light beam in the second image, the living body determination unit 104 can determine that the cornea is not specularly reflecting a polarized light beam, and can therefore determine that the subject is not a living body. Furthermore, when the corneal reflex determination unit 103 does not detect light indicating a light beam in the first image and does not detect light indicating a light beam in the second image, the living body determination unit 104 can determine that the cornea is not specularly reflecting a polarized light beam, and can therefore determine that the subject is not a living body. Furthermore, if the corneal reflex determination unit 103 does not detect light indicating a light beam in the first image and detects light indicating a light beam in the second image, the living body determination unit 104 can determine that the cornea does not regularly reflect the polarized light beam, and therefore can determine that the subject is not a living body.
[0050] When the eye detection unit 102 outputs an image in which the regions of both eyes are cut out, the liveness determination unit 104 may determine whether or not the subject is a living person based on the determination results of both eyes output by the corneal reflex determination unit 103. When the corneal reflex determination unit 103 outputs the determination results of both eyes independently, the liveness determination unit 104 first performs liveness determination on each of the same eyes in the first image and the second image output by the corneal reflex determination unit 103, and then outputs a liveness determination result based on the liveness determination results of the left and right eyes. In this case, the subject may be determined to be a living person only when both the left and right eyes are determined to be live, or may be determined to be a living person when at least one of the left and right eyes is determined to be live. When determining that the subject is a living person when at least one of the left and right eyes is determined to be live, for example, the subject may be determined to be a living person even when one eye is closed (winking) or when noise is mixed into the image of one eye.
[0051] The biometric determination unit 104 can also determine whether or not a subject is a living organism using multiple frames. When using multiple frames for determination, if the corneal reflex determination unit 103 determines that the cornea is reflecting light specularly in at least a certain number of frames among the multiple frames, it can determine that the subject is a living organism. This makes it possible to determine that the subject is a living organism even if the subject is blinking or if noise is mixed into the image of a certain frame, for example.
[0052] The communication unit 105 communicates with the external device 3 (see FIG. 3). The communication unit 105 transmits the determination result of the biometric determination unit 104 to the external device 3.
[0053] 3, the communication unit 105 is configured to perform wireless communication with the external communication unit 31 of the external device 3. Here, the communication means (method) of the communication unit 105 can be wireless communication such as WiFi or Bluetooth (registered trademark). As another example, the communication unit 105 may communicate with the external device 3 via a wired connection. In this way, the biometric determination device 10 can transmit the determination result as to whether the subject is a living body to the external device 3, such as a server, via the communication unit 105, and cause the external device 3 to perform face authentication, etc.
[0054] The external communication unit 31 transmits the data received from the communication unit 105 to the external device 3. The data received by the external communication unit 31 is, for example, the determination result of the biometric determination unit 104. Furthermore, the function provided in the external device 3 may be configured to be provided within the biometric determination device 10.
[0055] The external device 3 is preferably an authentication device that requires the biometric determination result of the subject. Note that the configuration of such an authentication device is publicly known, so a detailed description thereof will be omitted. Furthermore, the external device 3 may be various devices other than an authentication device, as long as they require the biometric determination result of the subject.
[0056] The communication unit 105 can also transmit the image captured by the camera 12 to the external device 3. This allows authentication to be performed without separately capturing an image of the subject, when the external device 3 is an image authentication device.
[0057] In this example, the external interface 106 transmits and receives electrical signals to and from the peripheral device 20 via a wired cable.
[0058] As shown in FIG. 3, the peripheral device 20 includes a display 21, a speaker 22, a remote control 23, a microphone 24, and a motion sensor 25, and each block (device) is connected to the external interface 106 via a wired cable.
[0059] The external interface 106 can also transmit the determination result of the biometric determination unit 104 to the peripheral device 20. For example, the determination result of the biometric determination unit 104 can be displayed on the display 21. In another example, a warning sound can be emitted from the speaker 22 based on the determination result of the biometric determination unit 104.
[0060] According to the first embodiment, a subject is illuminated with a light source equipped with a polarizing plate and a light source equipped with a polarizing plate orthogonal to the polarizing plate (a polarizing plate with a polarization axis perpendicular to the polarizing plate), and the subject is photographed (captured) with a camera equipped with a polarizing plate parallel to one of the polarizing plates (a polarizing plate with a polarization axis parallel to the other polarizing plate). From the pixel values of the eye area in one of the two facial images, it is possible to determine whether light is specularly reflected from the subject's cornea (detecting light representing specularly reflected light beams), thereby determining whether the subject is a living body. Whether light is specularly reflected from the cornea can be determined simply by checking whether bright pixels are present, and a high-resolution image is not required. This allows biometric determination to be performed from a long distance using a low-resolution camera, thereby improving the security of the authentication device as the external device 3. Furthermore, according to the first embodiment, it is possible to accurately determine that a fake image (printed material) with white dots in the eyes, as shown in FIG. 5, is not a living body.
[0061] <<Second embodiment>> A biometric determination device 10A according to a second embodiment of the present invention will be described. In the second embodiment, a configuration example will be described in which a pupil absorption determination unit is additionally provided, based on the configuration of the biometric determination device 10 according to the first embodiment. Note that components having the same configurations and functions as those in the first embodiment will be assigned the same reference numerals, and detailed description thereof will be omitted.
