Microparticle measuring system and microparticle measuring method

Abstract

To improve the accuracy when measurements relating to microparticles are performed using captured images.SOLUTION: A microparticle measuring system of an embodiment includes a light source that emits illumination light toward a shooting container in which a liquid containing microparticles to be measured is placed, an objective lens that condenses the illumination light, an imaging lens that forms an image of the illumination light being condensed, an image sensor that captures the illumination light being imaged and outputs a captured image, an adjustment mechanism that adjusts a shooting distance, which is the distance from the image sensor to the shooting container, and a detection unit that detects the microparticles based on a plurality of captured images each having a different shooting distance.SELECTED DRAWING: Figure 12

Description

[Technical field]

[0001] FIELD OF THE DISCLOSURE The present invention relates to a microparticle measurement system and a microparticle measurement method. [Background technology]

[0002] Conventionally, organic wastewater treatment has utilized various useful microorganisms to decompose organic matter in wastewater and remove nitrogen and phosphorus. In this case, wastewater treatment is performed based on indicators such as sludge concentration and treated water quality. Therefore, if the concentration of useful microorganisms that contribute to organic matter decomposition and nitrogen removal can be measured, it is expected that the wastewater treatment performance will be improved by stabilizing the control.

[0003] Techniques for measuring the concentration of beneficial microorganisms (microparticles such as Bacillus) include colony counting and PCR (Polymerase Chain Reaction), but these methods require highly specialized equipment, and have problems such as the time required to transport samples to specialized facilities and the long measurement times.

[0004] Therefore, for example, a technology has been proposed that uses the characteristics of light refraction by the microparticles being measured and detects microparticles (e.g., Bacillus spores) from captured images using image processing that uses deep learning. This makes it unnecessary to transport samples to specialized facilities and enables the concentration of microparticles to be measured in a short time. [Prior art documents] [Patent documents]

[0005] [Patent Document 1] JP 2023-79806 A Summary of the Invention [Problem to be solved by the invention]

[0006] However, in the above-mentioned conventional technology, there is a problem in that substances other than the target microparticles may have optical properties similar to those of the target microparticles under certain conditions, making it difficult to identify them using captured images and resulting in measurement errors.

[0007] Therefore, the present invention has been made in consideration of the above circumstances, and has an objective of providing a microparticle measurement system and a microparticle measurement method that can improve the accuracy when measuring microparticles using captured images. [Means for solving the problem]

[0008] The microparticle measuring system of the embodiment includes a light source that emits illumination light toward a shooting container in which a liquid containing the microparticles to be measured is placed, an objective lens that collects the illumination light, an imaging lens that forms an image of the collected illumination light, an image sensor that captures the image of the illuminated light and outputs a captured image, an adjustment mechanism that adjusts a shooting distance, which is the distance from the image sensor to the shooting container, and a detection unit that detects the microparticles based on a plurality of captured images each having a different shooting distance. [Brief description of the drawings]

[0009] [Figure 1] FIG. 1 is a schematic diagram of a microparticle measuring system according to an embodiment. [Diagram 2] FIG. 2 is an explanatory diagram of parameters in a ray tracing matrix. [Diagram 3] FIG. 3 is an explanatory diagram of the relative transmitted light intensity etc. for Bacillus spores. [Figure 4] FIG. 4 is an explanatory diagram of the relative transmitted light intensity and the like for acrylic particles. [Diagram 5] FIG. 5 is a diagram showing an example of a photographed image of sludge. [Figure 6] FIG. 6 is a diagram showing examples of captured images and teaching images used in deep learning. [Figure 7] FIG. 7 is a diagram showing an example of a Bacillus detection result by deep learning. [Figure 8] FIG. 8 is a diagram showing examples of captured images for each shooting distance. [Figure 9] FIG. 9 shows examples of captured images of bacteria in a spore state and bacteria not in a spore state. [Figure 10] FIG. 10 is an explanatory diagram of the Bacillus spore detection process using deep learning. [Figure 11] FIG. 11 is an explanatory diagram of the detection process of Bacillus spores by pattern matching. [Figure 12] FIG. 12 is a flowchart showing the process performed by the microparticle measuring system of the embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0010] Hereinafter, embodiments of a microparticle measuring system and a microparticle measuring method according to the present invention will be described with reference to the drawings. Note that hereinafter, Bacillus spores are also simply referred to as Bacillus.

