Biometric authentication device, biometric authentication method, and biometric authentication program

Abstract

In the present invention, a prediction unit predicts a stop position at which a body part of a subject of authentication stops, the body part moving toward an imaging device, on the basis of a plurality of images obtained by capturing the body part by means of the imaging device in a ranging mode. A control unit switches the photographing mode of the imaging device from the ranging mode to an authentication mode before the body part stops at the stop position. An authentication unit performs biometric authentication on the subject of authentication by using images of the body part captured by means of the imaging device in the authentication mode.

Description

Biometric authentication device, biometric authentication method, and biometric authentication program

[0001] The present invention relates to biometric authentication technology.

[0002] Biometric authentication is a technology that verifies an individual's identity using biometric features such as fingerprints, faces, veins, etc. Palm vein authentication, which verifies an individual's identity using palm veins, is a technology that uses a vein sensor to capture an image of the palm of the hand, acquires a vein pattern from the image, and then uses the vein pattern to perform authentication.

[0003] Regarding palm vein authentication, a low-cost vein authentication device that authenticates the veins of the palm and fingers and requires little installation space is known (see, for example, Patent Document 1).An automatic control device that uses a three-dimensional image sensor to predict the final indicated coordinates from an initial movement is also known (see, for example, Patent Document 2 and Non-Patent Document 1).

[0004] A beam generating optical system is also known that can reduce the size of the beam spot, prevent a decrease in spot brightness, and enable a thinner imaging device without reducing the sensitivity or accuracy of the distance measurement function (see, for example, Patent Document 3).

[0005] JP 2008-246011 A JP 2013-109444 A International Publication No. 2018 / 078793

[0006] Kusano and Omura, "A study on prediction methods for human pointing behavior using the minimal jerk model," IPSJ Interaction 2012, pp. 929-934, 2012.

[0007] In palm vein authentication, it is desirable that the position of the palm of the person to be authenticated be within a predetermined range in order to capture a palm vein image suitable for authentication. The predetermined range is defined by upper and lower limit values ​​of coordinates that increase as the palm moves away from the vein sensor. The predetermined range is also called the authentication range.

[0008] In order to capture a palm vein image in the authentication range, a distance measurement mode and an authentication mode may be used as imaging modes of the vein sensor.

[0009] The distance measurement mode is an imaging mode in which a palm is photographed using illumination light for distance measurement to obtain an image for distance measurement, the distance between the palm and the vein sensor is measured using the image for distance measurement, and the palm is guided so that its position falls within the authentication range. The distance measurement mode is also called the guidance mode. The authentication mode is an imaging mode in which a palm is photographed using illumination light for authentication to obtain a palm vein image for authentication.

[0010] However, when switching from the image capture mode to the authentication mode after confirming that the palm of the hand has entered and stopped within the authentication range in the distance measurement mode, a delay occurs due to the switching, making it difficult to quickly acquire a palm vein image and perform palm vein authentication when the palm of the hand stops within the authentication range.

[0011] This problem is not limited to palm vein authentication, but occurs in various biometric authentications that use images of body parts.

[0012] In one aspect, the present invention aims to perform rapid biometric authentication using an image of a body part moving toward an imaging device.

[0013] According to one embodiment, the biometric authentication device includes a prediction unit, a control unit, and an authentication unit.

[0014] The prediction unit predicts a stop position where a body part of the person to be authenticated will stop, based on multiple images of the body part of the person to be authenticated that are moving toward the imaging device, captured by the imaging device in a distance measurement mode. The control unit switches the imaging mode of the imaging device from a distance measurement mode to an authentication mode before the body part stops at the stop position. The authentication unit performs biometric authentication on the person to be authenticated, using the images of the body part captured by the imaging device in the authentication mode.

[0015] According to another embodiment, in a biometric authentication method, a computer executes the following processes.

[0016] The computer predicts a stopping position where a body part of a person to be authenticated moving toward an imaging device will stop, based on a plurality of images captured by the imaging device in a distance measurement mode. Before the body part stops at the stopping position, the computer switches the imaging mode of the imaging device from a distance measurement mode to an authentication mode, and performs biometric authentication on the person to be authenticated using the images of the body part captured by the imaging device in the authentication mode.

[0017] According to yet another embodiment, the biometric authentication program causes a computer to perform the following processes.

[0018] The computer predicts a stopping position where a body part of a person to be authenticated moving toward an imaging device will stop, based on a plurality of images captured by the imaging device in a distance measurement mode. Before the body part stops at the stopping position, the computer switches the imaging mode of the imaging device from a distance measurement mode to an authentication mode, and performs biometric authentication on the person to be authenticated using the images of the body part captured by the imaging device in the authentication mode.

[0019] In one aspect, an image of a body part moving towards an imaging device can be used to quickly perform biometric authentication.

