JP6648634B2 - Iris authentication device and iris authentication program - Google Patents

Description

  The present invention relates to an iris authentication device and an iris authentication program.

  The iris pattern is suitable for use in personal authentication because it uniquely represents the characteristics of a living body of an individual and can be authenticated without directly touching the device. However, when an iris pattern is used for personal authentication in a device that performs authentication in a variety of environments, such as a mobile terminal device, the authentication can be performed appropriately because the ambient light is reflected in the eye image used for iris authentication. It may not be possible.

In order to cope with the above problem, there is a technique for determining that the iris authentication cannot be properly performed due to the surrounding light reflected on the image of the eye. In this technique, the luminance characteristics of an eye image photographed using visible light illumination are compared with the luminance characteristics of an eye image photographed without using visible light illumination. If the difference between the luminance characteristic of the eye image captured using visible light illumination and the luminance characteristic of the eye image captured without visible light illumination is small, iris authentication is performed using the eye image. It is determined that it cannot be performed properly. If the difference between the luminance characteristics of the eye images using visible light illumination, and luminance characteristics of the eye images taken without using visible light illumination is small, it was taken without using visible light illumination eye There are many reflections of ambient light etc. on the image.

JP 2009-187375 A

  However, even if there is much reflection of ambient light etc. on the image of the entire eye, if the reflection on the iris part is less than that on the part other than the iris part, the iris authentication is performed. Can be done properly. In the above technology, since the luminance feature of the image of the entire eye is used, it is not possible to properly perform iris authentication using the image of the eye even when the reflection in the iris portion is small. Misjudgment may be performed.

  As one aspect of the present invention, it is an object of the present invention to make it possible to appropriately perform iris authentication using an image of an eye when the image of the eye is less reflected on the iris.

  In one embodiment, the first region dividing unit divides a first region including an iris of a first image obtained by irradiating infrared rays and capturing an eye of an iris authentication target into a plurality of first divided regions. The second region dividing unit converts a second region corresponding to the first region of the second image obtained by photographing the eye without irradiating infrared light into a plurality of second divided regions each corresponding to each of the plurality of first divided regions. Divided into The weight setting unit sets a weight value determined for each of the plurality of first divided regions based on whether or not the first divided region corresponds to a divided region including an iris. The divided region selecting unit is configured to determine each of the first representative values representing the luminance values in each of the first divided regions and the luminance value in each of the second divided regions corresponding to the position of each of the plurality of first divided regions. The first divided area having a large degree of difference from each of the second representative values representative of is selected. The iris authentication unit determines that the first image in which the sum of the weight values set in the selected first divided region is equal to or larger than the threshold value can be used for iris authentication.

  As one aspect, when the reflection of an eye image on the iris is small, it is possible to appropriately perform iris authentication using the eye image.

It is a block diagram showing an example of an important section function of an iris authentication device concerning an embodiment. FIG. 2 is a block diagram illustrating an example of a hardware configuration of the iris authentication device according to the embodiment. It is a conceptual diagram for explaining the outline of the iris authentication processing concerning an embodiment. 9 is a flowchart illustrating an example of the flow of an iris authentication process according to the embodiment. 6 is a flowchart illustrating an example of a flow of an iris authentication availability determination process according to the embodiment. It is a conceptual diagram showing an example of the 1st picture concerning an embodiment. It is a conceptual diagram showing an example of the 2nd picture concerning an embodiment. It is a conceptual diagram showing an example of the 1st division field concerning an embodiment. It is a conceptual diagram showing an example of the 2nd division field concerning an embodiment. It is a conceptual diagram showing an example of the weight value concerning an embodiment. It is a conceptual diagram for explaining selection of the 1st division field concerning an embodiment. It is a conceptual diagram showing an example of the 1st division field concerning an embodiment. It is a conceptual diagram showing an example of the 2nd division field concerning an embodiment. It is a conceptual diagram showing an example of the weight value concerning an embodiment. It is a conceptual diagram for explaining selection of the 1st division field concerning an embodiment.

  Hereinafter, an example of an embodiment will be described in detail with reference to the drawings.

