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

Abstract

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 that is 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 a gray image to thereby generate a second image, synthesizes the first and second images to thereby generate a third image, and generates, using the third image, a pseudo blood vessel pattern image that includes a pseudo blood vessel pattern.

Description

[Technical Field]

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

[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 great deal 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 in storage due to contracts with the subjects and the legal systems of each country. Therefore, there is a need for pseudo-vascular patterns that can replace 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. [Prior art documents] [Non-patent literature]

[0004] [Non-Patent Document 1] M. Satoh, Mathematical Life Sciences: Getting Started Now, ISBN: 4339067628, pp. 176-193, Corona Publishing, 2020. (Published: January 8, 2021) Summary of the Invention [Problem to be solved by the invention]

[0005] 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.

[0006] Therefore, the present disclosure proposes a technique that can generate a wide variety of pseudo blood vessel patterns. [Means for solving the problem]

[0007] The pseudo vascular pattern generating device of the present disclosure includes 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 first noise based on the first random number to a gray image, generates a second image by adding 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 that includes a pseudo vascular pattern using the third image. [Effects of the Invention]

[0008] According to the disclosed technique, a wide variety of simulated blood vessel patterns can be generated. [Brief explanation of the drawings]

[0009] [Figure 1] FIG. 1 is a diagram showing an example of the configuration of a pseudo blood vessel pattern generation system according to the present disclosure. [Figure 2] FIG. 2 is a diagram showing an example of a processing procedure in the pseudo blood vessel pattern generating device of the present disclosure. [Figure 3] FIG. 3 is a diagram showing an example of an image in the process of generating a pseudo blood vessel pattern according to the present disclosure. [Figure 4] FIG. 4 is a diagram showing an example of an image in the process of generating a pseudo blood vessel pattern according to the present disclosure. [Figure 5]FIG. 5 is a diagram showing an example of an image in the process of generating a pseudo blood vessel pattern according to the present disclosure. [Figure 6] FIG. 6 is a diagram showing an example of an image in the process of generating a pseudo blood vessel pattern according to the present disclosure. [Figure 7] FIG. 7 is a diagram showing an example of an image in the process of generating a pseudo blood vessel pattern according to the present disclosure. [Figure 8] FIG. 8 is a diagram showing an example of an image in the process of generating a pseudo blood vessel pattern according to the present disclosure. [Figure 9] FIG. 9 is a diagram showing an example of an image in the process of generating a pseudo blood vessel pattern according to the present disclosure. [Figure 10] FIG. 10 is a diagram showing an example of an image in the process of generating a pseudo blood vessel pattern according to the present disclosure. [Figure 11] FIG. 11 is a diagram showing an example of an image in the process of generating a pseudo blood vessel pattern according to the present disclosure. [Figure 12] FIG. 12 is a diagram showing an example of an image in the process of generating a pseudo blood vessel pattern according to the present disclosure. [Figure 13] FIG. 13 is a diagram showing the measurement results of FAR and FRR for a pseudo blood vessel pattern generated by the pseudo blood vessel pattern generating device of the present disclosure. [Figure 14] FIG. 14 is a diagram showing the FAR measurement results for the pseudo blood vessel pattern generated by the pseudo blood vessel pattern generating device of the present disclosure. DETAILED DESCRIPTION OF THE INVENTION

[0010] 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.

[0011] [Example] <Configuration of pseudo-vascular 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.

[0012] 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).

[0013] The pseudo blood vessel pattern generating device 10 includes a processor 11 and a storage unit 12. Examples of the processor 11 include a CPU (Central Processing Unit), a DSP (Digital Signal Processor), an FPGA (Field Programmable Gate Array), and an ASIC (Application Specific Integrated Circuit). Examples of the storage unit 12 include a memory and a storage. The pseudo blood vessel pattern generating device 10 is realized by, for example, a computer.

[0014] <Processing by the pseudo-vascular pattern generator> Fig. 2 is a diagram showing an example of a processing procedure in the pseudo blood vessel pattern generating device of the present disclosure, Fig. 3 to Fig. 12 are diagrams showing examples of images in the process of generating the pseudo blood vessel pattern of the present disclosure.

[0015] 2, in step S100, the processor 11 acquires a management ID (hereinafter, sometimes referred to as an “MID”) from the storage unit 12. The management ID is input by an operator to the pseudo vascular pattern generation device 10 using the input device 20, and is stored in advance in the storage unit 12.

