JP2021005149A - Biometric detection device, biometric authentication device, computer program, and biometric detection method - Google Patents

Abstract

To simply detect whether or not a subject shown in a captured image is a living body.SOLUTION: A biometric detection device comprises: a captured image input unit which accepts a captured image obtained by capturing a subject; a correlation score calculation unit which calculates a correlation score representing a correlation between the captured image and a correlation calculation object image obtained by displacing a part or the whole of the captured image by a certain space; and a determination unit which determines whether or not the subject is a living body on the basis of a result of comparison between the correlation score and a predetermined threshold value.SELECTED DRAWING: Figure 2

Description

The present invention relates to a biometric detection device, a biometric authentication device, a computer program, and a biometric detection method.

Conventionally, as a biometric authentication technique used for identity verification, for example, a biometric detection device described in Patent Document 1 is known. The biological detection device described in Patent Document 1 recognizes a specific part constituting the subject from a plurality of time-continuous images of the subject photographed by the photographing means, and recognizes the recognized specific portion. The specific part information about the subject is compared with the biological information about the relevant part in the actual living body, and whether or not the subject is a living body is detected.

Japanese Unexamined Patent Publication No. 2016-81416

However, in the conventional biometric detection device described above, since it is necessary to photograph the subject for a certain period of time, it takes time to obtain the biometric detection result. In addition, since it is necessary to process a plurality of images, there are problems such as a heavy load of information processing and a large amount of data stored.

The present invention has been made in consideration of such circumstances, and an object of the present invention is to easily detect whether or not the subject in the captured image is a living body.

(1) One aspect of the present invention is a correlation between an image capture image input unit that receives an image captured by a subject and a correlation calculation target image in which the captured image and a part or all of the captured image are shifted at regular intervals. A biometric detection device including a correlation score calculation unit for calculating a correlation score indicating the above, and a determination unit for determining whether or not the subject is a living body based on the result of comparison between the correlation score and a predetermined threshold value. Is.
(2) In one aspect of the present invention, the determination unit determines that the subject is not a living body when the appearance of the correlation score having a relatively high correlation has periodicity. It is a detection device.
(3) In one aspect of the present invention, the determination unit determines whether or not the subject is a living body based on the result of comparison between the correlation score having the highest correlation and the threshold value. The biological detection device of 1).
(4) In one aspect of the present invention, the determination unit determines whether or not the subject is a living body based on the result of comparison between the average value of the correlation score and the threshold value. It is a biological detection device of.
(5) In one aspect of the present invention, the correlation calculation target image is an image obtained by shifting the captured image in either the horizontal direction or the vertical direction, according to any one of (1) to (4) above. It is a biological detection device of.
(6) In one aspect of the present invention, the correlation calculation target image is an image in which the captured image is shifted in both the horizontal direction and the vertical direction, and the biological detection according to any one of (1) to (4) above. It is a device.
(7) One aspect of the present invention relates to an acquisition condition data storage unit that stores acquisition condition data of an image captured image used for determining the threshold value, and an image pickup unit that images the subject based on the acquisition condition data. The biological detection device according to any one of (1) to (6) above, further comprising an image pickup control unit for supplying image pickup setting data.

(8) One aspect of the present invention is a correlation between a captured image input unit that receives a captured image of a subject and a correlation calculation target image in which the captured image and a part or all of the captured image are shifted at regular intervals. A correlation score calculation unit that calculates a correlation score indicating the above, a determination unit that determines whether or not the subject is a living body based on the result of comparison between the correlation score and a predetermined threshold, and the captured image are used. It is a biometric authentication device including an authentication unit that executes personal authentication processing.
(9) In one aspect of the present invention, a correlation score indicating a correlation between a personal registration image used for the personal authentication process and a correlation calculation target image in which a part or all of the personal registration image is shifted at regular intervals is calculated. The biometric authentication device according to (8) above, further comprising a threshold value determining unit that determines the threshold value based on the calculated correlation score.

(10) One aspect of the present invention includes a captured image input step of receiving an captured image of a subject in a computer, and a correlation calculation target image in which the captured image and a part or all of the captured image are shifted at regular intervals. A correlation score calculation step for calculating a correlation score showing a correlation with the subject and a determination step for determining whether or not the subject is a living body based on the result of comparison between the correlation score and a predetermined threshold are executed. It is a computer program to make it.