[0062] The living body determination device 10A according to the second embodiment utilizes the fact that the iris reflects light well relative to the pupil.
[0063] Fig. 6 is a functional configuration diagram of a biometric determination device 10A according to the second embodiment, which includes a pupil absorption determination unit 107. As shown in Fig. 6, in the biometric determination device 10A, the pupil absorption determination unit 107 is connected after the eye detection unit 102 and before the biometric determination unit 104. Therefore, in the second embodiment, the functions of the eye detection unit 102 and the biometric determination unit 104 are somewhat different from those in the first embodiment, and therefore, hereinafter, they will be referred to as the eye detection unit 102A and the biometric determination unit 104A using similar reference numerals.
[0064] The eye detection unit 102A of the second embodiment has the same basic function as the eye detection unit 102 of the first embodiment, and cuts out the detected eye region from the image input from the camera 12.
[0065] On the other hand, the eye detection unit 102A outputs the cut-out eye region to the corneal reflex determination unit 103 and also to the pupil absorption determination unit 107.
[0066] The pupil absorption determination unit 107 determines whether or not the pupil is absorbing light and outputs the determination result. The pupil absorption determination unit 107 receives the image of the eye output by the eye detection unit 102A as input and determines whether or not the image of the eye is absorbing light.
[0067] Whether or not light is being absorbed by the pupil can be determined by checking whether or not there are dark pixels in the image (dark pixels indicating that light is being absorbed by the pupil). As shown in Figure 4, in the case of an infrared image of a real eye, the pupil area becomes dark due to the absorption of infrared light regardless of the polarization angle, so there are pixels with dark pixel values in the histogram. However, as shown in Figure 5, in the case of a printout, there are no dark pixels. This is because in the case of a printout, even the pupil area reflects light from the light source, and a certain amount of diffuse reflected light returns to the camera. With this method, the pupil absorption determination unit 107 scans the pixels in the eye area, and if there are a certain number or more pixels below a certain value, it can be determined that light is being absorbed by the pupil.
[0068] Another method for determining whether light is being absorbed by the pupil is to determine it from the shape of the histogram. Specifically, for example, first, the moving average of the histogram is calculated, and the resulting moving average is differentiated to determine the maximum value. It can be determined that light is being absorbed by the pupil from the number of maximum values found and their positions. For example, it can be determined based on conditions such as there being at least one maximum value below a pixel value of 50 and at least one maximum value between pixel values 100 and 200.
[0069] Another method is to calculate the gradient, kurtosis, skewness, half-width, etc. of the graph and use a predictive model such as a decision tree to determine whether light is being absorbed by the pupil. In this case, the gradient, etc. may be calculated multiple times by dividing the horizontal axis of the graph. Yet another method is to use deep learning. When using deep learning, this can be achieved by having a deep neural network learn the inscribed rectangle of the iris area of a real person in advance.
[0070] When the eye detection unit 102A detects both eyes, the pupil absorption determination unit 107 determines whether or not light is being absorbed by the pupil of each eye independently, and outputs the determination results independently.
[0071] The liveness determination unit 104A determines whether the subject is a living organism or not based on the determination results output by the corneal reflex determination unit 103 and the pupillary absorption determination unit 107, and outputs the determination result. When the corneal reflex determination unit 103 and the pupillary absorption determination unit 107 output the determination results for both eyes independently, the liveness determination unit 104A first performs liveness determination for each eye output by the corneal reflex determination unit 103 and the pupillary absorption determination unit 107, and then outputs a liveness determination result according to the liveness determination results for the left and right eyes. In this case, the subject may be determined to be a living organism only when both the left and right eyes are determined to be living organisms, or may be determined to be a living organism only when only one of the left and right eyes is determined to be living organisms.
[0072] When performing a biometric determination on the same eye output by the corneal reflex determination unit 103 and the pupillary absorption determination unit 107, the corneal reflex determination unit 103 may determine that the subject is a living organism when both of the following conditions are met: the corneal reflex determination unit 103 determines that light is reflected specularly by the cornea in the first image (detects light indicating a luminous flux) and determines that light is not reflected specularly by the cornea in the second image (does not detect light indicating a luminous flux); and the pupillary absorption determination unit 107 determines that light is absorbed by the pupil in both the first image and the second image. The subject may also be determined to be a living organism when either one of the following conditions is met.
[0073] Furthermore, according to the second embodiment, similarly to the first embodiment, the living body determination unit 104 can determine whether or not the subject is a living body using a plurality of frames.
[0074] According to the living body determination device 10A of the second embodiment, in addition to the effects based on the configuration of the first embodiment described above, by determining pupil absorption, living body determination can be performed with higher accuracy.
[0075] <<Third Embodiment>> A biometric determination device 10B according to a third embodiment of the present invention will be described. In the third embodiment, a configuration example will be described in which a face determination unit 108 is additionally provided while the configuration of the biometric determination device 10A according to the second embodiment is used as a base. Note that components having the same configurations and functions as those in the second embodiment will be assigned the same reference numerals, and detailed description thereof will be omitted.
