Analysis method, computer program, and analysis system

Abstract

Provided is, inter alia, an analysis method with which it is possible to reduce time and labor for obtaining a size of a granule.　According to this analysis method, a computer acquires an image obtained by imaging a plurality of granules, derives the size of each granule included in the image on the basis of the acquired image, and outputs information on the derived size of each granule.

Description

Analysis method, computer program, and analysis system

[0001] The present invention relates to an analysis method, a computer program, and an analysis system.

[0002] 2. Description of the Related Art A pellet manufacturing apparatus is known that manufactures granular pellets from a resin material. The pellets are used as raw materials for injection molding and the like.

[0003] JP 2012-66387 A

[0004] One of the qualities required for pellets is uniformity among individual pellets. Therefore, as part of the quality assurance of pellet manufacturing equipment, it may be necessary to measure the condition of each pellet manufactured by the pellet manufacturing equipment. Pellets are almost always analyzed manually, for example, by measuring the weight of each pellet using a weighing scale. Manually analyzing the large number of pellets manufactured by a pellet manufacturing equipment requires a great deal of time and effort. This problem can exist in fields that handle a variety of granular materials, not just pellets.

[0005] An object of the present disclosure is to provide an analytical method etc. that can reduce the time and effort required to obtain the size of granular bodies.

[0006] An analysis method according to one aspect of the present disclosure involves a computer acquiring an image of a plurality of granular bodies, deriving the size of each granular body contained in the image based on the acquired image, and outputting information relating to the derived size of each granular body.

[0007] An analysis method according to one aspect of the present disclosure includes using a jig having a plurality of holes spaced apart from each other, placing granular bodies in each hole of the jig to arrange the plurality of granular bodies at a distance from each other, supporting the imaging device on an imaging device support that adjusts the relative positional relationship between the plurality of granular bodies and the imaging device to a predetermined positional relationship, acquiring images of the plurality of granular bodies using the imaging device supported by the imaging device support, deriving the size of each granular body contained in the image based on the acquired images, and outputting information regarding the derived size of each of the granular bodies.

[0008] A computer program according to one aspect of the present disclosure causes a computer to perform a process of acquiring an image of a plurality of granular bodies, deriving the size of each granular body contained in the image based on the acquired image, and outputting information relating to the derived size of each granular body.

[0009] An analysis system according to one aspect of the present disclosure includes a processing unit that acquires an image of a plurality of granular bodies, derives the size of each granular body contained in the image based on the acquired image, and outputs information relating to the derived size of each granular body.

[0010] According to the present disclosure, it is possible to reduce the time and effort required to obtain the desired size of the granules.

[0011] FIG. 1 is a schematic diagram of an analysis system. FIG. 2 is a block diagram showing an example of the configuration of an information processing device and a user terminal. FIG. 3 is a diagram explaining an example of the configuration of a positioning tool. FIG. 4 is a diagram explaining an example of the configuration of an imaging device support. FIG. 5 is a flowchart showing an example of a method for analyzing pellets. FIG. 6 is a flowchart showing an example of a detailed procedure for deriving the size of each particle. FIG. 7 is a schematic diagram showing an example of an analysis result screen. FIG. 8 is a schematic diagram of an analysis system in a second embodiment. FIG. 9 is a flowchart showing an example of a detailed procedure for deriving the size of each particle in the second embodiment.

[0012] The present disclosure will be specifically described with reference to the drawings showing embodiments thereof.

[0013] First Embodiment Overall Configuration of Analysis System Fig. 1 is a schematic diagram of an analysis system 100. The analysis system 100 of this embodiment is a system for analyzing pellets manufactured by a pellet manufacturing apparatus 5.

[0014] The analysis system 100 includes an information processing device 1, a user terminal 2, a positioning tool 3, and an imaging device support tool 4. The information processing device 1 is connected to the user terminal 2 via a network N so that they can communicate with each other. The network N is a wired or wireless network that includes the Internet, a LAN (Local Area Network), or the like.

[0015] The information processing device 1 is a device capable of various information processing and sending and receiving information, such as a server computer, a personal computer, or a quantum computer. The information processing device 1 is managed, for example, by a provider (e.g., a manufacturer) of the pellet production device 5. The information processing device 1 analyzes the pellets produced by the pellet production device 5 based on images (hereinafter also referred to as pellet images) of the pellets produced by the pellet production device 5. The information processing device 1 provides the analysis results to the user via the user terminal 2.

[0016] The user terminal 2 is a portable information processing terminal having communication functions, display functions, and imaging functions, such as a smartphone or tablet terminal. The user terminal 2 acquires pellet images and transmits the acquired pellet images to the information processing device 1. The user terminal 2 receives analysis results corresponding to the transmitted pellet images from the information processing device 1 and presents them to the user. The user terminal 2 is used by users such as analysts who analyze pellets, manufacturers and maintenance companies of the pellet manufacturing device 5, and owners of the pellet manufacturing device 5.

