WO2025215901A1 - Feature point extraction method, control program, and information processing system - Google Patents

Abstract

This feature point extraction method includes a step (c) of comparing first feature point information relating to a web in first inspection data and second feature point information relating to the web in second inspection data, and a step (d) of extracting, on the basis of the result of the comparison in step (c), third-type feature points that are present in both the first and second inspection data and/or first-type feature points that are present in the first inspection data but are not present in the second inspection data, or second-type feature points that are not present in the first inspection data but are present in the second inspection data, wherein one of the first inspection data and the second inspection data is inspection data acquired by one or more inspection methods, and the other inspection data is inspection data acquired by one or more inspection methods including an inspection method different from the inspection method of the one inspection data.

Description

Feature point extraction method, control program, and information processing system

The present invention relates to a feature point extraction method, a control program, and an information processing system.

Liquid crystal display devices are increasingly being used in large-screen televisions and large monitors, and as a result, there is a demand for wider films to be used on the display surfaces of these devices. For example, there is a demand for wider films of 2000 mm or more. Furthermore, in order to anticipate substrate loss (film loss) and reduce transportation costs, there is a demand for the production of long film rolls with winding lengths of 1000 m or more, and even 3000 m or more.

When a defect or other quality issue occurs in a post-processing step that produces a product based on a web such as film, it is necessary to determine whether the defect occurred in the upstream process, i.e., during the production of the web and was originally present on the web, or whether it arose in the downstream process. If it is not possible to clearly determine that the defect occurred in the downstream process, improvements may be required in the upstream process. In attempting to respond to requests for improvement, the shipping standards for the upstream process may become stricter than necessary, resulting in over-specification. Also, in order to prevent quality issues before they occur, it is sometimes necessary to set overly strict shipping standards for web production based on estimates, even though it is not clear how this will affect the downstream process. Such cases also constitute over-specification. Over-specification leads to reduced yields, increased costs, is undesirable from an ecological perspective, and is undesirable for both the upstream and downstream process companies.

It is necessary to determine whether the defect was originally present on the web or whether it occurred during a post-processing step, and in doing so, it is necessary to match the coordinate system on the web from the previous process with the coordinate system from the subsequent process.

Patent Document 1 below discloses a technology for synchronizing the inspection results of a first and second inspection device in an optical film inspection system. In this inspection system, the inspection results of both devices are synchronized by using an encoder signal that indicates the distance between the first inspection device and the second inspection device, which is placed downstream in the transport direction, and the amount of film movement.

JP 2016-161576 A

The technology in Patent Document 1 synchronizes inspection results based on the mutual distance and movement distance between the inspection devices, and is unable to achieve synchronization when the film expands or contracts. Furthermore, synchronization is also unable to be achieved when two inspection devices are wound up with film in a roll and then have offline processing performed to unwind the roll.

The present invention was made in consideration of the above circumstances, and aims to efficiently collect information that is useful for process improvement and setting shipping standards both when manufacturing webs and in the manufacturing process where post-processing is performed using these webs.

The above-mentioned object of the present invention is achieved by the following means.

(1) A method for extracting feature points of a web, comprising:
A step (a) of acquiring first inspection data in a first manufacturing process of manufacturing a web or post-processing a manufactured web;
(b) acquiring second inspection data in a second manufacturing process that uses the web and is performed after the first manufacturing process;
(c) comparing first feature information of the web in the first inspection data with second feature information of the web in the second inspection data;
and (d) extracting, based on the comparison result of the step (c), third type feature points present in both the first and second test data, and/or first type feature points present in the first test data but not in the second test data, or second type feature points present in the second test data but not in the first test data,
A method for extracting feature points, wherein one of the first inspection data and the second inspection data is inspection data acquired by one or more inspection methods, and the other inspection data is inspection data acquired by one or more inspection methods including an inspection method different from the inspection method of the one inspection data.

(2) the first inspection data and the second inspection data are inspection data obtained by photographing a web with an inspection device;
The method for extracting feature points described in (1) above, wherein the imaging method used in the inspection device for the other inspection data is inspection data acquired using one or more imaging methods, including an imaging method different from the imaging method used in the inspection device for the one inspection data.

(3) The photographing method used to acquire the one of the inspection data includes at least one of a first photographing method for photographing transmitted light traveling straight through the web, a second photographing method for photographing transmitted light reflected within the web, a third photographing method for photographing reflected light specularly reflected from the web surface, and a fourth photographing method for photographing reflected light scattered from the web surface, depending on the positional relationship between the lighting and the photographing unit.
The method for extracting feature points described in (2) above, wherein the imaging method of the other test data includes a different imaging method from the imaging method of the one test data among the first to fourth imaging methods.

(4) The feature point extraction method described in (2) above, wherein the imaging method includes an imaging method using polarized light to detect the polarization state of light.

(5) At least one of the first test data and the second test data is
The feature point extraction method described in (1) above is inspection data that is integrated by aligning feature point information extracted from multiple primary data acquired by multiple types of inspection methods in the same inspection area on the web surface.

(6) In the step (d), after extracting the third type feature points using the integrated inspection data,
The feature point extraction method according to (5) above, further comprising a step (e) of classifying the feature points in the integrated inspection data into feature points in each of the plurality of primary data.

(7) a step (f) of accepting a selection of the inspection method for the one of the inspection data;
and (g) displaying, by selection in step (f), feature point information of the primary data classified in step (e) corresponding to the selected inspection method.

(8) A method for extracting feature points of a web, comprising:
A step (a) of acquiring first inspection data in a first manufacturing process of manufacturing a web or post-processing a manufactured web;
(b) acquiring second inspection data in a second manufacturing process that uses the web and is performed after the first manufacturing process;
(c) comparing first feature information of the web in the first inspection data with second feature information of the web in the second inspection data;
and (d) extracting third type feature points present in both the first and second inspection data based on the comparison result of the step (c),
At least one of the first inspection data and the second inspection data is inspection data obtained by integrating feature point information extracted from a plurality of primary data acquired by a plurality of types of inspection methods in the same inspection area by aligning the feature point information on the web surface;
The feature point extraction method further comprises a step (e) of classifying the feature points in the integrated inspection data into feature points in each of a plurality of primary data sets after extracting the third type feature points in the step (d) using the integrated inspection data.

(9) The first inspection data and the second inspection data are inspection data obtained by photographing a web with an inspection device,
The feature point extraction method according to (8) above, wherein the inspection device of the one of the inspection data is inspection data acquired by a plurality of imaging methods.

(10) a step (f) of accepting a selection of the inspection method for the one of the inspection data;
and (g) a step of displaying, by selection in step (f), feature point information of the primary data classified in step (e) corresponding to the selected inspection method.

(11) A control program for causing a computer to execute the extraction method described in any one of (1) to (10) above.

(12) A method for extracting feature points of a web, comprising:
an acquisition unit that acquires first inspection data in a first manufacturing process that manufactures a web or post-processes a manufactured web, and second inspection data in a second manufacturing process that performs post-processing using the web after the first manufacturing process;
a comparison unit that compares the first feature information of the web in the first inspection data with the second feature information of the web in the second inspection data;
an extraction unit that extracts, based on a comparison result from the comparison unit, third type feature points that are present in both the first and second test data, and/or first type feature points that are present in the first test data but not in the second test data, or second type feature points that are not present in the first test data but are present in the second test data,
An information processing system, wherein one of the first test data and the second test data is test data obtained by one or more test methods, and the other test data is test data obtained by one or more test methods including a test method different from the test method of the one test data.

(13) A method for extracting feature points of a web, comprising:
an acquisition unit that acquires first inspection data in a first manufacturing process that manufactures a web or post-processes a manufactured web, and second inspection data in a second manufacturing process that performs post-processing using the web after the first manufacturing process;
a comparison unit that compares the first feature information of the web in the first inspection data with the second feature information of the web in the second inspection data;
an extraction unit that extracts third type feature points that exist in both the first and second inspection data based on a comparison result from the comparison unit,
At least one of the first inspection data and the second inspection data is inspection data obtained by integrating feature point information extracted from a plurality of primary data acquired by a plurality of types of inspection methods in the same inspection area by aligning the feature point information on the web surface;
an information processing system, wherein the extraction unit uses the integrated inspection data to extract the third type feature points, and then classifies the feature points in the integrated inspection data into feature points in each of a plurality of primary data.