[0011] 1 is a schematic diagram of a microparticle measuring system 10 according to an embodiment. The microparticle measuring system 10 includes a light source 11, a stage 13, a stage driving unit 14, a laser displacement meter 15, an objective lens 16, an imaging lens 17, an image sensor 18, a measurement control unit 19, and an information processing device 20. The measurement control unit 19 and the information processing device 20 may be integrated into one unit. The information processing device 20 may also be divided into two or more units.

[0012] A light source 11 emits illumination light L toward a slide glass 12 (preparation: imaging container) on which a measurement sample SP (liquid; specimen) containing microparticles to be measured is placed.

[0013] The stage 13 supports a slide glass 12 that holds a measurement sample SP. Note that a hemocytometer may be used in place of the slide glass 12.

[0014] The stage driving unit 14 moves the stage 13 along the optical axis in the vertical direction in Fig. 1. The stage driving unit 14 is an example of an adjustment mechanism that adjusts the imaging distance, which is the distance from the image sensor 18 to the slide glass 12. The laser displacement meter 15 detects the position of the slide glass 12 by using a laser.

[0015] The objective lens 16 condenses the illumination light L into parallel light. The imaging lens 17 condenses the illumination light L, which has become parallel light, to form an image.

[0016] The image sensor 18 captures the illumination light imaged by the imaging lens 17 and outputs the captured image. The measurement control unit 19 controls the stage driving unit 14 and the image sensor 18 .

[0017] The information processing device 20 includes an acquisition unit 21, a detection unit 22, a calculation unit 23, a processing unit 24, a storage unit 25, a display unit 26, and an input unit 27.

[0018] The acquisition unit 21 acquires a captured image from the image sensor 18 .

[0019] The detection unit 22 detects microparticles, impurities, and the like that appear in the captured image.

[0020] For example, the stage driving unit 14 changes the shooting distance at regular intervals. In this case, the image sensor 18 captures the illumination light and outputs a captured image every time the shooting distance is changed at regular intervals by the stage driving unit 14. Then, the detection unit 22 detects microparticles based on a plurality of captured images with different shooting distances (details will be described later).

[0021] The detection unit 22 detects microparticles by image processing using deep learning, for example, based on a plurality of captured images captured at different shooting distances.

[0022] Further, the detection unit 22 may detect fine particles by image processing using pattern matching, for example, based on a plurality of captured images with different shooting distances from each other.

[0023] The calculation unit 23 calculates the concentration of fine particles and the like (hereinafter, also referred to as "measurement results") from the detection results by the detection unit 22.

[0024] The processing unit 24 executes various information processes. For example, the processing unit 24 causes the display unit 26 to display the measurement results.

[0025] The storage unit 25 stores the operation programs of each of the units 21 to 24, various parameters, the captured images acquired by the acquisition unit 21, the detection results by the detection unit 22, the measurement results by the calculation unit 23, the processing results by the processing unit 24, and the like.

[0026] The display unit 26 displays various information according to an instruction from the processing unit 24.

[0027] The input unit 27 is a means for information input by the user, such as a keyboard, a mouse, a touch panel, or the like.

[0028] Note that all or part of the processes performed by the above units 21 to 24 are executed by one processor (control unit) based on, for example, the operation programs and various parameters stored in the storage unit 25.

[0029] Next, the measurement principle of fine particles will be described. When illumination light is irradiated from the back side of fine particles in a liquid, due to the lens effect of the fine particles, the illumination light is condensed at a position corresponding to the particle diameter and refractive index of the fine particles.

[0030] Note that the closer to the condensing position, the higher the transmitted light intensity becomes, the transmitted light intensity becomes maximum at the condensing position, and as it moves away from the condensing position again, the transmitted light intensity decreases. That is, the position where the transmitted light intensity is maximum is the condensing position. At this time, the condensing position can be specified by measuring the distance between the objective lens 16 and the position where the transmitted light intensity is maximum.