(11) In one aspect of the present invention, the captured image input unit receives the captured image captured by the subject, and the correlation score calculation unit receives the captured image and a part or all of the captured image. Correlation calculation based on the result of comparison between the correlation score and a predetermined threshold, the correlation score calculation step for calculating the correlation score indicating the correlation with the correlation calculation target image shifted at regular intervals, and the determination unit, the subject is a living body. It is a biological detection method including a determination step for determining whether or not there is a presence.

According to the present invention, it is possible to easily detect whether or not the subject in the captured image is a living body.

It is a block diagram which shows the structural example of the biological detection system which concerns on 1st Embodiment. It is a block diagram which shows the structural example of the biological detection apparatus which concerns on 1st Embodiment. It is a flowchart which shows the example of the procedure of the living body detection method which concerns on 1st Embodiment. It is explanatory drawing of the correlation score calculation method which concerns on 1st Embodiment. It is explanatory drawing of the correlation score calculation method which concerns on 1st Embodiment. It is a block diagram which shows the structural example of the biological detection apparatus which concerns on 2nd Embodiment. It is a flowchart which shows the example of the procedure of the living body detection method which concerns on 2nd Embodiment. It is a block diagram which shows the structural example of the biometric authentication system which concerns on 3rd Embodiment. It is a block diagram which shows the structural example of the biometric authentication apparatus which concerns on 3rd Embodiment. It is a block diagram which shows the structural example of the biometric authentication apparatus which concerns on 3rd Embodiment. It is a block diagram which shows the structural example of the biometric authentication apparatus which concerns on 4th Embodiment. It is a block diagram which shows the structural example of the biological detection apparatus which concerns on 5th Embodiment.

Hereinafter, embodiments of the present invention will be described with reference to the drawings.

[First Embodiment]
FIG. 1 is a block diagram showing a configuration example of a biological detection system according to the first embodiment. In FIG. 1, the biometric detection device 1 and the user terminals 2a and 2b communicate with each other via the communication network NW. The communication network NW is, for example, a mobile phone network, a wireless communication network such as a wireless LAN (Local Area Network), the Internet, or the like.

The user terminals 2a and 2b (hereinafter, referred to as "user terminal 2" when not particularly distinguished) may be, for example, a mobile communication terminal device such as a smartphone or a tablet-type computer (tablet PC), or may be installed. It may be a stationary communication terminal device (for example, a stationary personal computer or the like).

The user terminal 2a holds the biologically captured image Pa. The biological image Pa is an image captured by a living body as a subject. The biological image Pa may be an image captured by a camera (imaging unit) included in the user terminal 2a, or an image captured by a camera (imaging unit) separate from the user terminal 2a. You may. The user terminal 2a transmits the biometric image Pa to the biometric detection device 1.

The user terminal 2b holds the non-living image Pb. The non-living image Pb is an image captured by a non-living object as a subject. As the non-living body image Pb, for example, an image taken by printing a printed matter obtained by printing an image taken by a living body as a subject (living body image) or a living body image is displayed on a display device such as a liquid crystal display device. Examples thereof include a captured image obtained by capturing a display screen. The biological image Pb may be an image captured by a camera (imaging unit) included in the user terminal 2b, or may be an image captured by a camera (imaging unit) separate from the user terminal 2b. You may. The user terminal 2b transmits the non-living image Pb to the living body detection device 1.

The biological detection device 1 uses the biological image Pa received from the user terminal 2a as an image to be detected as a biological detection target, and detects whether or not the subject shown in the biological image Pa is a living body. Further, the biological detection device 1 uses the non-biological image Pb received from the user terminal 2b as an image to be detected as a biological detection target, and detects whether or not the subject reflected in the non-biological image Pb is a living body.

FIG. 2 is a block diagram showing a configuration example of the biological detection device according to the first embodiment. In FIG. 2, the biological detection device 1 includes a captured image input unit 11, an edge enhancement processing unit 12, a correlation score calculation unit 13, and a determination unit 14. Each function of the biometric detection device 1 is realized by executing a computer program by a CPU (Central Processing Unit) included in the biometric detection device 1. The biometric detection device 1 may be configured by using a general-purpose computer device, or may be configured as a dedicated hardware device. For example, the biometric detection device 1 may be configured by using a server computer connected to a communication network such as the Internet.

The captured image input unit 11 receives the captured image of the biological detection target. The captured image of the biological detection target is a biological captured image Pa or a non-living captured image Pb. The captured image input unit 11 outputs the received captured image of the biological detection target to the edge enhancement processing unit 12.