[0016] Next, in step S105, the processor 11 initializes the value of a personal ID (hereinafter sometimes referred to as a "PID") to "1."

[0017] Next, in step S110, the processor 11 acquires a gray image Ia (FIG. 3) that has been stored in advance in the storage unit 12 from 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 gray image Ia.

[0018] Next, in step S115, the processor 11 sets a first random number seed and a second random number seed. The first random number seed and the second random number seed 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.

[0019] 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 memory unit 12, and processor 11 acquires from 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.

[0020] 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.

[0021] Next, in step S120, the processor 11 calculates the first normal distribution N(μ1, σ1 2 ) is generated based on the first random number seed, and the second normal distribution N(μ2,σ2 2) based on the second random number seed. Hereinafter, the random number generated based on the first random number seed may be referred to as the "first random number," and the random number generated based on the second random number seed may be referred to as the "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 the "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 the "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 (hereinafter may be referred to as the "second noise image") are generated.

[0022] 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.

[0023] Next, in step S130, the processor 11 diffuses the noise in the composite noise image Ic. The processor 11 generates 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"), for example, by applying a Gaussian filter to the composite noise image Ic.

[0024] Next, in step S135, the processor 11 enhances blood vessels in the noise diffusion image Id. The processor 11 applies 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").

[0025] 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) in which the vessel-enhanced image Ie has been smoothed (hereinafter, sometimes referred to as a "smoothed image"). Note that the processing of step S140 may be omitted.

[0026] 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 may be 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 enhancement image Ie to generate a color-inverted image Ig. Note that the processing of step S145 can also be omitted.

[0027] 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 the region of interest has been set in the color-inverted image Ig (hereinafter, sometimes referred to as the "image after region of interest setting"). In the image Ih after region of interest setting, the image within the region of interest becomes an image BV containing a pseudo blood vessel pattern (hereinafter, sometimes referred to as the "pseudo blood vessel pattern image"). Note that if the processing of step S145 is omitted, the processor 11 sets the 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 the region of interest in the blood vessel-enhanced image Ie in step S150.

[0028] Next, in step S155, the processor 11 causes the storage unit 12 to store the region-of-interest-setting image Ih generated in step S150.

[0029] Next, in step S160, processor 11 determines whether the value of PID has reached a predetermined value N. If the value of PID has not reached the predetermined value N (step S160: No), the process proceeds to step S165, and if the value of PID has reached the predetermined value N (step S160: Yes), the process ends.

[0030] In step S165, the processor 11 increments the value of PID by 1. After the process of step S165, the process returns to step S110.

[0031] 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.

[0032] For example, when the value of MID is "A," processor 11 sets the value of the first random number seed to "SA," when the value of MID is "B," the value of the first random number seed to "SB," and when the value of MID is "C," the value of the first random number seed to "SC." On the other hand, when the value of PID is "1," processor 11 sets the value of the second random number seed to "S1," when the value of PID is "2," the value of the second random number seed to "S2," and when the value of PID is "3," the value of the second random number seed to "S3."

[0033] In this way, the value of the first random number seed changes depending on the value of MID, and the value of the second random number seed changes depending on the value of PID.

[0034] Therefore, for example, when the value of MID acquired in step S100 is "A" and the predetermined value N is set to "3," as shown in FIG. 12, if the value of PID is "1," a first pseudo blood vessel pattern image BV-A1 is generated based on the first random number seed "SA" and the second random number seed "S1," if the value of PID is "2," a second pseudo blood vessel pattern image BV-A2 is generated based on the first random number seed "SA" and the second random number seed "S2," and if the value of PID is "3," a third pseudo blood vessel pattern image BV-A3 is generated based on the first random number seed "SA" and the second random number seed "S3."

[0035] For example, when the value of MID acquired in step S100 is "B" and the predetermined value N is set to "3," as shown in FIG. 12, if the value of PID is "1," a fourth pseudo blood vessel pattern image BV-B1 is generated based on the first random number seed "SB" and the second random number seed "S1," if the value of PID is "2," a fifth pseudo blood vessel pattern image BV-B2 is generated based on the first random number seed "SB" and the second random number seed "S2," and if the value of PID is "3," a sixth pseudo blood vessel pattern image BV-B3 is generated based on the first random number seed "SB" and the second random number seed "S3."