[0076] 7 is a functional configuration diagram of a biometric determination device 10B according to the third embodiment, which includes a face determination unit 108. As shown in FIG. 7, in the biometric determination device 10B, the face determination unit 108 is connected downstream of the camera 12 and upstream of the eye detection unit 102A and the external interface. Therefore, in the third embodiment, the functions of the camera 12, eye detection unit 102A, external interface 106, peripheral device 20, display 21, and speaker 22 are somewhat different from those in the second embodiment, and therefore, hereinafter, like reference numerals will be used to refer to the camera 12B, eye detection unit 102B, external interface 106B, peripheral device 20B, display 21B, and speaker 22B.
[0077] The camera 12B of the third embodiment has the same basic functions as the camera 12 of the first and second embodiments, and captures an image of a subject according to the image capture timing received from the image capture control unit 101.
[0078] On the other hand, camera 12B outputs the captured image to face determination section 108 instead of eye detection section 102B.
[0079] The face determination unit 108 calculates the size and orientation of the subject's face included in the image captured by the camera 12. If the calculated size of the subject's face is equal to or larger than a certain value and the orientation of the subject's face is equal to or smaller than a certain value relative to the optical axis of the camera (for example, the angle between the orientation of the face and the optical axis of the camera is equal to or smaller than a predetermined threshold angle), the image captured by the camera 12 is output to the eye detection unit 102B. Limiting the size of the subject's face means limiting the distance between the camera 12B and the subject, and if the distance is large, the image captured by the camera 12 is not output to the eye detection unit 102B. If the distance between the subject and the camera 12B is large, it becomes difficult to observe the reflection of light from the cornea and the absorption of light from the pupil in the image captured by the camera 12B. Limiting the distance between the subject and the camera 12B can prevent a decrease in the accuracy of biometric determination. Furthermore, if the orientation of the face is larger than a certain value, it becomes difficult to observe the reflection of light from the cornea and the absorption of light from the pupil in the image captured by the camera 12B. By restricting the orientation of the subject's face, it is possible to prevent a decrease in the accuracy of the biometric determination.
[0080] If the calculated size of the subject's face is equal to or smaller than a certain size, face determination unit 108 outputs information including the fact that the face is small to external interface 106B.
[0081] The external interface 106B is connected to the peripheral device 20B, and outputs the information received from the face determination unit 108, including the fact that the face is small, to either or both of a display 21B and a speaker 22B included in the peripheral device 20B.
[0082] When display 21B receives information including the fact that the face is small, it instructs the subject to move closer to camera 12B. For example, it can display a message such as "Please move closer" on the screen of display 21B, or an illustration instructing the subject to move closer.
[0083] When the speaker 22B receives information including the fact that the face is small, it instructs the subject to move closer to the camera 12B. For example, it can emit a voice such as "Please move closer to the camera."
[0084] If the calculated face orientation of the subject is equal to or greater than a certain value with respect to the optical axis ax1 of the camera, face determination unit 108 outputs information including the fact that the face orientation is large to external interface 106B.
[0085] The external interface 106B is connected to the peripheral device 20B, and outputs the information received from the face determination unit 108, including the fact that the face direction is large, to either or both of a display 21B and a speaker 22B included in the peripheral device 20B.
[0086] When display 21B receives information including the fact that the face is facing forward, it instructs the subject to face forward toward camera 12B. For example, it is possible to display a sentence such as "Please face forward" on the screen of display 21B, or to display an illustration instructing the subject to face forward.
[0087] When the speaker 22B receives information including the fact that the subject's face is facing in a large direction, the speaker 22B instructs the subject to face the camera 12B. For example, the speaker 22B can emit a voice message such as "Please face the camera."
[0088] Face determination unit 108 may calculate only the size of the face of the subject included in the image captured by camera 12. In this case, if the calculated size of the face of the subject is equal to or larger than a certain size, face determination unit 108 outputs the image captured by camera 12B to eye detection unit 102B.
[0089] Furthermore, face determination unit 108 may calculate only the orientation of the subject's face included in the image captured by camera 12. In this case, if the orientation of the subject's face is equal to or smaller than a certain value relative to the optical axis of the camera, face determination unit 108 outputs the image captured by camera 12B to eye detection unit 102B.
[0090] According to the third embodiment, it is possible to prevent a decrease in the accuracy of biometric determination by limiting the size and orientation of the face of the subject. Furthermore, when a face recognition device is connected to the biometric determination device 10B, it is expected that a decrease in the accuracy of face recognition can also be prevented by limiting the size and orientation of the face of the subject.
[0091] <<Fourth Embodiment>> In the fourth embodiment, an example of performing biometric determination using two cameras and one light source will be described, based on the configuration of the biometric determination device 10A according to the second embodiment. Components having the same configurations and functions as those in the second embodiment will be assigned the same reference numerals, and detailed descriptions thereof will be omitted.
[0092] 8 is a hardware configuration diagram of a biometric determination device 10C according to a fourth embodiment of the present invention. The biometric determination device 10C includes cameras 12C, 12D, and 13C instead of the camera 12, light source 13A, and light source 13B of the second embodiment. Therefore, in the fourth embodiment, the functions of a camera control unit 114H and a light source control unit 115H are somewhat different from those of the second embodiment, and therefore will be referred to as a camera control unit 114HC and a light source control unit 115HC using similar reference numerals hereinafter.