[0020] FIG. 1 is a functional configuration diagram of a biometric authentication device of an embodiment; FIG. 2 is a flowchart of a first biometric authentication process; FIG. 3 is a functional configuration diagram showing a specific example of a biometric authentication device; FIG. 4 is a diagram showing an illumination light for distance measurement and an illumination light for authentication; FIG. 5 is a diagram showing a planar arrangement of a light source for distance measurement and a light source for authentication; FIG. 6 is a diagram showing an image for distance measurement; FIG. 7 is a diagram showing a first switching control; FIG. 8 is a diagram showing a second switching control; FIG. 9 is a flowchart (part 1) of a second biometric authentication process; FIG. 10 is a flowchart (part 2) of a second biometric authentication process; FIG. 11 is a flowchart (part 3) of a second biometric authentication process; FIG. 12 is a flowchart (part 4) of a second biometric authentication process; FIG. 13 is a diagram showing a hardware configuration diagram of an information processing device.

[0021] Hereinafter, embodiments will be described in detail with reference to the drawings.

[0022] 1 shows an example of the functional configuration of a biometric authentication device according to an embodiment. The biometric authentication device 101 in FIG. 1 includes a prediction unit 111, a control unit 112, and an authentication unit 113.

[0023] Fig. 2 is a flowchart showing an example of the first biometric authentication process performed by the biometric authentication device 101 in Fig. 1. First, the prediction unit 111 predicts a stopping position of a body part of a person to be authenticated, which is moving toward the image capture device, based on a plurality of images captured by the image capture device in distance measurement mode (step 201).

[0024] Next, the control unit 112 switches the imaging mode of the imaging device from the distance measurement mode to the authentication mode before the body part stops at the stopping position (step 202). Next, the authentication unit 113 performs biometric authentication on the person to be authenticated using the image of the body part captured by the imaging device in the authentication mode (step 203).

[0025] The biometric authentication device 101 in FIG. 1 can quickly perform biometric authentication using an image of a body part that moves toward the image capture device.

[0026] Fig. 3 shows a specific example of the biometric authentication device 101 in Fig. 1. The biometric authentication device 301 in Fig. 3 includes a vein sensor 311, a prediction unit 312, a control unit 313, an authentication unit 314, and a storage unit 315. The prediction unit 312, the control unit 313, and the authentication unit 314 in Fig. 3 correspond to the prediction unit 111, the control unit 112, and the authentication unit 113 in Fig. 1, respectively.

[0027] The biometric authentication device 301 is used for various user authentication purposes in automated transaction devices such as ATMs (Automatic Teller Machines), entrance / exit devices, PCs (Personal Computers), multifunction peripherals, safes, lockers, and the like.

[0028] The vein sensor 311 is a hardware imaging device that captures an image of the palm of the person to be authenticated to obtain a palm vein image. For example, the imaging device described in Patent Document 3 can be used as the vein sensor 311.

[0029] The vein sensor 311 includes a near-infrared camera, and irradiates the palm of the person to be authenticated with near-infrared light to obtain a near-infrared image of the palm as a palm vein image. The palm is an example of a body part of the person to be authenticated.

[0030] The vein sensor 311 operates in either a distance measurement mode or an authentication mode. In the distance measurement mode, the vein sensor 311 irradiates the palm with illumination light for distance measurement, called a distance measurement beam, and in the authentication mode, the vein sensor 311 irradiates the palm with illumination light for authentication.

[0031] 4 shows examples of illumination light for distance measurement and illumination light for authentication. A user to be authenticated holds a palm 401 over the vein sensor 311 and moves the palm 401 toward the vein sensor 311. At this time, the vein sensor 311 operates in distance measurement mode, irradiates the palm 401 with illumination light for distance measurement 402, and captures an image of the palm 401 to obtain an image for distance measurement. The illumination light for distance measurement 402 is, for example, visible light.

[0032] When the palm 401 enters the authentication range, the vein sensor 311 operates in authentication mode, irradiates the palm 401 with authentication illumination light 403, and captures an authentication palm vein image by photographing the palm 401. The authentication illumination light 403 is, for example, near-infrared light.

[0033] Some of the near-infrared light is reflected from the surface of palm 401, but some passes through the skin and cells, penetrates into the interior of palm 401, and is absorbed by hemoglobin contained in the blood in the veins. By capturing an image of palm 401 illuminated with near-infrared light using a near-infrared camera, it is possible to obtain a palm vein image that includes the vein pattern in addition to surface information of palm 401.

[0034] The vein sensor 311 continuously captures images for distance measurement or palm vein images for authentication at a predetermined interval. Each captured image is sometimes called a frame, and the capture interval is sometimes called a frame time.

[0035] Fig. 5 shows an example of the planar arrangement of the distance measurement light source and the authentication light source in the vein sensor 311. The square in Fig. 5 represents the shape of the vein sensor 311 as viewed from above. Distance measurement light sources 501-1 to 501-4 are arranged at the four corners of the square, and authentication light sources 502-1 to 502-16 are arranged in a circle inside the distance measurement light sources 501-1 to 501-4.

