Inspection system

Abstract

The present invention provides an inspection system to inspect for the presence or absence of foreign matter in a liquid sealed in a container, the inspection system comprising: a flow inducing means for causing the liquid in the container to flow; a micro-vibration applying means for causing the container in which the liquid flows to micro-vibrate; and a detecting means for detecting and tracking floating matter present in the liquid in a time series of images obtained by continuously taking, with a camera, images of the liquid in the micro-vibrating container, and detecting the presence or absence of foreign matter on the basis of the movement trajectory of the tracked floating matter.

Description

[Technical Field]

[0001] The present invention relates to an inspection system, an inspection method, and a recording medium. [Background Art]

[0002] As a system for inspecting the presence or absence of foreign matter in a liquid sealed in a container, a system has been proposed in which after flowing the liquid in the container, the behavior of suspended matters in the liquid is observed, it is determined that the finally floating suspended matter is an air bubble, and the settling suspended matter is determined to be a foreign matter (see, for example, Patent Document 1). [Prior Art Documents] [Patent Documents]

[0003] [Patent Document 1] WO2021 / 214994 [Summary of the Invention] [Problem to be Solved by the Invention]

[0004] There are many types of foreign matter that may be mixed into a liquid, and the difference in specific gravity of the foreign matter relative to the liquid varies. Unlike foreign matter with high specific gravity such as metal fragments and glass fragments, foreign matter with low specific gravity such as fiber fragments takes time before behavior characteristic of foreign matter such as sedimentation can be observed. Therefore, there has been a problem that inspection efficiency decreases. Particularly in the case of high-viscosity liquids, the inspection efficiency decreases significantly.

[0005] An object of the present invention is to provide an inspection system that solves the problem of reduced inspection efficiency. [Means for Solving the Problem]

[0006] An inspection system according to one aspect of the present invention is an inspection system for inspecting the presence or absence of foreign matter in a liquid sealed in a container, comprising: flow inducing means for flowing the liquid in the container; and A means for applying micro-vibrations to cause the container in which the liquid flows to vibrate slightly, A first detection means detects and tracks suspended particles present in the liquid within a time-series image obtained by continuously photographing the liquid in the container during the aforementioned micro-vibrations using a camera, and detects the presence or absence of foreign matter based on the movement trajectory of the tracked suspended particles. It is configured to include the following:

[0007] Another embodiment of the present invention is an inspection method, A testing method for inspecting the presence or absence of foreign matter in a liquid sealed in a container, The liquid in the container is made to flow, The container in which the liquid flows is made to vibrate slightly, The liquid inside the container during the aforementioned micro-vibrations is continuously photographed by a camera to obtain a time-series of images in which suspended particles present in the liquid are detected and tracked, and the presence or absence of foreign matter is detected based on the movement trajectory of the tracked suspended particles. It is structured in this way.

[0008] Another embodiment of the present invention is a computer-readable recording medium, A computer that inspects for foreign matter in the liquid sealed in a container, A process of causing the liquid in the container to flow, A process of causing the container in which the liquid flows to vibrate slightly, The process involves continuously capturing images of the liquid in the container while it is vibrating using a camera, detecting and tracking suspended particles in the liquid within the resulting time-series images, and then detecting the presence or absence of foreign matter based on the movement trajectory of the tracked suspended particles. It is configured to record a program to perform that action. [Effects of the Invention]

[0009] By having the configuration described above, the present invention can shorten the time required to observe behaviors specific to foreign objects, such as sedimentation, thereby improving inspection efficiency. [Brief explanation of the drawing]

[0010] [Figure 1] It is a schematic diagram illustrating a schematic configuration of an inspection system that implements the inspection method according to the first embodiment of the present invention. [Figure 2] It is an explanatory diagram showing an example of a container to be inspected and a vibration direction in the first embodiment of the present invention. [Figure 3] It is a block diagram illustrating an example of the information processing apparatus in the first embodiment of the present invention. [Figure 4] It is a diagram illustrating a configuration example of a time-series image in the first embodiment of the present invention. [Figure 5] It is a diagram illustrating a configuration example of a corrected time-series image in the first embodiment of the present invention. [Figure 6] It is a diagram illustrating a configuration example of tracking information in the first embodiment of the present invention. [Figure 7] It is a diagram illustrating a configuration example of inspection result information in the first embodiment of the present invention. [Figure 8] It is a flowchart illustrating an example of pre-processing performed by the inspection system in the first embodiment of the present invention. [Figure 9] It is a flowchart illustrating an example of inspection processing performed on a container to be inspected by the inspection system in the first embodiment of the present invention. [Figure 10] It is a block diagram illustrating an example of the information processing apparatus in the second embodiment of the present invention. [Figure 11] It is a flowchart illustrating an example of inspection processing performed on a container to be inspected by the inspection system in the second embodiment of the present invention. [Figure 12] It is a configuration diagram of essential parts of the inspection system in the fourth embodiment of the present invention. [Figure 13] It is a configuration diagram of essential parts of the inspection system in the fifth embodiment of the present invention. [Figure 14] It is a block diagram of the inspection system in the sixth embodiment of the present invention. Mode for Carrying Out the Invention

[0011] [First Embodiment] First, the liquid to be inspected in the first embodiment of the present invention will be described.

[0012] Generally, liquids are classified into Newtonian fluids and non-Newtonian fluids, and non-Newtonian fluids are further divided into shear-thinning fluids and shear-thinning fluids. Of these, shear-thinning fluids have the characteristic that their viscosity decreases as the applied deformation rate (shear rate) increases (this is referred to as non-Newtonian viscosity). Typical examples of shear-thinning fluids are Bingham fluids (such as fresh cream and butter) and pseudoplastic fluids (such as polymer solutions). Liquids with this non-Newtonian viscosity characteristic decrease in viscosity as the applied deformation rate increases. When viscosity decreases, the settling rate of foreign matter such as fiber fragments and metal fragments, which are denser than the liquid, increases. Therefore, the time until the behavior specific to foreign matter, such as settling, can be observed can be shortened. Note that non-Newtonian viscosity returns to its original viscosity when the applied deformation rate falls below a certain level (including zero). Therefore, in order to photograph and observe the behavior of suspended matter in the liquid with the camera device 6 when viscosity has decreased, it is necessary to continuously apply micro-vibrations to the container 2 while photographing with the camera device 6.

[0013] The liquid to be tested in this embodiment is a liquid exhibiting the non-Newtonian viscosity characteristics described above. The type of liquid is not limited as long as it exhibits non-Newtonian viscosity characteristics. For example, the liquid may be a liquid medicine or drinking water.

[0014] Next, the configuration and operation of the first embodiment of the present invention will be described in detail.

[0015] Figure 1 is a schematic diagram showing the general configuration of an inspection system 1 that implements an inspection method according to the first embodiment of the present invention. Referring to Figure 1, the inspection system 1 is a system that inspects for the presence or absence of foreign matter in a liquid sealed in a container 2. The inspection system 1 mainly comprises a flow induction device 3, a micro-vibration device 4, a lighting device 5, a camera device 6, and an information processing device 7.