[0093] FIG. 9 illustrates the positional relationship between the biometric determination device 10C and the subject according to the fourth embodiment. The camera 12C and the light source 13C are installed a distance WC apart, and the camera 12D and the light source 13C are installed a distance WD apart. The cameras 12C and 12D capture images of the subject from a distance D. The biometric determination device 10C is installed at the height of a person's face, for example, on a stand or a wall. The optical axis ax1C of the camera 12C is different from the optical axis ay1C of the light source 13C, and the optical axis ax1D of the camera 12D is different from the optical axis ay1C of the light source 13C. The optical axis ax1C of the camera 12C and the optical axis ax1D of the camera 12D may be the same. While FIG. 9 illustrates the cameras 12C, 12D, and the light source 13C installed inside the biometric determination device 10C, they may also be installed outside the biometric determination device 10C via an interface or the like. Although FIG. 9 illustrates only one light source, the light source 13C may be configured with multiple light sources.
[0094] Polarizing plate 2C is provided on optical axis ay1C. Polarizing plate 1C and polarizing plate 1D are provided on optical axis ax1C and optical axis ax1D, respectively. Polarizing plate 1C and polarizing plate 1D are installed so that their polarization axes are perpendicular to each other. Polarizing plate 2C is also arranged so that its polarization axis angle is the same as that of either polarizing plate 1C or polarizing plate 1D (so that their polarization axes are parallel). In the following example, we will explain an example where the polarization axes of polarizing plate 2C and polarizing plate 1C are the same angle (an example where their polarization axes are parallel). Polarizing plate 2C is sometimes referred to as the "incident light polarizing unit" or "incident light polarizing plate." Polarizing plate 1C and polarizing plate 1D are sometimes referred to as the "reflected light polarizing unit," polarizing plate 1C is sometimes referred to as the "first reflected light polarizing plate," and polarizing plate 1D is sometimes referred to as the "second reflected light polarizing plate."
[0095] 10 is a block diagram showing the functional configuration of a biometric determination device 10C according to the fourth embodiment and its peripherals. In the fourth embodiment, cameras 12C and 12D are provided instead of camera 12. Furthermore, light source 13C is provided instead of light source 13A and light source 13B. Because the functions of the photography control unit 101 and eye detection unit 102A are somewhat different from those in the second embodiment, they will be referred to as photography control unit 101C and eye detection unit 102C using similar reference numerals below.
[0096] In addition to the functions of the photography control unit 101 in the second embodiment, the photography control unit 101C controls the timing of photography by the cameras 12C and 12D and the timing of illumination by the light source 13C. The photography control unit 101C illuminates the light source 13C, and while the light source 13C is illuminating, the camera 12C captures a first image and the camera 12D captures a second image. In this case, the photography timing of the cameras 12C and 12D may be simultaneous.
[0097] Eye detection unit 102C of the fourth embodiment has the same basic function as eye detection unit 102A of the second embodiment, and cuts out the detected eye regions from the images input from camera 12C and camera 12D.
[0098] According to the fourth embodiment, biometric determination is performed using two cameras and one light source, which allows simultaneous photography with two cameras, thereby enabling biometric determination to be performed in a shorter time than in the example using one camera and two light sources.
[0099] <<Fifth Embodiment>> In the fifth embodiment, an example of performing biometric determination using one camera and one light source will be described, based on the configuration of the biometric determination device 10C according to the fourth embodiment. Note that components having the same configurations and functions as those in the fourth embodiment are given the same reference numerals, and detailed descriptions thereof will be omitted.
[0100] 11 is a hardware configuration diagram of a biometric determination device 10D according to a fifth embodiment of the present invention. The biometric determination device 10D includes a camera 12E instead of the cameras 12C and 12D of the fourth embodiment. Therefore, in the fifth embodiment, the function of the camera control unit 114HC is somewhat different from that of the fourth embodiment, and therefore will be referred to as the camera control unit 114HD hereinafter using similar reference numerals.
[0101] FIG. 12 is a diagram showing the positional relationship between a biometric determination device 10D and a subject according to the fifth embodiment. The camera 12E and the light source 13C are installed a width WE apart, and the camera 12E captures an image of the subject from a distance D. The biometric determination device 10D is installed at the height of a person's face, for example, on a stand or a wall. The optical axis ax1E of the camera 12E and the optical axis ay1C of the light source 13C are different. While FIG. 12 shows the camera 12E and the light source 13C installed inside the biometric determination device 10D, they may also be installed outside the biometric determination device 10D via an interface or the like. Furthermore, although FIG. 12 shows only one light source, the light source 13C may also be configured with multiple light sources.
