Pseudo blood vessel pattern generation device and pseudo blood vessel pattern generation method

Abstract

Provided is a pseudo blood vessel pattern generation device 10, wherein a processor 11 generates a first random number on the basis of a first random seed, generates a second random number on the basis of a second random seed different from the first random seed, adds first noise based on the first random number to a gray image to thereby generate a first image, adds second noise based on the second random number to the gray image to thereby generate a second image, synthesizes the first and second images to thereby generate a third image, and generates a pseudo blood vessel pattern image by using the third image. The first random seed is associated with a management ID, and the second random seed is associated with a personal ID. The processor 11 generates the third image by combining the first image and the second image, both of which are based on a normal distribution, and sets the weight of the normal distribution when generating the third image. The processor generates a plurality of clusters, each of which is defined by a combination of the management ID and the weight, the plurality of clusters each including a plurality of pseudo blood vessel pattern images generated under a plurality of mutually different personal IDs.

Description

Pseudo-vascular pattern generating device and pseudo-vascular pattern generating method

[0001] The present disclosure relates to a pseudo blood vessel pattern generating device and a pseudo blood vessel pattern generating method.

[0002] Developing biometric authentication algorithms and systems based on vascular patterns requires a large amount of vascular pattern data. Conventionally, biometric authentication algorithms and systems have been developed using vascular patterns (hereinafter referred to as "real vascular patterns") extracted from images of actual living bodies (hereinafter referred to as "photographed images"). However, capturing images of living bodies to obtain a large number of real vascular patterns requires a significant amount of time and expense. Furthermore, since the real vascular patterns extracted from photographed images are used as personal identification data, it is difficult to store real vascular patterns due to contracts with the subjects and legal regulations in various countries. Therefore, pseudo-vascular patterns are needed as an alternative to real vascular patterns.

[0003] In response to this, a method is known in which a pseudo-vascular pattern is generated based on a mathematical model such as a reaction-diffusion equation using, for example, a wing pattern of a fruit fly or a Turing pattern.

[0004] However, the shape of the pseudo-vascular pattern generated based on the mathematical model is far from that of the actual vascular pattern. Furthermore, it is difficult to generate diverse pseudo-vascular patterns based on the mathematical model, so it is not practical to use the pseudo-vascular pattern generated based on the mathematical model to evaluate biometric authentication algorithms.

[0005] In contrast to this, there is prior art that generates a first image by adding white noise to a gray image, generates a second image by diffusing the white noise in the first image, generates a third image by applying a vascular enhancement filter to the second image, generates a fourth image by setting a region of interest in the third image, and generates a fifth image including a pseudo-vascular pattern based on the fourth image.

[0006] International Publication No. 2023 / 119653

[0007] M. Satoh, Mathematical Life Sciences: Getting Started Now, ISBN: 4339067628, pp. 176-193, Corona Publishing, 2020. (Published: January 8, 2021)

[0008] However, in the above-mentioned prior art, it is easy to weaken the correlation between pseudo vascular patterns but difficult to strengthen them, so even when using the above-mentioned prior art, it was difficult to approximate the distribution of pseudo vascular patterns to the distribution of actual biological vascular patterns that have a relatively strong correlation.

[0009] Therefore, the present disclosure proposes a technique that can generate pseudo-vascular patterns having correlations of various strengths.

[0010] The pseudo vein pattern generating device of the present disclosure includes a processor. The processor generates a first random number based on a first random number seed, generates a second random number based on a second random number seed different from the first random number seed, generates a first image by adding a first noise based on the first random number to a gray image, generates a second image by adding a second noise based on the second random number to the gray image, generates a third image by combining the first image and the second image, and generates a pseudo vein pattern image using the third image, the pseudo vein pattern image being an image including a pseudo vein pattern. The first random number seed is associated with an administration ID, and the second random number seed is associated with a personal ID. The processor generates the third image by combining the first image and the second image, both of which are based on a normal distribution. When generating the third image, the processor sets a weight for the normal distribution, and generates a plurality of clusters, each defined by a combination of the administration ID and the weight, the plurality of clusters including a plurality of the pseudo vein pattern images generated under a plurality of different personal IDs.

