Apparatus for generating a pseudo blood vessel pattern and method for generating a pseudo blood vessel pattern

Abstract

In a pseudo blood vessel pattern generation device 10, a processor 11 generates a first image obtained by adding white noise to a gray image, generates a second image obtained by diffusing white noise in the first image, generates a third image obtained by performing blood vessel highlighting filtering on the second image, generates a fourth image obtained by setting a region of interest to the third image, and generates a fifth image including a pseudo blood vessel pattern, on the basis of the fourth image.

Description

Technical Field

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

Background Art

[0002] For the development of biometric algorithms and biometric systems based on blood vessel patterns, a large amount of blood vessel pattern data is required. Conventionally, the development of biometric algorithms and biometric systems has been carried out using blood vessel patterns (hereinafter sometimes referred to as "actual blood vessel patterns") extracted from images of actual living bodies (hereinafter sometimes referred to as "captured images"). However, actually photographing a living body to obtain a large number of actual blood vessel patterns requires a great deal of time and cost for collecting the actual blood vessel patterns. In addition, if actually photographing a living body, since the actual blood vessel pattern extracted from the captured image is data for identifying an individual, it is difficult to store the actual blood vessel pattern in storage due to contracts with the photographed subjects and laws and regulations in each country. Therefore, there is a need for pseudo blood vessel patterns that substitute for actual blood vessel patterns.

[0003] On the other hand, for example, a method of generating a pseudo blood vessel pattern based on a mathematical model such as a reaction-diffusion equation using a wing pattern or a Turing pattern of Drosophila melanogaster is known.

Prior Art Documents

Non-Patent Documents

[0004]

Non-Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] However, the shape of the pseudo blood vessel pattern generated based on the mathematical model is quite different from that of the actual blood vessel pattern. In addition, since it is difficult to generate a pattern rich in diversity in the generation of the pseudo blood vessel pattern based on the mathematical model, it is not realistic to use the pseudo blood vessel pattern generated based on the mathematical model for the evaluation of the biometric authentication algorithm.

[0006] Therefore, in the present disclosure, a technique capable of generating a pseudo blood vessel pattern rich in diversity is proposed.

Means for Solving the Problems

[0007] The pseudo blood vessel pattern generation device of the present disclosure has a processor. The processor generates a first image obtained by adding white noise to a grayscale image, generates a second image obtained by diffusing the white noise in the first image, generates a third image obtained by applying a blood vessel enhancement filter to the second image, generates a fourth image obtained by setting a region of interest in the third image, and generates a fifth image including a pseudo blood vessel pattern based on the fourth image.

Effects of the Invention

[0008] According to the disclosed technique, a pseudo blood vessel pattern rich in diversity can be generated.

Brief Description of the Drawings

[0009]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Embodiments for Carrying Out 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 denoted by the same reference numerals.

[0011] [Embodiment] <Configuration of Pseudo-Vascular Pattern Generation System> FIG. 1 is a diagram showing a configuration example of a pseudo-vascular pattern generation system of the present disclosure.

[0012] In FIG. 1, the pseudo-vascular pattern generation system 1 includes a pseudo-vascular pattern generation apparatus 10, an input device 20, and a display 30. The input device 20 and the display 30 are connected to the pseudo-vascular pattern generation apparatus 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-vascular pattern generation 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), an ASIC (Application Specific Integrated Circuit), etc. Examples of the storage unit 12 include a memory, a storage, etc. The pseudo-vascular pattern generation device 10 is realized by, for example, a computer.

[0014] <Processing of the pseudo-vascular pattern generation device> FIG. 2 is a diagram showing an example of a processing procedure in the pseudo-vascular pattern generation device of the present disclosure. FIGS. 3 to 11 are diagrams showing examples of images in the process of generating the pseudo-vascular pattern of the present disclosure.

[0015] In FIG. 2, in step S100, the processor 11 initializes the value of the first counter n and the value of the second counter m to “1”.

[0016] Next, in step S105, the processor 11 acquires the grayscale image Ia (FIG. 3) 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 from 0 to 255, an image in which the gradation value of all pixels is, for example, 128, the intermediate value of 0 to 255, is stored in the storage unit 12 in advance as the grayscale image Ia.

[0017] Next, in step S110, the processor 11 sets a random number seed.

[0018] Next, in step S115, the processor 11 adds white noise to all pixels of the grayscale image Ia under the same random number seed. As a result, an image (hereinafter sometimes referred to as a “white noise-added image”) Ib (FIG. 4) in which white noise is added to the grayscale image Ia is generated.