[0102] Polarizing plate 1E is provided on each optical axis ax1E. Polarizing plate 1E is a polarizing plate whose polarization axes are orthogonal to each other on the left and right halves. This polarizing plate may be realized by combining two polarizing plates. The left or right half of polarizing plate 1E is positioned so that its polarization axis angle is the same as that of polarizing plate 1C (i.e., the polarization axes are parallel). In the following example, we will explain an example in which the polarization axis angles of the left half of polarizing plate 1E and polarizing plate 1C are the same (i.e., the polarization axes are parallel). Polarizing plate 1E is sometimes referred to as the "reflected light polarizing section" or "reflected light polarizing plate." The left half of polarizing plate 1E is sometimes referred to as the "first polarization characteristic section," and the right half of polarizing plate 1E is sometimes referred to as the "second polarization characteristic section." Polarizing plate 2C is sometimes referred to as the "incident light polarizing section" or "incident light polarizing plate."
[0103] 13 is a block diagram showing the functional configuration of a biometric determination device 10D and its peripherals according to the fifth embodiment. In the fifth embodiment, a camera 12E is provided instead of cameras 12C and 12D. Since the functions of an imaging control unit 101C and an eye detection unit 102C are somewhat different from those in the fourth embodiment, they will be referred to as an imaging control unit 101D and an eye detection unit 102D using similar reference numerals below.
[0104] The photographing control unit 101D controls the photographing timing of the camera 12E in addition to the functions of the photographing control unit 101C in the fourth embodiment. The photographing control unit 101D illuminates the light source 13C and causes the camera 12E to photograph an image while the light source 13C is illuminated.
[0105] In addition to the functions of cameras 12C and 12D of the fourth embodiment, camera 12E cuts out an image and outputs it to eye detection unit 102D. Specifically, the left half of the image is cut out as a first image, and the right half of the image is cut out as a second image, and the first image and second image are output to eye detection unit 102D. For example, the first image includes the half of the face on the left side relative to the central axis in the width direction of the face, and the second image includes the half of the face on the right side relative to the central axis.
[0106] The eye detection unit 102D of the fifth embodiment has the same basic function as the eye detection unit 102C of the fourth embodiment, and cuts out the detected eye areas from each of the first image and the second image input from the camera 12E.
[0107] According to the fifth embodiment, by performing the biometric determination using one camera and one light source, it is possible to perform the biometric determination with a simpler configuration than when using a plurality of cameras and light sources.
[0108] <<Modifications>> The present invention is not limited to the above-described embodiments and includes various modifications. For example, the above-described embodiments have been described in detail to clearly explain the present invention, and the present invention is not necessarily limited to those including all of the described configurations. Furthermore, it is possible to replace part of the configuration of one embodiment with the configuration of another embodiment, or to add the configuration of another embodiment to the configuration of one embodiment. Furthermore, it is possible to add, delete, or replace part of the configuration of each embodiment with other configurations.
[0109] In each of the above embodiments, specular reflection from a subject other than the corneal surface may be detected as an alternative method. For example, water droplets such as tears, saliva, and sweat generally exhibit strong specular reflection characteristics on printed materials such as paper. Therefore, specular reflection from water droplets on the subject's facial surface can also be detected. When using this method, the eye detection unit 102 cuts out an image including, for example, the inner corner of the eye, and outputs the cut image to the corneal reflex determination unit 103.
[0110] The present invention can also have the following configuration.
[0111] [1] a camera for capturing an image of a subject to be subjected to biometric determination; a controller for controlling the camera; an incident light polarization unit that polarizes a light beam incident from an external light source or an internal light source and outputs the polarized light beam toward the subject; a reflected light polarizing unit disposed between the subject and the camera; A biometric determination device comprising: The controller The light beam polarized by the incident light polarizing unit is incident on the subject, and the light beam reflected by the subject is incident on the reflected light polarizing unit. In this state, the light from the subject that is emitted from the reflected light polarizing unit is captured by the camera, thereby obtaining a living body determination image for determining whether the light beam incident on the subject is specularly reflected or not; determining whether the light beam incident on the subject is regularly reflected based on the image for biometric determination, thereby determining whether the subject is a living organism; It was configured as follows: Biometric detection device.
[0112] [2] In the liveness determination device according to [1], a first linear polarizer as the reflected light polarizing unit; a second linear polarizer as the incident light polarizing unit; a first imaging system that, when the polarized light beam is specularly reflected by the subject, polarizes the light beam by the first linear polarizer non-orthogonal to the polarization state of the light beam reflected by the subject, and captures the light from the subject that is emitted from the first linear polarizer by the camera; a second imaging system that, when the polarized light beam is specularly reflected by the subject, polarizes the light beam by the first linear polarizer perpendicular to the polarization state of the light beam reflected by the subject, and captures the light from the subject that is emitted from the first linear polarizer by the camera; Equipped with The controller acquiring, as the image for biometric determination, both a first image captured by the first imaging system and a second image captured by the second imaging system, or one image including the first image and the second image; If light representing the light beam is detected from the first image and light representing the light beam is not detected from the second image, it is determined that the light beam incident on the subject is specularly reflected. It was configured as follows: Biometric detection device.