[0016] Container 2 is a transparent or translucent, roughly cylindrical container, such as a glass bottle. Container 2 contains a transparent or translucent liquid exhibiting non-Newtonian viscosity. For example, container 2 could be a syringe or vial filled with a liquid drug exhibiting non-Newtonian viscosity. Such a liquid may contain foreign matter. Possible foreign matter includes, for example, glass fragments, metal fragments, rubber fragments, hair, fiber fragments, and soot. Of these, glass or metal fragments have the highest specific gravity, while hair, fiber fragments, and soot have the lowest, and rubber fragments have an intermediate specific gravity. However, since the specific gravity of all these foreign matter is higher than that of the liquid contained in container 2, when the liquid is stable, they sink near the bottom of container 2 and do not float. Therefore, the inspection system 1 uses a flow induction device 3 to induce flow in the liquid inside container 2, allowing the foreign matter to be observed as floating particles.

[0017] The fluid induction device 3 may be a device comprising, for example, a container gripping part that grips the container 2 in an upright position, and a rotation mechanism that rotates the container gripping part around a center line that passes from the center of the bottom surface to the center of the top surface of the container 2. Alternatively, the fluid induction device 3 may be a device comprising a container gripping part that grips the container 2 in an upright position, and a tilting mechanism that repeatedly tilts the container gripping part so that the axis of the container 2 is tilted in a predetermined direction, and then returns it to an upright position. In addition, the fluid induction device 3 may have any configuration as long as it is a device that can make the liquid sealed in the container 2 flow.

[0018] The micro-vibration device 4 is a device that causes the container 2 to vibrate slightly. The micro-vibration device 4 is configured to cause the container 2 to vibrate slightly along a predetermined micro-vibration trajectory. The micro-vibration trajectory is defined by a total of three parameters: the direction of vibration θ, the frequency f, and the displacement Δd.

[0019] The direction θ for causing micro-vibrations should preferably be one that more uniformly agitates the entire liquid in container 2. Such a direction can be generally determined by the shape of container 2. For example, as shown in Figure 2, if container 2 is a long, slender syringe, it is desirable to vibrate it in a direction perpendicular to the cylindrical axis. That is, if the cylindrical axis of container 2 in a stationary state is the Z-axis, and the axes perpendicular to it are the X-axis and Y-axis, it is desirable to make the direction parallel to the XY plane the direction in which container 2 is caused to vibrate. The same applies to bottle-shaped vials, etc. However, the trajectory of the micro-vibrations is not limited to a straight line, but may also be a curve such as a circular arc or an ellipse.

[0020] The frequency f of the micro-vibration and the displacement Δd determine the magnitude of the kinetic energy imparted to the liquid in the container by the micro-vibration. For highly viscous liquids, it is desirable to set a larger value for f × Δd in order to increase the kinetic energy and reduce viscosity. However, due to limitations imposed by the field of view of the camera device 6 and the need to miniaturize the inspection system, it is undesirable to make the displacement Δd larger than a certain level. Therefore, if the frequency f is below a certain level, it is difficult to impart sufficient kinetic energy to the liquid. For this reason, the frequency f should be at least 10 Hz or higher, and preferably 100 Hz or higher. The frequency band above 100 Hz may or may not include the ultrasonic band.

[0021] Various configurations are possible for the micro-vibration device 4 that causes the container 2 to vibrate along a micro-vibration trajectory. For example, the micro-vibration device 4 may be a device comprising a container gripping part that grips the container 2 in an upright position, and a reciprocating vibration mechanism that causes the container gripping part to vibrate back and forth along the micro-vibration trajectory in the range of +Δd and -Δd and at a frequency f. The reciprocating vibration mechanism may include, for example, a planar cam mechanism that converts the rotational motion of a rotary motor into reciprocating motion. Alternatively, the micro-vibration device 4 may be a device comprising a container gripping part that grips the container 2 in an upright position, and a reciprocating rotation mechanism that causes the container gripping part to reciprocate in the range of +α and -α (α is, for example, 90° or less) and at a frequency f, around a center line that passes from the center of the bottom surface to the center of the top surface of the container 2. In addition, the micro-vibration device 4 may have any configuration as long as it is a device that can cause the container 2 to vibrate.

[0022] Furthermore, the container gripping section for gripping the container 2 may be shared between the flow induction device 3 and the micro-vibration device 4, or it may be independent. By sharing the container gripping section between both devices, the time and effort required to transfer the container 2 between the devices can be reduced. In addition, the rotation mechanism of the flow induction device 3 and the reciprocating rotation mechanism of the micro-vibration device 4 may be shared. That is, the container 2 may be rotated repeatedly in directions such as +360° and -360° by a rotation mechanism that rotates the container 2 around a center line passing from the center of the bottom surface to the center of the top surface, thereby inducing liquid flow, and micro-vibrations may be applied by repeatedly rotating the container 2 in directions such as +90° and -90°.

[0023] The illumination device 5 is configured to irradiate the liquid flowing within the container 2 under inspection with illumination light. The illumination device 5 is, for example, a spot light source large enough to illuminate the entire liquid in the container 2 under inspection. The illumination device 5 is installed on the same side as the camera device 6 is installed, or on the opposite side, from the container 2. That is, the illumination by the illumination device 5 is transmitted illumination or reflected illumination. In the following description, the illumination device 5 will be described assuming that it is installed on the side opposite to the camera device 6, from the container 2.

[0024] The camera device 6 is an imaging device that continuously photographs the liquid flowing inside the container 2 at a predetermined frame rate from a fixed position opposite to the side where the illumination device 5 is installed, as viewed from the container 2. The predetermined frame rate may be, for example, less than 100 fps or 100 fps or more. The camera device 6 may consist of a color camera or a monochrome camera equipped with a CCD (Charge-Coupled Device) image sensor or a CMOS (Complementary MOS) image sensor having a pixel capacity of several million pixels. The exposure time of the camera device 6 is sufficiently short compared to the shooting cycle. The camera device 6 is connected to the information processing device 7 by wire or wireless connection. The camera device 6 is configured to transmit the time-series images obtained by shooting, along with information indicating the shooting time, to the information processing device 7.

[0025] The information processing device 7 is configured to perform image processing on time-series images captured by the camera device 6 to inspect for the presence or absence of foreign matter in the liquid sealed in the container 2. The information processing device 7 is connected to the flow induction device 3, the micro-vibration device 4, the lighting device 5, and the camera device 6 by wire or wireless.

[0026] Figure 3 is a block diagram showing an example of an information processing device 7. Referring to Figure 3, the information processing device 7 includes a communication I / F unit 71, an operation input unit 72, a screen display unit 73, a storage unit 74, and an arithmetic processing unit 75.

[0027] The communication interface unit 71 consists of a data communication circuit and is configured to communicate data with the flow induction device 3, the micro-vibration device 4, the lighting device 5, the camera device 6, and other external devices (not shown) via wired or wireless connection. The operation input unit 72 consists of an operation input device such as a keyboard or mouse and is configured to detect operator operations and output them to the calculation processing unit 75. The screen display unit 73 consists of a screen display device such as an LCD (Liquid Crystal Display) or PDP (Plasma Display Panel) and is configured to display various information such as inspection results on the screen in response to instructions from the calculation processing unit 75.

[0028] The storage unit 74 consists of one or more storage devices of one or more types, such as a hard disk or memory, and is configured to store processing information and programs 741 necessary for various processes in the arithmetic processing unit 75. The programs 741 are programs that realize various processing processes when read and executed by the arithmetic processing unit 75, and are pre-read from external devices or recording media (not shown) via data input / output functions such as the communication I / F unit 71 and stored in the storage unit 74. The main processing information stored in the storage unit 74 includes pre-processing information 742, time-series images 743, corrected time-series images 744, tracking information 745, and inspection result information 746.