[0031] In this case, the optical path of the illumination light can be expressed by the following equation: Therefore, if the particle diameter of the microparticle is known in addition to the distance between the objective lens 16 and the position where the transmitted light intensity is maximum, the refractive index of the microparticle can be determined by solving the equation expressed by the following ray tracing matrix.

[0032]

number

[0033] 2 is an explanatory diagram of parameters in a ray tracing matrix. In the above ray tracing matrix, the radius of the microparticle PC is r, the refractive index of the microparticle is n, and the distance between the microparticle and the objective lens 16 when the transmitted light intensity of the illumination light L is maximum for the target microparticle is z. In addition, the distance from the optical axis when the illumination light L is incident on the microparticle is x. 0 The incident angle of the illumination light L on the microparticle is u 0 In addition, the distance from the optical axis of the illumination light L incident on the image sensor 18 is x 1 The incident angle of the illumination light L incident on the image sensor 18 is u 1 Let us assume that.

[0034] Furthermore, the distance between the objective lens 16 and the imaging lens 17 is l 1 The distance between the imaging lens 17 and the image sensor 18 is l 2 The focal length of the objective lens is f 1 The focal length of the imaging lens 17 is f 2 Let us assume that.

[0035] Then, as described above, if the refractive index of the microparticle is known, the particle diameter of the microparticle can be calculated by solving the equation represented by the ray tracing matrix.

[0036] In addition, useful microorganisms used in organic wastewater treatment can be considered as microparticles under certain conditions, such as when the useful microorganisms form spores. When the useful microorganisms form spores, their shape does not change and the shape is almost constant for the useful microorganisms.

[0037] Since the spores of beneficial microorganisms have a specific size (e.g., particle diameter) and a specific refractive index, by treating them in the same way as microparticles, it is possible to detect such beneficial microorganisms and measure their number (and thus their concentration) per observation field.

[0038] When measuring the concentration, the observation position (image capture position) is scanned along the optical axis direction, and the number of beneficial microorganisms in a volume corresponding to the observation field of view x scanning distance is measured, thereby making it possible to measure the concentration.

[0039] By the way, in the case of a spore of the genus Bacillus (Bacillus spore) in sludge, which has a known refractive index and a particle size of 1 μm or less, the position corresponding to the distance z at which the transmitted light intensity is maximized is the focal length f 1 Therefore, based on a preset transmitted light intensity threshold, the part with a light intensity equal to or greater than the threshold can be regarded as a Bacillus spore.

[0040] In this case, the transmitted light intensity through the liquid containing the Bacillus spores is greater than the transmitted light intensity through the liquid not containing the Bacillus spores. Therefore, by setting the threshold value of the transmitted light intensity for determining whether or not a liquid contains Bacillus spores to a value slightly higher than the transmitted light intensity in a liquid that does not contain spores, Bacillus spores can be detected reliably.

[0041] Furthermore, by using a set threshold value, the sample is continuously moved in the optical axis direction while sequentially capturing images, and by combining this with deep learning (machine learning) that uses the transmitted light intensity at each location (each pixel) obtained from the captured images and the size (particle diameter) of the Bacillus spores as microparticles as judgment criteria, it is possible to detect and count the Bacillus spores, and ultimately to measure the concentration of the Bacillus spores with high accuracy.

[0042] When performing deep learning, for example, multiple samples with different concentrations of microparticles are prepared in advance, and supervised learning is performed so that the manual detection results by a user (measurement operator) for each sample are equivalent to the detection results obtained by deep learning, thereby obtaining microparticle detection results that correspond to the particle diameter and refractive index of the microparticles being learned.

[0043] Next, Fig. 3 is an explanatory diagram of the relative transmitted light intensity for Bacillus spores, etc. In detail, Fig. 3 is a diagram for explaining the relationship between the difference in the actual position of the objective lens 16 with respect to the distance z between the Bacillus spore and the objective lens 16 when the transmitted light intensity for the Bacillus spore is maximum, and the relative transmitted light intensity.