[0017] The user terminal 2 includes a display unit 24 (display device) and an imaging unit 26 (imaging device). In the example shown in Fig. 1, the user terminal 2 includes a substantially plate-shaped housing, with the display unit 24 disposed on the front side of the housing and a camera 261 (lens) and a light-emitting unit 262 of the imaging unit 26 disposed in a corner of the back side of the housing.

[0018] The positioning tool 3 is a jig for positioning the pellet. The imaging device support tool 4 is a tool for supporting the user terminal 2 that functions as an imaging device. The positioning tool 3 and the imaging device support tool 4 are used when capturing an image of the pellet.

[0019] The pellets to be analyzed by the analysis system 100 are manufactured by a pellet manufacturing apparatus 5. Pellets are an example of granular materials. The analysis system 100 may be configured to analyze pellets manufactured by multiple pellet manufacturing apparatuses 5 and present each analysis result to a user terminal 2 of the same or different users.

[0020] The pellet manufacturing apparatus 5 includes, for example, an extruder, a granulator, etc., and produces granular pellets by cutting the molten resin extruded from the extruder to a certain length by underwater cutting, strand cutting, etc., and granulating the cut resin. Examples of the raw material for the pellets include thermoplastic resins such as polypropylene (PP). The pellets may have a shape such as a perfect sphere, an oval sphere, a cylinder, or a prism. The pellets produced by the pellet manufacturing apparatus 5 can be used as a raw material for, for example, injection molding, blow molding, etc.

[0021] In this system, the information processing device 1 automatically performs a pellet analysis process based on the pellet image. In this embodiment, the pellet analysis process involves determining the size of each pellet. The particle size includes, for example, the particle area, pixel count, and particle size based on the pellet image. The information processing device 1 also determines a distribution map showing the distribution of particle sizes and statistical values ​​related to the particle sizes based on the obtained particle sizes. The statistical values ​​include, for example, the total number of data, maximum value, minimum value, average value, median value, standard deviation, and coefficient of variation. Information related to the size of each particle, including the obtained particle size, distribution map, and statistical values, is provided to the user as the analysis result.

[0022] The information processing device 1 performs image analysis on the pellet image and determines the size of each pellet by recognizing each pellet included in the pellet image. In this embodiment, the positioning device 3 and the imaging device support device 4 are used to adjust the arrangement of the pellets and the imaging state during imaging, thereby improving the accuracy of the analysis.

[0023] 2 is a block diagram showing an example of the configuration of the information processing device 1 and the user terminal 2. The information processing device 1 includes a processing unit 11, a storage unit 12, and a communication unit 13. The information processing device 1 may be a single computer, or may be a computer system configured by multiple computers and peripheral devices. The information processing device 1 may be a virtual machine whose entity is virtualized, or may be a cloud.

[0024] The processing unit 11 includes one or more processors such as a central processing unit (CPU), a microprocessing unit (MPU), or a graphics processing unit (GPU). The processing unit 11 includes a memory serving as a temporary storage medium, such as a static random access memory (SRAM) or a dynamic random access memory (DRAM). The processing unit 11 may include functions such as a timer that measures the elapsed time from when a measurement start instruction is given to when a measurement end instruction is given, a counter that counts numbers, and a clock that outputs date and time information. The CPU and other components included in the processing unit 11 read and execute various computer programs stored in the storage unit 12 to control each hardware component and cause the entire device to function as the information processing device 1 of the present disclosure. The processing unit 11 may be implemented as software, or part or all of it may be implemented as hardware, such as an application specific integrated circuit (ASIC) or a field programmable gate array (FPGA).

[0025] The storage unit 12 includes a non-volatile storage device such as a hard disk or a flash memory. The storage unit 12 may be separate from the information processing device 1 and may be one or more external storage devices connected externally. The storage unit 12 stores various computer programs and data referenced by the processing unit 11. The storage unit 12 of this embodiment stores a program 1P for causing a computer to execute processing related to deriving the size of each pellet particle.

[0026] A computer program (program product) including program 1P may be provided by a non-transitory recording medium 1A on which the computer program is readably recorded. The recording medium 1A is a portable memory such as a CD-ROM, a USB memory, or an SD (Secure Digital) card. The processing unit 11 reads the desired computer program from the recording medium 1A using a reading device (not shown) and stores the read computer program in the memory unit 12. Alternatively, the computer program may be provided via communication. Program 1P may be a single computer program or may be composed of multiple computer programs. Program 1P may also be executed on a single computer or may be executed cooperatively by multiple computers.

[0027] The communication unit 13 includes a communication device that realizes communication via the network N. The processing unit 11 transmits and receives data to and from the user terminal 2 through the communication unit 13.

[0028] The configuration of the information processing device 1 is not limited to the above example, and may include, for example, a display unit that displays images, an operation unit that accepts user operations, and the like.