[0113] [3] In the liveness determination device according to [1], the incident light polarization unit includes a first incident light polarization plate that polarizes the light beam incident from the external light source or the internal light source in a first polarization state and outputs the light beam toward the subject, and a second incident light polarization plate that polarizes the light beam incident from the external or internal light source in a second polarization state and outputs the light beam toward the subject; a reflected light polarizing plate as the reflected light polarizing unit, the reflected light polarizing plate having a property of transmitting at least a part of the light beam in the first polarization state and blocking the light beam in the second polarization state; Equipped with The controller the light beam polarized in the first polarization state by the first incident light polarizing plate is incident on the subject, and the light beam reflected by the subject is incident on the reflected light polarizing plate, and in this state, the light from the subject that is emitted from the reflected light polarizing plate is captured by the camera, thereby obtaining a first image as the image for biometric determination; the light beam polarized to the second polarization state by the second incident light polarizing plate is incident on the subject, and the light beam reflected by the subject is incident on the reflected light polarizing plate, and in this state, the light from the subject that is emitted from the reflected light polarizing plate is captured by the camera, thereby obtaining a second image as the image for liveness determination; If it is determined that the subject specularly reflects the incident light beam based on the first image and the second image, it is determined that the subject is a living organism, and if it is determined that the subject does not specularly reflect the incident light beam, it is determined that the subject is not a living organism. It was configured as follows: Biometric detection device.
[0114] [4] In the liveness determination device according to [1], an incident light polarizing plate as the incident light polarizing unit, which polarizes the light beam incident from the external light source or the internal light source in a first polarization state and outputs the polarized light toward the subject; the reflected light polarizing unit includes a first reflected light polarizing plate having a property of transmitting at least a part of the light flux in the first polarization state, and a second reflected light polarizing plate having a property of blocking the light flux in the first polarization state; Equipped with The controller the light beam polarized to the first polarization state by the incident light polarizing plate is incident on the subject, and the light beam reflected by the subject is incident on the first reflected light polarizing plate, and in this state, the light from the subject that is emitted from the first reflected light polarizing plate is captured by the camera, thereby obtaining a first image as the image for biometric determination; the light beam polarized to the first polarization state by the incident light polarizing plate is incident on the subject, and the light beam reflected by the subject is incident on the second reflected light polarizing plate, and in this state, the light from the subject that is emitted from the second reflected light polarizing plate is captured by the camera, thereby obtaining a second image as the image for liveness determination; If it is determined that the subject specularly reflects the incident light beam based on the first image and the second image, it is determined that the subject is a living organism, and if it is determined that the subject does not specularly reflect the incident light beam, it is determined that the subject is not a living organism. It was configured as follows: Biometric detection device.
[0115] [5] In the liveness determination device according to [1], an incident light polarizing plate as the incident light polarizing unit, which polarizes the light beam incident from the external light source or the internal light source in a first polarization state and outputs the polarized light toward the subject; the reflected light polarizing portion includes a reflected light polarizing plate including a first polarization characteristic portion having a characteristic of transmitting at least a part of the light flux in the first polarization state, and a second polarization characteristic portion that blocks the light flux in the first polarization state; Equipped with The controller a first image portion obtained by capturing, with the camera, the light from the subject that has been polarized to the first polarization state by the incident light polarizing plate and the light from the subject that has been reflected by the subject and that has been incident on the first polarization characteristic portion and the second polarization characteristic portion of the first reflected light polarizing plate; and a second image portion obtained by capturing, with the camera, the light from the subject that has been emitted from the second polarization characteristic portion. If it is determined that the subject specularly reflects the incident light beam based on the first image portion and the second image portion, it is determined that the subject is a living organism, and if it is determined that the subject does not specularly reflect the incident light beam, it is determined that the subject is not a living organism. It was configured as follows: Biometric detection device.
[0116] [6] In the liveness determination device according to any one of [3] to [5], The controller If light indicating the luminous flux is detected from the first image and light indicating the luminous flux is not detected from the second image, the subject is determined to be a living organism. It was configured as follows: Biometric detection device.
[0117] [7] a camera for capturing an image of a subject to be subjected to biometric determination; a controller for controlling the camera; an incident light polarization unit that polarizes a light beam incident from an external light source or an internal light source and outputs the polarized light beam toward the subject; a reflected light polarizing unit disposed between the subject and the camera; A living body determination method for determining whether the subject is a living body using The controller a polarized light beam incident on the subject, the light beam reflected by the subject being incident on the reflected light polarizing unit, and an image of the light from the subject that is emitted from the reflected light polarizing unit is captured by the camera, thereby obtaining a living body determination image for determining whether the light beam incident on the subject is regularly reflected; determining whether the light beam incident on the subject is regularly reflected based on the image for biometric determination, thereby determining whether the subject is a living organism; Biometric determination method. [Explanation of symbols]
[0118] 3...external device, 10, 10A, 10B, 10C, 10D...biometric determination device, 11...controller, 12, 12B, 12C, 12D, 12E...camera, 13A, 13B, 13C...light source, 20, 20B...peripheral device, 111H...CPU, 112H...ROM, 113H...RAM, 114H, 114HC, 114HD...camera control unit, 115H, 115HC...light source control unit, 116H...output unit, 101, 101C, 101D...photography control unit, 102, 102A, 102B, 102C, 102D...eye detection unit, 103...corneal reflex determination unit, 104, 104A...biometric determination unit, 105...communication unit, 106, 106B...external interface, 107...pupil absorption determination unit, 108...face determination unit
Claims
1. a camera for capturing an image of a subject to be subjected to biometric determination; a controller for controlling the camera; an incident light polarization unit that polarizes a light beam incident from an external light source or an internal light source and outputs the polarized light beam toward the subject; a reflected light polarizing unit disposed between the subject and the camera; A biometric determination device comprising: The controller The light beam polarized by the incident light polarizing unit is incident on the subject, and the light beam reflected by the subject is incident on the reflected light polarizing unit. In this state, the light from the subject that is emitted from the reflected light polarizing unit is captured by the camera, thereby obtaining a living body determination image for determining whether the light beam incident on the subject is specularly reflected or not; determining whether the light beam incident on the subject is regularly reflected based on the image for biometric determination, thereby determining whether the subject is a living organism; It was configured as follows: Biometric detection device.