The edge enhancement processing unit 12 executes edge enhancement processing on the captured image of the biological detection target output from the captured image input unit 11. The edge enhancement processing unit 12 performs edge detection (contour detection) using, for example, a Sobel filter as the edge enhancement processing. An edge detection method other than the Sobel filter may be applied. For example, an edge detection method such as "Canny method", "Laplacian method", or "prewitt method" may be applied. The edge enhancement processing unit 12 outputs the edge enhancement image as a result of executing the edge enhancement processing on the captured image of the biological detection target to the correlation score calculation unit 13.

The correlation score calculation unit 13 executes the correlation score calculation process on the edge-enhanced image output from the edge-enhanced processing unit 12. In the correlation score calculation process, a correlation score showing the correlation between the edge-enhanced image and the correlation calculation target image in which a part or all of the edge-enhanced image is shifted at regular intervals is calculated.

As an example of the present embodiment, the correlation score is an error (sum of squares of luminance difference) in the overlapping region of the edge-enhanced image and the correlation calculation target image. In this case, the larger the correlation score (larger error), the lower the correlation, and the smaller the correlation score (smaller error), the higher the correlation.

Here, the correlation score calculation method will be described with reference to FIGS. 4 and 5. 4 and 5 are explanatory views of the correlation score calculation method according to the present embodiment. The examples of FIGS. 4 and 5 are examples in which palm print authentication is performed as biometric authentication. Further, as the biological detection, it is an example of detecting whether or not the subject in the captured image used for the input image for identity verification in the palm print authentication is a living body.

FIG. 4 shows an edge-enhanced image Pe. In the example of FIG. 4, the edge-enhanced image Pe has a size of 300 pixels (pixels) in the X-axis direction (horizontal direction) and 300 pixels (pixels) in the size of the Y-axis direction (vertical direction). The correlation score calculation unit 13 acquires template images Ps from the edge-enhanced image Pe. In the example of FIG. 4, the template image Ps has a size of 50 pixels in the X-axis direction (horizontal direction) and 50 pixels in the size of the Y-axis direction (vertical direction). Further, in the example of FIG. 4, an image area having the size of the template image Ps is cut out from the central portion of the edge-enhanced image Pe to be used as the template image Ps. The template image Ps is a part of the edge-enhanced image Pe.

FIG. 5 shows the relationship between the edge-enhanced image Pe and the correlation calculation target image Pt when calculating the correlation score. In the example of FIG. 5, the position where the template image Ps is shifted by 10 pixels in the X-axis direction (horizontal direction) from the original position of the template image Ps in the edge enhancement processing unit 12 (0 [pixel] in FIG. 5) (FIG. 5). Among them, the one with 10 [pixel]) is set as the first correlation calculation target image Pt_10, and the image up to the position (50 [pixel] in FIG. 5) shifted by 50 pixels in the X-axis direction (horizontal direction) from the original position. , The correlation score indicating the correlation with the edge-enhanced image Pe is calculated for each correlation calculation target image shifted by 1 pixel in the X-axis direction (horizontal direction). Therefore, as the correlation calculation target image Pt, 41 correlation calculation target images Pt_10, Pt_11, Pt_12, etc., which are shifted by 1 pixel in the X-axis direction (horizontal direction) from the correlation calculation target image Pt_10 to the correlation calculation target image Pt_50, ... -, Pt_49, Pt_50. FIG. 5 shows the first correlation calculation target image Pt_10 in which the template image Ps is shifted by 10 pixels in the X-axis direction (horizontal direction) from the original position among the 41 correlation calculation target images Pt, and the template image Ps. Correlation calculation target image Pt_20 shifted by 20 pixels in the X-axis direction (horizontal direction) from the position, correlation calculation target image Pt_30 in which the template image Ps is shifted by 30 pixels in the X-axis direction (horizontal direction) from the original position, and a template. An example is the final correlation calculation target image Pt_50 in which the image Ps is shifted from the original position by 50 pixels in the X-axis direction (horizontal direction).

The correlation score calculation unit 13 calculates the correlation score showing the correlation with the edge-enhanced image Pe for each of the 41 correlation calculation target images Pt_10, Pt_11, Pt_12, ..., Pt_49, Pt_50. Specifically, as the correlation score, for each of the 41 correlation calculation target images Pt_10, Pt_11, Pt_12, ..., Pt_49, Pt_50, the error (sum of squares of the luminance difference) in the region overlapping with the edge-enhanced image Pe. ) Is calculated.