[0029] <User Terminal> The user terminal 2 includes a processing unit 21 , a storage unit 22 , a communication unit 23 , a display unit 24 , an operation unit 25 , and an imaging unit 26 .

[0030] The processing unit 21 includes one or more processors such as a CPU, a GPU, etc. The storage unit 22 includes a non-volatile storage device such as a hard disk or a flash memory. The storage unit 22 stores various computer programs and data referenced by the processing unit 21. The storage unit 12 of this embodiment stores a program 2P for causing a computer to execute processes related to outputting pellet images and obtaining analysis results. A computer program (program product) including the program 2P may be provided by a non-transitory recording medium 2A on which the computer program is readably recorded, or may be provided via communication.

[0031] The communication unit 23 includes a communication device that realizes communication via the network N. The processing unit 21 transmits and receives data to and from the information processing device 1 via the communication unit 23.

[0032] The display unit 24 includes a display device such as a liquid crystal display, an organic EL (Electro Luminescence) display, etc. The display unit 24 displays various information including the analysis results according to instructions from the processing unit 21.

[0033] The operation unit 25 is an interface that accepts user operations. The operation unit 25 includes, for example, a keyboard, a mouse, a touch panel device with a built-in display, a speaker, a microphone, etc. The operation unit 25 accepts operation input from the user and sends a control signal corresponding to the operation content to the processing unit 21.

[0034] The imaging unit 26 includes a camera 261 and a light-emitting unit 262 (see FIG. 4 ). The camera 261 includes a lens and an imaging element (e.g., a CCD or CMOS) (not shown) that converts incident light focused by the lens into an electrical signal. The light-emitting unit 262 includes a light-emitting element (e.g., an LED) and illuminates the imaging target. The light-emitting unit 262 irradiates light onto a predetermined range behind the user terminal 2 (toward the back of the housing) in synchronization with the timing at which the camera captures an image, for example. The light irradiated by the light-emitting unit 262 is reflected by the imaging target, and the reflected light is received by the camera 261, thereby acquiring an image. The camera 261 has an imaging area that is a predetermined range behind the user terminal 2 (toward the back of the housing).

[0035] 3 is a diagram illustrating an example of the configuration of the positioning tool 3. The positioning tool 3 includes a plate-shaped main body 31 that is substantially rectangular in a plan view, and a gripping portion 32 provided on one side of the main body 31. The main body 31 has a plurality of through holes 33 formed therein that penetrate the main body 31 in the thickness direction.

[0036] The multiple through holes 33 are spaced apart from one another in the plate surface direction, preferably at equal intervals. In the example shown in FIG. 1 , the multiple through holes 33 are aligned vertically and horizontally at regular intervals. Each pellet can be placed inside the through holes 33. By inserting a part or all of the pellet into the through holes 33, the pellet can be positioned. By inserting each pellet into a different through hole 33, the pellets can be easily spaced apart.

[0037] The positioning tool 3 is used with the plate surface facing up or down. A raised portion may be formed on the periphery of one side of the plate surface that faces upward during use. By surrounding the periphery of the main body 31 with the raised portion, it is possible to prevent pellets from falling off the one side of the plate surface.

[0038] The thickness dimension of the main body 31 is preferably smaller than the average height dimension of the pellets. The height dimension of the pellets means the diameter of the cross section of the pellets, which is substantially perpendicular to the length of the pellets in the extrusion direction. By making the thickness dimension of the main body 31 smaller than the average height dimension of the pellets, it is possible to prevent multiple pellets from being inserted into one through-hole 33 in an overlapping manner.

[0039] The shape and size of the through holes 33 can be appropriately set depending on the shape and size of the pellets so that the pellets can be inserted into the through holes 33. The shape of the through holes 33 is preferably circular in a plan view. The size of the through holes 33 (e.g., the diameter of the circle) is preferably slightly larger than or approximately the same as the average length of the pellets in the extrusion direction. By making the size of the through holes 33 slightly larger than or approximately the same as the average length of the pellets in the extrusion direction, it is possible to prevent multiple pellets from being inserted into one through hole 33. It is preferable that the shape and size of each through hole 33 provided in one positioning tool 3 are approximately the same.

[0040] The positioning tool 3 may include a plurality of types of positioning tools 3 having different sizes of through holes 33. For example, a positioning tool 3 for large pellets having a large-sized through hole 33 formed therein and a positioning tool 3 for small pellets having a through hole 33 smaller than that of the positioning tool 3 for large pellets may be prepared.

[0041] 3, the analyst fixes the positioning tool 3 on a substantially horizontal placement stand 6 such as a fixed stand or tray, with the plate surface facing up or down, and after inserting each of the pellets PE into the different through-holes 33, removes the positioning tool 3 upward from the stand or tray, etc. In this way, the pellets PE are spaced apart in the horizontal direction so as not to overlap or touch each other.