  The iris authentication device 10 shown in FIG. 1 includes an image acquisition unit 21, an infrared irradiation unit 22, a first region division unit 23, a second region division unit 24, a weight setting unit 25, a divided region selection unit 26, and iris authentication propriety determination. Part 27 is included. The image acquisition unit 21 captures an image of the user's eyes, and the infrared irradiation unit 22 irradiates infrared rays to the user's eyes.

  The first region dividing unit 23 divides the first region including the iris of the first image captured by the image acquiring unit 21 by irradiating infrared rays by the infrared irradiating unit 22 into a plurality of first divided regions. The second region dividing unit 24 converts a second region corresponding to the first region of the second image captured by the image acquiring unit 21 without irradiating infrared light into a plurality of first regions corresponding to each of the plurality of first divided regions. It is divided into a second divided area. The weight setting unit 25 is determined based on whether or not each of the plurality of first divided regions corresponds to a divided region including an iris, and sets a weight value with a larger weight for a divided region having a higher iris ratio. .

  The divided region selection unit 26 selects a first divided region in which the degree of difference between each of the first representative values and each of the second representative values is large. The first representative value is a value representing a feature of each of the first divided regions, and is determined using a luminance value in each of the first divided regions. As the first representative value, the average value of the luminance values of the plurality of pixels in the first divided area, the intermediate value of the luminance values of the plurality of pixels in the first divided area, or the average value of the plurality of pixels in the first divided area The maximum brightness value can be used. The plurality of pixels may be all pixels in the first divided region, or may be pixels sampled from the first divided region according to a predetermined rule.

  The second representative value is a value representing each feature of the second divided region, and is determined using the luminance value in each second divided region, similarly to the first divided region. As the second representative value, the average value of the luminance values of the pixels in the second divided region, the median value of the luminance values of the pixels in the second divided region, or the The maximum value of the luminance values of a plurality of pixels in the two divided areas can be used. The plurality of pixels may be all pixels in the second divided area, or may be pixels sampled from the second divided area according to a predetermined rule. The iris authentication availability determination unit 27 determines that the first image in which the sum of the weight values set in the selected first divided area is equal to or larger than the threshold is usable for iris authentication.

  The fact that the degree of difference between the first representative value and the corresponding second representative value is large means that reflection in the first divided area is small. When the reflection is small, each of the first representative values of the first image captured by irradiating the infrared ray is the second representative value of the second representative value corresponding to each of the first representative values of the second image captured without the infrared ray. Because each is larger. On the other hand, for example, when an object in front of the user appears in the eyes of the user, the object is not irradiated with infrared rays. Therefore, the degree of difference between the first representative value of the first divided area where the reflection of the object exists and the second representative value of the second divided area at the corresponding position is small.

  As an example, as shown in FIG. 2, the iris authentication device 10 includes a CPU (Central Processing Unit) 31, which is an example of a processor, a primary storage unit 32, a secondary storage unit 33, an external interface 34, an infrared light 35, and an infrared camera. 36 and a display 37. The CPU 31, the primary storage unit 32, the secondary storage unit 33, the external interface 34, the infrared light 35, the infrared camera 36, and the display 37 are mutually connected via a bus 39.

  The primary storage unit 32 is, for example, a volatile memory such as a RAM (Random Access Memory). The secondary storage unit 33 is a non-volatile memory such as a hard disk drive (HDD) or a solid state drive (SSD).

  The secondary storage unit 33 includes a program storage area 33A and a data storage area 33B. The program storage area 33A stores a program such as an iris authentication program, for example. The data storage area 33B stores, for example, intermediate data generated during the execution of the iris authentication program.

  The CPU 31 reads the iris authentication program from the program storage area 33A and expands the iris authentication program in the primary storage unit 32. The CPU 31 operates as the first region dividing unit 23, the second region dividing unit 24, the weight setting unit 25, the divided region selecting unit 26, and the iris authentication availability determining unit 27 in FIG. 1 by executing the iris authentication program. Note that a program such as an iris authentication program may be stored in an external server, and may be developed in the primary storage unit 32 via a network. Further, a program such as an iris authentication program may be stored in a non-temporary recording medium such as a DVD (Digital Versatile Disc), and may be developed in the primary storage unit 32 via a recording medium reading device.