[0011] According to the disclosed technique, pseudo blood vessel patterns having correlations of various strengths can be generated.

[0012] FIG. 1 is a diagram illustrating an example of the configuration of a pseudo vascular pattern generation system according to the present disclosure. FIG. 2 is a diagram illustrating an example of a processing procedure in a pseudo vascular pattern generation device according to the present disclosure. FIG. 3 is a diagram illustrating an example of an image in the process of generating a pseudo vascular pattern according to the present disclosure. FIG. 4 is a diagram illustrating an example of an image in the process of generating a pseudo vascular pattern according to the present disclosure. FIG. 5 is a diagram illustrating an example of an image in the process of generating a pseudo vascular pattern according to the present disclosure. FIG. 6 is a diagram illustrating an example of an image in the process of generating a pseudo vascular pattern according to the present disclosure. FIG. 7 is a diagram illustrating an example of an image in the process of generating a pseudo vascular pattern according to the present disclosure. FIG. 8 is a diagram illustrating an example of an image in the process of generating a pseudo vascular pattern according to the present disclosure. FIG. 9 is a diagram illustrating an example of an image in the process of generating a pseudo vascular pattern according to the present disclosure. FIG. 10 is a diagram illustrating an example of an image in the process of generating a pseudo vascular pattern according to the present disclosure. FIG. 11 is a diagram illustrating an example of an image in the process of generating a pseudo vascular pattern according to the present disclosure. FIG. 12 is a diagram illustrating an example of an image in the process of generating a pseudo vascular pattern according to the present disclosure. FIG. 13 is a diagram illustrating an example of a pseudo vascular pattern image according to the present disclosure. Fig. 14 is a diagram showing an example of a cluster of the present disclosure. Fig. 15 is a diagram showing measurement results of FRR and FAR for a pseudo blood vessel pattern generated by the pseudo blood vessel pattern generation device of the present disclosure. Fig. 16 is a diagram showing measurement results of FRR for a pseudo blood vessel pattern generated by the pseudo blood vessel pattern generation device of the present disclosure. Fig. 17 is a diagram showing measurement results of FAR for a pseudo blood vessel pattern generated by the pseudo blood vessel pattern generation device of the present disclosure.

[0013] Hereinafter, embodiments of the present disclosure will be described with reference to the drawings. In the following embodiments, the same components are designated by the same reference numerals.

[0014] [Example] <Configuration of pseudo blood vessel pattern generation system> FIG. 1 is a diagram showing an example of the configuration of a pseudo blood vessel pattern generation system according to the present disclosure.

[0015] 1, the pseudo blood vessel pattern generation system 1 includes a pseudo blood vessel pattern generation device 10, an input device 20, and a display 30. The input device 20 and the display 30 are connected to the pseudo blood vessel pattern generation device 10. Examples of the input device 20 include a pointing device such as a mouse and a keyboard. An example of the display 30 is an LCD (Liquid Crystal Display).

[0016] The pseudo blood vessel pattern generating device 10 includes a processor 11 and a storage unit 12. Examples of the processor 11 include a central processing unit (CPU), a digital signal processor (DSP), a field programmable gate array (FPGA), and an application specific integrated circuit (ASIC). Examples of the storage unit 12 include a memory and storage. The pseudo blood vessel pattern generating device 10 is realized by, for example, a computer.

[0017] <Processing of the pseudo blood vessel pattern generating device> Fig. 2 is a diagram showing an example of a processing procedure in the pseudo blood vessel pattern generating device of the present disclosure. Figs. 3 to 12 are diagrams showing examples of images in the pseudo blood vessel pattern generating process of the present disclosure.

[0018] 2, in step S100, the processor 11 acquires a management ID (hereinafter sometimes referred to as "MID") from the storage unit 12. The management ID is input by the operator to the pseudo blood vessel pattern generating device 10 using the input device 20 and is stored in advance in the storage unit 12.