The method for extracting feature points of a web according to the present invention comprises:
A step (a) of acquiring first inspection data in a first manufacturing process of manufacturing a web or post-processing a manufactured web;
(b) acquiring second inspection data in a second manufacturing process that uses the web and is performed after the first manufacturing process;
(c) comparing first feature information of the web in the first inspection data with second feature information of the web in the second inspection data;
and (d) extracting, based on the comparison result of the step (c), third type feature points present in both the first and second test data, and/or first type feature points present in the first test data but not in the second test data, or second type feature points present in the second test data but not in the first test data,
One of the first inspection data and the second inspection data is inspection data acquired by one or more inspection methods, and the other inspection data is inspection data acquired by one or more inspection methods including an inspection method different from the inspection method of the one inspection data. This makes it possible to efficiently collect information useful for process improvement and setting shipping standards both when manufacturing the web and in a manufacturing process in which post-processing is performed using the web.

Advantages and features provided by one or more embodiments of the present invention will be more fully understood from the following detailed description and the accompanying drawings, which are for purposes of illustration only and are not intended to be limiting.
FIG. 1 is a schematic diagram illustrating an application example of an information processing system according to an embodiment of the present invention. 1 is a table showing characteristics of various imaging methods. 10A and 10B are schematic diagrams showing the positional relationship between lighting and cameras in the first to fifth imaging methods. 1 is a table showing the correspondence between the image capturing units 1 to 6 and the image capturing methods in this embodiment. FIG. 1 is a schematic diagram illustrating an example of the configuration of an inspection device. FIG. 1 is a schematic diagram illustrating an example of the configuration of an inspection device. 10 is a table showing a list of inspection devices. 1 is a block diagram showing a schematic configuration of an information processing system. 4 is an example of various data stored in a storage unit. 10 is an example of an inspection data DB stored in a storage unit. 10 is a flowchart showing a process for generating first inspection data performed in a first manufacturing process. 10 is an example of an inspection data DB stored in a storage unit. 10 is a flowchart showing a process for generating second inspection data performed in a second manufacturing process. 10 is an example of an inspection data DB stored in a storage unit. 10 is a flowchart showing a feature point extraction process executed in the information processing system. 10 is an example of an operation screen displayed on a terminal device. FIG. 10 is a schematic diagram for explaining the extraction processing of feature points. 10 is a subroutine flowchart showing a comparison process 1 in step S34. 10 is an example of a probability density function calculated by kernel density estimation, which shows the positions and intensities of feature points. 10 is an example of a corresponding point list. 10 is a table for explaining first to third type feature points. 10 is an example of feature point extraction result data. 14 is an example of an inspection data DB stored in a storage unit corresponding to FIG. 13. 10 is a subroutine flowchart showing a display process of step S38. 10 is an example of an operation screen that accepts selection of primary data. 10 is a display example displayed on a preview screen. 10 is a display example displayed on a preview screen.

Embodiments of the present invention will now be described with reference to the accompanying drawings. However, the scope of the present invention is not limited to the disclosed embodiments. In the description of the drawings, identical elements will be given the same reference numerals, and duplicate explanations will be omitted. Furthermore, the dimensional proportions in the drawings have been exaggerated for the sake of explanation and may differ from the actual proportions.

(web)
In this embodiment, the web refers to a sheet-like material, including a resin film and a metal film. The web also includes a laminate. In the following description, the web refers to a long resin film, such as a film roll, and the film roll to be processed. The processing also includes a process of applying a coating liquid and a lamination process of overlaying another film-like material to produce a laminate.

(Minatorial information)
In this embodiment, feature points are defects on the film, and are generated by analyzing image data. Image analysis may involve using known techniques to extract, as feature points, pixels whose pixel values deviate from the average value of the surrounding pixels by a predetermined amount (the difference is greater than or equal to a predetermined amount) in image data captured from the film surface. Alternatively, feature points may be calculated using the "image processing for generating feature points" technique described below. In many cases, dozens to thousands of feature points are generated from one or more image data captured from a single film roll 80 (total length of several kilometers). Defects include both defects that could result in product defects and minor defects that do not result in product defects. Feature points include defects related to poor adhesion when films are bonded together (by ultrasonic welding, for example) and axial irregularities. Feature point information includes size and position (x-y coordinates). Alternatively, feature point information may be obtained by grouping (clustering) multiple nearby feature points together. The image processing for generating feature points will be described later.

FIG. 1 is a schematic diagram showing an application example of an information processing system 50 according to this embodiment. As shown in FIG. 1, the information processing system 50 communicates with terminal devices 70 and the like in factories A and B via a network. The network is a communication line such as a data communication network. Some networks may use a wired LAN or a wireless LAN (for example, a LAN conforming to the IEEE 802.11 standard). Details of the information processing system 50 will be provided later.

The terminal device 70 is, for example, a PC (personal computer). For example, the terminal device 70 is a PC used by an employee of a manufacturing company that operates Factory A and Factory B.

Factory A is equipped with the above-mentioned film roll manufacturing apparatus 1000. Factory A is operated or managed by, for example, a film manufacturer. Factory A carries out a first manufacturing process for manufacturing a film roll 80. In the first manufacturing process, multiple sub-processes are carried out, such as a drying process, a stretching process, and a winding process. Inspection devices 90a1, a2 (hereinafter collectively referred to as inspection devices 90) are placed before and after the multiple sub-processes. The film surface of the film roll 80 is inspected by the multiple inspection devices 90a1, 90a2. While Figure 1 shows two inspection devices 90a1, 90a2, the number of inspection devices 90 is not limited to this and may be one, or three or more.

Factory B is equipped with product manufacturing equipment 2000. Factory B is operated or managed by, for example, a coating manufacturer (hereinafter referred to as a user company or user). Each factory B is operated by multiple user companies. Factory B manufactures products using film rolls 80 shipped and transported from factory A. Factory B includes multiple sub-processes, which involve unwinding film (film F8, described below) from the film roll 80 and coating, or layering or adhering it with other films. The sub-processes correspond to the first and second manufacturing processes. Multiple inspection devices 90b1-90b4 (hereinafter collectively referred to as inspection devices 90) are located before and after the multiple sub-processes. While four inspection devices 90b1, 90b2, 90b3, and 90b4 are shown in Figure 1, the number of inspection devices 90 is not limited to this and may be three or fewer, or five or more.

In this embodiment, as a typical example, the process of manufacturing a film (web) is called the first manufacturing process, and the post-processing carried out at factory B using this manufactured film is called the second manufacturing process. For example, the post-processing process includes a coating process to apply a functional layer to the surface, and a lamination process to overlay a web of another film or the like. In the second manufacturing process, the film surface of the film roll 80 is also inspected by inspection device 90.

The material of the film F8 produced as shown in Figure 1 is not particularly limited, but typical examples include polycarbonate resin, polysulfone resin, acrylic resin, polyolefin resin, cyclic olefin resin, polyether resin, polyester resin, polyamide resin, polysulfide resin, unsaturated polyester resin, epoxy resin, melamine resin, phenolic resin, diallyl phthalate resin, polyimide resin, urethane resin, polyvinyl acetate resin, polyvinyl alcohol resin, styrene resin, cellulose acetate resin, and vinyl chloride resin. Furthermore, for example, the width of film F8 is preferably 1000 mm to 3200 mm, taking into consideration productivity, quality, etc. The thickness is preferably 15 μm to 500 μm, taking into consideration quality, handling, etc.

As a non-typical example of this embodiment, if the film manufactured in Factory B undergoes multiple post-processing steps, the first post-processing step may be referred to as the first manufacturing process, and the subsequent post-processing step may be referred to as the second manufacturing process. Alternatively, the film roll 80 manufactured in Factory A may be unwound and post-processed in a later process. In a typical example, the sub-processes performed in Factory B include a lamination process (also called a bonding process) in which other films are layered and bonded. The lamination process forms a laminate 80B (see the enlarged cross-sectional view of the bubble in Figure 1). Below, the first to third layers are bonded or applied to the raw film (F8) through several sub-processes performed in Factory B. Note that the enlarged cross-sectional views of the bubbles omit the adhesive layers between each layer. For example, Film F8 is a PVA (polyvinyl alcohol resin) layer, with the first layer being a TAC (triacetyl cellulose) layer, the second layer being an optically functional film layer such as a polarizer, and the third layer being a protector. The third layer may also be a separator, anti-glare film, or the like. The third layer is an opaque layer.