2. The living body determination device according to claim 1, a first linear polarizer as the reflected light polarizing unit; a second linear polarizer as the incident light polarizing unit; a first imaging system that, when the polarized light beam is specularly reflected by the subject, polarizes the light beam by the first linear polarizer non-orthogonal to the polarization state of the light beam reflected by the subject, and captures the light from the subject that is emitted from the first linear polarizer by the camera; a second imaging system that, when the polarized light beam is specularly reflected by the subject, polarizes the light beam by the first linear polarizer perpendicular to the polarization state of the light beam reflected by the subject, and captures the light from the subject that is emitted from the first linear polarizer by the camera; Equipped with The controller acquiring, as the image for biometric determination, both a first image captured by the first imaging system and a second image captured by the second imaging system, or one image including the first image and the second image; If light representing the light beam is detected from the first image and light representing the light beam is not detected from the second image, it is determined that the light beam incident on the subject is specularly reflected. It was configured as follows: Biometric detection device.
3. The living body determination device according to claim 1, the incident light polarization unit includes a first incident light polarization plate that polarizes the light beam incident from the external light source or the internal light source in a first polarization state and outputs the light beam toward the subject, and a second incident light polarization plate that polarizes the light beam incident from the external or internal light source in a second polarization state and outputs the light beam toward the subject; a reflected light polarizing plate as the reflected light polarizing unit, the reflected light polarizing plate having a property of transmitting at least a part of the light beam in the first polarization state and blocking the light beam in the second polarization state; Equipped with The controller the light beam polarized in the first polarization state by the first incident light polarizing plate is incident on the subject, and the light beam reflected by the subject is incident on the reflected light polarizing plate, and in this state, the light from the subject that is emitted from the reflected light polarizing plate is captured by the camera, thereby obtaining a first image as the image for biometric determination; the light beam polarized to the second polarization state by the second incident light polarizing plate is incident on the subject, and the light beam reflected by the subject is incident on the reflected light polarizing plate, and in this state, the light from the subject that is emitted from the reflected light polarizing plate is captured by the camera, thereby obtaining a second image as the image for liveness determination; If it is determined that the subject specularly reflects the incident light beam based on the first image and the second image, it is determined that the subject is a living organism, and if it is determined that the subject does not specularly reflect the incident light beam, it is determined that the subject is not a living organism. It was configured as follows: Biometric detection device.
4. The living body determination device according to claim 1, an incident light polarizing plate as the incident light polarizing unit, which polarizes the light beam incident from the external light source or the internal light source in a first polarization state and outputs the polarized light toward the subject; the reflected light polarizing unit includes a first reflected light polarizing plate having a property of transmitting at least a part of the light flux in the first polarization state, and a second reflected light polarizing plate having a property of blocking the light flux in the first polarization state; Equipped with The controller the light beam polarized to the first polarization state by the incident light polarizing plate is incident on the subject, and the light beam reflected by the subject is incident on the first reflected light polarizing plate, and in this state, the light from the subject that is emitted from the first reflected light polarizing plate is captured by the camera, thereby obtaining a first image as the image for biometric determination; the light beam polarized to the first polarization state by the incident light polarizing plate is incident on the subject, and the light beam reflected by the subject is incident on the second reflected light polarizing plate, and in this state, the light from the subject that is emitted from the second reflected light polarizing plate is captured by the camera, thereby obtaining a second image as the image for liveness determination; If it is determined that the subject specularly reflects the incident light beam based on the first image and the second image, it is determined that the subject is a living organism, and if it is determined that the subject does not specularly reflect the incident light beam, it is determined that the subject is not a living organism. It was configured as follows: Biometric detection device.
5. The living body determination device according to claim 1, an incident light polarizing plate as the incident light polarizing unit, which polarizes the light beam incident from the external light source or the internal light source in a first polarization state and outputs the polarized light toward the subject; the reflected light polarizing portion includes a first polarization characteristic portion having a characteristic of transmitting at least a part of the light flux in the first polarization state, and a reflected light polarizing plate including a second polarization characteristic portion that blocks the light flux in the first polarization state; Equipped with The controller a first image portion obtained by capturing, with the camera, the light from the subject that has been polarized to the first polarization state by the incident light polarizing plate, and a second image portion obtained by capturing, with the camera, the light from the subject that has been reflected from the first polarization characteristic portion, and a second image portion obtained by capturing, with the camera, the light from the subject that has been emitted from the second polarization characteristic portion, in a state in which the light beam that has been polarized to the first polarization state by the incident light polarizing plate is incident on the subject, and the light beam that has been reflected from the subject is incident on the first polarization characteristic portion and the second polarization characteristic portion of the reflected light polarizing plate; If it is determined that the subject specularly reflects the incident light beam based on the first image portion and the second image portion, it is determined that the subject is a living organism, and if it is determined that the subject does not specularly reflect the incident light beam, it is determined that the subject is not a living organism. It was configured as follows: Biometric detection device.