[0029] The pre-processing information 742 includes various pieces of information determined prior to the inspection of container 2. In this embodiment, the pre-processing information 742 includes micro-vibration trajectory information 7421 and a blur correction function 7422.

[0030] The micro-vibration trajectory information 7421 represents the trajectory in which the micro-vibration device 4 causes the container 2 to vibrate slightly. Specifically, the micro-vibration trajectory information 7421 is defined by a total of three parameters: the direction of vibration θ, the frequency f, and the displacement amount Δd.

[0031] The blur correction function 7422 is a function used to correct the blur in images obtained by the camera device 6. When a container 2 that vibrates slightly is photographed by the camera device 6, image blur occurs in the resulting image due to the movement of the subject. This type of blur is called motion blur. The degraded image caused by motion blur is generally expressed by the following equation. g(x,y)=h(x,y)*'f(x,y) ···(1) Here, f(x,y) is the original image, g(x,y) is the degraded image, h(x,y) is the PSF (Point Spread Function), and *' represents convolution. The blur correction function 7422 uses, for example, the above PSF. As will be described later, the image blur correction process is an image deconvolution process using the blur correction function 7422.

[0032] The time-series image 743 includes a series of images obtained by continuously capturing images of the liquid in container 2 while it is vibrating using the camera device 6. If suspended particles are present in the liquid in container 2, the time-series image 743 will show images of these suspended particles.

[0033] Figure 4 shows an example of the configuration of a time-series image 743. In this example, the time-series image 743 consists of entries comprising a container ID 7431, a capture time 7432, and a frame image 7433. The container ID 7431 field is set to an ID that uniquely identifies the container 2 being inspected. Possible container IDs include a serial number assigned to container 2, a barcode attached to container 2, or object fingerprint information taken from the cap of container 2. The capture time 7432 and frame image 7433 fields are set to the capture time and frame image, respectively. The capture time 7432 is set to a precision (e.g., milliseconds) that allows it to be distinguished from other adjacent frame images. In the example in Figure 4, a container ID is associated with each frame image 7433, but it is also possible to associate a container ID with a group of multiple frame images 7433.

[0034] The corrected time-series image 744 includes the frame image after correcting the image blur that occurred in the frame image 7433 included in the time-series image 743. Figure 5 shows an example of the configuration of the corrected time-series image 744. In this example, the corrected time-series image 744 consists of entries for container ID 7441, shooting time 7442, and corrected frame image 7443. The container ID 7441 and shooting time 7442 entries are set to the same container ID 7431 and shooting time 7432 as the frame image 7433 that was the subject of correction. The corrected frame image 7443 entry is set to the frame image that has been blur-corrected. In the example in Figure 4, a container ID is associated with each corrected frame image 7443, but the container ID may be associated with each group of multiple corrected frame images 7443.

[0035] The tracking information 745 contains information corresponding to the results of detecting and tracking floating objects present in the liquid inside container 2 based on the corrected time-series image 744. Figure 6 shows an example of the configuration of the tracking information 745. In this example, the tracking information 745 consists of entries for container ID 7451 and a pair of tracking ID 7452 and pointer 7453. The container ID 7451 entry is set with an ID that uniquely identifies container 2. An entry consisting of a pair of tracking ID 7452 and pointer 7453 is provided for each floating object to be tracked. The tracking ID 7452 item is set with an ID to distinguish the floating object to be tracked from other floating objects in the same container 2. The pointer 7453 item is set with a pointer to the movement trajectory information 7454 of the floating object to be tracked.

[0036] The movement trajectory information 7454 consists of entries that are pairs of time 74541 and location information 74542. The time 74541 and location information 74542 entries are set to the time of capture and coordinate values ​​indicating the position of the tracking object at that time (for example, the position of the object's center of gravity). The coordinate values ​​may be, for example, coordinate values ​​in a predetermined coordinate system. The predetermined coordinate system may be the camera coordinate system viewed with the camera as the center, or the world coordinate system considered with a certain position in space as the center. The entries of the movement trajectory information 7454 are arranged in order of time 74541. The time 74541 of the first entry is the start time of tracking. The time 74541 of the last entry is the end time of tracking. The times 74541 of entries other than the first and last are intermediate tracking times.

[0037] The inspection result information 746 represents the inspection result of container 2. Figure 7 shows an example of the configuration of the inspection result information 746. In this example, the inspection result information 746 consists of entries for container ID 7461 and inspection result 7462. The container ID 7461 entry is set with an ID that uniquely identifies container 2 after inspection. The inspection result 7462 entry is set with either OK (inspection passed) or NG (inspection failed). OK indicates that no foreign matter was detected in the liquid of the container. NG indicates that foreign matter was detected in the liquid of the container.

[0038] Referring again to Figure 3, the arithmetic processing unit 75 has a processor such as a CPU (Central Processing Unit) and its peripheral circuits, and is configured to realize various processing units by having the above hardware and program 741 cooperate by reading and executing the program 741 from the storage unit 74. The main processing units realized by the arithmetic processing unit 75 are the pre-processing unit 751, the flow induction unit 752, the micro-vibration application unit 753, the detection unit 754, and the output control unit 755.

[0039] The pre-processing unit 751 is configured to perform pre-processing before inspection of the container 2. In this example, the pre-processing unit 751 includes a micro-vibration trajectory determination unit 7511 and a blur correction function construction unit 7512.

[0040] The micro-vibration trajectory determination unit 7511 is configured to determine the trajectory that causes the container 2 to vibrate slightly. Specifically, the micro-vibration trajectory determination unit 7511 determines a total of three parameters: the direction θ, the frequency f, and the displacement amount Δd that cause the container 2 to vibrate slightly. For example, the micro-vibration trajectory determination unit 7511 stores a direction correspondence table that associates appropriate candidate directions θ for each type of container 2, and determines the direction θ according to the input type of container (e.g., syringe) through interactive processing with the operator via the operation input unit 72 and the screen display unit 73. In addition, the micro-vibration trajectory determination unit 7511 stores a frequency-displacement correspondence table that associates appropriate candidate combinations of frequency f and displacement amount Δd for each category of liquid viscosity, and determines the combination of frequency f and displacement amount Δd according to the input category of liquid viscosity through interactive processing with the operator. Based on the micro-vibration trajectory determined by the micro-vibration trajectory determination unit 7511, the operator selects a micro-vibration imparting device 4 to be incorporated into the inspection system 1 from among several pre-prepared micro-vibration imparting devices, and installs it into the inspection system 1 before inspecting the container 2. The micro-vibration trajectory determination unit 7511 also stores the three parameters of the determined micro-vibration trajectory as micro-vibration trajectory information 7421 in the storage unit 74.

[0041] The blur correction function construction unit 7512 is configured to construct a blur correction function based on the micro-vibration trajectory information 7421 determined by the micro-vibration trajectory determination unit 7511. For example, when constructing the PSF in Equation 1 described above as the blur correction function, the blur correction function construction unit 7512 determines the PSF from the direction θ of the micro-vibration and the displacement amount Δd. The blur correction function construction unit 7512 stores the constructed blur correction function as the blur correction function 7422 in the storage unit 74.

[0042] The flow induction unit 752 is configured to induce the flow of liquid in the container 2 by transmitting a flow start command to the flow induction device 3 via the communication I / F unit 71. The flow induction unit 752 is also configured to stop the induction of liquid flow by the flow induction device 3 by transmitting a flow stop command to the flow induction device 3 via the communication I / F unit 71. Even after the induction of liquid flow by the flow induction device 3 is stopped, the liquid in the container 2 will continue to flow for a while due to inertia.