In the example of FIG. 5, the correlation calculation target image Pt is an image in which the template image Ps is shifted in the X-axis direction (horizontal direction), but the shifting direction is not limited to this. The correlation calculation target image Pt may be an image in which the template image Ps is shifted in the Y-axis direction (vertical direction). Alternatively, the correlation calculation target image Pt may be an image in which the template image Ps is shifted in both the X-axis direction (horizontal direction) and the Y-axis direction (vertical direction).

Further, the size of the template image Ps and the image area for cutting out the template image Ps from the edge-enhanced image Pe may be determined according to the size of the edge-enhanced image Pe. The entire edge-weighted image may be used as a template image.

The explanation is returned to FIG.
The correlation score calculation unit 13 outputs the correlation score of the execution result of the correlation score calculation process to the determination unit 14.

The determination unit 14 determines whether or not the subject in the captured image of the biological detection target is a living body based on the result of comparison between the correlation score output from the correlation score calculation unit 13 and a predetermined threshold value. To do. An example of the determination method is shown below.

[Example 1 of judgment method]
In Example 1 of the determination method, the determination unit 14 determines the captured image of the biological detection target when the appearance of the correlation score having a relatively high correlation has periodicity based on the result of comparison between the correlation score and a predetermined threshold value. It is determined that the subject reflected in is not a living body. Specifically, in the example of FIG. 5, the correlation score “error (sum of squares of luminance difference)” is calculated for each of the 41 correlation calculation target images Pt_10, Pt_11, Pt_12, ..., Pt_49, and Pt_50. From the result of comparison between each of the 41 correlation scores and a predetermined threshold value, correlation scores that are less than the threshold value (correlation is relatively high) appear continuously at a certain number of pixel intervals and a certain number of times or more. In this case, it is determined that the appearance of the correlation score having a relatively high correlation has periodicity, and it is determined that the subject in the captured image of the biological detection target is not a living body. In addition, in order to allow some fluctuation as the periodicity, the interval of "(constant number of pixels) ± fluctuation width" may be applied to the determination of the periodicity.

Further, the determination unit 14 uses the result of comparison between the correlation score and a predetermined threshold value to obtain a captured image of the biological detection target except when the appearance of the correlation score having a relatively high correlation has periodicity. It may be determined that the subject in the picture is a living body.

According to Example 1 of the determination method, when the appearance of the correlation score having a relatively high correlation has periodicity based on the result of comparison between the correlation score and a predetermined threshold value, interference fringes (interference fringes) (in the captured image of the biological detection target) It can be determined that Moire) exists. Moire does not occur in the biologically captured image Pa in which the living body is captured as a subject. On the other hand, moire may occur in a non-living image Pb in which a non-living object is imaged as a subject. For example, when a printed matter is imaged with a camera as a subject, moire may occur. This is because the ink particles are regularly arranged on the printed matter, and the camera also has a structure in which the image sensor is regularly arranged. Further, when a display screen displayed on a display device such as a liquid crystal display device is taken as a subject and imaged by a camera, moire may occur. This is because the light emitting elements are regularly arranged on the display screen of the display device, and the camera also has a structure in which the image pickup elements are regularly arranged. Therefore, when moire is detected in the captured image, it can be determined that the subject in the captured image is not a living body. From this, in Example 1 of the determination method, when the appearance of the correlation score having a relatively high correlation has periodicity based on the result of comparison between the correlation score and a predetermined threshold value, the captured image of the biological detection target is displayed. It is determined that the subject in the picture is not a living body.

Generally, in a spoofing attack in biometric authentication in which an image captured by a camera is used as an input image for identity verification, an attacker displays a printed matter on which the biometric image is printed or a biometric image displayed on a liquid crystal display device or the like. In many cases, a captured image obtained by capturing the display screen displayed on the device with a camera is used. According to Example 1 of the determination method, such a spoofing attack can be prevented by detecting moire from the input image for identity verification and making the biological detection result "fail".

Further, according to Example 1 of the determination method, even if the quality of the captured image of the biological detection target differs for each user or each opportunity of biological detection, the subject reflected in the captured image of the biological detection target by the detection of moire. Can be determined not to be a living body. This means that the shooting environment such as the resolution of the camera and the brightness at the time of shooting (for example, whether or not the shooting light such as a flash is turned on), which affects the quality of the captured image to be detected by the living body, is different for each user or the living body is detected. Even if it differs from time to time, it has a special effect that the present embodiment can be applied.