6. The living body determination device according to claim 3, The controller If light indicating the luminous flux is detected from the first image and light indicating the luminous flux is not detected from the second image, the subject is determined to be a living organism. It was configured as follows: Biometric detection device.
7. The living body determination device according to claim 3, as the light sources, a first light source that generates a light beam that is incident on the first incident light polarizing plate, and a second light source that generates a light beam that is incident on the second incident light polarizing plate; Equipped with The controller controlling the first light source and the second light source to either ON or OFF; In a state where the first light source is controlled to be turned on and the second light source is controlled to be turned off, the camera captures an image of light from the subject to acquire the first image, and in a state where the second light source is controlled to be turned on and the first light source is controlled to be turned off, the camera captures an image of light from the subject to acquire the second image, thereby acquiring the first image and the second image at different times. It was configured as follows: Biometric detection device.
8. The living body determination device according to claim 3, the reflected light polarizing plate, the first incident light polarizing plate, and the second incident light polarizing plate are linear polarizing plates, the polarization axis of the first incident light polarizing plate and the polarization axis of the reflected light polarizing plate are parallel to each other, the polarization axis of the second incident light polarizing plate and the polarization axis of the reflected light polarizing plate are perpendicular to each other; Biometric detection device.
9. The living body determination device according to claim 4, the incident light polarizing plate, the first reflected light polarizing plate, and the second reflected light polarizing plate are linear polarizing plates; the polarization axis of the incident light polarizing plate and the polarization axis of the first reflected light polarizing plate are parallel to each other, the polarization axis of the incident light polarizing plate and the polarization axis of the second reflected light polarizing plate are perpendicular to each other; Biometric detection device.
10. The living body determination device according to claim 5, the incident light polarizing plate and the reflected light polarizing plate are linear polarizing plates, the polarization axis of the incident light polarizing plate and the polarization axis of the first polarization characteristic portion of the reflected light polarizing plate are parallel to each other, the polarization axis of the incident light polarizing plate and the polarization axis of the second polarization characteristic portion of the reflected light polarizing plate are perpendicular to each other; Biometric detection device.
11. The living body determination device according to claim 3, Each of the first incident light polarizing plate and the second incident light polarizing plate is a circular polarizing plate. The reflected light polarizing plate is composed of a circular polarizing plate. Biometric detection device.
12. The living body determination device according to claim 1, the light beam includes infrared light, The camera captures infrared light. Biometric detection device.
13. The living body determination device according to claim 1, The controller Detecting the position of the subject's eyes from the biometric determination image; determining whether the subject regularly reflects the light beam based on an image of a region of the image for liveness determination that includes the eye of the subject; It was configured as follows: Biometric detection device.
14. The living body determination device according to claim 13, The controller determining whether or not the pupil of the subject absorbs the light beam based on an image of a region including the eye of the subject in the image for biometric determination; Based on an image of a region including the eyes of the subject in the biometric determination image, Only when it is determined that the eye of the subject specularly reflects the light beam and when it is determined that the eye of the subject in the liveness determination image has pupil absorption, it is determined that the subject is a living organism, and in any other determination, it is determined that the subject is not a living organism. It was configured as follows: Biometric detection device.
15. The living body determination device according to claim 1, a peripheral device including at least one of a display and a speaker; The controller Detecting the size of the subject's face from the image captured by the camera; When the size of the face is equal to or smaller than a certain size, the peripheral device instructs the subject to move closer to the camera. It was configured as follows: Biometric detection device.
16. The living body determination device according to claim 1, a peripheral device including at least one of a display and a speaker; The controller Detecting the orientation of the subject's face from the image captured by the camera; When the orientation of the face is equal to or greater than a certain value with respect to the optical axis of the camera, the peripheral device instructs the subject to face the front of the camera. It was configured as follows: Biometric detection device.
17. a camera for capturing an image of a subject to be subjected to biometric determination; a controller for controlling the camera; an incident light polarization unit that polarizes a light beam incident from an external light source or an internal light source and outputs the polarized light beam toward the subject; a reflected light polarizing unit disposed between the subject and the camera; A living body determination method for determining whether the subject is a living body using The controller a polarized light beam incident on the subject, the light beam reflected by the subject being incident on the reflected light polarizing unit, and an image of the light from the subject that is emitted from the reflected light polarizing unit is captured by the camera, thereby obtaining a living body determination image for determining whether the light beam incident on the subject is regularly reflected; determining whether the light beam incident on the subject is regularly reflected based on the image for biometric determination, thereby determining whether the subject is a living organism; Biometric determination method.
Citation Information
Patent Citations
Methods and devices for birefringence-based biometric authentication
JP2021157826A