[0036] The distance measurement light sources 501-1 to 501-4 and the authentication light sources 502-1 to 502-16 are, for example, LED (Light-Emitting Diode) light sources. The distance measurement light sources 501-1 to 501-4 irradiate the palm 401 with distance measurement illumination light 402 in the distance measurement mode. The authentication light sources 502-1 to 502-16 irradiate the palm 401 with authentication illumination light 403 in the authentication mode.

[0037] 6A and 6B show examples of distance measurement images acquired by capturing an image of a palm 401 illuminated with distance measurement illumination light 402. Fig. 6A shows an example of an image when the palm 401 is positioned close to the vein sensor 311. Four beam spots 601 represent the distance measurement illumination light 402 illuminated from distance measurement light sources 501-1 to 501-4, respectively.

[0038] 6B shows an example of an image when the palm 401 is positioned far from the vein sensor 311. Four beam spots 602 represent the distance measurement illumination light 402 emitted from the distance measurement light sources 501-1 to 501-4, respectively.

[0039] The prediction unit 312 checks whether four beam spots are captured in the distance measurement image, and if four beam spots are captured, determines that the palm 401 is held over the vein sensor 311.

[0040] The distance from the center of the image in Fig. 6(a) to each beam spot 601 is longer than the distance from the center of the image in Fig. 6(b) to each beam spot 602. Thus, there is a predetermined correlation between the distance from the center of the distance measurement image to each beam spot and the distance between the palm 401 and the vein sensor 311.

[0041] Therefore, the prediction unit 312 uses this correlation to measure the distance between the palm 401 and the vein sensor 311 at the time the distance measurement image is captured. The image capture time may be, for example, the time when the image capture begins. The prediction unit 312 then uses the measured distance to determine the coordinate x(t(c)) of the palm 401 at the capture time t(c) of the image indicated by index c.

[0042] The coordinate x(t(c)) represents a coordinate in a direction perpendicular to the plane of Fig. 5. For example, the height representing the distance from the vein sensor 311 to the palm 401 is used as the coordinate x(t(c)).

[0043] When it is detected that the palm 401 has been held over the image, the prediction unit 312 generates start point information 321 and stores it in the storage unit 315. The start point information 321 includes c, t(c), and x(t(c)) at the start point. At the start point, c is 0, t(c) is 0, and x(t(c)) is x(0). Thereafter, each time an image is captured, c and t(c) are updated according to the following equations.

[0044] c=c+1 (1) t(c)=c×Δt (2)

[0045] Δt represents the photographing interval, and c represents the number of photographs taken between photographing time t(1) and photographing time t(c). The prediction unit 312 calculates the velocity V(t(c)) and acceleration a(t(c)) of the palm 401 at photographing time t(c) using the following equations.

[0046] V(t(c))={x(t(c))−x(t(c−1))} / Δt (3) a(t(c))={V(t(c))−V(t(c−1))} / Δt (4)

[0047] The prediction unit 312 predicts the position and time at which the palm 401, which is moving toward the vein sensor 311, will stop, based on a(t(c)) calculated from each of the multiple distance measurement images and a motion model of the human body. As the motion model of the human body, for example, the Jerk minimum model described in Non-Patent Document 1 is used.

[0048] The minimum jerk model in Non-Patent Document 1 is a movement model that utilizes the fact that the time integral of the jerk is minimized when a human hand moves. According to the minimum jerk model, the velocity and acceleration are 0 at the start and end points of the movement of a human hand, and if the coordinate of the start point is x0 and the coordinate of the end point is xf, the coordinate x(τ) of the hand can be expressed by the following equation using a parameter τ related to time t:

[0049] x(τ)=x0+(xf-x0)(6τ ５ -15τ ４ +10τ ３ ) (5) τ=t / T (6)

[0050] T represents the travel time for the hand to move from the starting point to the end point. While the hand moves from the starting point to the end point, the velocity reaches a maximum only once, and the acceleration reaches a minimum after reaching a maximum. If τ when the acceleration reaches a maximum is defined as τ1 and τ when the acceleration reaches a minimum is defined as τ2, then τ1 and τ2 can be found from the condition that the value of the jerk polynomial obtained by differentiating the right-hand side of equation (5) three times becomes 0. The found τ1 and τ2 are expressed by the following equations.

[0051] τ1 = (3 - 3 １／２ ) / 6≒0.21 (7) τ2=(3+3 １／２ ) / 6 ≒ 0.79 (8)

[0052] From equation (7), it can be seen that the time from when the hand tip starts moving until the acceleration reaches its maximum is approximately 21% of T. In other words, if the time at which the acceleration reaches its maximum while the palm 401 is moving is known, the movement time T from the start point to the end point can be calculated.