[0019] Next, in step S105, the processor 11 initializes the value of a personal ID (hereinafter sometimes referred to as a "PID") to "1".

[0020] Next, in step S110, the processor 11 acquires from the storage unit 12 a grayscale image Ia ( FIG. 3 ) that has been stored in advance in the storage unit 12. When the gradation value of each pixel forming the image takes any value between 0 and 255, an image in which the gradation values ​​of all pixels are, for example, 128, which is the intermediate value between 0 and 255, is stored in advance in the storage unit 12 as the grayscale image Ia.

[0021] Next, in step S115, the processor 11 sets a first random number seed and a second random number seed, which are different from each other, and the first random number seed is associated with the management ID, and the second random number seed is associated with the personal ID.

[0022] For example, a plurality of mutually different first random number seeds that correspond one-to-one to each of a plurality of mutually different management IDs and a plurality of mutually different second random number seeds that correspond one-to-one to each of a plurality of mutually different personal IDs are pre-stored in the memory unit 12, and the processor 11 acquires from the memory unit 12 the first random number seed that corresponds to the management ID acquired in step S100 and the second random number seed that corresponds to the current value of the personal ID.

[0023] Also, for example, the processor 11 may use the management ID acquired in step S100 as the first random number seed, and the current value of the personal ID as the second random number seed.

[0024] Next, in step S120, the processor 11 calculates the first normal distribution N(μ １ ,σ １ ２ ) based on the first random number seed, and generates random numbers according to the second normal distribution N(μ ２ ,σ ２ ２) based on the second random number seed. Hereinafter, a random number generated based on the first random number seed may be referred to as a "first random number," and a random number generated based on the second random number seed may be referred to as a "second random number." Also, in step S120, the processor 11 adds white noise based on the first random number (hereinafter may be referred to as "first noise") to all pixels of the grayscale image Ia, and adds white noise based on the second random number (hereinafter may be referred to as "second noise") to all pixels of the grayscale image Ia. Because the first random number seed and the second random number seed are different random number seeds, the first noise and the second noise are white noises with different noise states. As a result, an image Ib1 (FIG. 4) in which the first noise has been added to the grayscale image Ia and an image Ib2 (FIG. 5) in which the second noise has been added to the grayscale image Ia are generated.

[0025] Next, in step S125, the processor 11 combines the first noise image Ib1 and the second noise image Ib2. As a result, an image Ic (FIG. 6) in which the first noise image Ib1 and the second noise image Ib2 are combined (hereinafter, may be referred to as a "composite noise image") is generated. The composite noise image Ic is a normal distribution N(μ, σ ２ ) is an image that follows.

[0026] Next, in step S130, the processor 11 diffuses the noise in the composite noise image Ic by, for example, applying a Gaussian filter to the composite noise image Ic to generate an image Id (FIG. 7) in which the noise in the composite noise image Ic has been diffused (hereinafter, may be referred to as a "noise-diffused image").

[0027] Next, in step S135, the processor 11 enhances blood vessels in the noise diffusion image Id by applying a blood vessel enhancement filter such as a Frangi filter to the noise diffusion image Id to generate an image Ie ( FIG. 8 ) in which blood vessels are enhanced in the noise diffusion image Id (hereinafter, may be referred to as a “vessel enhancement image”).

[0028] Next, in step S140, the processor 11 smoothes the vessel-enhanced image Ie. The processor 11 smooths the vessel-enhanced image Ie using, for example, a Gaussian filter to generate an image If (FIG. 9) obtained by smoothing the vessel-enhanced image Ie (hereinafter, sometimes referred to as a "smoothed image"). Note that the processing of step S140 may be omitted.

[0029] Next, in step S145, the processor 11 inverts the color of the smoothed image If. As a result, an image Ig (FIG. 10) in which the smoothed image If is so-called negative-positive inverted (hereinafter, sometimes referred to as a "color-inverted image") is generated. Note that if the processing of step S140 is omitted, in step S145, the processor 11 inverts the color of the blood vessel-enhanced image Ie to generate the color-inverted image Ig. Note that the processing of step S145 can also be omitted.