[Example 2 of judgment method]
In Example 2 of the determination method, the determination unit 14 determines whether or not the subject in the captured image of the biological detection target is a living body based on the result of comparison between the correlation score having the highest correlation and a predetermined threshold value. judge. When moiré is present in the captured image, the correlation score with the highest correlation is considered to show a significantly higher correlation than the captured image without moiré. From this, in Example 2 of the determination method, as a result of comparison between the correlation score having the highest correlation and a predetermined threshold value, if there is a difference of a certain amount or more between the two and the correlation is relatively high, the subject is not a living body. Judgment is made, and if not, it is determined that the subject is a living body.

[Example 3 of judgment method]
In Example 3 of the determination method, the determination unit 14 determines whether or not the subject in the captured image of the biological detection target is a living body based on the result of comparison between the average value of the correlation score and the predetermined threshold value. To do. When moiré is present in the captured image, the average value of the correlation score is considered to show a significantly higher correlation than the captured image without moiré. From this, in Example 3 of the determination method, as a result of comparing the average value of the correlation score with the predetermined threshold value, it is determined that the subject is not a living body when the correlation is relatively high, and the subject is not. Is determined to be a living body.

The above is an explanation of an example of the determination method. The explanation is returned to FIG.
The determination unit 14 outputs a determination result of whether or not the subject in the captured image of the biological detection target is a living body.

Next, the procedure of the biological detection method according to the present embodiment will be described with reference to FIG. FIG. 3 is a flowchart showing an example of the procedure of the biological detection method according to the present embodiment.

(Step S11) The captured image input unit 11 receives the captured image of the biological detection target.

(Step S12) The edge enhancement processing unit 12 executes edge enhancement processing on the captured image to be detected by the living body.

(Step S13) The correlation score calculation unit 13 shifts the edge-enhanced image and a part or all of the edge-enhanced image at regular intervals with respect to the edge-enhanced image resulting from the execution of the edge-enhanced processing by the edge-enhanced processing unit 12. Correlation calculation A correlation score indicating the correlation with the target image is calculated.

(Step S14) Based on the result of comparison between the correlation score of the execution result of the correlation score calculation process by the correlation score calculation unit 13 and the predetermined threshold value, the determination unit 14 shows the subject in the captured image of the biological detection target. Determines whether or not is a living body.

(Step S15) The determination unit 14 outputs a determination result of whether or not the subject in the captured image of the biological detection target is a living body.

According to the first embodiment described above, it is possible to easily detect whether or not the subject in the captured image of the biological detection target is a living body. Specifically, since the biological detection can be performed only with the captured image of one biological detection target, the time required to obtain the information necessary for the biological detection (captured image of the biological detection target) can be shortened. Effects such as a small processing load and a small amount of data storage can be obtained. Therefore, the biological detection device 1 can be realized by using an information processing device having a relatively small information processing ability. For example, the biometric detection device 1 may be realized by using a smartphone, an embedded device, or the like.

The edge enhancement processing unit 12 may further perform binarization processing on the edge enhancement image as a result of executing the edge enhancement processing on the captured image to be detected by the living body. In this case, the edge enhancement processing unit 12 outputs the binarized image as a result of executing the binarization processing on the edge enhancement image to the correlation score calculation unit 13. The correlation score calculation unit 13 executes the correlation score calculation process on the binarized image output from the edge enhancement processing unit 12. When the correlation score calculation process is executed on the binarized image, the correlation score may be the sum of squares of the brightness differences as an error in the overlapping region between the binarized image and the correlation calculation target image. Alternatively, it may be the sum of the brightness differences.

[Second Embodiment]
The second embodiment is a modified example of the biological detection device 1 in the first embodiment. FIG. 6 is a block diagram showing a configuration example of the biological detection device according to the second embodiment. In FIG. 6, the parts corresponding to the parts of FIG. 2 are designated by the same reference numerals, and the description thereof will be omitted. The biological detection device 1 shown in FIG. 6 does not include an edge enhancement processing unit 12. Therefore, the correlation score calculation unit 13 executes the correlation score calculation process on the captured image of the biological detection target output from the captured image input unit 11. When the correlation score calculation process is executed for the captured image of the biological detection target, the correlation score is, for example, the sum of squares of the brightness difference as an error in the overlapping region between the captured image of the biological detection target and the correlation calculation target image. is there.

FIG. 7 is a flowchart showing an example of the procedure of the biological detection method according to the present embodiment.

(Step S11) The captured image input unit 11 receives the captured image of the biological detection target.

(Step S13) The correlation score calculation unit 13 calculates a correlation score indicating the correlation between the captured image of the biological detection target and the correlation calculation target image in which a part or all of the captured image is shifted at regular intervals.