[0043] The micro-vibration unit 753 is configured to initiate micro-vibration of the container 2 by transmitting a micro-vibration start command to the micro-vibration device 4 via the communication I / F unit 71. The micro-vibration unit 753 is also configured to stop micro-vibration of the container 2 by transmitting a micro-vibration stop command to the micro-vibration device 4 via the communication I / F unit 71.

[0044] The detection unit 754 is configured to detect and track suspended particles in the liquid in the liquid inside the container 2, which is being vibrated by the micro-vibration device 4, using a camera device 6 to continuously capture time-series images, and to detect the presence or absence of foreign matter based on the movement trajectory of the tracked suspended particles. The detection unit 754 includes a time-series image acquisition unit 7541, an image blur correction unit 7542, and a determination unit 7543.

[0045] The time-series image acquisition unit 7541 is configured to initiate the process of continuously capturing images of the liquid flowing in the container 2, which is undergoing slight vibrations, at a predetermined frame rate under the illumination of the illumination device 5, by transmitting a capture start command to the camera device 6 via the communication I / F unit 71. The time-series image acquisition unit 7541 is also configured to generate a time-series image 743, as shown in Figure 4, from the captured time-series images and store it in the storage unit 74. Furthermore, the time-series image acquisition unit 7541 is configured to terminate the capture by the camera device 6 by transmitting a capture end command to the camera device 6 via the communication I / F unit 71.

[0046] The image blur correction unit 7542 reads the time-series image 743 and the blur correction function 7422 from the storage unit 74, and is configured to perform deconvolution processing on each frame image 7433 in the time-series image 743 using the blur correction function 7422, as shown in the following equation. D = I * H ... (2) Here, D is the corrected image, I is the input image, H is the blur correction function, and * is the deconvolution. The image blur correction unit 7452 is configured to store the corrected time-series image 744, which includes the corrected frame image 7443 obtained by the above process, in the storage unit 74.

[0047] The determination unit 7543 reads the corrected time-series image 744 from the storage unit 74, detects and tracks floating objects present in the liquid within the time-series corrected frame image 7443 using processes such as binarization, and stores tracking information 745, including the movement trajectories of the tracked floating objects, in the storage unit 74. For example, the determination unit 7543 extracts all corrected frame images from the corrected time-series image 744 shown in Figure 5, and calculates all the movement trajectory information 7454 of floating objects present in the liquid in the container 2 from the time series of the extracted corrected frame images. Next, the determination unit 7543 calculates the container ID 7451, the tracking ID 7452 and pointer 7453 pair, and tracking information 745, including the calculated movement trajectory information 7454 of the floating objects, and stores them in the storage unit 74.

[0048] Furthermore, the determination unit 7543 is configured to detect the presence or absence of foreign matter based on the tracking information 745. For example, the determination unit 7543 reads the tracking information 745 from the storage unit 74 and, for each tracking ID 7452 of a floating object contained in the tracking information 7452, determines whether the floating object is a bubble or a foreign object based on the characteristics of the movement trajectory of the floating object represented by the movement trajectory information 7454 identified by the pointer 7453 corresponding to the tracking ID 7452. The reason why it is possible to determine whether a floating object is a foreign object or a bubble based on the movement trajectory of the floating object is that the characteristics of the movement trajectory of a foreign object in a liquid are different from those of a bubble. That is, bubbles, which have a significantly lower specific gravity than liquid, tend to move in the anti-gravity direction in the liquid. In contrast, foreign objects, which have a higher specific gravity than bubbles, do not tend to move in the anti-gravity direction in the liquid, but rather tend to move in the gravitational direction. Based on these findings, floating objects that trace a trajectory in the anti-gravity direction within a liquid can be identified as bubbles, while floating objects that trace a trajectory in the direction of gravity within a liquid can be identified as foreign objects.

[0049] Furthermore, the determination unit 7543 is configured to generate inspection result information 746 based on the detection results and store it in the storage unit 74. For example, when the determination unit 7543 determines that at least one floating object is a foreign object, it creates inspection result information 746 consisting of container ID 7461 and an inspection result of NG 7462 and stores it in the storage unit 74. Also, when the determination unit 7543 determines that all floating objects are air bubbles, it creates inspection result information 746 consisting of container ID 7461 and an inspection result of OK 7462 and stores it in the storage unit 74.

[0050] The output control unit 755 is configured to read the inspection result information 746 generated by the detection unit 754 from the storage unit 74, display it on the screen display unit 73, and / or transmit it to an external device (not shown) via the communication I / F unit 71.

[0051] Next, the overall operation of the inspection system 1 according to this embodiment will be described.

[0052] Figure 8 is a flowchart showing an example of pre-processing for the inspection system 1. Prior to the actual inspection of the container 2, the inspection system 1 performs the processing shown in Figure 8 by the pre-processing unit 751. Referring to Figure 8, the micro-vibration trajectory determination unit 7511 of the pre-processing unit 751 determines a total of three parameters for causing micro-vibrations of the container 2: the direction θ, the frequency f, and the displacement amount Δd. The three parameters of the determined micro-vibration trajectory are stored in the storage unit 74 as micro-vibration trajectory information 7421 (step S1).

[0053] Next, the blur correction function construction unit 7512 of the preprocessing unit 751 constructs a blur correction function 7422 based on the micro-vibration trajectory information 7421 determined by the micro-vibration trajectory determination unit 7511, and stores it in the storage unit 74 (step S2).

[0054] Figure 9 is a flowchart illustrating an example of the inspection process performed by the inspection system 1 on a container to be inspected. Referring to Figure 9, first, the flow induction unit 752 induces the flow of liquid in the container 2 by transmitting a flow start command to the flow induction device 3 (step S11). Next, the time-series image acquisition unit 7541 of the detection unit 754 starts the process of continuously photographing the flowing liquid in the container 2 at a predetermined frame rate by transmitting a shooting start command to the camera device 6 with the illumination device 5 turned on (step S12). Also, the micro-vibration application unit 753 transmits a micro-vibration start command to the micro-vibration application device 4 at the same time as or around the same time as the start of the shooting, causing the container 2 containing the flowing liquid to vibrate along a predetermined micro-vibration trajectory (step S13). The flow induction unit 752 transmits a flow stop command to the flow induction device 3 in synchronization with the start of the micro-vibration. As a result, the container 2 vibrates while remaining stationary. However, the flow induction unit 752 may not send a flow stop command to the flow induction device 3 at the start of the micro-vibration, but may send it at any point thereafter. That is, the container 2 may be tilted and oscillating while the micro-vibration is being induced.

[0055] The time-series image acquisition unit 7541 of the detection unit 754 receives frame images 7433 obtained by the camera device 6 in real time via the communication I / F unit 71 from the camera device 6, adds the ID 7431 of the container 2 to be inspected and the shooting time 7432, and adds them to the time-series image 743. In addition, as soon as a new frame image 7433 is added to the time-series image 743, the image blur correction unit 7542 applies the blur correction function 7422 to the added frame image 7433 to perform blur correction and adds it to the corrected time-series image 744 as a corrected frame image 7443 (step S14).

