Feature point extraction method, shipment standard setting method, and information processing system

Abstract

This feature point extraction method comprises: step (c) for comparing first feature point information about a film in first inspection data of a first manufacturing process with second feature point information about the film in second inspection data of a second manufacturing process; and step (d) for extracting, on the basis of the comparison result of step (c), a feature point which is present in one among the first and second inspection data and is not present in the other, or is determined defective in one among the first and second inspection data and is not determined defective in the other.

Description

Feature point extraction method, shipping standard setting method, and information processing system

[0001] The present invention relates to a method for extracting feature points, a method for setting shipping standards, and an information processing system.

[0002] 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 liquid crystal display devices. For example, wide films of 2000 mm or more are in demand. 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.

[0003] In the post-processing process for manufacturing film-based products, when defects or other quality issues occur, it is necessary to determine whether the defect occurred in the upstream process, i.e., during film manufacturing and was originally present on the film, or whether it occurred in the post-processing process. If it is not possible to clearly determine that the defect occurred in the post-processing process, improvements to the upstream process may be required. In response to requests for improvement, the shipping standards for the upstream process may become stricter than necessary, resulting in over-specification. Furthermore, in order to prevent quality issues before they occur, even though it is unclear how they will affect the downstream process, the shipping standards for film manufacturing may be set too strictly based on expectations. This also constitutes over-specification. Over-specification leads to reduced yields and increased costs, which is undesirable for both the upstream and downstream process companies.

[0004] Patent Document 1 discloses the following: "A quality monitoring system for performing quality control in a manufacturing process for roll-shaped anti-reflection film, which is comprised of multiple processes, by selecting defects that have occurred in the latest process based on inspection information for the upstream process and inspection information for the latest process, even if part of the product roll is removed between an upstream process and a latest process due to the occurrence of an abnormality, the quality monitoring system comprising: an inspection machine provided for each process in the manufacturing process; an inspection information management database that stores and manages the inspection information obtained from the inspection machine; a production information management database that manages quality information and performance information for each process of the product roll; a defect selection means that selects defects that have occurred in the latest process by correcting the coordinates of defect detection positions in the latest process and the previous process based on the inspection information management database and the production information management database; and a defect monitoring means that determines that the defects selected by the defect selection means are abnormal based on abnormality determination conditions and notifies the user of the abnormality." (Claim 1)

[0005] JP 2013-088247 A

[0006] The technology in Patent Document 1 detects defects that occur in the latest process, identifies anomalies, and notifies the user, which can prevent defects from occurring during manufacturing. However, it is insufficient in terms of collecting information to investigate the causes of quality problems, and does not lead to the setting of appropriate product standards or process improvements.

[0007] The present invention has been 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 producing a film and in the manufacturing process in which post-processing is performed using the film.

[0008] The above object of the present invention can be achieved by the following means.

[0009] (1) A method for extracting feature points of a film, comprising: (a) acquiring first inspection data in a first manufacturing process for manufacturing a film; (b) acquiring second inspection data in a second manufacturing process for performing post-processing using the manufactured film, which is carried out after the first manufacturing process; (c) comparing first feature point information of the film in the first inspection data with second feature point information of the film in the second inspection data; and (d) extracting, based on the comparison result of step (c), feature points that are present in one of the first and second inspection data but not in the other, or that are determined to be defects in one of the inspection data but not in the other.

[0010] (2) A method for extracting feature points of a film, comprising: (a) acquiring first inspection data in a first manufacturing process for manufacturing a film or in a second manufacturing process for performing post-processing using the manufactured film, which is performed after the first manufacturing process; (b) acquiring second inspection data in the second manufacturing process or at an inspection position after a sub-process downstream from the inspection position where the first inspection data was acquired in the second manufacturing process; (c) comparing first feature point information of the film in the first inspection data with second feature point information of the film in the second inspection data; and (d) extracting, based on the comparison result of step (c), feature points that are present in one of the first and second inspection data but not in the other, or that are determined to be defective in one of the inspection data but not determined to be defective in the other inspection data.