The inspection device 90 photographs the film, etc., and generates image data. As mentioned above, in the example shown in Figure 1, multiple inspection devices 90 are placed before and after the sub-processes, such as the stretching process and lamination process, of the film production line. The inspection device 90 will be explained below with reference to Figures 2 to 6.

(Inspection device 90)
Inspection devices for detecting surface irregularities, bubbles, cracks, and distortions in the internal structure of a transparent object such as film F8 include transmission-type imaging units and reflection-type imaging units. Inspection devices for detecting surface irregularities and scratches on an opaque object such as laminate 80B include reflection-type imaging units. Furthermore, for both transmission-type and reflection-type inspection devices, there are bright-field inspection devices that receive non-scattered light from the surface and dark-field inspection devices that receive scattered light, depending on the relative positions of the camera's optical axis, light source, and object under inspection. Bright-field inspection devices correspond to the first, third, and fifth imaging methods described below and receive non-scattered light. Dark-field inspection devices correspond to the second, fourth, and fifth imaging methods described below and receive scattered light. In a bright-field inspection system, if there is no defect, there is no scattering of light, so the light from the light source enters the light detection means without being blocked; if there is a defect, the light is blocked by the defect and does not enter the light detection means. Therefore, the defect is observed as a dark spot or streak against a bright background. In contrast, in a dark-field inspection system, if there is no defect, there is no scattering of light, so the light does not enter the light detection means. However, if there is a defect, the light is scattered by the defect and enters the light detection means. Therefore, the defect is observed as a bright spot or streak against a dark background.

The inspection device 90 in this embodiment may be any type of inspection device. One of the first and second inspection data is inspection data acquired using one or more inspection methods, while the other is inspection data acquired using one or more inspection methods, including one different from the inspection method of the first inspection data. Alternatively, one of the inspection data is inspection data acquired using multiple inspection methods (integrated inspection data, described below). It is preferable to use an inspection method with high detection sensitivity, but there may be limitations on the inspection method available depending on the condition of the object being inspected (subject). For example, inspection of polarizers, retardation films, optical compensation films, and optically functional films with liquid crystal layers requires the use of a polarized imaging method, such as a polarization camera. Furthermore, with opaque or low-transparency films, transmission imaging methods may not be possible, or even if they are used, the sensitivity may be low. For this reason, different inspection methods may be used for the first and second inspection data.

In this embodiment, each inspection device 90 has a photographing unit that applies one of the following first to fifth photographing methods. Figure 2 is a table explaining the characteristics of the various photographing methods. Figure 3 is a schematic diagram showing the positional relationship of the photographing unit 95 in the various photographing methods. The photographing unit 95 is composed of a light 91 and a camera 92. An example configuration of the light 91 and camera 92 of the photographing unit 95 will be described later.

(First imaging method)
As shown in FIG. 3A and the table in FIG. 2, the first imaging method captures transmitted light traveling straight through the transparent film F8. The camera 92 and the lighting device 91 are positioned opposite each other so as to straddle the subject (film F8). The illumination direction of the lighting device 91 and the optical axis of the camera 92 are aligned in a straight line. As shown in the table in FIG. 2, with the first imaging method, if there is a defect in the subject, the defect will obstruct the irradiated light, changing the amount of light received. The object to be inspected is a transparent film. Hereinafter, the first imaging method will also be referred to as "transmission 1."

(Second imaging method)
As shown in FIG. 3B and the table in FIG. 2, the second imaging method captures transmitted light reflected or scattered within the transparent film F8. The camera 92 and the illuminator 91 are positioned opposite each other so as to straddle the subject (film F8; the same applies below). The illumination direction of the illuminator 91 and the optical axis of the camera 92 are also positioned offset from each other so as not to coincide. The second imaging method receives scattered light from a foreign object present within the subject. The object to be inspected is a transparent film. Hereinafter, the second imaging method will also be referred to as "Transmission 2."

(Third Shooting Method)
As shown in FIG. 3(C) and the table in FIG. 2, the third imaging method captures light reflected specularly from the surface of the transparent film F8 or the surface of the opaque laminate 80B. The camera 92 and the lighting 91 are placed on the same side of the subject. The angle of incidence of the lighting direction of the lighting 91 relative to the surface of the subject is the same as the angle of incidence of the optical axis of the camera 92. The third imaging method detects the phase difference of the reach due to the apparent shape of the subject. The objects to be inspected are the transparent film and the opaque film (laminated body 80B). Hereinafter, the third imaging method will also be referred to as "Reflection 1."

(Fourth Shooting Method)
As shown in FIG. 3(D) and the table in FIG. 2, the fourth imaging method captures reflected light scattered on the surface of the transparent film F8 or the surface of the opaque laminate 80B. The camera 92 and the lighting device 91 are placed on the same side of the object. The angle of incidence of the lighting device 91 relative to the object surface and the angle of incidence of the optical axis of the camera 92 are offset so as not to coincide. The fourth imaging method receives scattered light caused by foreign matter on the object surface. The objects to be inspected are transparent and opaque films. Hereinafter, the fourth imaging method will also be referred to as "reflection 2."

(Fifth Shooting Method)
As shown in Figures 3(E) and (F), the fifth imaging method uses polarized light. Hereinafter, the fifth imaging method will also be referred to as "polarized light." The arrangement of the illumination 91 and the camera 92 can be any of the first to fourth methods. In imaging using polarized light, the polarization state is inspected. In imaging using polarized light, a polarized camera that captures the linearly polarized state may be used, or illumination that irradiates linearly polarized light (referred to as a polarized light source) may be used. Alternatively, in the fifth imaging method using polarized light, a polarizing plate may be used as shown, or this may be used in combination with a polarized camera and a polarized light source. The fifth imaging method is used, for example, to inspect films for polarizing plates. Films for polarizing plates include films with polarization properties (polarizers) and films used to manufacture these polarizers (hereinafter also referred to as raw film). The raw film is required to have non-polarized properties.

Figure 3(E) shows a photography method using polarized light used for the raw film of a polarizer or the protective film of a polarizer. The raw film is a film that is given polarization properties in a later process, and the protective film is a film that is used by layering it on top of the polarizer (polarizing film) in a later process. In the photography method shown in Figure 3(E), unpolarized light is output from the light source 91 (similar to Figure 3(F)). A direct polarizer 99a is placed between the light source 91 and the film F8 (raw film) to be inspected, and a linear polarizer 99b is placed between the film F8 and the camera 92. The linear polarizers 99a and 99b are arranged in a crossed Nicol configuration. That is, when viewed from the Z direction (the direction perpendicular to the film surface), the absorption axes of the two linear polarizers 99a and 99b intersect at a predetermined angle that is close to perpendicular to each other. For example, the absorption axes intersect at approximately 90° (89 to 91°) or so. With this configuration, if film F8 is normal, linearly polarized light that is irradiated through linear polarizer 99a and passes through film F8 is unlikely to pass through linear polarizer 99b. On the other hand, if film F8 has a defect (feature point), light that passes through the defective part will pass through linear polarizer 99b and be observed as a bright spot.

Figure 3 (F) shows a photography method using polarized light used in a polarizer (also called polarizing film) that has been given polarization properties. In the photography method shown in Figure 3 (F), linear polarizer 99b is positioned so that the absorption axis of film F8 and the absorption axis of linear polarizer 99b intersect at approximately right angles. Unpolarized light is output from illumination 91 to film F8 (polarizer). Light that passes through normal areas of film F8 does not easily pass through linear polarizer 99b, but light that passes through defective areas does pass through linear polarizer 99b and is observed as a bright spot.