[0053] The end point corresponds to the stopping position where the palm 401 stops. Therefore, the stopping time tf at which the palm 401 stops can be calculated from the moving time T. First, to calculate the coordinate xf of the stopping position at which the palm 401 stops, equation (5) is transformed to obtain the following equation:

[0054] xf=(x(τ)-x0) / (6τ ５ -15τ ４ +10τ ３ ) + x0 (9)

[0055] Next, by substituting x(τ1) for x(τ) in equation (9) and substituting τ1 in equation (7) for τ, the following equation is obtained.

[0056] xf=(4x(τ1)−(2+3 １／２ ) x 0) / (2-3 １／２ ) (10)

[0057] When the acceleration a(t(c)) reaches a maximum, the acceleration a(t(c)) changes from increasing to decreasing. Therefore, the prediction unit 312 uses x(0) included in the start point information 321 as x0, and the coordinate x(t(c)) when the acceleration a(t(c)) changes from increasing to decreasing as x(τ1), and calculates xf using equation (10) to predict the stop position. When the slope of the acceleration a(t(c)) changes from positive to negative, the prediction unit 312 determines that the acceleration a(t(c)) has changed from increasing to decreasing.

[0058] Next, the prediction unit 312 checks whether xf is within the authenticable range. If xf is equal to or less than the upper limit of the authenticable range and equal to or greater than the lower limit, the prediction unit 312 determines that xf is within the authenticable range.

[0059] If xf is included in the authentication range, the prediction unit 312 calculates the time t1 at which the acceleration a(t(c)) changes from increasing to decreasing using the following equation.

[0060] t1=c1×Δt (11)

[0061] c1 represents the index c when it is detected that the acceleration a(t(c)) has changed from increasing to decreasing.

[0062] Since t(c) included in the start point information 321 is 0, the time at the start point is 0. Therefore, the time from when the palm 401 starts to move until the acceleration reaches a maximum coincides with time t1, and the movement time T of the palm 401 coincides with the stop time tf. Therefore, the prediction unit 312 predicts the stop time tf by calculating the stop time tf using the following equation using equations (6) and (7):

[0063] tf=t1 / 0.21 (12)

[0064] Then, the prediction unit 312 outputs the predicted stop time tf to the control unit 313. The control unit 313 uses the stop time tf output from the prediction unit 312 to calculate the number N of times photography will be performed between time t1+Δt and the stop time tf, using the following formula.

[0065] N=(tf-t1) / Δt (13)

[0066] If the right side of equation (13) is a non-integer, the prediction unit 312 finds an integer N by rounding down the decimal point.

[0067] Next, the control unit 313 decrements N by 1 each time an image is captured until N reaches a predetermined number M. M is an integer greater than or equal to 1 and less than N. When N=M, the control unit 313 controls the vein sensor 311 to capture an image of the palm 401 in authentication mode by switching the imaging mode of the vein sensor 311 from the distance measurement mode to the authentication mode.

[0068] The time when N=M corresponds to a predetermined time before the stop time tf. Therefore, the control unit 313 can identify the predetermined time before the stop time tf by checking whether N has become M, and can switch the imaging mode of the vein sensor 311 from the distance measurement mode to the authentication mode at the predetermined time.

[0069] After the imaging mode is switched from the distance measurement mode to the authentication mode, the vein sensor 311 captures an image of the palm 401 to obtain a palm vein image 322 for authentication. The storage unit 315 stores the obtained palm vein image 322.

[0070] The authentication unit 314 performs palm vein authentication on the person to be authenticated using the palm vein image 322. The storage unit 315 stores a registered template 323 in advance. The registered template 323 includes registered feature information of one or more registered persons. The authentication unit 314 acquires the registered feature information of each registered person from, for example, a database server (not shown), and generates the registered template 323 using the acquired registered feature information.

[0071] The authentication unit 314 extracts feature information of the vein pattern from the vein pattern included in the palm vein image 322 and compares the extracted feature information with registered feature information included in the registered template 323 .

[0072] The authentication unit 314 calculates, for example, the similarity between the vein pattern feature information and the registered feature information of each person to be registered. If the similarity to any person to be registered is greater than a threshold, the authentication unit 314 determines that the authentication is successful. If the similarity to any person to be registered is equal to or less than the threshold, the authentication unit 314 determines that the authentication is unsuccessful. Then, the authentication unit 314 outputs an authentication result indicating whether the authentication is successful or unsuccessful.

[0073] Fig. 7 shows an example of a first switching control in the biometric authentication process performed by the biometric authentication device 301 of Fig. 3. In the switching control of Fig. 7, the imaging mode is not switched based on the stop time tf predicted by the prediction unit 312, but rather the imaging mode is switched after it is confirmed that the palm 401 has entered and stopped within an authenticable range 701 of the vein sensor 311. The authenticable range 701 is defined by an upper limit value 711 and a lower limit value 712 of the coordinate x(t(c)).