[0056] As soon as a new corrected frame image 7443 is added to the corrected time-series image 744, the determination unit 7543 detects floating objects from the added corrected frame image 7443, determines their identity with previously detected floating objects, and calculates their movement trajectory (step S15). Specifically, when the determination unit 7543 detects a new floating object floating in the liquid, it generates a new pair of tracking ID 7452 and pointer 7453, and reserves one entry in the movement trajectory information 7454 indicated by the pointer 7453, setting the shooting time 74541 of the frame in which the new floating object was detected and the position information 74542 of the detected floating object. On the other hand, if a floating object that was already detected in the corrected frame image immediately prior to the detection is detected again, rather than a new floating object, a new entry is added to the movement trajectory information 7454 of the floating object determined to be the same, and the capture time 7454 of the current frame and the position information 74542 of the detected floating object are set.

[0057] As soon as the movement trajectory information 7454 is updated, the determination unit 7543 determines whether the floating object is a bubble or a foreign object based on the movement trajectory information 7454 (step S16). When the determination unit 7543 determines that at least one floating object is a foreign object and not a bubble, it generates inspection result information 746, including the inspection result 7462 of NG, and stores it in the storage unit 74. At this point, the inspection system 1 terminates the inspection of the container 2 to be inspected. Accordingly, the micro-vibration application unit 753 sends a vibration termination command to the micro-vibration application device 4, and the time-series image acquisition unit 7541 sends a shooting termination command to the camera device 6.

[0058] On the other hand, if no floating objects are found to be foreign objects, the determination unit 7543 calculates the difference between the shooting time 7442 at the beginning of the corrected time-series image 744 and the current time. If this difference is less than the inspection time T seconds, the unit waits for the movement trajectory information to be updated, as the inspection time is still in progress. Here, the inspection time T seconds may be determined before the inspection by determining the type and size of all possible foreign objects that may be present, using the following method.

[0059] Determination Method 1: A foreign substance is actually mixed into the liquid in container 2, the time it takes for all the foreign substance to settle is measured, and T seconds is determined based on the measurement result. Determination Method 2: If the viscosity of the liquid is known, calculate the time it takes for all foreign matter to settle using the gravity sedimentation method based on the settling velocity of the particles, and determine T seconds based on the calculation result.

[0060] On the other hand, if the above difference is equal to or greater than the inspection time T seconds, the determination unit 7543 determines that no foreign matter was detected and generates inspection result information 746 including the inspection result 7462 of OK and stores it in the storage unit 74. At this point, the inspection system 1 terminates the inspection of the container 2 to be inspected. Accordingly, the micro-vibration application unit 753 sends a vibration termination command to the micro-vibration application device 4, and the time-series image acquisition unit 7541 sends a shooting termination command to the camera device 6.

[0061] When the determination unit 7543 generates the inspection result information 746, the output control unit 755 displays the inspection result information 746 on the screen display unit 73 and / or transmits it to an external device via the communication I / F unit 71 (step S17).

[0062] As described above, this embodiment includes a flow induction unit 752 that causes the liquid in the container 2 to flow, a micro-vibration application unit 753 that causes the container 2 in which the liquid flows to vibrate slightly, and a detection unit 754 that detects and tracks suspended matter present in the liquid in a time-series image obtained by continuously photographing the liquid in the container 2 while it is vibrating with a camera device 6, and detects the presence or absence of foreign matter based on the movement trajectory of the tracked suspended matter. Therefore, since the behavior of suspended matter can be observed with the viscosity of the liquid sealed in the container 2 reduced, the time until behavior specific to foreign matter, such as sedimentation, can be observed can be shortened. This improves inspection efficiency.

[0063] Furthermore, this embodiment includes an image blur correction unit 7542 that corrects blurring that occurs in images captured by the camera device 6 due to micro-vibrations of the container 2. Therefore, detection and tracking of suspended matter in the liquid can be performed accurately without being affected by micro-vibrations.

[0064] [Second Embodiment] Next, we will describe inspection system 1A according to the second embodiment of the present invention. Inspection system 1A differs from inspection system 1 described above in that it divides the inspection into a vibration-free inspection, which inspects the container 2 without causing micro-vibrations, and a vibration-induced inspection, which inspects the container 2 with micro-vibrations, and if a foreign object is detected in the vibration-free inspection, the vibration-induced inspection is omitted. Below, we will explain inspection system 1A, focusing on the differences from inspection system 1.

[0065] Figure 10 is a block diagram showing an example of an information processing device 7A used in the inspection system 1A. The same reference numerals as in Figure 3 indicate the same parts, with 747 being a time-series image, 748 being tracking information, 756 being a detection unit, 7561 being a time-series image acquisition unit, and 7562 being a determination unit.

[0066] The time-series image 747 includes a series of images obtained by continuously capturing images of the liquid inside container 2, which is not being subjected to micro-vibrations, using the camera device 6. If suspended particles are present in the liquid inside container 2, images of these suspended particles will be captured in the time-series image 747. The configuration of the time-series image 747 is the same as that of the time-series image 743 shown in Figure 4. However, the frame images of the time-series image 747 do not show image blurring due to micro-vibrations.

[0067] The tracking information 748 includes information corresponding to the results of detecting and tracking suspended matter present in the liquid inside container 2 based on the time-series image 747. The structure of the tracking information 748 is the same as the structure of the tracking information 745 shown in Figure 6.

[0068] The detection unit 756 is configured to detect and track suspended matter present in the liquid in a container 2 that is not vibrating, using a camera device 6 to continuously capture time-series images, and to detect the presence or absence of foreign matter based on the movement trajectory of the tracked suspended matter. The detection unit 756 includes a time-series image acquisition unit 7561 and a determination unit 7562.

[0069] The time-series image acquisition unit 7561 is configured to start the process of continuously capturing images of the liquid flowing in the container 2 at a predetermined frame rate under the illumination of the illumination device 5 by the camera device 6 by transmitting a capture start command to the camera device 6 via the communication I / F unit 71. The time-series image acquisition unit 7561 is also configured to generate a time-series image 747, as shown in Figure 4, from the captured time-series images and store it in the storage unit 74. Furthermore, the time-series image acquisition unit 7561 is configured to end the capture by the camera device 6 by transmitting a capture end command to the camera device 6 via the communication I / F unit 71.

[0070] The determination unit 7562 is configured to read a time-series image 747 from the storage unit 74, detect and track floating objects present in the liquid within the time-series frame image 7433, and store tracking information 748, including the movement trajectory of the tracked floating objects, in the storage unit 74.

[0071] Furthermore, the determination unit 7562 is configured to detect the presence or absence of foreign matter based on the tracking information 748. For example, the determination unit 7562 reads the tracking information 748 from the storage unit 74 and, for each tracking ID 7452 of a floating object contained in the tracking information 748, determines whether the floating object is a bubble or a foreign object based on the characteristics of the movement trajectory of the floating object represented by the movement trajectory information 7454 identified by the pointer 7453 corresponding to the tracking ID 7452.

[0072] Furthermore, the determination unit 7562 is configured to generate inspection result information 746 when it detects a foreign object and store it in the storage unit 74. For example, when the determination unit 7562 determines that at least one floating object is a foreign object, it creates inspection result information 746 consisting of the container ID 7461 and the inspection result 7462 of NG and stores it in the storage unit 74. On the other hand, if no foreign objects are detected within the inspection time T1 of the first half of the process, the determination unit 7562 terminates the detection process by the detection unit 756. At this point, the detection process is transferred to the detection unit 754.

[0073] Next, the overall operation of inspection system 1A according to this embodiment will be explained, focusing on the differences from inspection system 1.