[0011] (3) The feature extraction method according to (1) or (2) above, wherein the one inspection data is the first inspection data and the other inspection data is the second inspection data, and step (d) extracts first-type feature points that are present in the first inspection data but not present in the second inspection data, or that are determined to be defective in the first inspection data but not determined to be defective in the second inspection data.

[0012] (4) In the feature point extraction method described in (3) above, step (d) further extracts second-type feature points that are present in the second inspection data but not present in the first inspection data, or that are determined to be defects in the second inspection data but not determined to be defects in the first inspection data.

[0013] (5) The feature point extraction method described in (3) above, wherein the first inspection data and the second inspection data are inspection data obtained by processing an image of the film to extract feature point information, and the feature point information includes size information of the feature points and position information on the film.

[0014] (6) The method for extracting feature points according to (3) above, further comprising, before step (c), step (e) of aligning the film in the first inspection data and the second inspection data, wherein step (e) comprises: step (e1) of not shifting the relative positions of the first inspection data and the second inspection data and / or moving the position information of the feature points in the second inspection data; step (e2) of calculating the distance from each of the feature points in one of the first and second inspection data to the nearest feature point in the other inspection data; and step (e3) of repeating step (e1) and step (e2) so that the distance calculated in step (e2) is minimized.

[0015] (7) The method for extracting feature points according to (6) above, further comprising, after step (e), a step (f) of calculating a distance from each of a plurality of feature points in one of the first and second test data to a nearest feature point in the other test data, excluding distance values ​​equal to or greater than a predetermined threshold, and determining whether the processing of step (e) is appropriate based on the sum or average of the distance values ​​calculated from the distance values ​​after excluding the distance values.

[0016] (8) The method for extracting feature points according to (3) above, further comprising, before step (c), step (g) of aligning the film in the first inspection data and the second inspection data, performing kernel density estimation on a plurality of feature points in the first inspection data and the second inspection data to calculate probability density functions of the feature points, and comparing the calculated probability density functions to align the film.

[0017] (9) The method for extracting feature points according to (3) above, further comprising, before step (c), step (g) of aligning the film in the first inspection data and the second inspection data, performing kernel density estimation on a plurality of feature points in one of the first inspection data and the second inspection data to calculate a probability density function of the feature points, and comparing the calculated probability density function with position information of the feature points in the other inspection data, thereby aligning the film.

[0018] (10) A feature extraction method described in (3) above, wherein the post-processing treatment in the second manufacturing process is a coating treatment that adds a functional layer to the surface of the film manufactured in the first manufacturing process.

[0019] (11) The method for extracting feature points according to (3) above, further comprising, before the step (c), a step (g) of performing preprocessing on the first inspection data and the second inspection data to exclude feature points that do not meet predetermined conditions.

[0020] (12) The feature extraction method according to (1) or (2), wherein the one inspection data is the second inspection data and the other inspection data is the first inspection data, and step (d) extracts second-type feature points that are present in the second inspection data but not present in the first inspection data, or that are determined to be defects in the second inspection data but not determined to be defects in the first inspection data.

[0021] (13) The feature extraction method according to (2) above, wherein the first manufacturing process and the second manufacturing process each include a plurality of sub-processes, a plurality of pieces of inspection data are acquired at a plurality of inspection positions upstream and downstream of at least one of the sub-processes, and any of the plurality of pieces of inspection data is used as first inspection data, and inspection data at an inspection position downstream of the first inspection data is used as second inspection data.

[0022] (14) The feature point extraction method according to (13) above, further comprising the step (h) of accepting a selection of a combination of first inspection data and second inspection data from among the plurality of inspection data.

[0023] (15) A method for setting shipping standards, the method including: setting shipping standards for the first manufacturing process based on the first type feature points extracted by the feature point extraction method of (3) above.