[0074] The person to be authenticated holds the palm 401 over the vein sensor 311 and brings the palm 401 close to the vein sensor 311. At this time, the vein sensor 311 captures an image of the palm 401 in distance measurement mode and acquires an image for distance measurement indicated by a white square.

[0075] After confirming that the palm 401 has stopped within the authentication range 701, the control unit 313 switches the imaging mode from the distance measurement mode to the authentication mode. This causes the vein sensor 311 to capture an image of the palm 401 in the authentication mode and obtain a palm vein image for authentication, which is indicated by a hatched rectangle.

[0076] However, because a delay occurs due to the switching, the imaging mode has not yet switched to authentication mode when the palm 401 stops just below the upper limit value 711. Therefore, when the palm 401 stops, the palm 401 is still imaged in the distance measurement mode, and palm vein authentication is not performed.

[0077] Fig. 8 shows an example of a second switching control in the biometric authentication process performed by the biometric authentication device 301 in Fig. 3. In the switching control in Fig. 8, the imaging mode is switched based on the stop time tf predicted by the prediction unit 312.

[0078] 7 , the person to be authenticated holds the palm 401 over the vein sensor 311 and brings the palm 401 close to the vein sensor 311. When the prediction unit 312 detects that the palm 401 has been held over the sensor, it calculates the coordinate x(0) of the starting point. The vein sensor 311 captures an image of the palm 401 in distance measurement mode and acquires an image for distance measurement, indicated by a white rectangle.

[0079] When the prediction unit 312 detects that the acceleration a(t(c)) has changed from increasing to decreasing, it uses the coordinate x(t1) at that time to calculate xf using equation (10) and also calculates the stop time tf.

[0080] The control unit 313 calculates the number of times N to capture images between time t1+Δt and stop time tf using equation (13), and decrements N by 1 each time an image is captured. When N=M, the control unit 313 switches the capture mode from distance measurement mode to authentication mode. This causes the vein sensor 311 to capture an image of the palm 401 in authentication mode and acquire a palm vein image for authentication, indicated by a hatched rectangle.

[0081] When M=1, even if the palm 401 stops just below the upper limit value 711, the imaging mode can be switched to the authentication mode at the moment the palm 401 stops, and an image of the palm 401 can be captured. This allows a palm vein image to be quickly acquired and palm vein authentication to be performed, improving the operability of the vein sensor 311 for the user to be authenticated.

[0082] Furthermore, by setting the predetermined number M to an appropriate value, it is possible to switch the imaging mode to the authentication mode and capture an image of the palm 401 at the timing when the palm 401 enters the authentication range 701. In this case as well, a palm vein image can be quickly acquired and palm vein authentication can be performed, improving the operability of the vein sensor 311 by the person to be authenticated.

[0083] The authenticable range 701 and the photographing interval Δt change depending on the vein sensor 311. Therefore, a value of M suitable for identifying the timing at which the palm 401 enters the authenticable range 701 may be determined by repeating experiments in which palm vein authentication is actually performed using the biometric authentication device 301.

[0084] If the imaging mode is switched at the timing when the palm 401 enters the authentication range 701, a palm vein image may be acquired and palm vein authentication may be performed before the palm 401 stops. However, even if the palm 401 is moving, if the speed of the palm 401 is sufficiently slow, it is possible to acquire a palm vein image suitable for authentication.

[0085] 9A to 9D are flowcharts showing an example of the second biometric authentication process performed by the biometric authentication device 301 in Fig. 3. In the following description, the distance measurement light sources 501-1 to 501-4 in Fig. 5 may be collectively referred to as a distance measurement light source group, and the authentication light sources 502-1 to 502-16 may be collectively referred to as an authentication light source group.

[0086] First, the control unit 313 controls the vein sensor 311 to turn off the distance measurement light source group and the authentication light source group (step 901), and controls the vein sensor 311 to operate in the distance measurement mode (step 902). As a result, the vein sensor 311 turns on the distance measurement light source group.

[0087] Next, the vein sensor 311 starts capturing an image (step 903) and acquires the captured image (step 904). The prediction unit 312 then uses the captured image to check whether a palm is placed over the vein sensor 311 (step 905). If a palm is not placed over the vein sensor 311 (NO in step 905), the biometric authentication device 301 repeats the processes from step 903 onwards.

[0088] If the palm of the hand is held out (step 905, YES), the prediction unit 312 sets the index c to 0 (step 906). Next, the prediction unit 312 measures the distance between the palm and the vein sensor 311 using the captured image, and calculates the coordinate x(t(c)) of the palm from the measured distance (step 907).

[0089] Then, the prediction unit 312 generates starting point information 321 including c, t(c), and x(t(c)) (step 908). In the starting point information 321, c is 0, t(c) is 0, and x(t(c)) is x(0).