[0030] Next, in step S150, the processor 11 sets a region of interest (ROI) in the color-inverted image Ig. This generates an image Ih (FIG. 11) in which a region of interest has been set in the color-inverted image Ig (hereinafter, sometimes referred to as a "region-of-interest-set image"). Note that if the processing of step S145 is omitted, the processor 11 sets a region of interest in the smoothed image If in step S150. Also, if the processing of steps S140 and S145 are omitted, the processor 11 sets a region of interest in the vessel-enhanced image Ie in step S150.

[0031] Next, in step S155, the processor 11 performs a geometric transformation on the post-region-of-interest setting image Ih. This generates an image Ii (FIG. 12) in which the post-region-of-interest setting image Ih has been geometrically transformed (hereinafter, may be referred to as the "post-geometric transformation image"). In the post-geometric transformation image Ii, the image within the region of interest becomes an image BV containing a pseudo blood vessel pattern (hereinafter, may be referred to as the "pseudo blood vessel pattern image"). Examples of geometric transformations performed on the post-region-of-interest setting image Ih include affine transformation and projective transformation. Note that the processing of step S155 may be omitted. If the processing of step S155 is omitted, the image within the region of interest in the post-region-of-interest setting image Ih becomes the pseudo blood vessel pattern image BV.

[0032] Next, in step S160, the processor 11 stores the post-geometric transformation image Ii generated in step S155 in the storage unit 12.

[0033] Next, in step S165, the processor 11 determines whether the PID value has reached a predetermined value N. If the PID value has not reached the predetermined value N (step S165: No), the process proceeds to step S170, and if the PID value has reached the predetermined value N (step S165: Yes), the process ends.

[0034] In step S170, the processor 11 increments the value of PID by 1. After the process of step S170, the process returns to step S110.

[0035] The operator can set the predetermined value N using the input device 20. The operator can also use the display 30 to visually recognize the pseudo blood vessel pattern image BV.

[0036] Here, the processor 11 changes the values ​​of the first random number seed and the second random number seed set in step S115 according to the values ​​of the MID and PID.

[0037] For example, when the value of MID is "A" (MID=A), the processor 11 sets the value of the first random number seed to "SA," when the value of MID is "B" (MID=B), the processor 11 sets the value of the first random number seed to "SB," and when the value of MID is "C" (MID=C), the processor 11 sets the value of the second random number seed to "S1," when the value of PID is "1" (PID=1), the processor 11 sets the value of the second random number seed to "S2," when the value of PID is "2" (PID=2), and the processor 11 sets the value of the second random number seed to "S3" when the value of PID is "3" (PID=3).

[0038] In this way, the value of the first random number seed changes depending on the value of the MID, and the value of the second random number seed changes depending on the value of the PID.

[0039] <Combining the First Noise Image and the Second Noise Image> The processor 11 generates a first normal distribution N(μ １ ,σ １ ２ ) and a first noise image Ib1 generated based on a second normal distribution N(μ ２ ,σ ２ ２ ) (where μ １ ≦μ ２ and σ １ ２ ≦σ ２ ２ ) and a second noise image Ib2 generated based on the normal distribution N(μ, σ ２ In order to generate a synthetic noise image Ic conforming to the above, weights for the mean and variance of the normal distribution that can be generated from each of the first random number seed and the second random number seed are set as follows. Hereinafter, the weight for the mean of the normal distribution (hereinafter sometimes referred to as "average weight") w ａ (However, 0≦w ａ ≦1) and the weight for the variance of the normal distribution (hereinafter referred to as the "variance weight") w ｂ (However, 0≦w ｂ ≦1) will be explained separately.

[0040] <How to set the average weight> μ １ = 0, μ２ If μ≠0, the processor 11 calculates the average weight w ａ Since it is difficult to set μ １ or μ ２ Reset one of the following.