  The infrared light 35 is an example of the infrared irradiator 22 and irradiates infrared light so as to illuminate the user's eyes. The infrared camera 36 is an example of the image acquisition unit 21 and is a camera having sensitivity to both infrared light and natural light. The infrared camera 36 captures images of a user's eye illuminated by the infrared light 35 and a user's eye not illuminated by the infrared light 35, and data of the captured image is stored in, for example, a secondary storage. The data is stored in the data storage area 33B of the unit 33. When the iris pattern is registered in the iris authentication device 10, the user's eyes to be photographed are set in advance to either the right eye or the left eye, and the set eyes are photographed by the infrared camera 36.

  The display 37 displays, for example, an image of the user's eye before being photographed or an image of the photographed user's eye, a result of determining whether or not iris authentication is possible, and an instruction to the user so that the user can confirm the display. I do. An external device is connected to the external interface 34. The external interface 34 controls transmission and reception of various information between the external device and the CPU 31. The example in which the infrared light 35, the infrared camera 36, and the display 37 are included in the iris authentication device 10 has been described. However, all or a part of the infrared light 35, the infrared camera 36, and the display 37 may be an external device connected via the external interface 34.

  The iris authentication device 10 may be, for example, a smartphone, but the present embodiment is not limited to this. For example, the iris authentication device 10 may be a portable device such as a tablet, a digital camera, or a portable game device. In addition, a part or all of the iris authentication device 10 may be, for example, a computer arranged via a network, separated from the infrared light 35, the infrared camera 36, the display 37, and the like.

  When the computer arranged via the network is the iris authentication device 10, the iris authentication program is stored in a server as the computer arranged via the network. A first image and a second image are acquired by an information terminal including an infrared light 35, an infrared camera 36, a display 37, and the like. The server performs iris authentication processing using the first image and the second image transmitted from the information terminal, and transmits a determination result of iris authentication availability, an instruction to the user, a determination result of iris authentication, and the like from the server to the information terminal. .

  Next, the outline of the operation of the iris authentication device 10 will be described. In the present embodiment, as illustrated in FIG. 3, the CPU 31 obtains a first image 51 </ b> A obtained by irradiating an infrared ray on the user's eyes with the infrared light 35 and photographing the user's eyes with the infrared camera 36. Further, the CPU 31 obtains the second image 51B obtained by photographing the user's eyes with the infrared camera 36 without irradiating infrared light. The CPU 31 extracts the first region including the iris of the first image 51A with the extraction unit 61A, and extracts the second region including the iris of the second image 51B with the extraction unit 61B.

  The CPU 31 divides the first region into a plurality of first divided regions by the dividing unit 62A, and divides the second region into a plurality of second divided regions each corresponding to each of the plurality of first divided regions by the dividing unit 62B. Divided into The CPU 31 sets, in the setting unit 64, a weight value determined based on whether or not each of the plurality of first divided regions corresponds to a divided region including an iris. For example, as illustrated in FIG. 8, a weight value of 0.1 is set for the first divided region including the center of the pupil 82A and the first divided region on the outer periphery of the first region 71A, and includes the pupil 82A and the iris 81A. 0.3 is set in the first divided region, and 1 is set in the first divided region including only the iris 81A.

  The CPU 31 obtains each of the first representative values representing the luminance values of the plurality of pixels in each of the first divided regions by the obtaining unit 63A, and obtains each of the first representative values corresponding to each of the plurality of first divided regions by the obtaining unit 63B. Each of the second representative values representing the luminance values of a plurality of pixels in each of the second divided regions to be obtained is obtained. As described above, when the first representative value is the average value of the luminance values of all the pixels in each first divided region, the second representative value is the average of the luminance values of all the pixels in each second divided region. It can be a value.