(Step S14) Based on the result of comparison between the correlation score of the execution result of the correlation score calculation process by the correlation score calculation unit 13 and the predetermined threshold value, the determination unit 14 shows the subject in the captured image of the biological detection target. Determines whether or not is a living body.

(Step S15) The determination unit 14 outputs a determination result of whether or not the subject in the captured image of the biological detection target is a living body.

According to the second embodiment described above, since the edge enhancement process is not executed, the time required for biological detection can be shortened accordingly. Further, since the load of information processing can be reduced, the biological detection device 1 can be realized by using an information processing device having a smaller information processing ability.

[Third Embodiment]
FIG. 8 is a block diagram showing a configuration example of the biometric authentication system according to the third embodiment. In FIG. 8, the parts corresponding to the parts of FIG. 1 are designated by the same reference numerals, and the description thereof will be omitted. In FIG. 8, the biometric authentication device 5 and the user terminals 2a and 2b communicate with each other via the communication network NW. The user terminal 2a transmits the biometric image Pa to the biometric authentication device 5. The user terminal 2b transmits the non-biological image Pb to the biometric authentication device 5.

The biometric authentication device 5 uses the biometric image Pa received from the user terminal 2a as an image to be detected as a biometric image, and detects whether or not the subject reflected in the biometric image Pa is a living body. Further, the biometric authentication device 5 uses the biometric image Pa as an input image for identity verification for biometric authentication.

The biometric authentication device 5 uses the non-biological image Pb received from the user terminal 2b as an image to be detected as a biometric image, and detects whether or not the subject shown in the non-biological image Pb is a living body. Further, the biometric authentication device 5 uses the non-biometric image Pb as an input image for identity verification for biometric authentication.

9 and 10 are block diagrams showing a configuration example of the biometric authentication device according to the third embodiment.

[Structure example 1 of biometric authentication device]
A configuration example 1 of the biometric authentication device 5 according to the present embodiment will be described with reference to FIG. In FIG. 9, the parts corresponding to the parts of FIG. 2 are designated by the same reference numerals, and the description thereof will be omitted. In FIG. 9, the biometric authentication device 5 includes an authentication unit 51. The authentication unit 51 executes the personal authentication process by using the captured image (reception captured image) received from the user terminal 2 by the captured image input unit 11 as the input image for identity verification. The authentication unit 51 outputs the authentication result "the person" or "not the person" of the execution result of the person authentication process.

In the biometric authentication device 5 shown in FIG. 9, the determination unit 14 inputs a determination result of whether or not the subject shown in the reception image is a living body to the authentication unit 51. If the determination result is "living body", the authentication unit 51 executes the personal authentication process, and if not, does not execute the personal authentication process. As a result, the load of information processing by the authentication unit 51 is reduced.

According to the configuration example 1 of the biometric authentication device, when the time required for biometric authentication is shorter than the time required for biometric authentication, biometric authentication is performed as a preprocessing for biometric authentication to improve the overall processing efficiency. Can be planned.

[Structure example 2 of biometric authentication device]
A configuration example 2 of the biometric authentication device 5 according to the present embodiment will be described with reference to FIG. In FIG. 10, the same reference numerals are given to the portions corresponding to the respective parts of FIG. 2, and the description thereof will be omitted. In FIG. 10, the biometric authentication device 5 includes an authentication unit 51. The authentication unit 51 executes the personal authentication process by using the captured image (reception captured image) received from the user terminal 2 by the captured image input unit 11 as the input image for identity verification. The authentication unit 51 outputs the authentication result "the person" or "not the person" of the execution result of the person authentication process.

In the biometric authentication device 5 shown in FIG. 10, the edge enhancement processing unit 12, the correlation score calculation unit 13, and the determination unit 14 are subjected to personal authentication processing using the reception image as an input image for personal identification. The authentication result of the execution result of "is the person" or "not the person" is input from the authentication unit 51. The edge enhancement processing unit 12 executes the edge enhancement processing when the authentication result is "the person", and does not execute the edge enhancement processing when the authentication result is not. The correlation score calculation unit 13 executes the correlation score calculation process when the authentication result is "the person", and does not execute the correlation score calculation process when the authentication result is not.

When the authentication result from the authentication unit 51 is "the person", the determination unit 14 determines the result of comparison between the correlation score of the execution result of the correlation score calculation process by the correlation score calculation unit 13 and a predetermined threshold value. Based on this, it is determined whether or not the subject shown in the reception image is a living body. Next, the determination unit 14 outputs a determination result as to whether or not the subject shown in the reception image is a living body. In this determination result, if the subject shown in the reception image is a living body, the final authentication result is "the person", while if the subject shown in the reception image is not a living body, the final authentication result is obtained. "I'm not the person".