[0044] Fig. 4 is an explanatory diagram of the relative transmitted light intensity for acrylic particles, etc. In detail, Fig. 4 is a diagram for explaining the relationship between the difference in the actual position of the objective lens 16 relative to the distance z between the acrylic particle (microparticle) and the objective lens 16 when the transmitted light intensity is maximum for an acrylic particle having a particle diameter of 30 μm, and the relative transmitted light intensity.

[0045] First, images of the Bacillus spores and acrylic particles were acquired at the focal position by the image sensor 18. Then, the stage 13 was moved vertically along the optical axis direction by the stage driving unit 14, and the position difference Δz between the position of the objective lens 16 when the relative transmitted light intensity of each microparticle on the image sensor 18 was maximized and the actual position of the objective lens 16 was measured by the laser displacement meter 15.

[0046] Figure 3(A) is a photographed image of a liquid containing Bacillus spores, in which the relative transmitted light intensity is maximum. As shown in Figure 3(A), it can be seen that the relative transmitted light intensity is maximum at the center of the photographed area. As shown in Figure 3(B), it was calculated that the relative transmitted light intensity is maximum at a position difference Δz = 0 μm in the liquid containing Bacillus spores.

[0047] In contrast, as shown in FIG. 4(B), in the case of a liquid containing acrylic particles with a particle diameter of 30 μm, the relative transmitted light intensity has a negative value at the position difference Δ0 μm where the relative transmitted light intensity of the Bacillus spores is maximum. In other words, it can be seen that the transmitted light intensity is lower than the background light intensity. Also, as shown in FIG. 4(A), it can be seen that the relative transmitted light intensity is minimum around the acrylic particles. And, as shown in FIG. 4(B), in the case of a liquid containing acrylic particles with a particle diameter of 30 μm, it was calculated that the relative transmitted light intensity is maximum outside the position difference Δz = ±15 μm.

[0048] Also, Figure 4(C) is a photographed image in which the relative transmitted light intensity is maximum in a liquid containing acrylic particles with a particle diameter of 30 μm. As shown in Figure 4(C), it can be seen that the relative transmitted light intensity is maximum at the center of the photographed area. And, as shown in Figure 4(D), in a liquid containing acrylic particles with a particle diameter of 30 μm, it was calculated that the relative transmitted light intensity is maximum at a position difference Δz = 26 μm.

[0049] Based on this measurement result, the position difference Δz corresponding to the difference between the distance z from the microparticles Bacillus spores and acrylic particles having a particle diameter of 30 μm to the objective lens 16 when the transmitted light intensity is at its maximum and the focal length of the objective lens was calculated using the above-mentioned ray tracing matrix for Bacillus spores and acrylic particles having a particle diameter of 30 μm. The position difference Δz in the liquid containing Bacillus spores was Δz = 0.9 μm, and the position difference Δz in the liquid containing acrylic particles having a particle diameter of 30 μm was Δz = 22.5 μm, which was found to be almost consistent with the measurement result using the laser displacement meter 15. The distance between the objective lens 16 and the imaging lens 17 at this time was l 1= 130 mm, and the distance between the imaging lens 17 and the image sensor 18 is l 2 = 164.5 mm, the focal length of the objective lens is f 1 = 4.1125 mm, and the focal length of the imaging lens 17 is f 2 = 164.5 mm. The Bacillus spores had r = 1 μm and n = 1.4, and the acrylic particles had n = 1.5.

[0050] In particular, it was found that a position difference Δz=0.9 μm in the liquid containing Bacillus spores is effectively equal to the focal length of the objective lens 16 (within the depth of field), and the relative transmitted light intensity is maximum at the focal position. This demonstrates that in measuring Bacillus spores, it is possible to detect Bacillus spores by measuring the transmitted light intensity at the focal length.

[0051] In this way, the characteristic of Bacillus spores that the center glows brightly when the transmitted light intensity is at its maximum can be utilized to detect Bacillus spores from the captured image.

[0052] Next, Fig. 5 is a diagram showing examples of photographed images of sludge. As shown in Fig. 5(a) and (b), in addition to Bacillus spores B, impurities C may also be seen in the photographed images.