[0019] Next, in step S120, the processor 11 diffuses the white noise in the white noise-added image Ib. The processor 11 generates an image Ic (hereinafter sometimes referred to as a "white noise diffused image") (Fig. 5) in which the white noise is diffused in the white noise-added image Ib, for example, by applying a Gaussian filter to the white noise-added image Ib.

[0020] Next, in step S125, the processor 11 emphasizes blood vessels in the white noise diffused image Ic. The processor 11 generates an image Id (hereinafter sometimes referred to as a "blood vessel emphasized image") (Fig. 6) in which blood vessels are emphasized in the white noise diffused image Ic, for example, by applying a blood vessel emphasizing filter such as a Frangi filter to the white noise diffused image Ic.

[0021] Next, in step S130, the processor 11 smooths the blood vessel emphasized image Id. The processor 11 generates an image Ie (hereinafter sometimes referred to as a "smoothed image") (Fig. 7) that is smoothed with respect to the blood vessel emphasized image Id, for example, by smoothing the blood vessel emphasized image Id using a Gaussian filter. Note that the process of step S130 can also be omitted.

[0022] Next, in step S135, the processor 11 inverts the color of the smoothed image Ie. Thereby, an image If (hereinafter sometimes referred to as a "color inverted image") (Fig. 8) in which the smoothed image Ie is inverted in a so-called negative-positive manner is generated. Note that when the process of step S130 is omitted, in step S135, the processor 11 generates the color inverted image If by inverting the color of the blood vessel emphasized image Id. Note that the process of step S135 can also be omitted.

[0023] Next, in step S140, the processor 11 sets a region of interest (ROI) in the color-inverted image If. As a result, an image (hereinafter sometimes referred to as "image after ROI setting") Ig (FIG. 9) in which the ROI is set for the color-inverted image If is generated. When the process of step S135 is omitted, in step S140, the processor 11 sets the ROI in the smoothed image Ie. Also, when the processes of steps S130 and S135 are omitted, in step S140, the processor 11 sets the ROI in the blood vessel enhancement image Id.

[0024] Next, in step S145, the processor 11 generates an image (hereinafter sometimes referred to as "pseudo blood vessel pattern image") BVnm including a pseudo blood vessel pattern by performing geometric transformation on the image Ig after ROI setting. Examples of geometric transformation include affine transformation, Thin-Plate Spline transformation, and the like.

[0025] Next, in step S150, the processor 11 stores the pseudo blood vessel pattern image BVnm generated in step S145 in the storage unit 12.

[0026] Next, in step S155, the processor 11 determines whether the value of the second counter m has reached the second predetermined value M. When the value of the second counter m has not reached the second predetermined value M (step S155: No), the process proceeds to step S160, and when the value of the second counter m has reached the second predetermined value M (step S155: Yes), the process proceeds to step S165.

[0027] In step S160, the processor 11 increments the value of the second counter m. After the process of step S160, the process returns to step S145.

[0028] Here, as shown in FIG. 10, the processor 11 changes the value of the parameter P used for the geometric transformation performed in step S145 according to the value of the second counter m. For example, when the value of the second counter m is "1", the processor 11 sets the value of the parameter P to "Pa", when the value of the second counter m is "2", the processor 11 sets the value of the parameter P to "Pb" different from Pa, and when the value of the second counter m is "3", the processor 11 sets the value of the parameter P to "Pc" different from both Pa and Pb.

[0029] Therefore, for example, when the second predetermined value M is set to "3", as shown in FIG. 10, when the value of the first counter n is "1", when the value of the second counter m is "1", the image Ig after the region of interest setting is geometrically transformed using the parameter Pa to generate the first pseudo blood vessel pattern image BV11, when the value of the second counter m is "2", the image Ig after the region of interest setting is geometrically transformed using the parameter Pb to generate the second pseudo blood vessel pattern image BV12, and when the value of the second counter m is "3", the image Ig after the region of interest setting is geometrically transformed using the parameter Pc to generate the third pseudo blood vessel pattern image BV13.

[0030] On the other hand, in step S165, the processor 11 determines whether the value of the first counter n has reached the first predetermined value N. When the value of the first counter n has not reached the first predetermined value N (step S165: No), the process proceeds to step S170. When the value of the first counter n has reached the first predetermined value N (step S165: Yes), the processing procedure ends.

[0031] In step S170, the processor 11 increments the value of the first counter n. After the process of step S170, the process returns to step S105.