The CPU 31 causes the selector 65 to determine a large degree of difference based on the degree of difference between the first representative value of the first divided area and the second representative value of the second divided area at a position corresponding to the first divided area. The selection of the first divided region is executed for all the first divided regions of the first region. For example, the degree of the difference may be a difference between the first representative value of the first divided region and the second representative value of the second divided region at a position corresponding to the first divided region. That is, when the difference between the first representative value and the second representative value is large, the degree of the difference is large. In this case, as exemplified in Expression (1), if the difference between the first representative value and the second representative value exceeds a predetermined value, the first divided area is selected.
First representative value−second representative value> predetermined value (1)

Although the example in which the degree of difference is the difference between the first representative value and the second representative value has been described, the present embodiment is not limited to this. For example, the degree of the difference may be a ratio between the first representative value and the second representative value. That is, when the ratio of the first representative value to the second representative value is large, the degree of difference is large. In this case, as exemplified in Expression (2), if the ratio of the first representative value to the second representative value exceeds a predetermined value, the first divided area is selected.
First representative value / second representative value> predetermined value (2)

  Since the first image is photographed by irradiating infrared rays and the second image is photographed without irradiating infrared rays, the first representative value, which is a representative value of the luminance value in the first divided region, is normally used. Is larger than a second representative value which is a representative value of the luminance values in the second divided area. Therefore, the left side of Expression (1) is a positive value. However, in order to deal with an exceptional state, if the left side of Expression (1) is a negative value, the first divided region may not be selected. This is because it is unlikely that an exceptional state will occur in a divided area with less reflection.

  As described above, since the first image is shot by irradiating infrared rays and the second image is shot without irradiating infrared rays, the left side of Expression (2) usually has a value larger than 1. However, in order to deal with an exceptional state, when the left side of Expression (2) is smaller than 1, the first divided region may not be selected. This is because it is unlikely that an exceptional state will occur in a divided area with less reflection.

  The CPU 31 determines that the first image 51A can be used for iris authentication when the sum of the weight values set for the selected first divided region is equal to or greater than the threshold value.

  As described above, the fact that the degree of difference between the first representative value and the corresponding second representative value is large means that reflection in the first divided area is small. On the other hand, the degree of difference between the first representative value of the first divided region where the reflection is present and the second representative value of the second divided region at the corresponding position is small.

  In addition, since the weight value determined based on whether or not it corresponds to the divided region including the iris is set for each of the first divided regions, the sum of the weight values of the first divided regions having a large degree of difference is A large value indicates that the reflection is small and the number of the first divided regions including the iris is large. Therefore, if the sum of the weight values is equal to or greater than the threshold, it is determined that the first image 51A can be used for iris authentication.

  Note that the extraction unit 61A and the extraction unit 61B may be configured by one extraction unit, and the extraction of the first region from the first image and the extraction of the second region from the second image may be sequentially performed. Further, the dividing unit 62A and the dividing unit 62B may be configured by one dividing unit, and the division of the first region into the first divided region and the division of the second region into the second divided region may be sequentially performed. Further, the acquisition unit 63A and the acquisition unit 63B are configured by one acquisition unit, and the acquisition of the first representative value from the first divided region and the acquisition of the second representative value from the second divided region are performed by one acquisition unit. You may do so.

  Next, the operation of the iris authentication device 10 will be described. FIG. 4 illustrates an iris authentication process. For example, when the user turns on the power of the iris authentication device 10, the CPU 31 performs an iris authentication availability determination process of determining whether or not the captured image can be used for iris authentication in step 101. Details of the iris authentication availability determination processing will be described later. The CPU 31 determines in step 102 whether or not the determination result in step 101 indicates that the captured image can be used for iris authentication. If the determination in step 102 is denied, that is, it must be available. If so, the process returns to step 101.

  If the determination in step 102 is affirmative, that is, if it is available, the CPU 31 executes iris authentication in step 103. Existing technology such as pattern matching with a previously registered iris pattern can be applied to iris authentication. In step 104, the CPU 31 determines the result of the iris authentication in step 103. If the determination in step 103 is denied, that is, if the authentication is not passed, the process returns to step 101. If the determination in step 103 is affirmative, that is, if the authentication has passed, the iris authentication processing ends.

  FIG. 5 exemplifies the iris authentication availability determination processing in step 101 of FIG. In step 141, the CPU 31 irradiates the infrared light 35 and shoots the image with the infrared camera 36, thereby acquiring the first image of the eye on the preset side as described above.