[0053] Next, Fig. 6 shows examples of captured images and training images used in deep learning. (a) is a captured image showing Bacillus spores B and impurities C. A user provides the center position P of Bacillus spores B as correct answer data for this captured image, which is used as the training image shown in (b). Deep learning can be performed by training a network to detect the center position P of Bacillus spores B in the captured image using these images.

[0054] 7 is a diagram showing an example of a Bacillus detection result by deep learning. The detection unit 22 calculates the likelihood of the Bacillus spore detection result by image processing using deep learning (the possibility (likelihood) that each pixel is the center position of the Bacillus spore).

[0055] Fig. 7(a) is an input image (photographed image). The detection unit 22 calculates a likelihood map, for example, as shown in Fig. 7(b). In this likelihood map, the brighter the area, the higher the likelihood, and the darker the area, the lower the likelihood. The symbol Q is a portion where the likelihood is high, corresponding to Bacillus spore B (Fig. 7(a)).

[0056] The detection unit 22 then performs threshold processing on this likelihood and determines that a pixel having a likelihood equal to or greater than a certain level is the center position of the Bacillus spore, thereby obtaining the detection result shown in Fig. 7(c). In Fig. 7(c), the symbol S indicates the center position of the detected Bacillus spore.

[0057] However, when the above detection is performed using a single captured image as with conventional technology, bacteria that are not in a spore state (substances that are not the microparticles being measured) can have optical characteristics similar to those of bacteria in a spore state (the microparticles being measured) under certain conditions, making it difficult to distinguish them using the captured image and resulting in measurement errors.

[0058] Taking such situations into consideration, the following describes in detail a technique that can improve the accuracy of measurements related to microparticles using captured images.

[0059] Fig. 8 shows examples of images captured at different shooting distances. In Fig. 8(a), the focal position is further back in the order of (a4) → (a1), that is, the shooting distance is shorter. The brightness of the Bacillus spores is almost the same in (a3) ​​and (a4), (a2) is darker than them, and (a1) is even darker.

[0060] In Figure 8(b), the focal position is closer in the order of (b1) → (b4), that is, the shooting distance is longer. The brightness of the Bacillus spores is almost the same in (b1) and (b2), (b3) is darker than them, and (b4) is even darker.

[0061] Next, FIG. 9 shows an example of a captured image of bacteria B (Bacillus spores) in a spore state and bacteria D not in a spore state. As shown in (a), bacteria B and D are captured at focus positions (1), (2), and (3). In this case, bacteria B and D look different, as shown in (b). Specifically, for bacteria B, the brightness is "dark," "light," and "dark" at focus positions (1), (2), and (3). On the other hand, for bacteria D, the brightness is "light" at focus positions (1), (2), and (3). In other words, when bacteria D has a shape like a vertically elongated sphere as shown in (a) and is arranged as shown in the figure, its optical characteristics are close to those of bacteria B. Note that when bacteria D is rotated 90 degrees on the paper, its optical characteristics are not close to those of bacteria B.

[0062] Therefore, for example, if one attempts to detect spores using only the image captured at focus position (2), it is difficult to distinguish between spore-state bacteria B and non-spore-state bacteria D, resulting in a decrease in detection accuracy. However, if one attempts to detect spores using all of the images captured at focus positions (1), (2), and (3), it is easier to distinguish between spore-state bacteria B and non-spore-state bacteria D because the bacteria look different at each focus position, resulting in a higher detection accuracy. Therefore, by acquiring multiple images while shifting the focus position (shooting distance) at a certain interval or the like, and using these multiple images, it becomes possible to identify with high accuracy whether the bacteria shown in the captured images are in a spore state or not.

[0063] Next, FIG. 10 is an explanatory diagram of the detection process of Bacillus spores by deep learning. (a) is an example of a captured image and a training image used when training a deep learning model. (a1) is a plurality of captured images taken while moving the focus position at regular intervals when photographing sludge, and the focus position is different for each captured image. For this captured image, the user provides the center position of the Bacillus spore as the correct answer data, and the image is set as the training image shown in (a2). Using these captured images, a network can be trained to detect the center position of the Bacillus spore from the captured images, thereby generating a deep learning model.