[0042] It is preferable that the surface of the placement table 6 is matte-treated. By matting the surface of the placement table 6, which serves as the background when capturing an image of the pellets, unnecessary reflections when capturing an image of the pellets are suppressed, thereby improving the accuracy of recognizing the pellets in the pellet image. A matte-treated background plate may be provided on the placement table 6.

[0043] The placement table 6 may be provided with at least one first position marker 61 indicating the installation position of the positioning tool 3. When the first position marker 61 is provided, it is preferable to insert the pellet into the through-hole 33 with the positioning tool 3 aligned with the first position marker 61. The placement table 6 may be provided with at least one second position marker 62 indicating the installation position of the imaging device support tool 4 described below.

[0044] 4 is a diagram illustrating an example configuration of the imaging device support 4. The imaging device support 4 holds the user terminal 2 when photographing a pellet, thereby adjusting the relative positional relationship between the pellet and the user terminal 2 to a predetermined positional relationship.

[0045] The imaging device support 4 is, for example, a box having a substantially rectangular parallelepiped shape, and includes a first opening 41 that opens on the bottom surface, an upper surface 42, and side surfaces 43. The imaging device support 4 is used with the bottom surface facing downward.

[0046] The first opening 41 has an opening area that is larger than at least the area in which the through-hole 33 of the positioning tool 3 is formed. The first opening 41 may be formed in a part of the bottom surface.

[0047] A recess 421 is formed on the top surface 42 as a support portion for supporting the user terminal 2. A second opening 422 is formed in the recess 421 to expose the lens of the camera 261 and the light-emitting portion 262 of the imaging portion 26 of the user terminal 2. In the example shown in Fig. 4, the second opening 422 is formed in one corner of the recess 421, which has a substantially rectangular shape, to accommodate a user terminal 2 in which the imaging portion 26 is arranged in one corner of the back surface of the user terminal 2. The second opening 422 is preferably formed approximately near the center of the top surface 42. The shapes and sizes of the recess 421 and the second opening 422 can be set as appropriate to accommodate the shape and size of the user terminal 2 that is expected to be used.

[0048] As a constituent material of the imaging device support 4, a light-opaque material, metal, or the like is suitable from the viewpoint of preventing leakage of light emitted by the light-emitting unit 262 of the user terminal 2 to the outside. The imaging device support 4 may be colored or coated with a light-opaque material such as carbon black on its outer periphery. The surface of the recess 421 may be provided with a protective material with cushioning properties to prevent misalignment of the user terminal 2 and to improve protection.

[0049] The imaging device support 4 may have any other configuration as long as it has a mechanism that can support the user terminal 2 at a specific position relative to the pellet. The imaging device support 4 is not limited to a box, and may be, for example, a stand.

[0050] 4, the analyst adjusts the positions of the pellets PE and the first openings 41 so as to cover the pellets P arranged on a substantially horizontal placement table 6, and places the imaging device support 4 on the placement table 6 with the first openings 41 facing downward. When the second position marker 62 is provided, it is preferable to place the imaging device support 4 on the placement table 6 in a state where the imaging device support 4 is aligned with the second position marker 62.

[0051] The analyst places the user terminal 2 on the recess 421 with the back of the user terminal 2 facing downward and aligning at least one corner where the imaging unit 26 is located with one corner of the recess 421. This aligns the imaging unit 26 of the user terminal 2 with the second opening 422. The imaging device support 4 can support the user terminal 2 while fixing the positional relationship between the user terminal 2 and the imaging unit 26 with respect to the pellet PE. In other words, the imaging device support 4 can adjust the relative position and distance between the pellet PE and the user terminal 2 to a predetermined position and distance.

[0052] By fixing the positional relationship of the user terminal 2 and the imaging unit 26 with respect to the pellet PE, it is possible to align the imaging range, light intensity, etc., even when, for example, imaging is performed multiple times in succession. By using at least one of the first position marker 61 and the second position marker 62 to position at least one of the placement position of the pellet PE and the position of the user terminal 2, it is possible to bring the relative positional relationship between the pellet PE and the user terminal 2 closer to a predetermined positional relationship.

[0053] <Pellet Analysis Method (Processing Procedure)> Fig. 5 is a flowchart showing an example of a pellet analysis method. The following description will be given assuming that the processes of steps S11 to S13 are performed by an analyst, and the processes of step S14 and subsequent steps are performed by the information processing device 1. The processing unit 11 of the information processing device 1 executes the processes of step S14 and subsequent steps in accordance with a program 1P stored in the storage unit 12.

[0054] The analyst prepares a predetermined number of pellets produced by the pellet production device 5 as the analysis target. The analyst uses the positioning tool 3 to position each of the prepared pellets, arranging the pellets on the arrangement table 6 so that they are spaced apart from one another (step S11). If multiple positioning tools 3 are prepared, the analyst selects from the multiple positioning tools 3 a positioning tool 3 into which the manufactured pellets can be inserted, depending on the state of the manufactured pellets. If multiple positioning tools 3 can be selected, the one with the smallest through hole 33 can be selected preferentially. Note that the use of the positioning tool 3 is not essential if the pellets can be spaced apart.