(Modification of the first imaging method)
As shown in FIG. 3(G), a variation of the first imaging method (hereinafter referred to as imaging method 1b) uses a knife edge to block a portion of the illumination light. In imaging method 1b, transmitted light traveling straight and reflected or scattered within the transparent film F8 is captured. The camera 92 and the illumination 91 are positioned in the same manner as in the first imaging method, and the illumination direction of the illumination 91 and the optical axis of the camera 92 are aligned. In addition, in imaging method 1b, a knife-edge light-blocking member 915 is positioned near the subject on the illumination 91 side. The light-blocking member 915 is a flat plate positioned so that its tip is aligned with the optical axis, blocking one side of the illumination light from the optical axis. In the example shown in FIG. 3(G), the left half of the light on the paper surface relative to the optical axis is blocked. Changes in the refractive index of the subject, such as its thickness, change the angle at which the light reaches the subject. The subject is a transparent film. The imaging method 1b can be used as an alternative to the first imaging method.

Figure 4 is a table showing the correspondence between imaging units 1 to 6 and imaging methods in this embodiment. Imaging units 1 to 6 correspond to imaging methods 1 to 5, respectively.

Figures 5A and 5B are schematic diagrams showing an example configuration of the inspection device 90. Figures 5A and 5B show an example of the fourth imaging method (Reflection 2) as a representative example of the first to fifth imaging methods. Note that while the example in Figure 5A shows an example in which the inspection device 90 is composed of one imaging unit 95, as will be described later, the inspection device 90 may include multiple imaging units 95 that apply multiple imaging methods.

Figure 5A is a schematic diagram showing the configuration of a reflective inspection device 90 as viewed from the width direction (X direction). Figure 5B is a schematic diagram showing the configuration of the inspection device 90 as viewed from the transport direction (Y direction). The inspection device 90 includes a light 91, a camera 92 as an optical sensor, an image analysis unit 93 as a data processing device, and a memory unit 94. The inspection device 90 optically inspects feature points (hereinafter simply referred to as defects) that occur on the film F8 during transport. In the inspection device 90, the camera 92 optically inspects the film F8 in the film roll 80 and generates image data as inspection data. The image data includes not only still images but also video data consisting of a time-series of consecutive still images. Furthermore, feature points may be extracted directly from signal data without being converted into image data. The number of cameras 92, the angle of view, and the distance to the film surface are set so that the entire width of the film F8 is the inspection area (capture range). The number of cameras is determined so that multiple cameras can be arranged in the width direction when a single camera cannot adequately capture the entire width of the film. FIG. 5B illustrates an example in which two cameras 92 are arranged in the width direction (X direction). The image analysis unit 93 may combine multiple images obtained by continuous shooting with one camera 92 to generate a single image data piece that includes the entire film surface of the film roll 80. Alternatively, the image analysis unit 93 may store multiple image data pieces in the storage unit 94 in association with the shooting times. Similar image data pieces obtained by multiple cameras 92 arranged in the width direction may also be combined. The image analysis unit 93 can determine the longitudinal position of the film F8 by referencing the stored transport speed (winding speed or unwinding speed) and the shooting times associated with the image data. In the following description, it is assumed that multiple image data pieces obtained by continuous shooting are stored for one film roll 80 in association with the shooting times. The image analysis unit 93 generates defect information by analyzing the image data. The inspection device 90 inspects for defects that occur during the manufacturing process, such as when the long film F8 is being wound up.

The illumination 91 irradiates the inspection area of the film F8 with light. The illumination 91 irradiates light uniformly across the width of the rolled film F8 (a direction perpendicular to the longitudinal direction of the film F8 and parallel to the film surface). Here, "uniform" means that the illuminance on the film F8 is approximately the same across the width of the film F8 (e.g., the difference between the maximum and minimum values is less than a specified value).

Camera 92 is an optical sensor that optically reads the inspection area of film F8. Camera 92 is equipped with imaging elements such as a CCD (Charge Coupled Device) or CMOS (Complementary Metal Oxide Semiconductor), lenses, etc. Camera 92 is an area sensor that generates two-dimensional image data from the output signals of each imaging element. Camera 92 is illuminated by illumination 91 and detects diffused light from the light reflected in the inspection area of film F8. Here, either a color camera or a black and white camera (monochrome camera) may be used as camera 92.

The one or more cameras 92 have a shooting range that spans the entire width of the film F8, and in one shooting session, the entire width of the film F8 is simultaneously read. The cameras 92 may be those that detect light in the visible light range or those that detect light in the infrared range. The fifth shooting method uses a polarized camera (a normal camera) with a polarizing filter.

Furthermore, it is desirable that the contrast between the signal values corresponding to the illuminated areas on film F8 illuminated by light from illumination 91 and the signal values corresponding to the non-illuminated areas not illuminated by light from illumination 91 in the output signal from camera 92 be equal to or greater than a predetermined value. In other words, it is desirable that only the areas on film F8 illuminated by light from illumination 91 (illuminated areas) appear bright.

Contrast is expressed as the difference or ratio between two values to be processed (here, the signal value corresponding to the illuminated area and the signal value corresponding to the non-illuminated area), and the greater the difference between the two values, the greater the contrast. To increase the contrast between the illuminated and non-illuminated areas, it is desirable to use strong, highly directional lighting 91.

Here, "strong" means that when the illuminance at an irradiation distance of 50 mm is E50, the illuminance E50 is 50,000 lx or more. Furthermore, "highly directional" means that when the illuminance at an irradiation distance of 50 mm is E50 and the illuminance at an irradiation distance of 100 mm is E100, the relationship (E50 - E100)/E50<0.5 is satisfied.

The image analysis unit 93 is composed of a CPU, RAM, etc., and reads various processing programs stored in the memory unit 94, loads them into RAM, and performs various processes in cooperation with these programs.

The storage unit 94 is composed of an HDD, SSD (Solid State Drive), etc., and stores various processing programs, data required to execute those programs, etc. The storage unit 94 also stores captured image data (inspection data) linked to the time of capture. The storage unit 94 also stores the winding speed (e.g., 100 m/min) of the film roll manufacturing apparatus 1000, or the unwinding conditions (e.g., 30 m/min) of film F8 in the product manufacturing apparatus 2000. These winding speeds and unwinding conditions may be included in the inspection list of the inspection DB (see table T13 in Figure 9).

The image analysis unit 93 performs data processing on the output signal of the camera 92 (optical sensor) to detect characteristic points (position and intensity) of defects, etc. on the film F8. The data processing includes image processing of the image data obtained from the output signal of the camera 92, defect determination processing to determine defects based on the data after image processing, and quantitative evaluation processing to quantitatively evaluate defects based on the data after image processing.

(Inspection equipment list)
FIG. 6 is a table showing a list of inspection devices. As shown in Table T01 of the inspection device list 1, inspection devices a to f have one or more inspection instruments. For example, inspection device b has imaging unit 2 and imaging unit 3, and inspection device c has imaging unit 1 and imaging unit 4. Imaging units 1 to 6 are as shown in FIG. 4 above. For example, imaging unit 1 takes images using the first imaging method as shown in FIG. 3(A). Inspection devices a to f correspond to any of the inspection devices 90 (90a1, 90a2, 90b1, etc.) shown in FIG. 1. Note that the combination of imaging units included in the inspection device (inspection device 90) shown in Table T01 is an example, and other combinations of imaging units may be included.

As shown in Table T01, when an inspection device includes multiple imaging units, the inspection data (primary data) obtained from the multiple imaging units is integrated into a single piece of inspection data that takes into account positional information between the imaging units. Hereinafter, the inspection data before integration is referred to as primary data, and the inspection data obtained by integrating multiple primary data is also referred to as integrated inspection data. The integrated inspection data corresponds to the first inspection data or the second inspection data. This positional information between the multiple imaging units is recorded as "inter-inspector positional information" as shown in Table T01. The multiple imaging units are set to image the same inspection area of a subject, such as film F8, in the width direction (X direction), but there may be a slight misalignment in the length direction (Y direction). This slight misalignment in the Y direction is adjusted using this "inter-inspector positional information."

Table T02 of Inspection Device List 2 shows the combinations of inspection devices corresponding to the first inspection data and the second inspection data. The selection of the inspection device for each of the first inspection data and the second inspection data can be made by the user, as described below (button b1 in Figure 15).