[0024] (16) An information processing system comprising: an acquisition unit that acquires first inspection data from a first manufacturing process for manufacturing a film and second inspection data from a second manufacturing process that is carried out after the first manufacturing process and involves post-processing using the manufactured film; a comparison unit that compares first feature point information of the film in the first inspection data with second feature point information of the film in the second inspection data; and an extraction unit that extracts, based on the comparison result from the comparison unit, feature points that are present in one of the first and second inspection data but not in the other, or feature points that are determined to be defective in one of the inspection data but not in the other.

[0025] (17) An information processing system comprising: an acquisition unit that acquires first inspection data from a first manufacturing process for manufacturing a film or a second manufacturing process that is carried out after the first manufacturing process and involves post-processing using the manufactured film, and second inspection data from the second manufacturing process or an inspection position after a sub-process downstream from the inspection position where the first inspection data was acquired in the second manufacturing process; a comparison unit that compares first feature point information of the film in the first inspection data with second feature point information of the film in the second inspection data; and an extraction unit that extracts, based on the comparison result of the comparison unit, feature points that are present in one of the first and second inspection data but not in the other, or feature points that are determined to be defective in one of the inspection data but not in the other.

[0026] (18) The information processing system described in (16) or (17) above, wherein the extraction unit extracts first-type feature points that are present in the first inspection data but not present in the second inspection data, or that are determined to be defects in the first inspection data but not determined to be defects in the second inspection data.

[0027] The feature extraction method of the present invention includes a step (c) of comparing first feature information of the film in the first inspection data from the first manufacturing process with second feature information of the film in the second inspection data from the second manufacturing process, and a step (d) of extracting, based on the comparison result of step (c), feature points that are present in one of the first and second inspection data but not in the other, or feature points that are determined to be defects in one of the inspection data but not in the other, thereby making it possible to efficiently collect information useful for process improvement and setting shipping standards both during film manufacturing and in manufacturing processes where post-processing is performed using the film.

[0028] 1 is a schematic diagram showing an application example of the information processing system according to the first embodiment. FIG. 2 is a table for explaining extracted first to third type feature points. FIG. 3 is a block diagram showing a schematic configuration of the information processing system. FIG. 4 is an example of a user list stored in a storage unit. FIG. 5 is an example of a lot list stored in a storage unit. FIG. 6 is an example of an inspection data DB stored in a storage unit. FIG. 7 is an example of an inspection data DB stored in a storage unit. FIG. 8 is an example of an inspection data DB stored in a storage unit. FIG. 9 is a flowchart showing a generation process of first inspection data performed in a first manufacturing process. FIG. 10 is a schematic diagram showing a configuration of an inspection device. FIG. 11 is a schematic diagram showing a configuration of an inspection device. FIG. 12 is a flowchart showing a generation process of second inspection data performed in a second manufacturing process. FIG. 13 is a flowchart showing a feature point extraction process performed in an information processing system. FIG. 14 is a schematic diagram for explaining the feature point extraction process. FIG. 15 is a subroutine flowchart showing the alignment process of step S34. FIG. 16 is a flowchart showing a shipping standard setting process for the first manufacturing process. FIG. 17 is a subroutine flowchart showing the alignment process of step S34 in the second embodiment. FIG. 18 is an example of a probability density function indicating the position and intensity of feature points calculated by kernel density estimation. FIG. 19 is a schematic diagram showing an application example of the information processing system according to the third embodiment. 18 is an enlarged schematic diagram of the vicinity of the winding device in the manufacturing process of a product using a film roll, and a schematic diagram showing the inspection position of an inspection device for second inspection data.

[0029] Hereinafter, embodiments of the present invention will 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, the same elements are denoted by the same reference numerals, and duplicate explanations will be omitted. Furthermore, the dimensional proportions in the drawings are exaggerated for the convenience of explanation and may differ from the actual proportions.

[0030] 1 is a schematic diagram showing an application example of an information processing system 50 according to the first embodiment. As shown in FIG. 1, the information processing system 50 is connected to terminal devices 70 and the like in factories A and B via a network for mutual communication. The network is a communication line such as a data communication network. Some networks may use a wired LAN, a wireless LAN, or the like (for example, a LAN conforming to the IEEE 802.11 standard).

[0031] 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.