[0090] Next, the vein sensor 311 starts capturing the next image (step 909) and acquires the captured image (step 910). Then, the prediction unit 312 increments c by 1 (step 911), and the vein sensor 311 starts capturing the next image (step 912).

[0091] Next, the prediction unit 312 calculates the coordinate x(t(c)), velocity V(t(c)), and acceleration a(t(c)) using the image acquired in step 910 (step 913). The prediction unit 312 then checks whether x(t(c)) is within the authenticatable range (step 914). If x(t(c)) is equal to or less than the upper limit of the authenticatable range and equal to or greater than the lower limit, the prediction unit 312 determines that x(t(c)) is within the authenticatable range.

[0092] If x(t(c)) is within the authentication range (step 914, YES), the vein sensor 311 acquires the image that is already being captured (step 915), and the prediction unit 312 requests the control unit 313 to switch the imaging mode of the vein sensor 311. Then, the control unit 313 switches the imaging mode from distance measurement mode to authentication mode (step 916). As a result, the vein sensor 311 turns off the group of light sources for distance measurement and turns on the group of light sources for authentication.

[0093] Next, the vein sensor 311 starts capturing an image of the palm in authentication mode (step 917) and acquires a palm vein image 322 (step 918). The authentication unit 314 then performs palm vein authentication on the person to be authenticated using the palm vein image 322 and checks whether the authentication is successful (step 919).

[0094] If the authentication fails (step 919, NO), the authentication unit 314 outputs an authentication result indicating that the authentication failed (step 921), and the biometric authentication device 301 repeats the processing from step 901. If the authentication is successful (step 919, YES), the authentication unit 314 outputs an authentication result indicating that the authentication was successful (step 920), and the biometric authentication device 301 ends the processing.

[0095] If x(t(c)) is not within the authentication range (step 914, NO), the prediction unit 312 checks whether the acceleration a(t(c)) has changed from an increase to a decrease (step 922). If the acceleration a(t(c)) has not changed from an increase to a decrease (step 922, NO), the biometric authentication device 301 repeats the processing from step 910 onwards.

[0096] If the acceleration a(t(c)) changes from increasing to decreasing (step 922, YES), the prediction unit 312 performs the process of step 923. In step 923, the prediction unit 312 calculates the coordinate xf of the stopping position of the palm using x(0) included in the start point information 321 and the coordinate x(t(c)) when the acceleration a(t(c)) changes from increasing to decreasing.

[0097] Next, the prediction unit 312 checks whether xf is included in the authenticable range (step 924). If xf is not included in the authenticable range (step 924, NO), the biometric authentication device 301 repeats the processes from step 904 onwards.

[0098] If xf is within the authentication range (step 924, YES), the prediction unit 312 calculates the time t1 when the acceleration a(t(c)) changes from increasing to decreasing, and uses t1 to calculate the stop time tf when the palm stops (step 925). The prediction unit 312 then outputs the predicted stop time tf to the control unit 313.

[0099] Next, the control unit 313 uses the time t1 and the stop time tf to calculate the number N of times of photographing to be performed between the time t1+Δt and the stop time tf (step 926).

[0100] Next, the vein sensor 311 acquires the image that is already being captured (step 927) and starts capturing the next image (step 928). The control unit 313 then decrements N by 1 (step 929) and compares N with a predetermined number M (step 930). If N does not match M (NO in step 930), the biometric authentication device 301 repeats the processing from step 927 onwards.

[0101] If N matches M (step 930, YES), the vein sensor 311 acquires the image already being captured (step 931), and the control unit 313 switches the image capture mode from the distance measurement mode to the authentication mode (step 932). As a result, the vein sensor 311 turns off the group of light sources for distance measurement and turns on the group of light sources for authentication.

[0102] Next, the control unit 313 sets the number of retries R to 0 (step 933), and increments R by 1 (step 934).The control unit 313 then compares R with a threshold value TH (step 935). TH may be, for example, M+1.

[0103] If R is smaller than TH (step 935, YES), the vein sensor 311 starts capturing an image of the palm in authentication mode (step 936) and acquires the captured palm vein image 322 (step 937).The authentication unit 314 then performs palm vein authentication on the person to be authenticated using the palm vein image 322 and checks whether the authentication is successful (step 938).

[0104] If the authentication fails (step 938, NO), the authentication unit 314 outputs an authentication result indicating that the authentication failed (step 940), and the biometric authentication device 301 repeats the processes from step 934 onwards. If R reaches TH (step 935, NO), the biometric authentication device 301 repeats the processes from step 901 onwards. If the authentication is successful (step 938, YES), the authentication unit 314 outputs an authentication result indicating that the authentication was successful (step 939), and the biometric authentication device 301 ends the process.

[0105] Fig. 10 shows an example of biometric authentication processing performed by the biometric authentication device 301 in Fig. 3. In this example, Δt=10 msec and M=1.