In this embodiment, one of the first test data and the second test data is test data acquired using one or more test methods. The other test data is test data acquired using one or more test methods, including a test method different from the test method of the one test data. Alternatively, one test data is test data acquired using multiple test methods. For example, in Example 1 of Table T02, the first test data uses test data acquired from test device a, and the second test data uses test data acquired from test device c. In this case, the first test data is test data acquired using one test method (first test method), and the other second test data is test data acquired using two test methods (first and fourth test methods). The same applies to Examples 2 and 3.

The above is a description of the inspection device 90. In the following, we will assume that the first and second inspection data were acquired using the combination of Example 1 in Table T02 (within the dashed rectangular frame in Table T02).

(Information Processing System 50)
The information processing system 50 will be described below with reference to Figs. 7 to 9. Fig. 7 is a block diagram showing a schematic configuration of the information processing system 50. The information processing system 50 is, for example, a server. As shown in Fig. 7, the information processing system 50 includes a control unit 51, a storage unit 52, and a communication unit 53.

(Control unit 51)
The control unit 51 has a CPU and memories such as RAM, ROM, etc. The CPU is a control circuit configured with a multi-core processor or the like that controls each of the above-mentioned units and executes various arithmetic processing in accordance with a program, and each function of the information processing system 50 is realized by the CPU executing the corresponding program.

The control unit 51 functions as an acquisition unit 511 and a reception unit 512 in cooperation with the communication unit 53. The control unit 51 also functions as a comparison unit 513, an analysis unit 514, an extraction unit 515, and a display output unit 516. The acquisition unit 511 acquires the first and second inspection data obtained by inspection in the first and second manufacturing processes. The reception unit 512 accepts the user's selection of an inspection method or inspection device (photographing unit). The comparison unit 513 extracts feature points from each of the first and second inspection data. The comparison unit 513 searches for corresponding feature points between the first and second inspection data through a comparison process. In the comparison process, the comparison unit 513 generates feature point descriptors (descriptor 2 described below) for the two inspection data (image data), and uses these feature point descriptors to perform a feature point matching process between the inspection data and output the comparison results (a corresponding point list shown in Figure 19 described below). The analysis unit 514 uses the corresponding point list to calculate an index indicating the relationship (hereinafter referred to as relationship information). The relationship information includes a scatter plot and statistical information such as the mean, regression line, variance, standard deviation, and correlation coefficient. The extraction unit 515 uses the comparison results to extract (classify) first to third type feature points. The display output unit 516 transmits the feature point extraction results and display data of feature points for each primary data to the terminal device 70, or displays them on a display unit (not shown), in response to a request from the terminal device 70, etc.

(Storage unit 52)
The memory unit 52 is a large-capacity auxiliary storage device that stores various programs including an operating system and various data. For example, a hard disk, a solid-state drive, a flash memory, a ROM, etc. are used as the storage. The memory unit 52 stores a user list, a lot list, an inspection data DB, an authorized device list, etc. The user list and lot list are managed and registered by an administrator through access to the terminal device 70. For example, this administrator is a person in charge of the relevant department of the manufacturer that operates Factory A. The inspection device list is the one shown in FIG. 6 above.

(User list)
FIG. 8 shows an example of various data stored in the storage unit 52. Table T11 shown in FIG. 8 is an example of a user list. The user list stores user IDs, user names, contact information, etc. Each user is assigned access rights to a search data DB (inspection database), and is granted access rights to various data (inspection data, extracted data, etc.) related to the film roll 80 (identified by lot ID) that the user is involved in.

(Lot list)
Table T12 in Fig. 8 is an example of a lot list. The lot list records a lot ID assigned to each film roll, a product name (also called a type), a delivery destination user ID (orderer), multiple manufacturing conditions, size (width, length, thickness), manufacturing date, etc.

(Test data DB)
FIG. 9 is an example of an inspection DB (database) stored in the storage unit 52. The inspection data DB stores data related to the inspection of various film rolls 80, such as the first and second inspection data and feature point extraction results shown in FIG. 9. As described above, the first inspection data is data obtained from the inspection in the first manufacturing process. The second inspection data is data obtained from the inspection in the second manufacturing process. The feature point extraction results are data generated by the information processing system 50 using the first and second inspection data.

Table T13 shown in Figure 9 is an example of an inspection list registered in the inspection data DB. The inspection list stores the inspection ID, lot ID, inspection device ID, inspection data, inspection date and time, etc. The inspection device ID corresponds to the inspection device name in table T01 in Figure 6. Examples of inspection data included in the inspection list will be described later.

(Communication unit 53)
The communication unit 53 also serves as an interface for network connection with an external device such as a PC.

(Generation of first and second test data)
The process of generating the first and second inspection data performed in the first and second manufacturing steps will be described below with reference to Figures 10 to 13. Figure 10 is a flowchart showing the process of generating the first inspection data performed in the first manufacturing step.

As mentioned above, the following description will be based on Example 1 of Table T02 in Figure 6. That is, the first test data is obtained by test device a, and the second test data is obtained by test device c. In this case, the first test data is test data obtained by the first test method (first imaging method). The second test data is test data obtained by the two first and fourth test methods (first and second imaging methods).

(First test data generation process)
(Step S11)
In the typical example described above, in the first manufacturing step, the film roll 80 is manufactured by the film roll manufacturing apparatus 1000 .

(Step S12)
The inspection device 90 photographs the film and stores the image data. The inspection device 90 is the same as that described with reference to FIGS.

(Step S13)
If the inspection device 90 has multiple imaging units, the process of step S15 is performed, and if the inspection device 90 has one imaging unit, the process of step S14 is performed. In this example, the inspection device a has one imaging unit 1 (transmission 1), so the process of step S14 is performed.

(Step S14)
The image analysis unit 93 performs image processing, which will be described below, on the image data to generate a plurality of feature points.

(Image processing for generating feature points)
The image analysis unit 93 acquires two-dimensional image data generated by the camera 92 and stored in the storage unit 94 .

The image analysis unit 93 performs data processing on the image data (examination data) acquired from the camera 92.

The image analysis unit 93 divides the image data into multiple regions. For example, the image analysis unit 93 divides the image data into n regions (e.g., several to several tens) in the width direction (hereinafter referred to as regions a1 to an).

Next, the image analysis unit 93 acquires image data for one area a1 and performs mathematical processing on the image data for area a1. Appropriate mathematical processing is provided depending on the type of defect to be detected (gauge band, vertical wrinkles, diagonal wrinkles, etc.).

Mathematical processing includes preprocessing, enhancement processing, signal processing, image feature extraction, etc.

Pretreatment includes the following:
- Image cropping,
- Low-pass filter, high-pass filter, Gaussian filter, median filter, bilateral filter, - morphological transformation, color transformation (L*a*b*, sRGB, HSV, HSL), contrast adjustment, noise removal, restoration of blurred and shaken images, mask processing, Hough transform, projection transformation, etc.

Examples of enhancement processing include the Sobel filter, Scharr filter, Laplacian filter, Gabor filter, and Canny algorithm.

The signal processing includes the following:
- Basic statistical quantities (maximum, minimum, average, median, standard deviation, variance, quartile), square root of the sum of squares, difference, sum, product, ratio, distance matrix calculation, differential and integral calculus, threshold processing (binarization, adaptive binarization, etc.), - Fourier transform, wavelet transform, peak detection (peak value, number of peaks, half-width, etc.), etc.

Examples of image feature extraction include template matching and SIFT features.

Next, the image analysis unit 93 performs threshold processing on the values (feature amounts) obtained by mathematical processing of the image data of area a1. Threshold processing is a process that determines whether or not the defect is the target of detection based on a predetermined threshold, and also determines the rank (intensity) of the defect.

In threshold processing, determining the presence and type of defect corresponds to "defect determination processing." Also, in threshold processing, classifying defects into multiple ranks according to the threshold corresponds to "quantitative evaluation processing."

For example, defects are classified into multiple ranks for a parameter (feature) that takes a value between 1 and 100. For example, ranks are classified according to the size (diameter or area) of the defect. Ranks classified by size may also be further subdivided according to the parameter value.

The image analysis unit 93 performs similar processing on areas other than area a1.