[0032] Factory A is equipped with a film roll manufacturing apparatus 1000. Factory A is operated or managed by, for example, a film manufacturer. Factory A performs a first manufacturing process for manufacturing a film roll 80. The film surface of the film roll 80 is inspected by an inspection device 90. The inspection device 90 is, for example, a camera. The film is, for example, an optical film, and its width is, for example, in the range of 1000 mm to 3000 mm. The film thickness is set to a range of 15 μm to 80 μm, taking into consideration quality, handling, etc. The length of the film roll 80 wound around the winding shaft is, for example, in the range of 2000 m to 10000 m. The film here includes a web. A web is a sheet-like material, and includes a resin film and a metal film.

[0033] Factory B is equipped with a product manufacturing device 2000. Factory B is operated or managed, for example, by a coating manufacturer (hereinafter also 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 unwinds film (film F8, described below) from the film roll 80 and performs a second manufacturing process, which is a post-processing process such as coating. For example, the post-processing process involves a coating process to apply a functional layer to the surface. In the second manufacturing process, the film surface of the film roll 80 is also inspected by an inspection device 90. The inspection device 90 is, for example, a camera.

[0034] (Outline of Feature Point Extraction Processing) Details of the feature point extraction processing will be described later, but an outline of the feature point extraction processing will be described below with reference to FIG.

[0035] In the first manufacturing process at factory A, during product inspection, the film is optically inspected by inspection device 90, and inspection data (also referred to as failure data or defect data) is generated. Specifically, inspection data (hereinafter referred to as first inspection data) including feature point information (feature points, positions, and intensities) is generated by analyzing image data obtained by photographing the surface of the film. Information processing system 50 acquires the first inspection data from terminal device 70 at factory A (step S1).

[0036] Here, feature points refer to defects on the film, and are generated by analyzing image data. Image analysis may involve extracting, as feature points, pixels whose pixel values ​​deviate by a predetermined amount from the average value of the surrounding pixels (the difference is greater than or equal to a predetermined amount) in image data captured from a film surface using known techniques. Alternatively, feature points may be calculated using the "image processing for generating feature points" technique described below. In many cases, dozens to hundreds of feature points are generated from one or more image data captured from a single film roll 80 (total length 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 film pieces 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.

[0037] The film roll 80 manufactured in Factory A is transported to Factory B. In the second manufacturing process at Factory B, the film roll 80 is optically inspected by an inspection device 90 during product inspection, generating inspection data. Image data obtained by photographing the film surface is analyzed to generate inspection data containing feature points (hereinafter referred to as second inspection data). The information processing system 50 acquires the second inspection data from the terminal device 70 at Factory B (Step S2). It is preferable that the inspection device 90 at Factory A (first manufacturing process) and the inspection device 90 at Factory B (second manufacturing process) are the same, i.e., have the same measurement system and the same measurement conditions, but this is not limited to this. Factories A and B may have different required performance, quality, and product specifications (hereinafter referred to as product specifications, etc.), and an inspection device 90 with an appropriate measurement system and measurement conditions may be used depending on the respective product specifications, etc.

[0038] The information processing system 50 performs a feature point extraction process by comparing the first and second inspection data for the same film roll 80 (step S3). Specifically, the information processing system 50 performs the feature point extraction process by comparing feature points at corresponding positions on the film surface in the first and second inspection data. In this specification, detecting feature points from image data is referred to as "generating feature points." Comparing the first and second inspection data and classifying the feature points into one of the following first to third type feature points is referred to as "extracting feature points."

[0039] 2 is a table illustrating the first to third type feature points extracted by the feature point extraction process. A plurality of feature points generated from the inspection data of one film roll 80 may be classified into each of the first to third type feature points. For example, out of several hundred feature points, some may be extracted as first type feature points, some as second type feature points, and the rest as third type feature points.

[0040] (First type feature points) First type feature points are feature points that are present in the first inspection data but not present in the second inspection data. First type feature points are feature points that disappear in the second manufacturing process (e.g., the coating 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.