[0074] Figure 11 is a flowchart illustrating an example of the inspection process performed by the inspection system 1A on a container to be inspected. Referring to Figure 11, first, the flow induction unit 752 induces the flow of liquid in the container 2 by transmitting a flow start command to the flow induction device 3 (step S11). Next, the time-series image acquisition unit 7561 of the detection unit 756 starts the process of continuously photographing the flowing liquid in the container 2 at a predetermined frame rate by transmitting a shooting start command to the camera device 6 with the illumination device 5 turned on (step S12). At this time, since the micro-vibration imparting device 4 is not activated, the container 2 containing the flowing liquid is not vibrating. In other words, a vibration-free inspection is performed first.

[0075] The time-series image acquisition unit 7561 of the detection unit 756 receives frame images 7433 obtained by the camera device 6 in real time via the communication I / F unit 71 from the camera device 6, adds the ID 7431 and shooting time 7432 of the container 2 to be inspected, and adds it to the time-series image 747. As soon as the new frame image 7433 is added to the time-series image 747, the determination unit 7562 detects floating objects from the added frame image 7433, determines their identity with previously detected floating objects, and calculates their movement trajectory (step S21). Specifically, when the determination unit 7562 detects new floating objects floating in the liquid, it generates a new pair of tracking ID 7452 and pointer 7453, and secures one entry in the movement trajectory information 7454 indicated by the pointer 7453, setting the shooting time 74541 of the frame in which the new floating object was detected and the position information 74542 of the detected floating object. On the other hand, if a floating object that was already detected in the previous frame image is detected again, rather than a new floating object, a new entry is added to the movement trajectory information 7454 of the floating object determined to be the same, and the capture time 7454 of the current frame and the location information 74542 of the detected floating object are set.

[0076] As soon as the movement trajectory information 7454 is updated, the determination unit 7562 determines whether the floating object is a bubble or a foreign object based on the movement trajectory information 7454 (step S22). When the determination unit 7562 determines that at least one floating object is a foreign object and not a bubble (YES in step S23), it generates inspection result information 746 including the inspection result 7462 of NG and stores it in the storage unit 74 (step S17). At this point, the inspection system 1A terminates the inspection of the container 2 to be inspected. That is, the inspection system 1A terminates the inspection without performing the vibration inspection. Accordingly, the time-series image acquisition unit 7561 sends a shooting termination command to the camera device 6.

[0077] On the other hand, if no floating objects are found to be foreign objects, the determination unit 7562 calculates the difference between the first image capture time 7432 of the time-series image 743 and the current time. If the difference is less than the vibration-free inspection time T1 seconds, the unit waits for the movement trajectory information to be updated, as the vibration-free inspection period is still ongoing. Here, the vibration-free inspection time T1 seconds is determined before inspection by determining the type and size of foreign objects that have the characteristic of settling quickly (glass fragments and metal fragments) (hereinafter referred to as weight foreign objects) among all foreign objects that may be present, using the following method.

[0078] Determination Method 1: Mix a weight of foreign matter into the liquid in container 2, measure the time it takes for all of the weight of foreign matter to settle, and determine T1 seconds based on the measurement result. Determination Method 2: If the viscosity of the liquid is known, the time it takes for the weight of the foreign matter to settle is calculated by the sedimentation rate of the particles using the gravity sedimentation method, and T1 seconds is determined based on the calculation result.

[0079] On the other hand, if the above difference is equal to or greater than the vibration-free inspection time T1 seconds, the determination unit 7543 terminates the detection process of the detection unit 756. That is, the inspection system 1A terminates the vibration-free inspection and immediately starts the vibration inspection.

[0080] First, the micro-vibration application unit 753 transmits a micro-vibration start command to the micro-vibration application device 4, causing the container 2 containing the flowing liquid to vibrate along a predetermined micro-vibration trajectory (step S13). The time-series image acquisition unit 7541 of the detection unit 754 receives the frame image 7433 captured by the camera device 6 in real time via the communication I / F unit 71, adds the ID 7431 and shooting time 7432 of the container 2 to be inspected, and adds it to the time-series image 743. Furthermore, as soon as a new frame image 7433 is added to the time-series image 743, the image blur correction unit 7542 applies the blur correction function 7422 to the added frame image 7433 to perform blur correction, and adds it to the corrected time-series image 744 as a corrected frame image 7443 (step S14).

[0081] As soon as a new corrected frame image 7443 is added to the corrected time-series image 744, the determination unit 7543 detects floating objects from the added corrected frame image 7443, determines their identity with previously detected floating objects, and calculates their movement trajectory (step S15). Also, as soon as the movement trajectory information 7454 is updated, the determination unit 7543 determines whether the floating objects are bubbles or foreign objects based on the movement trajectory information 7454 (step S16). When the determination unit 7543 determines that at least one floating object is a foreign object and not a bubble, it generates inspection result information 746 including the inspection result 7462 of NG and stores it in the storage unit 74 (step S17). At this point, the inspection system 1 terminates the inspection of the container 2 to be inspected. Accordingly, the micro-vibration application unit 753 sends a vibration termination command to the micro-vibration application device 4, and the time-series image acquisition unit 7541 sends a shooting termination command to the camera device 6.

[0082] On the other hand, if no floating objects are found to be foreign objects, the determination unit 7543 calculates the difference between the first captured time 7442 of the corrected time-series image 744 and the current time. If this difference is less than the vibration inspection time T2 seconds, the unit waits for the movement trajectory information to be updated, as the vibration inspection time is still in progress. Here, the vibration inspection time T2 seconds determines the type and size of foreign objects other than those that settle quickly (glass fragments and metal fragments) among all possible foreign objects that may be present (hereinafter referred to as lightweight foreign objects), and may be determined before inspection using the following method.

[0083] Determination Method 1: Lightweight foreign matter is actually mixed into the liquid in container 2, the time it takes for all the lightweight foreign matter to settle is measured, and T2 seconds is determined based on the measurement result. Determination Method 2: If the viscosity of the liquid is known, calculate the time it takes for all lightweight foreign matter to settle using the gravity sedimentation method based on the settling velocity of the particles, and determine T2 seconds based on the calculation result.

[0084] On the other hand, if the above difference is equal to or greater than the vibration inspection time T2 seconds, the determination unit 7543 determines that no foreign matter was detected and generates inspection result information 746 including the inspection result 7462 of OK and stores it in the storage unit 74. At this point, the inspection system 1 terminates the inspection of the container 2 to be inspected. Accordingly, the micro-vibration application unit 753 sends a vibration termination command to the micro-vibration application device 4, and the time-series image acquisition unit 7541 sends a shooting termination command to the camera device 6.

[0085] When the determination unit 7543 generates the inspection result information 746, the output control unit 755 displays the inspection result information 746 on the screen display unit 73 and / or transmits it to an external device via the communication I / F unit 71 (step S17).

[0086] Thus, this embodiment divides the inspection into a vibration-free inspection, which inspects the container 2 without causing micro-vibrations, and a vibration-assisted inspection, which inspects the container 2 with micro-vibrations. First, the vibration-free inspection is performed to check for the presence or absence of heavy foreign matter. Heavy foreign matter is a type of foreign matter that has the characteristic of settling quickly, and therefore tends to settle quickly even in the original viscous liquid without vibration. For this reason, in containers 2 containing heavy foreign matter, it is possible to detect the foreign matter early using only the vibration-free inspection. Here, as with inspection system 1, if vibration is applied from the beginning to reduce the viscosity of the liquid, heavy foreign matter can be made to settle even faster. However, depending on the frame rate of the camera device 6, it may be difficult or impossible to track foreign matter that settles too quickly. This is because the distance traveled by floating objects between preceding and succeeding frame images becomes too large. In particular, as will be described later, when correcting image blur by setting the shooting period of the camera device 6 that photographs the container 2 during micro-vibrations to an integer multiple of the micro-vibration period, the shooting period becomes longer, and there is a strong tendency for the distance traveled by floating objects between preceding and succeeding frame images to become large. The inspection system 1A of this embodiment is suitable, for example, in such cases.