[0041] Also, μ １ ≦μ≦μ ２ In this case, the processor 11 １ and μ ２ For the weighted average (w ａ μ １ + (1-w ａ ) μ ２ Average weight w satisfying ａ In particular, μ １ = μ = μ ２ If so, then any average weight w ａ Under the weighted average (w ａ μ １ + (1-w ａ ) μ ２ Since the equation (μ) holds, the processor 11 calculates the first normal distribution N(μ) generated from the first random number seed and the second random number seed. １ ,σ １ ２ ) and the second normal distribution N(μ ２ ,σ ２ ２ ) and the average weight w ａ Set.

[0042] Also, μ<μ １ or μ ２ If μ, the average weight w ａ Within the domain of ａ μ １ + (1-w ａ ) μ ２ Since there is no value that satisfies μ １ or μ ２ Either μ １ ≦μ and μ≦μ ２ Reset to a value that satisfies the above conditions.

[0043] <How to set the variance weight> σ １ ２ ≦σ ２ ≦σ２ ２ In this case, the processor 11 １ ２ and σ ２ ２ For the weighted average (w ｂ σ １ ２ + (1-w ｂ ) σ ２ ２ = σ ２ ) the distribution weight w ｂ In particular, we set σ １ ２ = σ ２ = σ ２ ２ If so, then any variance weight w ｂ Under the weighted average (w ｂ σ １ ２ + (1-w ｂ ) σ ２ ２ = σ ２ ) is established, the processor 11 calculates the first normal distribution N(μ １ ,σ １ ２ ) and the second normal distribution N(μ ２ ,σ ２ ２ ) and the variance weight w ｂ Set.

[0044] Also, σ ２ <σ １ ２ or σ ２ ２ <σ ２ In this case, the distribution weight w ｂ Within the domain of ｂ σ １ ２ + (1-w ｂ ) σ ２ ２ = σ ２ ), the processor 11 does not find a value that satisfies σ １ ２ or σ ２ ２ Either of these is σ １ ２ ≦σ２ and σ ２ ≦σ ２ ２ Reset to a value that satisfies the above conditions.

[0045] In the following, the average weight w ａ and the variance weight w ｂ are sometimes collectively referred to as the "normal distribution weight w".

[0046] <Pseudo Blood Vessel Pattern Image> FIG. 13 is a diagram showing an example of a pseudo blood vessel pattern image according to the present disclosure.

[0047] When the MID value acquired in step S100 is "A" (MID=A) and the predetermined value N in step S165 is set to "2" (N=2), the first pseudo blood vessel pattern image BV1 to the tenth pseudo blood vessel pattern image BV10 are generated according to the magnitude of the normal distribution weight w (w=0.0, 0.2, 0.4, 0.6, 0.8), as shown in Fig. 13. The first pseudo blood vessel pattern image BV1 to the tenth pseudo blood vessel pattern image BV10 are generated under MID=A. The first pseudo blood vessel pattern image BV1 to the fifth pseudo blood vessel pattern image BV5 are generated under PID=1, and the sixth pseudo blood vessel pattern image BV6 to the tenth pseudo blood vessel pattern image BV10 are generated under PID=2. Furthermore, the first pseudo blood vessel pattern image BV1 and the sixth pseudo blood vessel pattern image BV6 are generated under w=0.0, the second pseudo blood vessel pattern image BV2 and the seventh pseudo blood vessel pattern image BV7 are generated under w=0.2, the third pseudo blood vessel pattern image BV3 and the eighth pseudo blood vessel pattern image BV8 are generated under w=0.4, the fourth pseudo blood vessel pattern image BV4 and the ninth pseudo blood vessel pattern image BV9 are generated under w=0.6, and the fifth pseudo blood vessel pattern image BV5 and the tenth pseudo blood vessel pattern image BV10 are generated under w=0.8.