[0032] Here, the processor 11 changes the value of the random number seed set in step S110 according to the value of the first counter n. For example, when the value of the first counter n is "1", the processor 11 sets the value of the random number seed to "Sa", when the value of the first counter n is "2", the processor 11 sets the value of the random number seed to "Sb" different from Sa, and when the value of the first counter n is "3", the processor 11 sets the value of the random number seed to "Sc" different from both Sa and Sb.

[0033] Therefore, for example, when the first predetermined value N is set to "3", as shown in FIG. 11, when the value of the first counter n is "1", when the value of the second counter m is "1", the first pseudo blood vessel pattern image BV11 based on the random number seed Sa and the parameter Pa is generated, when the value of the second counter m is "2", the second pseudo blood vessel pattern image BV12 based on the random number seed Sa and the parameter Pb is generated, and when the value of the second counter m is "3", the third pseudo blood vessel pattern image BV13 based on the random number seed Sa and the parameter Pc is generated. Also, as shown in FIG. 11, when the value of the first counter n is "2", when the value of the second counter m is "1", the fourth pseudo blood vessel pattern image BV21 based on the random number seed Sb and the parameter Pa is generated, when the value of the second counter m is "2", the fifth pseudo blood vessel pattern image BV22 based on the random number seed Sb and the parameter Pb is generated, and when the value of the second counter m is "3", the sixth pseudo blood vessel pattern image BV23 based on the random number seed Sb and the parameter Pc is generated. Also, as shown in FIG. 11, when the value of the first counter n is "3", when the value of the second counter m is "1", the seventh pseudo blood vessel pattern image BV31 based on the random number seed Sc and the parameter Pa is generated, when the value of the second counter m is "2", the eighth pseudo blood vessel pattern image BV32 based on the random number seed Sc and the parameter Pb is generated, and when the value of the second counter m is "3", the ninth pseudo blood vessel pattern image BV33 based on the random number seed Sc and the parameter Pc is generated.

[0034] Here, the first pseudo-vascular pattern image BV11, the second pseudo-vascular pattern image BV12, and the third pseudo-vascular pattern image BV13 are generated based on different parameters Pa, Pb, Pc under the same random number seed Sa. Therefore, the feature points of the pseudo-vascular patterns included in each of the first pseudo-vascular pattern image BV11, the second pseudo-vascular pattern image BV12, and the third pseudo-vascular pattern image BV13 are similar to each other.

[0035] Also, the fourth pseudo-vascular pattern image BV21, the fifth pseudo-vascular pattern image BV22, and the sixth pseudo-vascular pattern image BV23 are generated based on different parameters Pa, Pb, Pc under the same random number seed Sb. Therefore, the feature points of the pseudo-vascular patterns included in each of the fourth pseudo-vascular pattern image BV21, the fifth pseudo-vascular pattern image BV22, and the sixth pseudo-vascular pattern image BV23 are similar to each other.

[0036] Also, the seventh pseudo-vascular pattern image BV31, the eighth pseudo-vascular pattern image BV32, and the ninth pseudo-vascular pattern image BV33 are generated based on different parameters Pa, Pb, Pc under the same random number seed Sc. Therefore, the feature points of the pseudo-vascular patterns included in each of the seventh pseudo-vascular pattern image BV31, the eighth pseudo-vascular pattern image BV32, and the ninth pseudo-vascular pattern image BV33 are similar to each other.

[0037] On the one hand, the first pseudo blood vessel pattern image BV11, the second pseudo blood vessel pattern image BV12, and the third pseudo blood vessel pattern image BV13 are generated based on the random number seed Sa, the fourth pseudo blood vessel pattern image BV21, the fifth pseudo blood vessel pattern image BV22, and the sixth pseudo blood vessel pattern image BV23 are generated based on the random number seed Sb, and the seventh pseudo blood vessel pattern image BV31, the eighth pseudo blood vessel pattern image BV32, and the ninth pseudo blood vessel pattern image BV33 are generated based on the random number seed Sc. Therefore, the feature points of the pseudo blood vessel patterns included in each of the first pseudo blood vessel pattern image BV11, the second pseudo blood vessel pattern image BV12, and the third pseudo blood vessel pattern image BV13, the feature points of the pseudo blood vessel patterns included in each of the fourth pseudo blood vessel pattern image BV21, the fifth pseudo blood vessel pattern image BV22, and the sixth pseudo blood vessel pattern image BV23, and the feature points of the pseudo blood vessel patterns included in each of the seventh pseudo blood vessel pattern image BV31, the eighth pseudo blood vessel pattern image BV32, and the ninth pseudo blood vessel pattern image BV33 are different from each other.