[0064] (b) is a diagram showing an example of Bacillus detection processing using deep learning. When multiple images (b1) taken while moving the focus position at regular intervals are used as input data for deep learning, a likelihood map (b2) of the detection result of Bacillus spores is calculated. This likelihood is subjected to threshold processing, and a pixel with a likelihood above a certain level is determined to be the center position of the Bacillus spore, thereby obtaining the detection result of Bacillus spores (b3).

[0065] As described above, in addition to deep learning, the detection process of Bacillus spores can also be performed by pattern matching. FIG. 11 is an explanatory diagram of the detection process of Bacillus spores by pattern matching. (a) shows a plurality of captured images taken while moving the focus position at regular intervals when photographing sludge, and the focus position is different for each captured image. (b) shows a plurality of captured images taken separately while moving the focus position at regular intervals, and a representative image of Bacillus spores at each focus position is used as a template image. The similarity between the input image (a) and the template image (b) is calculated, and the coordinates having a similarity degree equal to or higher than a certain level are regarded as the detection result of Bacillus spores (c).

[0066] 12 is a flowchart showing processing by the microparticle measuring system 10 of the embodiment. The measurement operator collects water from a water treatment device in which the microorganism (Bacillus) to be measured exists, performs a predetermined pretreatment (filtering, heating, etc.) on the collected sample, and sets the sample after pretreatment in the microparticle measuring system 10. Next, the measurement operator adjusts the height of the stage 13 of the microparticle measuring system 10 to an initial position. The initial position of the height of the stage 13 is, for example, a height at which the focal position is aligned with the bottom of the stage 13.

[0067] Generally, the specific gravity of the microorganism (Bacillus) in the measurement sample SP is greater than 1, so for example, after preparing the measurement sample SP, wait 10 to 20 minutes for the microorganism (Bacillus) to settle and become stable, and then perform the processes from step S1 onwards.

[0068] In step S1, the acquisition unit 21 acquires a captured image from the image sensor 18 and stores it in the storage unit 25.

[0069] Next, in step S2, the processing unit 24 determines whether the number of shootings has reached a predetermined number (for example, 20 times). If Yes, it proceeds to step S4; if No, it proceeds to step S3.

[0070] In step S3, the stage drive unit 14 changes the height of the stage 13 at regular intervals according to an instruction from the processing unit 24 and returns to step S1. Note that the change in the height of the stage 13 may be manually performed by the measurement operator. Also, the regular interval for moving the stage 13 may be, for example, about 1.0 [μm]. This length is an example of an appropriate length for discriminating between Bacillus spores (fine particles with a diameter of about 3.4 [μm]) in a spore state and bacteria that are not in a spore state, and is not limited thereto. This length is obtained empirically by experiments, for example.

[0071] In step S4, the detection unit 22 detects Bacillus spores shown in the captured images based on a plurality of captured images with different shooting distances (FIGS. 10 and 11).

[0072] Next, in step S5, the calculation unit 23 calculates the number of detected Bacillus spores and the concentration from the detection results in step S4.

[0073] Next, in step S6, the processing unit 24 causes the display unit 26 to display the measurement results.

[0074] In this way, according to the fine particle measurement system 10 of the present embodiment, by using a plurality of captured images with different shooting distances, it is possible to improve the accuracy when performing measurements regarding fine particles.

[0075] Also, if the change interval of the shooting distance is a regular interval, the change of the shooting distance becomes easy.

[0076] Furthermore, in the case where the microparticle measuring system 10 has a configuration including a stage driving unit 14 for adjusting the height of the stage 13, the shooting distance can be easily changed by controlling the stage driving unit 14.

[0077] In addition, when the microparticle measurement system 10 is configured to include an imaging device drive unit (adjustment mechanism) that adjusts the shooting distance by moving the objective lens 16, the imaging lens 17, and the image sensor 18 together, the shooting distance can be easily changed by controlling the imaging device drive unit.

[0078] In addition, higher detection accuracy can be achieved by detecting microparticles through image processing using deep learning based on multiple captured images taken at different shooting distances.