[0048] According to the first pseudo blood vessel pattern image BV1 to the tenth pseudo blood vessel pattern image BV10 shown in FIG. 13, it can be seen that the larger the normal distribution weight w, the more similar the pseudo blood vessel pattern images BV become between PID=1 and PID=2, that is, the greater the similarity (hereinafter sometimes referred to as "pattern image similarity") of the pseudo blood vessel pattern images BV between PID=1 and PID=2. For example, it can be seen that the pattern image similarity between the fifth pseudo blood vessel pattern image BV5 and the tenth pseudo blood vessel pattern image BV10 is greater than the pattern image similarity between the fourth pseudo blood vessel pattern image BV4 and the ninth pseudo blood vessel pattern image BV9, the pattern image similarity between the fourth pseudo blood vessel pattern image BV4 and the ninth pseudo blood vessel pattern image BV9 is greater than the pattern image similarity between the third pseudo blood vessel pattern image BV3 and the eighth pseudo blood vessel pattern image BV8, the pattern image similarity between the third pseudo blood vessel pattern image BV3 and the eighth pseudo blood vessel pattern image BV8 is greater than the pattern image similarity between the second pseudo blood vessel pattern image BV2 and the seventh pseudo blood vessel pattern image BV7, and the pattern image similarity between the second pseudo blood vessel pattern image BV2 and the seventh pseudo blood vessel pattern image BV7 is greater than the pattern image similarity between the first pseudo blood vessel pattern image BV1 and the sixth pseudo blood vessel pattern image BV6.

[0049] <Cluster Generation> FIG. 14 is a diagram illustrating an example of a cluster according to the present disclosure.

[0050] For example, under MID=A, the processor 11 sets the normal distribution weight w to w1 (w=w1) and w2 (w=w2) greater than w1, and generates six pseudo blood vessel pattern images BV by varying the PID from "1," "2," and "3" under w=w1 and from "4," "5," and "6" under w=w2. This generates a first cluster CL1 defined by the combination of MID=A and w=w1, and a second cluster CL2 defined by the combination of MID=A and w=w2. The first cluster CL1 includes three pseudo blood vessel pattern images BV generated under MID=A, w=w1, and PIDs=1, 2, and 3, while the second cluster CL2 includes three pseudo blood vessel pattern images BV generated under MID=A, w=w2, and PIDs=4, 5, and 6. Since w2>w1, the pattern image similarity between the three pseudo blood vessel pattern images BV belonging to the second cluster CL2 is greater than the pattern image similarity between the three pseudo blood vessel pattern images BV belonging to the first cluster CL1.

[0051] For example, the processor 11 generates three pseudo blood vessel pattern images BV by setting the normal distribution weight w to w1 (w=w1) under MID=B and varying the PID to "7", "8", and "9" under w=w1. This generates a third cluster CL3 defined by the combination of MID=B and w=w1. The three pseudo blood vessel pattern images BV generated under MID=B, w=w1, and PID=7, 8, and 9 belong to the third cluster CL3.

[0052] Here, the pseudo blood vessel pattern image belonging to the first cluster CL1 and the pseudo blood vessel pattern image belonging to the second cluster CL2 are generated from the same MID. Therefore, the first cluster CL1 and the second cluster CL2 have similar properties, resulting in a strong correlation between the first cluster CL1 and the second cluster CL2. Meanwhile, the pseudo blood vessel pattern image belonging to the first cluster CL1 and the pseudo blood vessel pattern image belonging to the second cluster CL2 are generated from normal distribution weights w of different magnitudes, resulting in a difference in similarity between the pseudo blood vessel pattern images belonging to the first cluster CL1 and the pseudo blood vessel pattern images belonging to the second cluster CL2, as described above. Therefore, by forming the first cluster CL1 and the second cluster CL2, it is possible to generate a wide variety of pseudo blood vessel patterns, including pseudo blood vessel patterns that are highly correlated with each other.

[0053] Furthermore, the pseudo blood vessel pattern image belonging to the first cluster CL1 and the pseudo blood vessel pattern image belonging to the third cluster CL3 are generated from different MIDs. Therefore, the first cluster CL1 and the third cluster CL3 have different properties, and therefore the correlation between the first cluster CL1 and the third cluster CL3 is weak. Therefore, by forming the third cluster CL3 in addition to the first cluster CL1 and the second cluster CL2, it is possible to generate even more diverse pseudo blood vessel patterns.