[0055] Each pellet is preferably placed on the placement table 6 in such a position that the extrusion direction of the pellet is horizontal. The analyst may adjust the position of the pellet by, for example, applying a certain amount of vibration to each pellet with the positioning tool 3 installed or removed.

[0056] After the pellets are arranged, the analyst may observe each pellet to determine whether the pellets are arranged at an appropriate interval. If it is determined that the pellets are arranged at an appropriate interval, the analyst proceeds to the next step S12. If it is determined that the pellets are not arranged at an appropriate interval, the analyst may, for example, rearrange the pellets using the same positioning tool 3, correct the arrangement without using the positioning tool 3, or rearrange the pellets using a different positioning tool 3, depending on the number of pellets that are not arranged at an appropriate interval.

[0057] The analyst places the imaging device support 4 on the placement stand 6 so as to cover the arranged pellets, and supports the user terminal 2 on the placed imaging device support 4 (step S12).

[0058] The analyst takes an image of the pellet by operating the user terminal 2 while it is supported by the imaging device support 4 (step S13). Note that the use of the imaging device support 4 is not essential when taking an image of the pellet.

[0059] The processing unit 21 of the user terminal 2 causes the imaging unit 26 to capture an image of the pellet. The imaging unit 26 generates a pellet image including the pellet. For example, if the resin pellet is white, the brightness of the pixels corresponding to the pellet grains in the pellet image is higher than the brightness of the pixels corresponding to the background other than the pellet grains. The pellet image may include a scale bar for identifying the size of the pellet. The processing unit 21 transmits the pellet image obtained by imaging to the information processing device 1, for example, based on the operation of the analyst.

[0060] If the number of grains to be analyzed is greater than the total number of through-holes 33 in the positioning tool 3, the analyst may repeat the processes of steps S11 to S13 multiple times and capture multiple images. The processes of steps S11 to S13 are performed, for example, at the site where the pellet manufacturing apparatus 5 is installed.

[0061] The processing unit 11 of the information processing device 1 acquires the pellet image by receiving it from the user terminal 2 (step S14). The pellet image may be associated with the imaging magnification at which the image was captured.

[0062] The processing unit 11 derives the size of each pellet contained in the pellet image based on the acquired pellet image (step S15). In this embodiment, as an example, the number of pixels of each pellet in the pellet image is derived. Note that the processing unit 11 may also perform predetermined preprocessing on the acquired pellet image and derive the size of each pellet based on the pellet image after preprocessing. Examples of preprocessing include grayscale conversion processing that converts an image containing RGB (Red, Green, Blue) values ​​into a grayscale image.

[0063] 6 is a flowchart showing an example of a detailed procedure for deriving the size of each particle. The processing procedure shown in the flowchart of FIG. 6 corresponds to the details of step S15 in the flowchart of FIG.

[0064] The processing unit 11 performs a binarization process on the pellet image that has been subjected to predetermined preprocessing as necessary (step S21). The processing unit 11 converts pixel values ​​of the pellet image to 0 (black) or 1 (white) through the binarization process. The method of the binarization process is not particularly limited, but for example, the brightness value (pixel value) of a pixel is compared with a predetermined threshold, and if the pixel value is equal to or greater than the threshold, the pixel value is set to 1. The threshold may be set in advance by an analyst, taking into account, for example, the color of the pellet.

[0065] The processing unit 11 analyzes the binarized image obtained by the binarization process to identify regions where the pixel value is equal to or greater than a threshold as pellet regions (step S22), and extracts the boundaries of each of the identified pellet regions (step S23). The processing unit 11 calculates the number of pixels in each of the identified pellet regions, i.e., the number of pixels of each pellet (step S24). The processing unit 11 may store the calculation results of the number of pixels for each pellet region in the storage unit 12 as a file in a predetermined file format, such as a CSV file. The processing unit 11 then returns to step S16 in the flowchart of FIG. 5.

[0066] 5 , the processing unit 11 generates a histogram showing the distribution of the pixel counts of the particles based on the derived pixel counts of each particle (step S16). Based on the derived pixel counts for each particle, the processing unit 11 calculates statistical values ​​including, for example, the total number of particles, the maximum value, minimum value, average value, median value, standard deviation, and coefficient of variation of the pixel counts (step S17).

[0067] The processing unit 11 may convert the derived size of each particle into another index value using a predetermined coefficient or function formula. For example, the processing unit 11 may convert the number of pixels of each particle into the weight of each particle using a predetermined coefficient or function formula.

[0068] The processing unit 11 generates an analysis result screen showing the analysis results including at least one of the derived pixel count, histogram, and statistical value for each pellet (step S18). The processing unit 11 transmits the generated analysis result screen to the user terminal 2, which is the sender of the pellet image to be analyzed (step S19), and ends the series of processes.