  In step 142, the CPU 31 determines whether the first image includes an eye image using an existing technique such as pattern matching. If the determination in step 142 is negative, that is, if the user has turned his / her eyes away from the lens of the infrared camera 36, the CPU 31 returns to step 141.

  If the determination in step 142 is affirmative, that is, if the first image includes the eye image, the CPU 31 determines in step 143 that the first area 71A including the iris 81A has the first image as illustrated in FIG. 6A. Extract from The CPU 31 acquires the image of the eye on the same side as the first image as the second image by photographing the second image with the infrared camera 36 without irradiating the infrared light 35 in step 144. In step 145, the CPU 31 determines whether the second image includes an eye image using an existing technique such as pattern matching. If the determination in step 145 is negative, that is, if the user has turned his / her eyes away from the lens of the infrared camera 36, the CPU 31 returns to step 141.

  Note that, in steps 141 and 144, an example in which one eye of the user is imaged has been described, but the present embodiment is not limited to this. Both eyes of the user may be photographed, and the following processing may be performed on the image of each eye.

  If the determination in step 145 is affirmative, in step 146, the CPU 31 extracts, from the second image, a second area 71B including the iris 81B and corresponding to the image of the first area 71A, as illustrated in FIG. 6B. I do. At step 147, the CPU 31 divides the first area 71A into N (N is an integer of 2 or more) first divided areas, and divides the first area 71A into the first divided areas by using the same division pattern. , The second region 71B is divided into N second divided regions corresponding to each of the first divided regions.

  FIGS. 7A and 7B show an example in which the first area 71A and the second area 71B are each divided into 25 × 5 × 5 rectangles. However, the present embodiment is not limited to this. The number of divisions may be more or less than 25. Also, the shape of each of the first divided region and the second divided region may be a triangle, a hexagon, or the like, instead of a rectangle. However, the shapes of the first divided region and the second divided region are the same.

  In step 148, the CPU 31 sets a weight value determined based on whether or not each of the first divided regions corresponds to a divided region including the iris. Specifically, first, information on the center position of the pupil, the outer periphery of the pupil, and the outer periphery of the iris is acquired from the first region 71A by using an existing technique such as Hough transform or pattern matching.

  Next, the pupil and the iris are specified based on the acquired information on the center position of the pupil, the outer periphery of the pupil, and the outer periphery of the iris, and the first pupil and the iris are determined according to the ratio of the area of the iris included in the first divided region. A weight value is set for the divided area. Therefore, even if the size and position of the iris to be photographed and the size and position of the pupil are different depending on the photographing condition or the photographing condition, the first divided region in which the ratio of the area of the iris that has a large influence on the iris recognition is large. Can be set to a large weight value.

  As described above, in FIG. 8, the weight value 0.1 is set in the first divided region including the center of the pupil 82A and the first divided region on the outer periphery of the first region 71A, and the first divided region including the pupil 82A and the iris 81A is set. An example is shown in which 0.3 is set in one divided area and 1 is set in the first divided area including only the iris 81A. However, the present embodiment is not limited to this. For example, when the ratio of the area occupied by the iris 81A in the first divided region is 100%, a weight value of 1 may be set in the first divided region. If the first divided region includes the iris 81A and the pupil 82A, and the ratio of the area occupied by the iris 81A is 50% or more, a weight value of 0.3 may be set in the first divided region. Further, when the first divided region includes a white eye other than the iris 81A and the pupil 82A, a weight value of 0.1 may be set in the first divided region.

  In step 149, the CPU 31 determines a difference between each of the first representative values of each of the plurality of first divided regions and each of the second representative values of each of the plurality of second divided regions. A first divided area having a high degree is selected. In detail, first, an average value of the luminance values of all the pixels in each first divided area, which is an example of the first representative value, is obtained, and the average value of the luminance values in each second divided area, which is an example of the second representative value, is obtained. The average value of the luminance values of all pixels is obtained.