When the authentication result from the authentication unit 51 is "not the person", the determination unit 14 outputs "not the person" as the determination result (final authentication result).

According to the configuration example 2 of the biometric authentication device, the load of information processing by the edge enhancement processing unit 12, the correlation score calculation unit 13, and the determination unit 14 is reduced. Further, when the time required for biometric authentication is shorter than the time required for biometric authentication, the efficiency of the overall processing can be improved by performing biometric detection as a post-processing of biometric authentication.

The biometric authentication device 5 may be configured so that the configuration example 1 of FIG. 9 and the configuration example 2 of FIG. 10 can be arbitrarily switched.
For example, it is possible to switch which process of biometric detection or biometric authentication is executed first based on the past biometric detection result or biometric authentication result. As an example of this, the previous biometric detection result "OK (living body) or NG (not living body)" is stored, and when the previous biometric detection result is NG, the biometric authentication process is performed. The biometric detection process is executed first. This is because it is assumed that the impostor repeats fraud in the same way several times, so if the previous biometric detection result was NG, there is a high possibility that the biometric detection result will be NG again, and biometric authentication. This is because it is more efficient to execute the biometric detection process before the process.

[Fourth Embodiment]
The fourth embodiment is a modified example of the biometric authentication device 5 in the third embodiment. FIG. 11 is a block diagram showing a configuration example of the biometric authentication device according to the fourth embodiment. In FIG. 11, the parts corresponding to the parts of FIG. 9 are designated by the same reference numerals, and the description thereof will be omitted. The biometric authentication device 5 shown in FIG. 11 further includes a threshold value determination unit 71.

The threshold value determination unit 71 calculates a correlation score indicating the correlation between the personal registration image used in the personal authentication process in the authentication unit 51 and the correlation calculation target image in which a part or all of the personal registration image is shifted at regular intervals. .. The method of calculating the correlation score is the same as the method of calculating the correlation score in the correlation score calculation unit 13. The personal registration image is held in advance by the authentication unit 51. The threshold value determination unit 71 determines the threshold value used by the determination unit 14 based on the calculated correlation score. For example, the threshold may be determined based on the highest correlation score. For example, the correlation score with the highest correlation may be determined as the threshold value. For example, the threshold value may be determined based on the average value of the correlation scores. For example, the average value of the correlation score may be determined as a threshold value.

Similarly, the threshold value determination unit 71 may be provided for the biometric authentication device 5 shown in FIG.

[Fifth Embodiment]
The fifth embodiment is a modification of the biological detection device 1 in the first embodiment. FIG. 12 is a block diagram showing a configuration example of the biological detection device according to the fifth embodiment. In FIG. 12, the parts corresponding to the parts of FIG. 2 are designated by the same reference numerals, and the description thereof will be omitted. The biometric authentication device 5 shown in FIG. 12 further includes an acquisition condition data storage unit 81 and an imaging control unit 82.

The acquisition condition data storage unit 81 stores the acquisition condition data of the captured image used for determining the threshold value used by the determination unit 14. The acquisition condition data is data indicating a shooting environment such as the resolution of the camera and the brightness at the time of shooting (for example, whether or not a shooting light such as a flash is turned on) that affects the quality of the captured image.

The imaging control unit 82 supplies imaging setting data to a camera (imaging unit) that images a subject based on the acquisition condition data stored in the acquisition condition data storage unit 81. The imaging setting data is transmitted to, for example, a user terminal 2 provided with a camera. As a result, the user terminal 2 sets the acquisition conditions of the captured image in its own camera based on the imaging setting data.

The biometric detection device 1 shown in FIG. 6 may also be provided with the acquisition condition data storage unit 81 and the imaging control unit 82.

Although the embodiments of the present invention have been described in detail with reference to the drawings, the specific configuration is not limited to this embodiment, and design changes and the like within a range not deviating from the gist of the present invention are also included.

In the above-described embodiment, palmprint authentication is taken as an example, but biometric authentication using an captured image can be applied. For example, it can be applied to fingerprint authentication and face authentication.

Further, in the above-described embodiment, it has been described by taking as an example that it is detected whether or not the subject in the captured image used for the input image for identity verification is a living body in biometric authentication such as palm print authentication. However, it is not limited to this. The captured image of the target for detecting whether or not the subject is a living body is not limited to the captured image used for biometric authentication, and can be applied to any captured image.