[0069] The processing entity in the above flowchart is not limited. Part or all of the processing executed by the information processing device 1 may be executed by the user terminal 2, for example.

[0070] In the above description, the analysis results are configured to be output (displayed) through the display unit 24 of the user terminal 2, but the analysis results may also be output to the display unit of the information processing device 1 or to a device other than the user terminal 2. The analysis results may also be output to a printing device or the like and presented to the user on paper media. The analysis results may also be output to a processing unit or software within or outside the information processing device 1 for executing various processes based on the analysis results.

[0071] Although the above describes an example in which the user terminal 2 functions as an imaging device for pellet images and a display device for analysis results, the imaging device and the display device do not have to be a single common user terminal 2, but may be provided as separate devices. The information processing device 1 is not limited to one that receives pellet images via the user terminal 2, but may also receive pellet images via an input unit of its own device.

[0072] <Analysis Result Screen> Fig. 7 is a schematic diagram showing an example of the analysis result screen 241. The processing unit 21 of the user terminal 2 causes the display unit 24 to display the analysis result screen 241 shown in Fig. 7 based on the screen information acquired from the information processing device 1.

[0073] The analysis result screen 241 includes, for example, an image display section 242 that displays the pellet image to be analyzed, a graph display section 243 that displays a histogram, and a statistical value display section 244 that displays various statistical values.

[0074] The information processing device 1 displays the pellet image acquired as the analysis target on the image display unit 242. Information indicating the recognition result of each pellet may be superimposed on the pellet image displayed on the image display unit 242. The information processing device 1 performs image processing to visibly indicate the boundaries of each pellet region, such as superimposing a boundary line indicating the boundary of each pellet region extracted in step S23 on the pellet image, as shown in FIG. 7 . The information processing device 1 may also perform image processing to visibly indicate each pellet region, such as coloring each pellet region or performing mask processing.

[0075] The information processing device 1 generates a histogram based on the pixel counts of all pellet regions included in the pellet image and displays it on the graph display unit 243. The histogram is a graph with the pixel count on the horizontal axis and the number of pellet regions (number of pellets) on the vertical axis. Note that the distribution diagram showing the distribution of pixel counts is not limited to a histogram, and may be a scatter plot, pie chart, or other form of diagram.

[0076] The information processing device 1 calculates various statistical values ​​based on the number of pixels in all pellet regions included in the pellet image, and displays the calculated various statistical values ​​in a list on the statistical value display unit 244.

[0077] The analyst can accurately grasp the state of the pellets through the analysis result screen 241.

[0078] According to this embodiment, the information processing device 1 automatically derives information about the pellet size based on the pellet image, thereby reducing the time and effort required for analyzing the pellets. By presenting a distribution map and various statistical values, the interpretability of the analysis results is improved, and the state of the pellets can be easily and accurately understood.

[0079] By spacing the pellets apart, each individual pellet in the image can be accurately recognized, improving the accuracy of analyzing the number of pellets and the size of each pellet. Using a binarization process allows for efficient and accurate detection and size calculation of pellets. Using a segmentation model allows for accurate detection of a variety of pellets.

[0080] The use of the positioning fixture 3 allows the pellets to be spaced apart easily and efficiently, and also ensures excellent uniformity in the pellet placement. The use of the imaging device support fixture 4 allows the conditions during photography to be kept constant, eliminating the need for adjustments for each photography. In addition, data integration is facilitated when processing multiple pellet images in an integrated manner.

[0081] Applying the analytical method of the present disclosure to resin pellets that can be used as raw materials for plastic molding, such as injection molding and blow molding, which require uniformity in particular, and that are manufactured using a pellet manufacturing device equipped with an extruder, is advantageous because it allows for efficient acquisition of desired analytical results.

[0082] Second Embodiment In the second embodiment, the details of the grain size derivation process are different from those in the first embodiment. The following mainly describes the differences from the first embodiment, and the same reference numerals are used to designate components that are common to the first embodiment, and detailed descriptions thereof will be omitted.

[0083] 8 is a schematic diagram of an analysis system 100 according to the second embodiment. The analysis system 100 according to the second embodiment is capable of transmitting and receiving data to and from an image analysis server 7 via a network N.

[0084] The image analysis server 7 is a server device equipped with a segmentation model 71. The segmentation model 71 is a model for segmenting objects in an image. The information processing device 1 of the second embodiment uses the segmentation model 71 to detect pellet grains from a pellet image. Note that the segmentation model 71 is not limited to being provided by the image analysis server 7, and may be configured to be provided in the storage unit 12 of the information processing device 1.

[0085] The segmentation model 71 is a learning model generated by machine learning. The configuration of the segmentation model 71 is not particularly limited, and can be constructed using a known learning algorithm. The segmentation model 71 may be constructed using, for example, SAM (Segment Anything Model), U-Net, NN (Neural Network), CNN (Convolutional Neural Network), R-CNN (Regions with Convolutional Neural Networks), Mask R-CNN, YOLO (You Only Look Once), Transformer, SegNet, Deeplab, PSPNet (Pyramid Scene Parsing Network), BiSeNet (Bilateral Segmentation Network), support vector machine, regression tree, or the like. As the segmentation model 71, a model capable of recognizing objects (pellets) in an image on a pixel-by-pixel basis is preferred.