[0038] Therefore, the pseudo blood vessel patterns included in each of the first pseudo blood vessel pattern image BV11, the second pseudo blood vessel pattern image BV12, and the third pseudo blood vessel pattern image BV13 can be defined as three variations of the pseudo blood vessel patterns of the first person. Also, the pseudo blood vessel patterns included in each of the fourth pseudo blood vessel pattern image BV21, the fifth pseudo blood vessel pattern image BV22, and the sixth pseudo blood vessel pattern image BV23 can be defined as three variations of the pseudo blood vessel patterns of the second person different from the first person. Also, the pseudo blood vessel patterns included in each of the seventh pseudo blood vessel pattern image BV31, the eighth pseudo blood vessel pattern image BV32, and the ninth pseudo blood vessel pattern image BV33 can be defined as three variations of the pseudo blood vessel patterns of the third person different from the first person and the second person.

[0039] Note that the operator can set the first predetermined value N and the second predetermined value M using the input device 20. Also, the operator can visually recognize the pseudo blood vessel pattern image BVnm using the display 30.

[0040] <False Accept Rate (FAR) and False Reject Rate (FRR) of Others FIG. 12 is a diagram showing measurement results of FAR and FRR for the pseudo blood vessel pattern generated by the pseudo blood vessel pattern generation device of the present disclosure. In FIG. 12, by setting the first predetermined value N to "1000" and the second predetermined value M to "1000", the measurement results in the l33 format when the pseudo blood vessel pattern generation device 10 generates 1,000,000 pseudo blood vessel pattern images are shown. As shown in FIG. 12, in this measurement result, as FAR decreases, FRR increases, and as FRR decreases, FAR increases. Also, in this measurement result, FAR is 0% at -0.2420 or more, and FRR is 0% at -0.1874 or less. Thus, the 1,000,000 pseudo blood vessel patterns included in the 1,000,000 pseudo blood vessel pattern images generated by the pseudo blood vessel pattern generation device 10 have similar feature points among the same persons and have the diversity that the feature points are different among different persons, and thus satisfy the ideal relationship of FAR and FRR which are the main indicators used for evaluating the biometric authentication algorithm.

[0041] The above describes the embodiments.

[0042] As described above, the pseudo blood vessel pattern generation device (the pseudo blood vessel pattern generation device 10 in the embodiment) of the present disclosure has a processor (the processor 11 in the embodiment). The processor generates a first image (the white noise added image Ib in the embodiment) obtained by adding white noise to a gray image (the gray image Ia in the embodiment), generates a second image (the white noise diffused image Ic in the embodiment) obtained by diffusing the white noise in the first image, generates a third image (the blood vessel emphasized image Id in the embodiment) obtained by applying a blood vessel enhancement filter to the second image, generates a fourth image (the image Ig after setting the region of interest in the embodiment) obtained by setting a region of interest in the third image, and generates a fifth image (the pseudo blood vessel pattern image BVnm in the embodiment) including a pseudo blood vessel pattern based on the fourth image.

[0043] For example, the processor adds white noise to the grayscale image based on a plurality of different random number seeds.

[0044] Also for example, the processor generates a fifth image by geometrically transforming a fourth image using a plurality of different parameters.

[0045] By doing so, a pseudo-vascular pattern rich in diversity can be generated.

Explanation of Signs

[0046] 1 Pseudo-vascular pattern generation system 10 Pseudo-vascular pattern generation device 11 Processor 12 Storage unit

Claims

A storage unit that stores a gray image, which is an image in which the gradation value of all pixels takes an intermediate value. A processor that generates a first image by adding white noise to all pixels of the gray image under the same random number seed, generates a second image by diffusing the white noise in the first image by applying a Gaussian filter to the first image, generates a third image by applying a Frangi 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 by performing a geometric transformation on the fourth image. A pseudo-vascular pattern generation device comprising the above.

2. The processor adds the white noise to the gray image based on a random number seed that is the same for all pixels and different for each gray image. The pseudo-vascular pattern generation device according to Claim 1.

3. The processor generates a plurality of different fifth images by performing the geometric transformation on the fourth image using a plurality of different parameters under the same random number seed. The pseudo-vascular pattern generation device according to Claim 1.

4. Generate a first image by adding white noise to all pixels of a gray image, which is an image in which the gradation value of all pixels takes an intermediate value, under the same random number seed. Generate a second image by diffusing the white noise in the first image by applying a Gaussian filter to the first image. Generate a third image by applying a Frangi filter to the second image. Generate a fourth image by setting a region of interest in the third image. Generate a fifth image including a pseudo-vascular pattern by performing a geometric transformation on the fourth image. A method for generating a pseudo-vascular pattern.

Images