Further, a computer program for realizing the functions of the above-described devices may be recorded on a computer-readable recording medium, and the program recorded on the recording medium may be read by the computer system and executed. The "computer system" referred to here may include hardware such as an OS and peripheral devices.
The "computer-readable recording medium" is a flexible disk, a magneto-optical disk, a ROM, a writable non-volatile memory such as a flash memory, a portable medium such as a DVD (Digital Versatile Disc), and a built-in computer system. A storage device such as a hard disk.

Further, the "computer-readable recording medium" is a volatile memory (for example, DRAM (Dynamic)) inside a computer system that serves as a server or client when a program is transmitted via a network such as the Internet or a communication line such as a telephone line. It also includes those that hold the program for a certain period of time, such as Random Access Memory)).
Further, the program may be transmitted from a computer system in which this program is stored in a storage device or the like to another computer system via a transmission medium or by a transmission wave in the transmission medium. Here, the "transmission medium" for transmitting a program refers to a medium having a function of transmitting information, such as a network (communication network) such as the Internet or a communication line (communication line) such as a telephone line.
Further, the above program may be for realizing a part of the above-mentioned functions. Further, a so-called difference file (difference program) may be used, which can realize the above-mentioned functions in combination with a program already recorded in the computer system.

1 ... Biometric detection device, 2a, 2b ... User terminal, 11 ... Captured image input unit, 12 ... Edge enhancement processing unit, 13 ... Correlation score calculation unit, 14 ... Judgment unit, 5 ... Biometric authentication device, 51 ... Authentication unit, 71 ... Threshold determination unit, 81 ... Acquisition condition data storage unit, 82 ... Image control unit, NW ... Communication network

Claims (11)

An image input unit that receives an image of the subject,
A correlation score calculation unit that calculates a correlation score indicating a correlation between the captured image and a correlation calculation target image in which a part or all of the captured image is shifted at regular intervals.
A determination unit that determines whether or not the subject is a living body based on the result of comparison between the correlation score and a predetermined threshold value.
A biological detection device equipped with. The determination unit determines that the subject is not a living body when the appearance of the correlation score having a relatively high correlation has periodicity.
The biological detection device according to claim 1. The determination unit determines whether or not the subject is a living body based on the result of comparison between the correlation score having the highest correlation and the threshold value.
The biological detection device according to claim 1. The determination unit determines whether or not the subject is a living body based on the result of comparison between the average value of the correlation score and the threshold value.
The biological detection device according to claim 1. The correlation calculation target image is an image obtained by shifting the captured image in either the horizontal direction or the vertical direction.
The biometric detection device according to any one of claims 1 to 4. The correlation calculation target image is an image obtained by shifting the captured image in both the horizontal direction and the vertical direction.
The biometric detection device according to any one of claims 1 to 4. An acquisition condition data storage unit that stores acquisition condition data of the captured image used for determining the threshold value, and
An imaging control unit that supplies imaging setting data to an imaging unit that images the subject based on the acquisition condition data is further provided.
The biometric detection device according to any one of claims 1 to 6. An image input unit that receives an image of the subject,
A correlation score calculation unit that calculates a correlation score indicating a correlation between the captured image and a correlation calculation target image in which a part or all of the captured image is shifted at regular intervals.
A determination unit that determines whether or not the subject is a living body based on the result of comparison between the correlation score and a predetermined threshold value.
An authentication unit that executes personal authentication processing using the captured image,
A biometric authentication device equipped with. A correlation score showing the correlation between the personal registration image used for the personal authentication process and the correlation calculation target image in which a part or all of the personal registration image is shifted at regular intervals is calculated, and based on the calculated correlation score. A threshold value determining unit for determining the threshold value is further provided.
The biometric authentication device according to claim 8. On the computer
An image input step that accepts an image of the subject,
A correlation score calculation step for calculating a correlation score indicating a correlation between the captured image and a correlation calculation target image in which a part or all of the captured image is shifted at regular intervals.
A determination step for determining whether or not the subject is a living body based on the result of comparison between the correlation score and a predetermined threshold value.
A computer program to run. The captured image input unit receives the captured image of the subject, and the captured image input step.
A correlation score calculation step in which the correlation score calculation unit calculates a correlation score indicating a correlation between the captured image and a correlation calculation target image in which a part or all of the captured image is shifted at regular intervals.
A determination step in which the determination unit determines whether or not the subject is a living body based on the result of comparison between the correlation score and a predetermined threshold value.
Biometric detection method including.

Images