[0041] (Second-type feature points) Second-type feature points are feature points that are not present in the first inspection data but are present in the second inspection data. 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.

[0042] (Third-class feature points) Third-class feature points are feature points that exist in both the first inspection data and the second inspection data. These third-class feature points are feature points that originate from the first manufacturing process and require management. Because these third-class feature points originate from the first manufacturing process, they can be used to improve the first manufacturing process.

[0043] The information processing system 50 feeds back the feature point extraction results to the users at Factory A and Factory B (Step S4). For example, the extraction results are sent to the terminal device 70 in response to access from the terminal device 70 of the user of the manufacturer of the target film roll 80 and the terminal device 70 of the user to whom the film roll 80 was delivered. This is the outline of the feature point extraction process. More detailed content of the process will be described later.

[0044] (Information Processing System 50) The information processing system 50 will be described below with reference to Figs. 3 to 5. Fig. 3 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. 3, the information processing system 50 includes a control unit 51, a storage unit 52, and a communication unit 53.

[0045] (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 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.

[0046] The control unit 51 functions as an acquisition unit 511 in cooperation with the communication unit 53. The control unit 51 also functions as an alignment unit 512, a comparison extraction unit 513, and an output unit 514. The acquisition unit 511 acquires first and second inspection data obtained by inspections in the first and second manufacturing processes. The alignment unit 512 aligns the coordinates of the first and second inspection data by shifting the relative positions of the feature points in the first and second inspection data or by moving (shifting) the position information of the second inspection data. The comparison extraction unit 513 corresponds to a comparison unit and an extraction unit. The comparison extraction unit 513 compares the feature points in the first and second inspection data after the alignment process and extracts the first to third type feature points shown in FIG. 2 . The output unit 514 transmits the feature point extraction results to the terminal device 70 or displays them on a display unit (not shown) in response to a request from the terminal device 70.

[0047] (Storage Unit 52) ​​The storage 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 storage unit 52 stores a user list, a lot list, an inspection data DB, etc. Of these, the user list and lot list are managed and registered by an administrator who accesses the terminal device 70. For example, this administrator is a person in charge of the relevant department of the manufacturer that operates Factory A.

[0048] (User List) Figure 4A is an example of a user list stored in the storage unit. 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.

[0049] 4B shows an example of a lot list stored in the storage unit. The lot list records the lot ID assigned to each film roll, the product name (also called the type), the delivery destination user ID (orderer), and multiple manufacturing conditions, size (width, length, thickness), manufacturing date, etc.

[0050] (Inspection Data DB) The inspection data DB stores data related to the inspection of various types of film roll 80, such as the first and second inspection data and feature point extraction results as shown in Figures 5A to 5C. 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.

[0051] 5A shows an example of an inspection list registered in the inspection data DB. The inspection list stores an inspection ID, a lot ID, an inspection device ID, inspection data, inspection date and time, etc.

[0052] FIG. 5B shows an example of the contents of inspection data (inspection ID: i0101) in the inspection list. The inspection data includes a feature point ID, which is automatically assigned a consecutive number to each feature point, and for each feature point ID, its XY coordinate position and intensity. The intensity is the rank of the feature point, which will be described later. The intensity information may also include information on the size (diameter, area) of the feature point. The XY coordinate position is based on the origin of the film surface (e.g., the left end 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 FIG. 4B). Y is the coordinate in the length direction of the film and can range, for example, from 0 to 10000 m depending on the film size.

[0053] 5C shows 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 and the extraction results for each feature point. The extraction results (Types 1 to 3) are the classifications shown in FIG. 2 above. The 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.

[0054] Note that multiple first and second inspection data sets 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 is inspected (photographed), and multiple second inspection data sets are generated by inspections in several downstream processes. In this case, the information processing system 50 may generate multiple feature point extraction result data sets for one piece of first inspection data in a one-to-many relationship with multiple pieces of second inspection data sets. Furthermore, the user may be able to select which second inspection data sets to associate with each piece of first inspection data.

[0055] (Communication Unit 59) The communication unit 59 is also an interface for connecting to an external device such as a PC via a network.