After processing each of the regions a1-an, the image analysis unit 93 integrates the results for each of the regions a1-an, and data processing ends. Specifically, the image analysis unit 93 generates data that associates the rank of the detected defects with their location (x and y coordinates) for each region (each position in the width direction of the film F8).

After data processing, the image analysis unit 93 stores the results of the data processing in the storage unit 94. The image analysis unit 93 performs this type of data processing on each of the multiple image data obtained in the inspection of one film roll 80, and obtains the processing results. By aggregating these processing results, inspection data such as that shown in Figure 11 is generated.

Figure 11 shows an example of the contents of test data (test ID: i0101) in the test list. The test data contains feature point IDs that are automatically assigned consecutive numbers to each feature point, as well as feature point descriptors 1 and 2 (hereinafter simply referred to as descriptor 1, etc.) for each feature point ID. In addition, each feature point in the test data is given information indicating which imaging unit used to obtain it (the "imaging unit" column). In the example of Figure 11, primary data obtained by one imaging unit, 1, was used, so imaging unit 1 is described for all feature points.

Descriptor 1 is information about a feature point alone, recording its XY coordinate position and intensity. Intensity is the rank of the feature point, which will be described later. Intensity information may also include information about the feature point's size (diameter, area) and brightness. The XY coordinate position is based on the origin of the film surface (for example, the left edge of the leading edge). X is the coordinate in the width direction of the film, and can range, for example, from 0 to 3000 mm depending on the film size (see Table T12). Y is the coordinate in the length direction of the film, and can range, for example, from 0 to 10,000 m depending on the film size. Descriptor 1 is generated by the image analysis unit 93 of the inspection device 90.

Descriptor 2 is peripheral information, and is vector or array information that represents surrounding information such as relationships with other feature points. For example, SIFT features may be used as descriptors, or the probability density function of feature points calculated by kernel density estimation may be used as descriptors. Descriptor 2 is mainly generated by the comparison unit 513.

(Steps S15 to S16)
If there are multiple imaging units, the processes of steps S15 and S16 are performed. The processes here are the same as steps S25 and S26 in Fig. 12 described later, and the details of the processes will be explained together in the description of steps S25 and S26 described later.

(Step S17)
Terminal device 70 in the first manufacturing process sends inspection data including information on multiple feature points obtained in the processing up to step S14 or step S16 to information processing system 50. Acquisition unit 511 of information processing system 50 stores the acquired inspection data as first inspection data in the inspection data DB of storage unit 52. The inspection data shown in FIG. 11 is an example of such first inspection data.

(Generation process of second test data)
FIG. 12 is a flowchart showing the process of generating second inspection data performed in the second manufacturing process.

(Step S21)
In the second manufacturing process, for example, after the first manufacturing process, the product manufacturing apparatus 2000 performs post-processing using the film roll 80 to manufacture a product using the film F8.

(Step S22)
The inspection device 90 photographs the surface of the film F8 before post-processing, or the film F8 during or after post-processing, or the surface of the laminate 80B, and stores the image data.

(Step S23)
If the inspection device 90 has multiple imaging units, the process of step S25 is performed, and if the inspection device 90 has one imaging unit, the process of step S24 is performed. In this example, the inspection device c has two imaging units, imaging unit 1 (transmission 1) and imaging unit 4 (reflection 2), so the process of step S15 is performed.

(Step S24)
If the inspection device is configured with one imaging unit (imaging unit 25), step S24 is executed. The processing here is the same as step S14, and therefore a description thereof will be omitted.

(Step S25)
The image analysis unit 93 generates a plurality of feature points from the inspection data (image data) obtained from each imaging unit through processing similar to that of step S14 or S24, and generates primary inspection data. In this case, two primary data are generated corresponding to imaging unit 1 and imaging unit 4 of 2. The configuration of each primary data is similar to the inspection data shown in Fig. 11, and is composed of a feature point ID and a feature point descriptor 1 (XY coordinates, size).

(Step S26)
The image analysis unit 93 generates integrated inspection data as one piece of inspection data from the plurality of primary data based on the position information and the inter-inspector position information (see Table T01). The processing in steps S25 and S26 is the same as that in steps S15 and S16.

(Step S27)
Terminal device 70 in the second manufacturing process sends inspection data including the plurality of feature point information obtained in the processing up to step S24 or step S26 to information processing system 50. Acquisition unit 511 of information processing system 50 stores the acquired inspection data in the inspection data DB of storage unit 52 as second inspection data.

Figure 13 shows an example of the contents of the second test data (test ID: i0102) generated and saved in this way. In the example shown in Figure 13, the "Image capture unit" column of the test data describes which image capture unit (image capture method) was used to capture the image, either Image capture unit 1 or Image capture unit 4.

(Feature point extraction process)
The feature point extraction process executed by the information processing system 50 will be described below with reference to Figs. 14 to 24C. Fig. 14 is a flowchart showing the feature point extraction process. Fig. 15 is an example of an operation screen 701 displayed on the terminal device 70. Fig. 16 is a schematic diagram for explaining the feature point extraction process.

The information processing system 50 starts the processing from step S31 onward in response to a start instruction from the user via the operation screen on the terminal device 70, or when the second inspection data is registered in the inspection data DB of the storage unit 52 and a pair of first and second inspection data is obtained. On the operation screen 701 in Figure 15, the user selects a lot and then uses button b1 to select the first and second inspection data from the multiple inspection data linked to that lot. The second inspection data is inspection data obtained in a process downstream of the first inspection data. In the example in Figure 15, the selection indicates that the first inspection data was obtained by inspection device a and the second inspection data was obtained by inspection device c. The user operates the analysis start button b0, which causes the control unit 51 to start the feature point extraction process.

(Step S31)
The acquiring unit 511 acquires the same lot of inspection data, that is, a pair of first and second inspection data, from the inspection data DB.

(Steps S32 and S33)
The comparison unit 513 performs preprocessing on the first inspection data under a first condition, and performs preprocessing on the second inspection data under a second condition.

As shown in FIG. 16, as preprocessing for the second condition, the comparison unit 513 performs preprocessing to reverse the Y coordinate (up and down) of the second inspection data to match any differences between winding (first manufacturing process) and unwinding (second manufacturing process) of the second inspection data. Furthermore, in the second manufacturing process, the comparison unit 513 performs preprocessing to reverse the X coordinate (left and right) of the second inspection data (or first inspection data) depending on information on whether the shooting area of the camera 92 is set to the front or back of the film F8.

Furthermore, the comparison unit 513 performs at least one of the following noise removal processes on the first and second test data as the noise removal processes included in the first and second conditions.
(1) Removal of low-rank feature points.
(2) Remove extremely small feature points.
(3) Eliminate consecutive hits.
(4) Eliminate concentrated impacts in the width direction. This occurs especially at the leading and trailing edges of film F8.

(Step S34)
The comparison unit 513 searches for feature points in one test data that are identical to or correspond to feature points in the other test data through comparison processing, and matches the feature points with each other. Fig. 17 is a subroutine flowchart showing the processing of step S34.

(Step S401)
The comparison unit 513 generates a descriptor 2 for each feature point of the first and second test data. For example, the comparison unit 513 uses a SIFT feature amount as the descriptor, or a probability density function of the feature points calculated by kernel density estimation as the descriptor.

(Steps S402 and S403)
The comparison unit 513 compares the feature points of the first and second test data to search for the most similar feature points. The comparison unit 513 evaluates the similarity between the feature points using Descriptor 1 and Descriptor 2, and regards the most similar feature points as corresponding feature points.

For example, when comparing feature points between the first and second test data, the comparison unit 513 searches for feature points in the first test data that correspond to feature points of interest in the second test data. In this case, the comparison unit 513 determines that feature points in the first test data that match the X and Y coordinates of descriptor 1 of the feature point in the second test data or that have the closest intensity are the same point. Alternatively, the comparison unit 513 determines that feature points with the closest distance (Euclidean distance) between the X and Y coordinates of descriptor 1 are the same point (corresponding points). The comparison unit 513 excludes feature points that are farther apart than a set threshold from the determination of corresponding points. Note that in this embodiment, the threshold in the Y direction is set to a value that is two to three orders of magnitude larger than the threshold in the X direction. For example, the threshold in the X direction is several millimeters, and the threshold in the Y direction is several meters. The threshold in the Y direction is two to three orders of magnitude larger than the threshold in the X direction because there is a greater amount of change.