[0054] <False Acceptance Rate (FAR) and False Rejection Rate (FRR)> Fig. 15 is a diagram showing measurement results of FRR and FAR for a pseudo blood vessel pattern generated by the pseudo blood vessel pattern generation device of the present disclosure. Fig. 16 is a diagram showing measurement results of FRR for a pseudo blood vessel pattern generated by the pseudo blood vessel pattern generation device of the present disclosure. Fig. 17 is a diagram showing measurement results of FAR for a pseudo blood vessel pattern generated by the pseudo blood vessel pattern generation device of the present disclosure.

[0055] In measuring the FRR and FAR shown in FIGS. 15, 16, and 17, the MID value was set to one value, the predetermined value N was set to "1000," and the PID value was changed to 1000 values, thereby generating 1000 pseudo blood vessel pattern images BV using the pseudo blood vessel pattern generating device 10. Three different geometric transformations were performed on each pseudo blood vessel pattern image BV. Two sets of data (hereinafter sometimes referred to as "registration data") were used to register the pseudo blood vessel pattern images BV generated from each pseudo blood vessel pattern image BV after the three geometric transformations in a database, and one set of data (hereinafter sometimes referred to as "verification data") was used to compare the pseudo blood vessel pattern images BV with the data registered in the database. These three sets of data were used to generate 1000 pairs of pseudo blood vessel pattern images BV after the geometric transformations.

[0056] 15 shows the FRR measurement results for 1,000 pseudo blood vessel pattern image BV pairs after geometric transformation, in which the enrollment data and the matching data have the same MID and the same PID (i.e., 1,000 pairs without rearrangement), and the FAR measurement results for 999,000 pairs of pseudo blood vessel pattern image BV pairs after geometric transformation, in which the enrollment data and the matching data have the same MID and different PID. Also, FIG. 15 shows the FRR and FAR measurement results when the normal distribution weight w is changed to 0.00, 0.20, 0.40, 0.60, and 0.80. In the measurement results shown in FIG. 15, the FRR is 0% at or below approximately -0.18, regardless of the magnitude of the normal distribution weight w. On the other hand, when the normal distribution weight w is 0.00 or 0.20, the FAR is 0% at approximately -0.28 or more, when the normal distribution weight w is 0.40, the FAR is 0% at approximately -0.27 or more, when the normal distribution weight w is 0.60, the FAR is 0% at approximately -0.22 or more, and when the normal distribution weight w is 0.80, the FAR is 0% at approximately -0.16 or more. As such, the measurement results shown in Figure 15 show that while the FRR distribution hardly changes when the normal distribution weight w is changed, the FAR distribution shifts to the right in the figure as the normal distribution weight w is increased.

[0057] FIG. 16 shows the measurement results of the mean and median of each FRR distribution when the normal distribution weight w is changed from 0.00 to 0.96 in increments of 0.02 under the same conditions as FIG. 15 . FIG. 17 shows the measurement results of the mean and median of each FAR distribution when the normal distribution weight w is changed from 0.00 to 0.96 in increments of 0.02 under the same conditions as FIG. 15 . The measurement results shown in FIG. 16 show that the mean and median of the FRR hardly change even when the normal distribution weight w is changed. On the other hand, the measurement results shown in FIG. 17 show that the mean and median of the FAR increase as the normal distribution weight w increases.

[0058] The measurement results shown in FIGS. 15, 16, and 17 reveal that the pseudo blood vessel patterns contained in the pseudo blood vessel pattern image generated by the pseudo blood vessel pattern generation device 10 have diversity and satisfy the ideal conditions for FAR and FRR, which are the main indices used in evaluating biometric authentication algorithms.

[0059] Furthermore, from the measurement results shown in FIGS. 15, 16, and 17, it can be seen that the FAR of the pseudo blood vessel pattern included in the pseudo blood vessel pattern image generated by the pseudo blood vessel pattern generating device 10 can be easily adjusted by changing the normal distribution weight w.