Next, for example, as shown in Expression (3), the average value of the luminance values of all the pixels in the first divided region and the luminance of all the pixels in the second divided region at a position corresponding to the first divided region When the difference between the value and the average value exceeds a predetermined value, the selection of the first divided region is executed for all the first divided regions. In the example of FIG. 9, the selected first divided area is represented by 1, and the unselected first divided area is represented by 0.
Average value of luminance values of all pixels in first divided area−average value of luminance values of all pixels in second divided area> predetermined value (3)

  When the reflection 83A exists, as described above, the average value of the luminance value of the first divided region including the reflection 83A and the average value of the luminance value of the second divided region at a position corresponding to the first divided region And the difference is small. Therefore, as illustrated in FIG. 9, the first divided region in which the ratio of the reflection 83A is large is not selected.

Note that the degree of difference is determined by the average value of the luminance values of all the pixels in the first divided region and the average value of the luminance values of all the pixels in the second divided region at positions corresponding to the respective first divided regions. Have been described, but the present embodiment is not limited to this. For example, as shown in Expression (4), the degree of the difference is determined by each of the average values of the luminance values of all the pixels in the first divided region and the average value of the second divided region at a position corresponding to each of the first divided regions. May be the ratio to each of the average values of the luminance values.
Average value of luminance values of all pixels in the first divided region / average luminance value of all pixels in the second divided region> predetermined value (4)

In step 150, the CPU 31 determines a threshold value T used to determine whether the first image can be used for iris authentication. More specifically, as illustrated in Expression (5), the weight values of all the first divided regions illustrated in FIG. 8 are summed, and the sum is multiplied by the required judgment rate n. The determination required rate n is the ratio of the area of the iris that is not reflected to the entire area of the iris, which is determined in the iris authentication possible performance of the iris authentication in step 103 of FIG.
T = sum of weight values of all first divided areas × n (5)

In step 151, the CPU 31 determines whether the first image can be used for iris authentication. Specifically, as illustrated in Expression (6), it is determined whether or not the sum of the weight values set for the selected first divided region is equal to or greater than a threshold T.
Sum of weight values set for the selected first divided area ≧ T (6)

  If the determination in step 151 is affirmative, that is, if the first image can be used for iris authentication, the CPU 31 sets 1 to the flag F in step 152, and ends the iris authentication availability determination processing. If the determination in step 151 is negative, that is, if the first image is not usable for iris authentication, the flag F is set to 0, and the iris authentication availability determination processing ends. The flag F is a flag representing the result of the iris authentication availability determination, and is included in, for example, the data storage area 33 </ b> B of the secondary storage unit 33.

  The flag F is used in step 102 of FIG. 4 to determine whether the first image can be used for iris authentication. Specifically, the CPU 31 determines whether the flag F is set to 0 or 1 in step 102 of FIG. When the flag F is set to 0, it is determined that the first image is not usable for iris authentication, and when the flag F is set to 1, it is determined that the first image is usable for iris authentication. I do. In step 103, the CPU 31 uses the first divided region represented by 1 illustrated in FIG. 12, that is, the first divided region in which the degree of difference between the first representative value and the corresponding second representative value is large. Perform iris authentication.

  For example, the sum of the weight values of all the first divided regions illustrated in FIG. 8 is 7.4 (= 0.1 × 18 + 0.3 × 2 + 1 × 5). Assuming that the required judgment rate n is 0.5, the threshold T is 3.7 (= 7.4 × 0.5). Among the weight values exemplified in FIG. 8, the weight value is represented by 1 in FIG. 9, that is, the sum of the weight values of the selected first divided region is 5.0 (= 0.1 × 17 + 0.3 × 1 + 1 × 3), which is greater than or equal to the threshold value T (= 3.7). Therefore, the CPU 31 determines in step 151 in FIG. 5 that the first image can be used for iris authentication in the examples of FIGS. 6A to 9.

  FIGS. 10A and 10B show a first region 71C and a second region in which the ratio of the areas 83C and 83D reflected on the irises 81C and 81D in the first image and the second image is larger than in FIGS. 6A and 6B. 71D is exemplified. FIG. 11 illustrates a weight value set for the first divided region in FIG. 10A. The determination of the weight value is the same as described above, and the description is omitted. In FIG. 12, the selected first divided area is represented by 1 and the unselected first divided area is represented by 0. The selection of the first divided region is the same as described above, and thus the description is omitted.