Furthermore, the comparison unit 513 may use descriptor 2 in addition to descriptor 1 to extract feature points that are most similar based on the distance between vectors in high-dimensional vector space. In this case, the comparison unit 513 may use a probability density function calculated by kernel density estimation as described above as descriptor 2. Figure 18 is an example of a probability density function calculated by kernel density estimation that indicates the position and intensity (density) of feature points. In Figure 18, the vertical and horizontal axes are XY coordinates, and it is shown that the higher the concentration, the higher the density.

The comparison unit 513 determines that one feature point corresponds to only one other feature point. For example, for a feature point in the second test data, the feature point in the first test data whose descriptor vectors are closest to the feature point in the second test data is registered as the corresponding point in the corresponding point list.

Figure 19 is an example of a corresponding point list stored in the memory unit 52. The corresponding point list associates each feature point in the second inspection data with the most similar feature point in the first inspection data. The corresponding point list also describes the X and Y coordinates of the feature points in the second inspection data, the Euclidean distance between the associated feature points, the difference dx in the X coordinate, and the difference dy in the Y coordinate.

(Step S404)
The analysis unit 514 generates correlation information between feature points that exist in both the first and second test data. That is, the analysis unit 514 generates a scatter plot with X or Y on the horizontal axis and dx or dy on the vertical axis and statistical information as data indicating correlation information for feature points that have corresponding feature points in the corresponding point list. The statistical information includes a regression line and a correlation coefficient. With this, the control unit 51 ends the processing in FIG. 17, returns to the processing in FIG. 14, and performs step S35 and subsequent steps.

(Step S35)
The extraction unit 515 classifies feature points from the correspondence list, the first test data, and the second test data into first to third type feature points. The first to third type feature points will be described later. Specifically, the extraction unit 515 classifies, in the correspondence list, feature points of the second test data that are not associated with feature points of the first test data as second type feature points. Furthermore, the extraction unit 515 classifies, among feature points of the first test data that are not included in the correspondence list (feature points that are not associated with feature points of the second test data), as first type feature points. Furthermore, the extraction unit 515 classifies, among feature points in the integrated test data, feature points classified as third type feature points into feature points of each of the multiple primary data.

(First to third type feature points)
FIG. 20 is a table for explaining the first to third type feature points.

(First type feature point)
The first type feature points are feature points that are present in the first inspection data but not present in the second inspection data. The first type feature points are feature points that disappear in the second manufacturing process (e.g., the coating process or the lamination process). These first type feature points are feature points that do not need to be managed in the first manufacturing process. In this case, the manufacturing conditions that cause the first type feature points to occur may be subject to relaxed standards in the first manufacturing process.

(Second type feature point)
The second type feature points are feature points that are not present in the first inspection data but are present in the second inspection data. The second type feature points are feature points that newly appear in the second manufacturing process. Because these second type feature points are feature points that originate in the second manufacturing process, they can be used to improve the second manufacturing process.

(Third-class feature point)
The third type feature points are feature points that exist in both the first inspection data and the second inspection data. These third type feature points are feature points that originate from the first manufacturing process and require management. Because these third type feature points originate from the first manufacturing process, they can be used to improve the first manufacturing process.

(Step S36)
The control unit 51 outputs the feature point extraction information extracted in the processes up to step S35. The feature point extraction information is output by the control unit 51 registering it in the inspection data DB, or by the display output unit 516 transmitting it to the terminal device 70 and displaying it on the display unit thereof.

Figure 21A is an example of extraction result data (hereinafter simply referred to as extracted data). The extracted data records the inspection IDs of the original first and second inspection data, as well as the extraction results for each feature point. The extraction results (types 1 to 3) are classified as shown in Figure 20. Integrated feature point IDs are automatically assigned consecutive numbers, and integrated feature points are generated corresponding to feature points that are present in either or both of the first and second inspection data. The number of integrated feature point IDs is greater than or equal to the number of first inspection and second inspection feature point IDs.

FIG. 21B is an example of an inspection DB corresponding to FIG. 13. Although some of the description of feature point descriptors 1 and 2 has been omitted in FIG. 21B, it is the same as FIG. 13. In the second inspection data shown in FIG. 21B, the rightmost column ("Extraction Results") describes the extraction results of second-type or third-type feature points, depending on the processing in step S35. Note that for the first inspection data as well, if multiple primary data sets are obtained using multiple imaging units, an "Extraction Results" column is added, and the extraction results of first-type or third-type feature points are described therein.

It should be noted that multiple first and second inspection data may be generated for one lot ID by multiple inspection devices. For example, in the second manufacturing process, the film roll 80 in its original wound state may be inspected (photographed), and multiple second inspection data may be generated by inspections in several downstream processes. In this case, the information processing system 50 may generate multiple feature point extraction result data for one piece of first inspection data in a one-to-many relationship with multiple pieces of second inspection data. The user may also be able to select which second inspection data to associate with (for example, button b1 in Figure 15 above).

(Steps S37 and S38)
The control unit 51 determines whether at least one of the first and second test data is integrated test data. For example, the second test data is obtained by integrating two primary data generated by the test device c (see FIG. 6) using test data from each of the imaging units using two test methods (step S26 in FIG. 12). In such a case, the control unit 51 proceeds to step S38 and displays information about the feature points. FIG. 22 is a subroutine flowchart showing the processing of step S38.

(Steps S501 and S502)
The reception unit 512 receives a selection of primary data or integrated data from the user for display. FIG. 23 shows an operation screen 702 for receiving a selection, which is displayed on the terminal device 70. The operation screen 702 shown in FIG. 23 is displayed following the operation screen 701. The user can select the test data to be displayed on the preview screen by pressing button b2 on the operation screen 702. The example of the operation screen 702 shows a state in which the second test data has been selected. The type of feature point and its display content can be selected.

Button b3 allows you to select which of the two imaging units to use for data. If both imaging units are selected, the data will be substantially the same as the integrated data. Additionally, button b4 allows you to select the type of feature points to display and the type of graph to preview. For example, in the example shown on operation screen 702, imaging unit 4 and third type feature points are selected in the second test data. In response to this selection, data for feature point IDs where the imaging unit is "imaging unit 4" and the extraction result is "third type" is extracted from the second test data shown in FIG. 21B, and the extracted data is displayed in the preview display area b10 in the type of graph selected with button b2.

24A is an example of a scatter plot previewed by the settings on the operation screen 702. When both image capture unit 1 and image capture unit 4 are selected with button b2, both sets of data are plotted on the scatter plot in a manner that allows for differentiation, such as by color coding. In FIG. 24A, the horizontal axis represents the X coordinate of each feature point on the web, and the vertical axis represents the Y coordinate. The legend Area 0.1 to 0.5 indicates the approximate size (area) of the feature point. For example, an area of 0.1 is plotted in the graph area as a circle corresponding to the size of the small circle shown in the legend. In FIG. 24A (similar to FIG. 24B), feature points obtained from the primary data of the two image capture units 1 and 4 that make up the second test data selected with button b3 in FIG. 23 are plotted. FIG. 24B is an example of a histogram previewed by the settings on the operation screen 702, which corresponds to step S502. In FIG. 24B, the vertical axis represents the frequency of occurrence of feature points for each image capture unit, and the horizontal axis represents the area (Area) of the feature point. Figure 24B shows two types of occurrence frequencies in the primary data. Optical A and B in the legend correspond to the imaging units, respectively. For example, Optical A is primary data obtained by imaging unit 1, and Optical B is primary data obtained by imaging unit 4.

In this manner, in this embodiment, the first feature point information of the web in the first inspection data is compared with the second feature point information of the web in the second inspection data, and based on the comparison results, third type feature points present in both the first and second inspection data and/or first type feature points present in the first inspection data but not in the second inspection data, or second type feature points absent in the first inspection data but present in the second inspection data, are extracted. One of the first inspection data and the second inspection data is inspection data acquired using one or more inspection methods, and the other inspection data is inspection data acquired using one or more inspection methods, including an inspection method different from the inspection method used for the one inspection data. In this manner, information useful for process improvement and setting shipping standards can be efficiently collected both when manufacturing the web and in the manufacturing process where post-processing is performed using the web.