[0087] Furthermore, in this embodiment, if a foreign object is detected during the vibration-free inspection, the vibration-based inspection is omitted. In addition, during the vibration-based inspection, the behavior of suspended matter is observed with the viscosity of the liquid sealed in container 2 reduced, thus shortening the time until behaviors specific to foreign objects, such as sedimentation, can be observed. This improves inspection efficiency.

[0088] [Third Embodiment] Next, an inspection system according to a third embodiment of the present invention (referred to as inspection system 1B) will be described. Inspection system 1B differs from the first or second embodiment in that the shooting period (1 / frame rate) of the camera device 6 that photographs the liquid in the container 2 during micro-vibration is set to an integer multiple (1x, 2x, ...) of the micro-vibration period (1 / frequency f), and is otherwise the same as the first or second embodiment.

[0089] By setting the imaging period of the camera device 6, which photographs the container 2 while it is vibrating, to an integer multiple of the vibration period, the motion due to the vibration is captured at the same pixel position. Therefore, the movement of suspended particles in the liquid and the movement due to the vibration can be separated. In other words, with inspection system 1B, the vibrating container 2 can be photographed in a state where it appears to be stationary at the same position. Consequently, the detection and tracking of suspended particles in the liquid can be performed accurately without being affected by the vibration. Note that in inspection system 1B, the image blur correction unit 7542 may or may not be omitted.

[0090] [Fourth Embodiment] Next, an inspection system 1C according to a fourth embodiment of the present invention will be described. Figure 12 is a diagram showing the main components of the inspection system 1C. Referring to Figure 12, the inspection system 1C differs from the first to third embodiments in that it further includes a mirror 61 that reflects the image of the container 2 and inputs it to a camera device 6, and a mirror drive unit 62 that drives the mirror 61 in response to the micro-vibrations of the container 2. Otherwise, it is the same as the first to third embodiments. In the example shown in Figure 12, the micro-vibration trajectory of the container 2 is a straight line, but the micro-vibration trajectory may also be a curve such as a circular arc or an ellipse.

[0091] By driving the mirror 61, which reflects the image of container 2 and inputs it to the camera device 6, in accordance with the slight vibrations of container 2, it is possible to photograph container 2, which is vibrating slightly, in an apparent state of being stationary in the same position. Therefore, detection and tracking of suspended matter in the liquid can be performed accurately without being affected by slight vibrations. In inspection system 1C, the image blur correction unit 7542 may or may not be omitted.

[0092] [Fifth Embodiment] Next, an inspection system 1D according to a fifth embodiment of the present invention will be described. Figure 13 is a diagram showing the main components of the inspection system 1D. Referring to Figure 13, the inspection system 1D differs from the first to third embodiments in that it further includes a camera drive unit 63 that drives (vibrates) the camera device 6 in response to the micro-vibrations of the container 2, and is otherwise the same as the first to third embodiments. In the example shown in Figure 13, the micro-vibration trajectory of the container 2 is a straight line, but the micro-vibration trajectory may be a curve such as a circular arc or an ellipse. Also, the camera drive unit 63 may be configured to vibrate the container 2 together with the camera device 6. That is, the camera drive unit 63 and the micro-vibration device 4 may be common to both.

[0093] By driving the camera device 6 in response to the slight vibrations of the container 2, the vibrating container 2 can be photographed while appearing to be stationary in the same position. Therefore, the detection and tracking of suspended matter in the liquid can be performed accurately without being affected by the slight vibrations. In the inspection system 1D, the image blur correction unit 7542 may or may not be omitted.

[0094] [Sixth Embodiment] Next, a sixth embodiment of the present invention will be described. Figure 14 is a block diagram of the inspection system 100 according to this embodiment. This embodiment will provide an overview of the inspection system described above.

[0095] Referring to Figure 14, the inspection system 100 is an inspection system for checking for the presence or absence of foreign matter in a liquid sealed in a container, and comprises a flow induction means 101, a micro-vibration application means 102, and a detection means 103.

[0096] The flow induction means 101 is configured to induce flow of the liquid in the container. The flow induction means 101 can be configured, for example, similarly to the flow induction unit 752 in Figure 3 or Figure 10. The micro-vibration imparting means 102 is configured to cause micro-vibrations in the container in which the liquid is flowing. The micro-vibration imparting means 102 can be configured, for example, similarly to the micro-vibration imparting unit 753 in Figure 3 or Figure 10. The detection means 103 is configured to detect and track suspended matter present in the liquid in a time-series image obtained by continuously photographing the liquid in the container during micro-vibration with a camera, and to detect the presence or absence of foreign matter based on the movement trajectory of the tracked suspended matter. The detection means 103 can be configured, for example, similarly to the detection unit 754 in Figure 3 or Figure 10.

[0097] The inspection system 100 configured in this way functions as follows: First, the flow induction means 101 causes the liquid in the container to flow. Next, the micro-vibration imparting means 102 causes the container in which the liquid is flowing to vibrate slightly. Then, the detection means 103 detects and tracks suspended matter present in the liquid in the time-series images obtained by continuously photographing the liquid in the container while it is vibrating with a camera, and detects the presence or absence of foreign matter based on the movement trajectory of the tracked suspended matter.

[0098] According to the inspection system 100 configured and operating as described above, the behavior of suspended particles can be observed while the viscosity of the liquid sealed in the container is reduced by micro-vibrations. This shortens the time required to observe behaviors specific to foreign objects, such as sedimentation, thereby improving inspection efficiency.

[0099] Although the present invention has been described above with reference to the embodiments described above, the present invention is not limited to the embodiments described above. Various modifications to the configuration and details of the present invention can be made within the scope of the present invention as can be understood by those skilled in the art.

[0100] For example, instead of the CPU mentioned above, an information processing device can use a GPU (Graphic Processing Unit), DSP (Digital Signal Processor), MPU (Micro Processing Unit), FPU (Floating Number Processing Unit), PPU (Physics Processing Unit), TPU (Tensor Processing Unit), quantum processor, microcontroller, or a combination of these. [Industrial applicability]

[0101] This invention can be used in a wide range of fields for inspecting for the presence or absence of foreign matter in liquids sealed in containers such as syringes and vials.