  The sum of the weight values of all the first divided regions in FIG. 11 is 7.6 (= 0.1 × 17 + 0.3 × 3 + 1 × 5). Assuming that the required judgment rate n is 0.5, the threshold T is 3.8 (= 7.6 × 0.5). Among the weight values exemplified in FIG. 11, the weight value is represented by 1 in FIG. 12, that is, the sum of the weight values of the selected first divided area is 3.3 (= 0.1 × 17 + 0.3 × 2 + 1 × 1), which is smaller than the threshold value T (= 3.8). Therefore, the CPU 31 determines in step 151 of FIG. 5 that the first image is not usable for iris authentication in the examples of FIGS. 10A to 12.

  Note that the present embodiment is not limited to the order of the processes illustrated in FIGS. 4 and 5. The order of the processing can be changed as appropriate.

  As described above, in the present embodiment, the CPU 31 divides the first region including the iris of the first image captured by irradiating infrared rays into a plurality of first divided regions. The CPU 31 divides the second area corresponding to the first area of the second image captured without irradiating infrared light into a plurality of second divided areas each corresponding to each of the plurality of first divided areas. The CPU 31 sets a weight value determined for each of the plurality of first divided regions based on whether or not the first divided region corresponds to a divided region including the iris. The CPU 31 represents each of the first representative values representing the luminance values in each of the first divided regions and the luminance values in each of the second divided regions corresponding to the positions of the plurality of first divided regions. A first divided region having a large degree of difference from each of the second representative values is selected. The CPU 31 determines that the first image in which the sum of the weight values set in the selected first divided area is equal to or larger than the threshold value can be used for iris authentication.

  Thus, in the present embodiment, when the eye image used for iris authentication has a lot of reflection on the iris that has a large influence on the iris authentication, it is possible to appropriately perform the iris authentication using the eye image. A determination is made that it is not possible. On the other hand, when the reflection on the iris is small, it is possible to determine that the iris authentication can be appropriately performed using the image of the eye. Therefore, when the reflection of the eye image on the iris is small, the iris authentication can be appropriately performed using the eye image.

  Regarding each of the above embodiments, the following supplementary notes are further disclosed.

(Appendix 1)
A first region dividing unit that divides a first region including the iris of a first image obtained by irradiating infrared rays and capturing an eye of an iris authentication target into a plurality of first divided regions;
Dividing a second region corresponding to the first region of the second image obtained by photographing the eye without irradiating infrared light into a plurality of second divided regions each corresponding to each of the plurality of first divided regions; A two-region dividing unit;
A weight setting unit that sets a weight value determined based on whether or not each of the plurality of first divided regions corresponds to a divided region including an iris;
Each of the first representative values representing the luminance value in each of the first divided regions and the luminance value in each of the second divided regions corresponding to the position of each of the plurality of first divided regions. A division area selection unit that selects the first division area having a large degree of difference from each of the second representative values;
An iris authentication availability determination unit that determines that the first image whose sum of the weight values set in the selected first divided area is equal to or greater than a threshold is usable for iris authentication;
An iris authentication device, including:
(Appendix 2)
The degree of the difference is
The magnitude of the difference obtained by subtracting the second representative value from the first representative value, or the magnitude of the ratio of the first representative value to the second representative value.
The iris authentication device according to attachment 1.
(Appendix 3)
Each of the first representative value and the second representative value is a maximum value, an average value, or a median value of luminance values of a plurality of pixels in each divided region.
The iris authentication device according to attachment 1 or 2.
(Appendix 4)
The weight setting unit sets a weight value in the order of the first divided region including the center of the pupil, the first divided region including the pupil and the iris, and the first divided region including the iris.
The iris authentication device according to any one of supplementary notes 1 to 3.
(Appendix 5)
An infrared irradiating unit that irradiates infrared rays to the eyes of the iris authentication target,
An image acquisition unit that captures the eye with the infrared irradiation unit irradiating infrared light, and captures the eye without irradiating infrared light.
Further comprising,
The iris authentication device according to any one of supplementary notes 1 to 4.
(Appendix 6)
Dividing a first region including an iris of a first image obtained by irradiating infrared rays with an eye of an iris authentication target into a plurality of first divided regions;
Dividing a second region corresponding to the first region of the second image obtained by photographing the eye without irradiating infrared light into a plurality of second divided regions each corresponding to each of the plurality of first divided regions;
Setting a weight value determined based on whether or not each of the plurality of first divided regions corresponds to a divided region including an iris;
Each of the first representative values representing the luminance value in each of the first divided regions and the luminance value in each of the second divided regions corresponding to the position of each of the plurality of first divided regions. Selecting the first divided region having a large degree of difference from each of the second representative values;
It is determined that the first image in which the sum of the weight values set in the selected first divided area is equal to or larger than a threshold value can be used for iris authentication,
A program that causes a computer to execute iris authentication processing.
(Appendix 7)
The degree of the difference is
The magnitude of the difference obtained by subtracting the second representative value from the first representative value, or the magnitude of the ratio of the first representative value to the second representative value.
Appendix 6 program.
(Appendix 8)
Each of the first representative value and the second representative value is a maximum value, an average value, or a median value of luminance values of a plurality of pixels in each divided region.
The program according to Appendix 6 or Appendix 7.
(Appendix 9)
Setting a weight value in the order of the first divided region including the center of the pupil, the first divided region including the pupil and the iris, and the first divided region including the iris;
The program according to any one of supplementary notes 6 to 8.