[0086] In the following description, it is assumed that the segmentation model 71 is a SAM. The SAM is a general-purpose segmentation model constructed by performing pre-training. The SAM segments objects in an image on a pixel-by-pixel basis. The SAM can also segment objects in a specific region in an image.

[0087] Fig. 9 is a flowchart showing an example of a detailed procedure for deriving the size of each particle in the second embodiment. The processing procedure shown in the flowchart in Fig. 9 corresponds to the details of step S15 in the flowchart in Fig. 5. Of the analysis processing in the second embodiment, the processing other than step S15 is the same as in the first embodiment.

[0088] The processing unit 11 of the information processing device 1 inputs the pellet image, which has been subjected to predetermined preprocessing as necessary, to the segmentation model 71 provided by the image analysis server 7 or to the segmentation model 71 that has been trained in the information processing device 1 (step S31). The processing unit 11 acquires the pellet detection result output from the segmentation model 71 (step S32). The detection result from the segmentation model 71 includes the position and range of the image area corresponding to the pellet, the number of pixels in the image area corresponding to the pellet, etc. Note that the processing unit 11 may calculate the number of pixels based on the detection by the segmentation model 71.

[0089] In the above-described process, the processing unit 11 may specify coordinate points or rectangular areas in the pellet image to the segmentation model 71 to perform segmentation. The coordinate points or rectangular areas can be specified taking into consideration the position of each pellet so as to correspond to each of the multiple pellets included in the pellet image. When arranging pellets using the positioning tool 3, if the position of each through-hole 33 of the positioning tool 3 can be obtained in advance, the processing unit 11 may store in advance coordinate points or rectangular areas set to correspond to the position and size of each through-hole 33.

[0090] According to this embodiment, by using the segmentation model 71, pellets can be easily and accurately detected from a pellet image. By using the SAM, detection accuracy can be improved, especially for highly transparent pellets. By specifying areas in the image corresponding to the respective positions of each pellet and performing segmentation, each pellet can be properly detected. By taking into account the structure of the positioning tool 3, it becomes easy to specify the areas in the image.

[0091] The application of the analysis system 100 is not limited to pellets, but can be widely applied to the analysis of granular materials other than pellets, such as feed for livestock and pets, agricultural and horticultural fertilizers, pharmaceuticals, wood pellets used in biomass power generation, rice grains, etc.

[0092] The embodiments disclosed herein are illustrative in all respects and should not be considered limiting. The technical features described in each embodiment can be combined with each other, and the scope of the present invention is intended to include all modifications within the scope of the claims and equivalents thereto. The sequences shown in each embodiment are not limited, and within the scope of no contradiction, each processing step may be executed in a different order, or multiple processes may be executed in parallel. The entity that performs each process is not limited, and within the scope of no contradiction, the process of each device may be executed by another device.

[0093] The matters described in each embodiment can be combined with each other. Furthermore, the independent claims and dependent claims described in the claims can be combined with each other in any and all combinations, regardless of the reference format. Furthermore, the claims use a format in which a claim references two or more other claims (multiple claim format), but this is not limited to this. A multiple claim (multi-multi claim) that references at least one other multiple claim may also be used.