[0036] For example, when the value of MID acquired in step S100 is "C" and the predetermined value N is set to "3," as shown in FIG. 12, if the value of PID is "1," a seventh pseudo blood vessel pattern image BV-C1 is generated based on the first random number seed "SC" and the second random number seed "S1," if the value of PID is "2," an eighth pseudo blood vessel pattern image BV-C2 is generated based on the first random number seed "SC" and the second random number seed "S2," and if the value of PID is "3," a ninth pseudo blood vessel pattern image BV-C3 is generated based on the first random number seed "SC" and the second random number seed "S3."

[0037] Here, each of the nine pseudo blood vessel pattern images BV, the first pseudo blood vessel pattern image BV-A1 to the ninth pseudo blood vessel pattern image BV-C3, is generated from a plurality of different synthetic noise images Ic, each generated based on a different combination of the first random number seed and the second random number seed. Therefore, the feature points of the pseudo blood vessel patterns included in each of the nine pseudo blood vessel pattern images BV, the first pseudo blood vessel pattern image BV-A1 to the ninth pseudo blood vessel pattern image BV-C3, are different from one another.

[0038] 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.

[0039] <Combining the first noise image and the second noise image> The processor 11 calculates the first normal distribution N(μ1, σ1 2 ) and the first noise image Ib1 generated based on the second normal distribution N(μ2, σ2 2 ) (where μ1≦μ2 and σ1 2 ≦σ2 2 ) and the 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 normal distribution, the 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 the "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) setting method will be explained separately.

[0040] <How to set the average weight> If μ1=0, μ2=0, and μ≠0, the processor 11 sets the average weight w aSince it is difficult to set μ1 or μ2, either μ1 or μ2 is reset.

[0041] If μ1≦μ≦μ2, the processor 11 calculates a weighted average (w a μ1+(1-w a )μ2=μ) a In particular, when μ1=μ=μ2, an arbitrary average weight w a Under the weighted average (w a μ1+(1-w a )μ2=μ) is established, the processor 11 calculates the first normal distribution N(μ1,σ1 2 ) and the second normal distribution N(μ2,σ2 2 ) and the average weight w a Set.

[0042] Also, if μ<μ1 or μ2<μ, the average weight w a Within the domain of a μ1+(1-w a Since there is no value that satisfies the condition μ1=μ), processor 11 resets either μ1 or μ2 to a value that satisfies the conditions μ1≦μ and μ≦μ2.

[0043] <How to set the distribution weight> σ1 2 ≦σ 2 ≦σ2 2 In this case, the processor 11 2 and σ2 2 For the weighted average (w b σ1 2 +(1-w b )σ2 2 =σ 2 ) the distribution weight w b In particular, σ1 2 =σ 2 =σ2 2 If so, then any variance weight w b Under the weighted average (w b σ1 2 +(1-w b )σ22 =σ 2 ) holds, the processor 11 generates the first normal distribution N(μ1, σ1 2 ) and the second normal distribution N(μ2,σ2 2 ) and the variance weight w b Set.

[0044] Also, σ 2 <σ1 2 or σ2 2 <σ 2 In this case, the distribution weight w b Within the domain of b σ1 2 +(1-w b )σ2 2 =σ 2 ), there is no value that satisfies σ1 2 or σ2 2 Either of these is σ1 2 ≦σ 2 and σ 2 ≦σ2 2 Reset to a value that satisfies the above conditions.

[0045] <False Accept Rate (FAR) and False Reject Rate (FRR)> Fig. 13 is a diagram showing the measurement results of FAR and FRR for a pseudo blood vessel pattern generated by the pseudo blood vessel pattern generating device of the present disclosure, and Fig. 14 is a diagram showing the measurement results of FAR for a pseudo blood vessel pattern generated by the pseudo blood vessel pattern generating device of the present disclosure.

[0046] In measuring the FAR and FRR shown in FIG. 13, 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 image BV after the three geometric transformations, generated from each pseudo blood vessel pattern image BV, in a database, and one set of data (hereinafter sometimes referred to as "matching data") for matching with the data registered in the database, forming a total of three sets of data, thereby generating 1000 pairs of pseudo blood vessel pattern images BV after the geometric transformations.

[0047] In measuring the FAR shown in FIG. 14, the MID value was changed in two ways, and the predetermined value N was set to "1000" to change the PID value in 1000 ways, thereby generating 2000 pseudo blood vessel pattern images BV by the pseudo blood vessel pattern generating device 10. Two different geometric transformations were performed on each pseudo blood vessel pattern image BV corresponding to the first MID, and the results were associated with two pieces of registered data. One geometric transformation different from the two geometric transformations was performed on each pseudo blood vessel pattern image BV corresponding to the second MID, and the result was associated with one piece of verification data. A total of three pieces of data, two pieces of registered data and one piece of verification data, of pseudo blood vessel pattern images BV with the same PID after the geometric transformation were treated as one set, and 1000 pairs of pseudo blood vessel pattern images BV after the geometric transformation were generated.