[0060] The above is a description of the embodiment.

[0061] As described above, the pseudo vascular pattern generation device (pseudo vascular pattern generation device 10 of the embodiment) of the present disclosure includes a processor (processor 11 of the embodiment). The processor generates a first random number based on a first random number seed, generates a second random number based on a second random number seed different from the first random number seed, adds first noise based on the first random number to a gray image (gray image Ia of the embodiment) to generate a first image (first noise image Ib1 of the embodiment), and adds second noise based on the second random number to the gray image to generate a second image (second noise image Ib2 of the embodiment). The processor also generates a third image (composite noise image Ic of the embodiment) by combining the first image and the second image, and generates a pseudo vascular pattern image (pseudo vascular pattern image BV of the embodiment) using the third image.

[0062] Here, the first random number seed is associated with an administrative ID, and the second random number seed is associated with a personal ID. The processor generates a third image by combining a first image and a second image, both of which are based on normal distributions. The processor also sets a weight for the normal distribution when generating the third image. The processor then generates a plurality of clusters, each defined by a combination of the administrative ID and the weight, each including a plurality of pseudo blood vessel pattern images generated under a plurality of mutually different personal IDs.

[0063] By generating such multiple clusters, each cluster can contain multiple pseudo blood vessel patterns that are highly correlated with each other. Furthermore, the correlation between pseudo blood vessel patterns can be strengthened between clusters with the same management ID but different weights, while the correlation between pseudo blood vessel patterns can be weakened between clusters with different management IDs. Therefore, by generating such multiple clusters, pseudo blood vessel patterns with various strengths of correlation can be generated.

[0064] REFERENCE SIGNS LIST 1 pseudo blood vessel pattern generation system 10 pseudo blood vessel pattern generation device 11 processor 12 storage unit

Claims

1. A pseudo-vascular pattern generating device comprising: a processor that generates a first random number based on a first random number seed, generates a second random number based on a second random number seed different from the first random number seed, generates a first image by adding a first noise based on the first random number to a gray image, generates a second image by adding a second noise based on the second random number to the gray image, generates a third image by combining the first image and the second image, and generates a pseudo-vascular pattern image using the third image, the pseudo-vascular pattern image being an image including a pseudo-vascular pattern; the first random number seed is associated with an administration ID and the second random number seed is associated with a personal ID; the processor generates the third image by combining the first image and the second image, both of which are based on a normal distribution; sets a weight for the normal distribution when generating the third image; and generates a plurality of clusters, each defined by a combination of the administration ID and the weight, the plurality of clusters including a plurality of pseudo-vascular pattern images generated under a plurality of different personal IDs.

2. The pseudo vascular pattern generating device according to claim 1, wherein the processor generates a fourth image by diffusing noise contained in the third image, generates a fifth image by applying a vascular enhancement filter to the fourth image, and generates the pseudo vascular pattern image by setting a region of interest in the fifth image.

3. The pseudo-vascular pattern generating device according to claim 1, wherein the processor sets a first weight for the mean of the normal distribution and a second weight for the variance of the normal distribution when generating the third image.

4. A pseudo-vascular pattern generating method comprising: generating a first random number based on a first random number seed; generating a second random number based on a second random number seed different from the first random number seed; generating a first image by adding first noise based on the first random number to a gray image; generating a second image by adding second noise based on the second random number to the gray image; generating a third image by combining the first image and the second image; generating a pseudo-vascular pattern image using the third image, the pseudo-vascular pattern image being an image including a pseudo-vascular pattern; the first random number seed is associated with an administration ID and the second random number seed is associated with a personal ID; generating the third image by combining the first image and the second image, both of which are based on a normal distribution; setting a weight for the normal distribution when generating the third image; and generating a plurality of clusters, each defined by a combination of the administration ID and the weight, the plurality of clusters including a plurality of the pseudo-vascular pattern images generated under a plurality of the personal IDs that are different from each other.

Images