Furthermore, at least one of the first and second inspection data is inspection data that is integrated by aligning on the web surface feature point information extracted from multiple primary data sets acquired in the same inspection area using multiple types of inspection methods. This makes it possible to obtain more appropriate inspection data using one or more appropriate inspection methods according to the state of the web in each process.

Furthermore, in this embodiment, after extracting type 3 feature points as shown in FIG. 22, the feature points in the integrated inspection data are classified into feature points in each of the multiple primary data. By doing this, it is possible to determine, for example, whether each feature point is a highly reliable feature point or a low-reliability feature point. For example, type 3 feature points are likely to be feature points that actually occurred. Conversely, type 2 feature points that occurred (detected) using only one of the two inspection methods are likely to be low-reliability and noisy. For example, in the second inspection data used to inspect an opaque web, the imaging method can only be reflection 1 or reflection 2. In such cases, there is often a lot of noise and a low S/N ratio, but the user can more reliably identify type 3 feature points that were also detected as feature points in the first inspection data as feature points.

The configuration of the information processing system 50 described above is the main configuration used to explain the features of the above embodiment, but is not limited to the above configuration and can be modified in various ways within the scope of the claims. Furthermore, configurations that are commonly found in information processing devices/systems are not excluded.

The information processing system 50 may also include an inspection device 90 arranged in the first manufacturing process and/or the second manufacturing process. The feature point generation function of the image analysis unit 93 of the inspection device 90 may also be performed by the control unit 51 of the information processing system 50. In this case, the inspection device 90 sends image data of the film surface and the shooting conditions (information such as transport speed, camera direction, and angle of view) to the information processing system 50, and the feature point generation process is performed on the control unit 51 side.

Furthermore, the means and methods for performing various processes in the information processing system 50 according to the above-described embodiment can be realized by either a dedicated hardware circuit or a programmed computer. The above program may be provided by a computer-readable recording medium such as a USB memory or a DVD (Digital Versatile Disc)-ROM, or may be provided online via a network such as the Internet. In this case, the program recorded on the computer-readable recording medium is typically transferred to and stored in a storage unit such as a hard disk. Furthermore, the above program may be provided as standalone application software, or may be incorporated into the software of a device as one of its functions.

Although embodiments of the present invention have been described and illustrated in detail, the disclosed embodiments are made for purposes of illustration and example only and are not intended to be limiting. The scope of the present invention should be interpreted by the language of the appended claims.

This application is based on a Japanese patent application (Patent Application No. 2024-063185) filed on April 10, 2024, the disclosure of which is incorporated herein by reference in its entirety.

50 Information processing system 51 Control unit 511 Acquisition unit 512 Reception unit 513 Comparison unit 514 Analysis unit 515 Extraction unit 516 Display output unit 52 Memory unit 90, 90a1 to 90a2, 90b1 to 90b4 Inspection device 91 Lighting 92 Camera 95 Photography unit 1000 Film roll manufacturing device 2000 Product manufacturing device

Claims (13)

A method for extracting feature points on a web, comprising:
A step (a) of acquiring first inspection data in a first manufacturing process of manufacturing a web or post-processing a manufactured web;
(b) acquiring second inspection data in a second manufacturing process that uses the web and is performed after the first manufacturing process;
(c) comparing first feature information of the web in the first inspection data with second feature information of the web in the second inspection data;
and (d) extracting, based on the comparison result of the step (c), third type feature points present in both the first and second test data, and/or first type feature points present in the first test data but not in the second test data, or second type feature points present in the second test data but not in the first test data,
A method for extracting feature points, wherein one of the first inspection data and the second inspection data is inspection data acquired by one or more inspection methods, and the other inspection data is inspection data acquired by one or more inspection methods including an inspection method different from the inspection method of the one inspection data. the first inspection data and the second inspection data are inspection data obtained by photographing a web with an inspection device,
2. The feature point extraction method according to claim 1, wherein the imaging method of the other inspection data in the inspection device is inspection data acquired using one or more imaging methods, including an imaging method different from the imaging method of the one inspection data in the inspection device. The imaging method used to acquire the one of the inspection data includes at least one of a first imaging method for imaging transmitted light traveling straight through the web, a second imaging method for imaging transmitted light reflected within the web, a third imaging method for imaging reflected light specularly reflected from the web surface, and a fourth imaging method for imaging reflected light scattered from the web surface, depending on the positional relationship between the lighting and the imaging unit;
3. The feature point extraction method according to claim 2, wherein the imaging method of the other test data includes an imaging method, among the first to fourth imaging methods, that is different from the imaging method of the one test data. The feature point extraction method described in claim 2, wherein the imaging method includes an imaging method using polarized light that detects the polarization state of light. At least one of the first test data and the second test data is
2. The feature extraction method according to claim 1, wherein the inspection data is integrated by aligning feature information extracted from multiple primary data sets acquired by multiple types of inspection methods in the same inspection area on the web surface. In the step (d), after extracting the third type feature points using the integrated inspection data,
The feature point extraction method according to claim 5 , further comprising the step (e) of classifying the feature points in the integrated inspection data into feature points in each of the plurality of primary data. a step (f) of accepting a selection of the inspection method for the one of the inspection data;
and (g) displaying, by selection in step (f), feature point information of the primary data classified in step (e) corresponding to the selected inspection method. A method for extracting feature points on a web, comprising:
A step (a) of acquiring first inspection data in a first manufacturing process of manufacturing a web or post-processing a manufactured web;
(b) acquiring second inspection data in a second manufacturing process that uses the web and is performed after the first manufacturing process;
(c) comparing first feature information of the web in the first inspection data with second feature information of the web in the second inspection data;
and (d) extracting third type feature points present in both the first and second inspection data based on the comparison result of the step (c),
At least one of the first inspection data and the second inspection data is inspection data obtained by integrating feature point information extracted from a plurality of primary data acquired by a plurality of types of inspection methods in the same inspection area by aligning the feature point information on the web surface;
The feature point extraction method further comprises a step (e) of classifying the feature points in the integrated inspection data into feature points in each of a plurality of primary data sets after extracting the third type feature points in the step (d) using the integrated inspection data. the first inspection data and the second inspection data are inspection data obtained by photographing a web with an inspection device,
The feature point extraction method according to claim 8 , wherein the inspection device of the one inspection data is inspection data acquired by a plurality of imaging methods. a step (f) of accepting a selection of the inspection method for the one of the inspection data;
and (g) displaying, by selection in step (f), feature point information of the primary data classified in step (e) corresponding to the selected inspection method. A control program for causing a computer to execute the extraction method described in any one of claims 1 to 10. A method for extracting feature points on a web, comprising:
an acquisition unit that acquires first inspection data in a first manufacturing process that manufactures a web or post-processes a manufactured web, and second inspection data in a second manufacturing process that performs post-processing using the web after the first manufacturing process;
a comparison unit that compares the first feature information of the web in the first inspection data with the second feature information of the web in the second inspection data;
an extraction unit that extracts, based on a comparison result from the comparison unit, third type feature points that are present in both the first and second test data, and/or first type feature points that are present in the first test data but not in the second test data, or second type feature points that are not present in the first test data but are present in the second test data,
An information processing system, wherein one of the first test data and the second test data is test data obtained by one or more test methods, and the other test data is test data obtained by one or more test methods including a test method different from the test method of the one test data. A method for extracting feature points on a web, comprising:
an acquisition unit that acquires first inspection data in a first manufacturing process that manufactures a web or post-processes a manufactured web, and second inspection data in a second manufacturing process that performs post-processing using the web after the first manufacturing process;
a comparison unit that compares the first feature point information of the web in the first inspection data with the second feature point information of the web in the second inspection data;
an extraction unit that extracts third type feature points that exist in both the first and second inspection data based on a comparison result from the comparison unit,
At least one of the first inspection data and the second inspection data is inspection data that is integrated by aligning feature point information extracted from a plurality of primary data acquired by a plurality of types of inspection methods in the same inspection area on the web surface,
an information processing system, wherein the extraction unit uses the integrated inspection data to extract the third type feature points, and then classifies the feature points in the integrated inspection data into feature points in each of a plurality of primary data.