Reference Signs List 10 iris authentication device 23 first region dividing unit 24 second region dividing unit 25 weight setting unit 26 divided region selecting unit 27 iris authentication propriety determining unit 31 CPU
32 Primary storage unit 33 Secondary storage unit

Claims (6)

A first region dividing unit that divides a first region including the iris of a first image obtained by irradiating infrared rays and capturing an eye of an iris authentication target into a plurality of first divided regions;
Dividing a second region corresponding to the first region of the second image obtained by photographing the eye without irradiating infrared light into a plurality of second divided regions each corresponding to each of the plurality of first divided regions; A two-region dividing unit;
A weight setting unit that sets a weight value determined based on whether or not each of the plurality of first divided regions corresponds to a divided region including an iris;
Each of the first representative values representing the luminance value in each of the first divided regions and the luminance value in each of the second divided regions corresponding to the position of each of the plurality of first divided regions. A division area selection unit that selects the first division area having a large degree of difference from each of the second representative values;
An iris authentication availability determination unit that determines that the first image whose sum of the weight values set in the selected first divided area is equal to or greater than a threshold is usable for iris authentication;
An iris authentication device, including: The degree of the difference is
The magnitude of the difference obtained by subtracting the second representative value from the first representative value, or the magnitude of the ratio of the first representative value to the second representative value.
The iris authentication device according to claim 1. Each of the first representative value and the second representative value is a maximum value, an average value, or a median value of luminance values of a plurality of pixels in each divided region.
The iris authentication device according to claim 1 or 2. The weight setting unit sets a weight value in the order of the first divided region including the center of the pupil, the first divided region including the pupil and the iris, and the first divided region including the iris.
An iris authentication device according to any one of claims 1 to 3. An infrared irradiating unit that irradiates infrared rays to the eye of the iris authentication target,
An image capturing unit that captures the eye with the infrared irradiation unit irradiating infrared light, and captures the eye without irradiating infrared light.
Further comprising,
The iris authentication device according to any one of claims 1 to 4. Dividing a first region including an iris of a first image obtained by irradiating infrared rays with an eye of an iris authentication target into a plurality of first divided regions;
Dividing a second region corresponding to the first region of the second image obtained by photographing the eye without irradiating infrared light into a plurality of second divided regions each corresponding to each of the plurality of first divided regions;
Setting a weight value determined based on whether or not each of the plurality of first divided regions corresponds to a divided region including an iris;
Each of the first representative values representing the luminance value in each of the first divided regions and the luminance value in each of the second divided regions corresponding to the position of each of the plurality of first divided regions. Selecting the first divided region having a large degree of difference from each of the second representative values;
It is determined that the first image whose sum of the weight values set in the selected first divided area is equal to or larger than a threshold value can be used for iris authentication,
A program that causes a computer to execute iris authentication processing.