[0102] Some or all of the above embodiments may also be described as follows, but are not limited to the following: [Note 1] An inspection system for checking for the presence or absence of foreign matter in a liquid sealed in a container, A flow-inducing means for causing the liquid in the container to flow, A means for applying micro-vibrations to cause the container in which the liquid flows to vibrate slightly, A first detection means detects and tracks suspended particles present in the liquid within a time-series image obtained by continuously photographing the liquid in the container during the aforementioned micro-vibrations using a camera, and detects the presence or absence of foreign matter based on the movement trajectory of the tracked suspended particles. An inspection system equipped with the following features. [Note 2] The container is further provided with a second detection means that, before the container is subjected to slight vibration, continuously photographs the liquid inside the container while it is flowing using the camera to obtain a time-series of images, detects and tracks suspended matter present in the liquid, and detects the presence or absence of foreign matter based on the movement trajectory of the tracked suspended matter. When a foreign object is detected by the second detection means, the detection process by the first detection means is omitted. The inspection system described in Appendix 1. [Note 3] The system further includes a correction means for correcting the blurring that occurs in the time-series image due to the aforementioned micro-vibrations. The inspection system described in Appendix 1. [Note 4] The correction means performs deconvolution processing on the image using a blur correction function constructed based on the trajectory of the micro-vibrations. The inspection system described in Appendix 3. [Note 5] The aforementioned blur correction function is a point image distribution function. The inspection system described in Appendix 4. [Note 6] The system further comprises means for generating the blur correction function based on the trajectory of the aforementioned micro-vibrations. The inspection system described in Appendix 4. [Note 7] The camera takes images at a period that is an integer multiple of the vibration period of the micro-vibration. The inspection system described in Appendix 1. [Note 8] The system further includes a mirror that reflects the image of the container and inputs it to the camera, and a mirror drive unit that drives the mirror in response to minute vibrations of the container. The inspection system described in Appendix 1. [Note 9] The camera further includes a camera drive unit that drives the camera in response to minute vibrations of the container. The inspection system described in Appendix 1. [Note 10] The aforementioned liquid is a liquid exhibiting non-Newtonian viscosity properties. The inspection system described in any of the appendices 1 through 9. [Note 11] A testing method for inspecting the presence or absence of foreign matter in a liquid sealed in a container, The liquid in the container is made to flow, The container in which the liquid flows is made to vibrate slightly, The liquid inside the container during the aforementioned micro-vibrations is continuously photographed by a camera to obtain a time-series of images in which suspended particles present in the liquid are detected and tracked, and the presence or absence of foreign matter is detected based on the movement trajectory of the tracked suspended particles. Testing method. [Note 12] A computer that inspects for foreign matter in the liquid sealed in a container, A process of causing the liquid in the container to flow, A process of causing the container in which the liquid flows to vibrate slightly, The process involves continuously capturing images of the liquid in the container while it is vibrating using a camera, detecting and tracking suspended particles in the liquid within the resulting time-series images, and then detecting the presence or absence of foreign matter based on the movement trajectory of the tracked suspended particles. A computer-readable recording medium containing a program for performing a certain action. [Explanation of Symbols]

[0103] 100 Inspection Systems 101 Flow-inducing means 102 Means for imparting micro-vibrations 103 Detection means

Claims

1. An inspection system for checking for the presence or absence of foreign matter in a liquid sealed in a container, A flow-inducing means for causing the liquid in the container to flow, A means for applying micro-vibrations to cause the container in which the liquid flows to vibrate slightly, A first detection means detects and tracks suspended particles present in the liquid within a time-series image obtained by continuously photographing the liquid in the container during the aforementioned micro-vibrations using a camera, and detects the presence or absence of foreign matter based on the movement trajectory of the tracked suspended particles. The system includes a second detection means that, before the container is subjected to micro-vibration, continuously captures images of the liquid inside the container while it is flowing using the camera, detects and tracks suspended matter present in the liquid in the time-series images obtained, and detects the presence or absence of foreign matter based on the movement trajectory of the tracked suspended matter, When a foreign object is detected by the second detection means, the detection process by the first detection means is omitted. Inspection system.

2. An inspection system for checking for the presence or absence of foreign matter in a liquid sealed in a container, A flow-inducing means for causing the liquid in the container to flow, A means for applying micro-vibrations to cause the container in which the liquid flows to vibrate slightly, A first detection means detects and tracks suspended particles present in the liquid within a time-series image obtained by continuously photographing the liquid in the container during the aforementioned micro-vibrations using a camera, and detects the presence or absence of foreign matter based on the movement trajectory of the tracked suspended particles. Correction means for correcting blurring that occurs in the time-series image due to the aforementioned micro-vibrations, An inspection system equipped with the following features.

3. The correction means performs deconvolution processing on the image using a blur correction function constructed based on the trajectory of the micro-vibrations. The inspection system according to claim 2.

4. The aforementioned blur correction function is a point image distribution function. The inspection system according to claim 3.

5. The system further comprises means for generating the blur correction function based on the trajectory of the aforementioned micro-vibrations. The inspection system according to claim 3.

6. An inspection system for checking for the presence or absence of foreign matter in a liquid sealed in a container, A flow-inducing means for causing the liquid in the container to flow, A means for applying micro-vibrations to cause the container in which the liquid flows to vibrate slightly, A first detection means detects and tracks suspended particles present in the liquid within a time-series image obtained by continuously photographing the liquid in the container during the aforementioned micro-vibrations using a camera, and detects the presence or absence of foreign matter based on the movement trajectory of the tracked suspended particles. A mirror that reflects the image of the container and inputs it to the camera, A mirror drive unit that drives the mirror in response to the slight vibrations of the container, An inspection system equipped with the following features.

7. An inspection system for inspecting the presence or absence of foreign matter in a liquid sealed in a container, A flow-inducing means for causing the liquid in the container to flow, A means for applying micro-vibrations to cause the container in which the liquid flows to vibrate slightly, A first detection means detects and tracks suspended particles present in the liquid within a time-series image obtained by continuously photographing the liquid in the container during the aforementioned micro-vibrations using a camera, and detects the presence or absence of foreign matter based on the movement trajectory of the tracked suspended particles. A camera drive unit that drives the camera in response to the slight vibrations of the container, An inspection system equipped with the following features.

8. A testing method for inspecting the presence or absence of foreign matter in a liquid sealed in a container, Computers A first process of causing the liquid in the container to flow, Before the container in which the liquid flows is subjected to slight vibration, a second process is performed in which floating particles present in the liquid are detected and tracked in a time-series image obtained by continuously photographing the liquid in the container while it is flowing with a camera, and the presence or absence of foreign matter is detected based on the movement trajectory of the tracked floating particles. A third process involves: causing the container in which the liquid flows to vibrate slightly; continuously photographing the liquid inside the container during the slight vibration with the camera to obtain a time-series image in which suspended particles present in the liquid are detected and tracked; and detecting the presence or absence of foreign matter based on the movement trajectory of the tracked suspended particles. Perform If a foreign object is detected in the second process, the third process is omitted. Testing method.

9. A method for inspecting whether or not there are foreign substances in a liquid sealed in a container, Computers A first process of causing the liquid in the container to flow, A second process involves vibrating the container in which the liquid flows, continuously photographing the liquid inside the container with a camera during the vibration, detecting and tracking suspended particles in the liquid within the time-series images obtained, and detecting the presence or absence of foreign matter based on the movement trajectory of the tracked suspended particles. A third process that drives the camera in response to the minute vibrations of the container, A testing method that performs this test.

10. A computer that inspects for foreign matter in the liquid sealed in a container, A first process of causing the liquid in the container to flow, Before the container in which the liquid flows is subjected to slight vibration, a second process is performed in which floating particles present in the liquid are detected and tracked in a time-series image obtained by continuously photographing the liquid in the container while it is flowing with a camera, and the presence or absence of foreign matter is detected based on the movement trajectory of the tracked floating particles. The container in which the liquid flows is made to vibrate slightly, and the liquid inside the container during the slight vibration A third process involves detecting and tracking suspended particles in a liquid within a time-series of images obtained by continuously capturing images with a camera, and detecting the presence or absence of foreign matter based on the movement trajectory of the tracked suspended particles. A program to perform the following: A program that omits the third process if a foreign object is detected in the second process.

Images