[0106] From the image captured at 0 msec, it is detected that a palm is held out, and from the image captured at 20 msec, when c = 3, it is detected that the acceleration a(t(c)) has changed from an increase to a decrease. Therefore, c1 = 3, and from equation (11), t1 = 30 msec.

[0107] At this time, the prediction unit 312 uses the coordinate x(t1) to calculate xf according to equation (10) and also calculates the stop time tf. In this example, tf = 143 msec. The control unit 313 calculates the number N of times photography will be performed between the next photography time of 40 msec and the stop time of 143 msec according to equation (13). In this case, N = 11.

[0108] Next, the control unit 313 decrements N by 1 each time an image is captured, and after capturing of an image at a capture time of 130 msec begins, N = M = 1. Then, the control unit 313 switches the capture mode of the vein sensor 311 from the distance measurement mode to the authentication mode.

[0109] Then, the vein sensor 311 starts capturing an image of the palm in authentication mode at 140 msec, which is before the stop time 143 msec, and acquires a palm vein image. The authentication unit 314 performs palm vein authentication using the acquired palm vein image. This allows the palm vein image to be quickly acquired and palm vein authentication to be performed when the palm stops.

[0110] On the other hand, when M=2, after image capture begins at 120 msec, N=M=2, and the capture mode is switched from distance measurement mode to authentication mode. Then, at 130 msec, palm capture begins in authentication mode. This allows palm vein authentication to be performed by quickly acquiring a palm vein image before the palm stops moving. M may be an integer of 3 or greater.

[0111] As another switching control, the biometric authentication device 301 may switch the imaging mode at the timing when it is determined that xf is within the authenticable range. In this case, the processes of step 925 in Fig. 9C to step 930 in Fig. 9D are omitted. Then, when xf is within the authenticable range (step 924, YES), the prediction unit 312 requests the control unit 313 to switch the imaging mode of the vein sensor 311, and the biometric authentication device 301 immediately performs the processes from step 931 onwards.

[0112] In this case, too, a palm vein image can be quickly acquired and palm vein authentication can be performed before the palm stops moving.

[0113] If the imaging mode is switched at the timing when it is determined that xf is within the authentication range, a palm vein image may be acquired and palm vein authentication may be performed before the palm enters the authentication range. However, if the palm speed is sufficiently slow, it is possible to acquire a palm vein image suitable for authentication.

[0114] The configurations of the biometric authentication device 101 in Fig. 1 and the biometric authentication device 301 in Fig. 3 are merely examples, and some components may be omitted or changed depending on the application or conditions of the biometric authentication device. For example, if a vein sensor 311 is installed outside the biometric authentication device 301 in Fig. 3, the vein sensor 311 can be omitted from the configuration of the biometric authentication device 301. The vein sensor 311 may capture an image of a body part other than the palm to obtain a vein image.

[0115] The biometric authentication device 301 can also perform biometric authentication using other biometric images such as palm prints, fingerprints, and faces instead of palm vein authentication. In this case, an image sensor that acquires other biometric images is used instead of the vein sensor 311.

[0116] The flowcharts shown in FIGS. 2 and 9A to 9D are merely examples, and some of the processes may be omitted or changed depending on the configuration or conditions of the biometric authentication device.

[0117] The illumination light for distance measurement and the illumination light for authentication shown in Fig. 4 are merely examples, and the illumination light for distance measurement and the illumination light for authentication change depending on the vein sensor 311. The planar arrangement of the light source for distance measurement and the light source for authentication shown in Fig. 5 and the image for distance measurement shown in Fig. 6 are merely examples, and the planar arrangement of the light source for distance measurement and the light source for authentication and the image for distance measurement change depending on the vein sensor 311.

[0118] The switching control shown in FIGS. 7, 8, and 10 is merely an example, and the switching control changes depending on the predicted stopping position and stopping time of the palm.

[0119] Equations (1) to (13) are merely examples, and the biometric authentication device 301 may perform switching control using other calculation formulas. The prediction unit 312 may predict the stopping position and stopping time of the palm based on other movement models such as a minimum torque change model or a minimum muscle tension change model instead of the minimum jerk model.

[0120] Fig. 11 shows an example of the hardware configuration of an information processing device (computer) used as the biometric authentication device 101 in Fig. 1 and the biometric authentication device 301 in Fig. 3. The information processing device in Fig. 11 includes a CPU 1101, a memory 1102, an input device 1103, an output device 1104, an auxiliary storage device 1105, a medium drive device 1106, and a network connection device 1107. These components are hardware and are connected to each other via a bus 1108. The vein sensor 311 in Fig. 3 may be connected to the bus 1108.

[0121] The memory 1102 is a semiconductor memory such as a read-only memory (ROM) or a random access memory (RAM), and stores programs and data used in processing. The memory 1102 may function as the storage unit 315 in FIG.