[0079] Furthermore, by detecting microparticles through image processing using pattern matching based on a plurality of captured images taken at different shooting distances, it is possible to achieve a certain level of detection accuracy while shortening the calculation time.

[0080] Furthermore, the information processing device 20 of this embodiment includes a control device such as a CPU (Central Processing Unit), a storage device such as a ROM (Read Only Memory) and a RAM (Random Access Memory), an external storage device such as an HDD (Hard Disk Drive), a display device such as a display device, and input devices such as a keyboard and a mouse, and has a hardware configuration that utilizes a normal computer.

[0081] In addition, the program executed by the information processing device 20 of this embodiment is provided as a file in an installable or executable format, recorded on a computer-readable recording medium such as a semiconductor storage device such as a DVD (Digital Versatile Disk), a USB (Universal Serial Bus) memory, or an SSD (Solid State Drive).

[0082] The program may be stored on a computer connected to a network such as the Internet and provided by being downloaded via the network.The program may be provided or distributed via a network such as the Internet.The program may be provided by being pre-installed in a ROM or the like.

[0083] Although some embodiments of the present invention have been described, these embodiments are presented as examples and are not intended to limit the scope of the invention. These novel embodiments can be implemented in various other forms, and various omissions, substitutions, and modifications can be made without departing from the spirit of the invention. These embodiments and their modifications are included in the scope and spirit of the invention, and are included in the scope of the invention and its equivalents described in the claims.

[0084] For example, the predetermined number of times used as the threshold for the number of times of shooting in step S2 of Fig. 12 is not limited to 20 times, and may be another number of times. In other words, the threshold for the number of times of shooting and the interval at which the shooting distance is changed can be set to any appropriate value based on experiments, simulations, etc. [Explanation of symbols]

[0085] 10...microparticle measuring system, 11...light source, 12...slide glass, 13...stage, 14...stage driving unit, 15...laser displacement meter, 16...objective lens, 17...imaging lens, 18...image sensor, 19...measurement control unit, 20...information processing device, 21...acquisition unit, 22...detection unit, 23...calculation unit, 24...processing unit, 25...storage unit, 26...display unit, 27...input unit

Claims

1. A light source that emits illumination light to a container in which a liquid containing microparticles to be measured is placed; an objective lens for collecting the illumination light; an imaging lens that forms an image from the condensed illumination light; an image sensor that captures the focused illumination light and outputs a captured image; an adjustment mechanism for adjusting a photographing distance, which is a distance from the image sensor to the photographing container; a detection unit that detects the microparticles based on a plurality of the captured images having different shooting distances; A microparticle measuring system comprising:

2. The adjustment mechanism changes the shooting distance at regular intervals, The microparticle measuring system according to claim 1 , wherein the image sensor captures the illumination light and outputs the captured image each time the photographing distance is changed at the fixed interval by the adjustment mechanism.

3. The microparticle measuring system according to claim 1 , wherein the adjustment mechanism is a stage driving unit that adjusts the height of a stage on which the imaging container is placed.

4. 2. The microparticle measuring system according to claim 1, wherein the adjustment mechanism is an imaging device driving section that adjusts the shooting distance by integrally moving the objective lens, the imaging lens, and the image sensor.

5. The microparticle measuring system according to claim 1 , wherein the detection unit detects the microparticles by image processing using deep learning, based on the plurality of captured images having different shooting distances.

6. The microparticle measuring system according to claim 1 , wherein the detection section detects the microparticles by image processing using pattern matching, based on the plurality of captured images captured at different shooting distances.

7. A microparticle measuring method using a microparticle measuring system including a light source that emits illumination light to a container in which a liquid containing microparticles to be measured is placed, an objective lens that condenses the illumination light, an imaging lens that forms an image of the condensed illumination light, an image sensor that photographs the image of the illumination light and outputs a photographed image, an adjustment mechanism, and a detection unit, The adjustment mechanism adjusts a photographing distance, which is a distance from the image sensor to the photographing container; a step of detecting the microparticles based on a plurality of the captured images captured at different shooting distances by the detection unit; A method for measuring fine particles comprising:

Images