[0048] Fig. 13 shows the measurement results of the FAR for 999,000 pairs of 1,000 pseudo blood vessel pattern image BV pairs after geometric transformation, which were rearranged so that the registered data and the matching data had the same MID and different PID, and the FRR for 1,000 pseudo blood vessel pattern image BV pairs after geometric transformation, which had the same MID and PID between the registered data and the matching data (i.e., 1,000 pairs not rearranged). In the measurement results shown in Fig. 13, the FAR was 0% when the value was -0.173 or more, and the FRR was 0% when the value was -0.091 or less.

[0049] On the other hand, Fig. 14 shows the measurement results of FAR for 1,000 pairs of pseudo blood vessel pattern images BV after geometric transformation, where the registered data and the matching data have different MIDs and the same PIDs (i.e., 1,000 pairs before recombination). In the measurement results shown in Fig. 14, FAR is 0% at -0.198 or more.

[0050] The measurement results shown in FIGS. 13 and 14 show that the pseudo blood vessel patterns contained in the pseudo blood vessel pattern image generated by the pseudo blood vessel pattern generating device 10 have diversity and satisfy the ideal conditions of FAR and FRR, which are the main indices used in evaluating biometric authentication algorithms.

[0051] The above is a description of the embodiment.

[0052] 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 then generates a third image (composite noise image Ic of the embodiment) by combining the first and second images, and generates a pseudo vascular pattern image (pseudo vascular pattern image BV of the embodiment) using the third image.

[0053] For example, the processor generates a fourth image (noise-diffused image Id in the embodiment) by diffusing noise contained in the third image, generates a fifth image (vessel-enhanced image Ie in the embodiment) by applying a vascular enhancement filter to the fourth image, and generates a pseudo-vascular pattern image by setting a region of interest in the fifth image.

[0054] This allows for the generation of a wide variety of simulated blood vessel patterns.

[0055] In addition, the first random number seed is associated with the management ID, and the second random number seed is associated with the personal ID.

[0056] This allows for the generation of diverse pseudo-vascular patterns under the condition that the same set of multiple mutually different personal IDs belong to each of multiple mutually different management IDs, making it possible to reuse the same set of personal IDs when generating pseudo-vascular patterns. This prevents the exhaustion of personal IDs for pseudo-vascular patterns, and also makes it easier to manage pseudo-vascular patterns by managing them using management IDs.

[0057] The processor also calculates the first normal distribution (the first normal distribution N(μ1, σ1 2)) and a second normal distribution (the second normal distribution N(μ,σ) 2 )) and a second image based on the third image.

[0058] For example, the processor may use a first weight for the mean of the normal distribution (the mean weight w in the embodiment) when generating the third image. a ) and the second weight for the variance of the normal distribution (variance weight w b ) and set it.

[0059] In this way, a third image that follows a normal distribution can be generated by combining the first image and the second image. [Explanation of symbols]

[0060] 1. Pseudo-vascular pattern generation system 10. Artificial blood vessel pattern generator 11 processors 12 Storage section

Claims

1. 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 blood vessel pattern image that is an image including a pseudo blood vessel pattern using the third image; A pseudo-vascular pattern generating device comprising:

2. The processor: generating a fourth image by diffusing noise contained in the third image; generating a fifth image by applying a vessel enhancement filter to the fourth image; generating the pseudo blood vessel pattern image by setting a region of interest in the fifth image; The pseudo-vascular pattern generating device according to claim 1 .

3. The first random number seed is associated with an administration ID, and the second random number seed is associated with a personal ID. The pseudo-vascular pattern generating device according to claim 1 .

4. the processor generates the third image by combining the first image based on a first normal distribution and the second image based on a second normal distribution; The pseudo-vascular pattern generating device according to claim 1 .

5. the processor, when generating the third image, sets a first weight to a mean of the normal distribution and a second weight to a variance of the normal distribution.

5. The pseudo-vascular pattern generating device according to claim 4.

6. generating a first random number based on a first random number seed; generating a second random number based on a second random number seed; generating a first image by adding a 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 an image including a pseudo-vascular pattern using the third image; A method for generating pseudo-vascular patterns.

Images