[0094] The following supplementary notes are further disclosed with respect to the above embodiments. (Supplementary Note 1) An analysis method in which a computer acquires an image of a plurality of granular bodies, derives the size of each granular body included in the image based on the acquired image, and outputs information about the derived size of each granular body. (Supplementary Note 2) The analysis method according to Supplementary Note 1, in which the information about the size of each granular body includes at least one of a distribution map showing the distribution of granular body sizes and statistics of the sizes of each granular body. (Supplementary Note 3) The analysis method according to Supplementary Note 1 or Supplementary Note 2, in which the image is an image of the plurality of granular bodies arranged at a distance from one another. (Supplementary Note 4) The analysis method according to any one of Supplementary Notes 1 to 3, in which a binarization process is performed on the image, and the size of each granular body is derived based on the image after the binarization process. (Supplementary Note 5) The analysis method according to any one of Supplementary Notes 1 to 4, in which the size of each granular body included in the image is derived using a segmentation model. (Supplementary Note 6) The analysis method according to any one of Supplementary Notes 1 to 5, wherein the image is an image of a plurality of granular objects positioned by placing the granular objects in each hole of a jig having a plurality of holes spaced apart from one another. (Supplementary Note 7) The analysis method according to any one of Supplementary Notes 1 to 6, wherein the image is an image of an imaging device supported by an imaging device support for adjusting the relative positional relationship between the plurality of granular objects and the imaging device to a predetermined positional relationship. (Supplementary Note 8) The analysis method according to any one of Supplementary Notes 1 to 7, wherein the image is an image of the plurality of granular objects against a matte background. (Supplementary Note 9) The analysis method according to any one of Supplementary Notes 1 to 8, wherein the granular objects are resin pellets. (Supplementary Note 10) An analysis method comprising: using a jig having a plurality of holes spaced apart from one another, placing granular bodies in each hole of the jig to arrange the plurality of granular bodies at a distance from one another; supporting an imaging device on an imaging device support that adjusts the relative positional relationship between the plurality of granular bodies and the imaging device to a predetermined positional relationship; acquiring images of the plurality of granular bodies using the imaging device supported on the imaging device support; deriving the size of each granular body contained in the image based on the acquired images; and outputting information related to the derived size of each of the granular bodies.(Supplementary Note 11) The analysis method according to Supplementary Note 10, wherein the information relating to the size of each granular body includes at least one of a distribution map showing a distribution of granular body sizes and statistical values ​​of the sizes of each granular body. (Supplementary Note 12) The analysis method according to Supplementary Note 10 or Supplementary Note 11, wherein the image is an image of the plurality of granular bodies arranged at a distance from one another. (Supplementary Note 13) The analysis method according to any of Supplementary Notes 10 to 12, wherein a binarization process is performed on the image, and the size of each granular body is derived based on the image after the binarization process. (Supplementary Note 14) The analysis method according to any of Supplementary Notes 10 to 13, wherein the size of each granular body included in the image is derived using a segmentation model. (Supplementary Note 15) The analysis method according to any of Supplementary Notes 10 to 14, wherein the image is an image of the plurality of granular bodies against a matte background. (Supplementary Note 16) The analytical method according to any one of Supplementary Note 10 to Supplementary Note 15, wherein the granular material is a resin pellet.

[0095] REFERENCE SIGNS LIST 100 Analysis system 1 Information processing device 11 Processing unit 12 Storage unit 13 Communication unit 1P Program (computer program) 1A Recording medium 2 User terminal 21 Processing unit 22 Storage unit 23 Communication unit 24 Display unit 25 Operation unit 26 Imaging unit 2P Program (computer program) 2A Recording medium 3 Positioning tool (jig) 33 Through-hole 4 Imaging device support tool

Claims

1. An analysis method in which a computer acquires images of a plurality of granular bodies, derives the size of each granular body contained in the images based on the acquired images, and outputs information regarding the derived size of each granular body.

2. The analytical method according to claim 1, wherein the information relating to the size of each of the granular bodies includes at least one of a distribution diagram showing the distribution of the sizes of the granular bodies and statistical values ​​of the sizes of each of the granular bodies.

3. The analytical method according to claim 1 or claim 2, wherein the image is an image of the plurality of granular bodies arranged at a distance from each other.

4. An analysis method according to any one of claims 1 to 3, further comprising: performing a binarization process on the image; and deriving the size of each of the granular bodies based on the image after the binarization process.

5. The analysis method according to any one of claims 1 to 4, wherein the size of each granular body contained in the image is derived using a segmentation model.

6. An analytical method according to any one of claims 1 to 5, wherein the image is an image of a plurality of granular bodies positioned by placing the granular bodies in each hole of a jig having a plurality of holes spaced apart from one another.

7. An analysis method described in any one of claims 1 to 6, wherein the image is captured by an imaging device supported by an imaging device support for adjusting the relative positional relationship between the multiple granular bodies and the imaging device to a predetermined positional relationship.

8. The analytical method according to any one of claims 1 to 7, wherein the image is an image of the plurality of granular bodies against a matte background.

9. The analytical method according to any one of claims 1 to 8, wherein the granular material is a resin pellet.

10. An analytical method comprising: using a jig having a plurality of holes spaced apart from one another, placing granular bodies in each of the holes in the jig to arrange the granular bodies at a distance from one another; supporting the imaging device on an imaging device support that adjusts the relative positional relationship between the plurality of granular bodies and the imaging device to a predetermined positional relationship; acquiring images of the plurality of granular bodies using the imaging device supported on the imaging device support; deriving the size of each granular body contained in the images based on the acquired images; and outputting information related to the derived size of each of the granular bodies.

11. A computer program that causes a computer to execute the following process: acquire images of a plurality of granular bodies; derive the size of each granular body contained in the images based on the acquired images; and output information relating to the derived size of each granular body.

12. An analysis system comprising a processing unit that executes the following processes: acquiring an image of a plurality of granular bodies; deriving the size of each granular body contained in the image based on the acquired image; and outputting information relating to the derived size of each granular body.

13. The analytical system according to claim 12, comprising a jig having a plurality of holes spaced apart from one another.

14. An analysis system according to claim 12 or claim 13, further comprising an imaging device support for adjusting the relative positional relationship between the plurality of granular bodies and the imaging device to a predetermined positional relationship.

Images