[0122] The CPU 1101 (processor) operates as the prediction unit 111, the control unit 112, and the authentication unit 113 in Fig. 1 by executing a program using the memory 1102. The CPU 1101 also operates as the prediction unit 312, the control unit 313, and the authentication unit 314 in Fig. 3 by executing a program using the memory 1102.

[0123] The input device 1103 is, for example, a keyboard, a pointing device, etc., and is used for inputting instructions or information from an operator. The output device 1104 is, for example, a display device, a printer, a speaker, etc., and is used for outputting inquiries or instructions to an operator and processing results. The processing results may be authentication results indicating authentication success or authentication failure.

[0124] The auxiliary storage device 1105 is, for example, a magnetic disk device, an optical disk device, a magneto-optical disk device, a tape device, or the like. The auxiliary storage device 1105 may be a hard disk drive or a solid state drive (SSD). The information processing device stores programs and data in the auxiliary storage device 1105 and can use them by loading them into the memory 1102. The auxiliary storage device 1105 may operate as the storage unit 315 in FIG. 3.

[0125] The medium drive device 1106 drives a portable recording medium 1109 and accesses the recorded contents thereof. The portable recording medium 1109 is a memory device, a flexible disk, an optical disk, a magneto-optical disk, etc. The portable recording medium 1109 may be a CD-ROM (Compact Disk Read Only Memory), a DVD (Digital Versatile Disk), a USB (Universal Serial Bus) memory, etc. An operator can store programs and data on the portable recording medium 1109 and load them into the memory 1102 for use.

[0126] In this way, the computer-readable recording medium that stores the program and data used in the processing is a physical (non-transitory) recording medium such as memory 1102, auxiliary storage device 1105, or portable recording medium 1109.

[0127] The network connection device 1107 is a communication circuit connected to a communication network such as a wide area network (WAN) or a local area network (LAN), and performs data conversion associated with communication. The information processing device receives programs and data from external devices via the network connection device 1107, and loads them into the memory 1102 for use.

[0128] It is not necessary for the information processing device to include all of the components shown in Figure 11, and some components may be omitted depending on the purpose or conditions of the information processing device. For example, if an interface with an operator is not required, the input device 1103 and the output device 1104 may be omitted. If the portable recording medium 1109 or a communication network is not used, the medium drive device 1106 or the network connection device 1107 may be omitted.

[0129] Although the disclosed embodiments and their advantages have been described in detail, those skilled in the art may make various modifications, additions, and omissions without departing from the scope of the invention as clearly set forth in the claims.

Claims

1. A biometric authentication device, comprising: a prediction unit configured to predict a stop position where a body part of an authentication target person moving toward an imaging device stops, based on a plurality of images captured by the imaging device in a distance measurement mode; a control unit configured to switch a shooting mode of the imaging device from the distance measurement mode to an authentication mode before the body part stops at the stop position; and an authentication unit configured to perform biometric authentication on the authentication target person using an image of the body part captured by the imaging device in the authentication mode.

2. The biometric authentication device according to claim 1, wherein the prediction unit obtains a position and an acceleration of the body part at a shooting time of each of the plurality of images based on the plurality of images, and predicts the stop position from the position of the body part when the acceleration of the body part reaches a maximum based on a motion model of a human body.

3. The biometric authentication device according to claim 2, wherein the prediction unit checks whether or not the stop position is included in an authentication possible range, and when the stop position is included in the authentication possible range, predicts a stop time when the body part stops at the stop position from a time when the acceleration of the body part reaches a maximum based on the motion model; and the control unit specifies a predetermined time before the stop time based on the stop time, and switches the shooting mode of the imaging device from the distance measurement mode to the authentication mode at the predetermined time.

4. The biometric authentication device according to claim 2, wherein the prediction unit checks whether or not the stop position is included in an authentication possible range; and the control unit switches the shooting mode of the imaging device from the distance measurement mode to the authentication mode when the stop position is included in the authentication possible range.

5. The biometric authentication device according to any one of claims 1 to 4, wherein the distance measurement mode is a shooting mode for shooting the body part using illumination light for distance measurement, and the authentication mode is a shooting mode for shooting the body part using illumination light for authentication.

6. A biometric authentication method, characterized in that a computer executes a process of predicting a stop position where a body part of an authentication target person moving toward an imaging device stops based on a plurality of images captured by the imaging device in a distance measurement mode, switching a shooting mode of the imaging device from the distance measurement mode to an authentication mode before the body part stops at the stop position, and performing biometric authentication on the authentication target person using an image of the body part captured by the imaging device in the authentication mode.

7. A biometric authentication program for causing a computer to execute a process of predicting a stop position where a body part of an authentication target person moving toward an imaging device stops based on a plurality of images captured by the imaging device in a distance measurement mode, switching a shooting mode of the imaging device from the distance measurement mode to an authentication mode before the body part stops at the stop position, and performing biometric authentication on the authentication target person using an image of the body part captured by the imaging device in the authentication mode.

Images