[0056] (Generation Process of First and Second Inspection Data) The generation process of the first and second inspection data performed in the first and second manufacturing processes will be described below with reference to Figures 6 to 8. Figure 6 is a flowchart showing the generation process of the first inspection data performed in the first manufacturing process.

[0057] (Process for Generating First Inspection Data) (Step S11) In the first manufacturing process, the film roll 80 is manufactured by the film roll manufacturing apparatus 1000. At this time, the film roll is manufactured according to shipping standard z.

[0058] (Step S12) The inspection device 90 photographs the film and stores the image data. The configuration of the inspection device 90 will be described below with reference to FIG.

[0059] (Inspection device 90) The following types of devices are available for detecting irregularities on the surface of a transparent body such as film F8 as an object to be inspected, as well as bubbles, cracks, distortions in the internal structure, and the like inside the transparent body: (1) A transmission type inspection device that detects defects in the object to be inspected by irradiating the object with light and receiving the light that has passed through the object to be inspected. (2) A reflection type inspection device that detects defects in the object to be inspected by receiving the light reflected from the object to be inspected.

[0060] Furthermore, for both the transmissive and reflective types, there are bright-field inspection devices that receive unscattered 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. In a bright-field inspection device, if there is no defect, there is no scattering of light, so 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 dot or streak against a bright background. In contrast, in a dark-field inspection device, if there is no defect, there is no scattering of light, so 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 dot or streak against a dark background. The inspection device 90 in this embodiment may be of any type. It is preferable, but not limited to, that the first inspection data and the second inspection data be acquired by the same type of inspection device.

[0061] (Reflection-Type Inspection Device) FIG. 7A is a schematic diagram showing the configuration of a reflection-type inspection device 90 as viewed from the width direction (Y direction). FIG. 7B is a schematic diagram showing the configuration of the inspection device 90 as viewed from the transport direction (X direction). The inspection device 90 includes a light source 91, a camera 92 as an optical sensor, an 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 number of cameras, the angle of view, and the distance to the film surface of the camera 92 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. 7B shows an example of two cameras 92 arranged in the width direction (Y direction). The analysis unit 93 may combine multiple images obtained by continuous shooting with a single camera 92 to generate a single image data piece containing the entire film surface of the film roll 80, or 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 analysis unit 93 can determine the longitudinal position of the film F8 based on the shooting times associated with the image data by referencing the stored transport speed (winding speed or unwinding speed). In the following description, it is assumed that multiple image data pieces obtained by continuous shooting are stored in association with the shooting times for one film roll 80. The analysis unit 93 generates defect information by analyzing the image data. The inspection device 90 inspects the long film F8 for defects that occur during the manufacturing process, such as during winding.

[0062] The light source 91 irradiates the inspection area of ​​the film F8 with light. The light source 91 irradiates the 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 substantially uniform across the width of the film F8 (e.g., the difference between the maximum and minimum values ​​is equal to or less than a predetermined value).

[0063] The camera 92 is an optical sensor that optically reads the inspection area of ​​the film F8. The camera 92 includes an imaging element such as a CCD (Charge Coupled Device) or a CMOS (Complementary Metal Oxide Semiconductor), a lens, and the like. The camera 92 is an area sensor that generates two-dimensional image data from the output signals of the imaging elements. The camera 92 detects diffused light that is irradiated by the light source 91 and reflected from the inspection area of ​​the film F8. Here, either a color camera or a black-and-white camera (monochrome camera) may be used as the camera 92.

[0064] The camera 92 has a photographing range that spans the entire width of the film F8, and simultaneously reads the entire width of the film F8 in one photograph. The camera 92 may be one that detects light in the visible light range or in the infrared range.

[0065] Furthermore, it is desirable that the contrast between the signal values ​​corresponding to the irradiated areas on the film F8 that are irradiated with light from the light source 91 and the signal values ​​corresponding to the non-irradiated areas that are not irradiated with light from the light source 91 be equal to or greater than a predetermined value in the output signal from the camera 92. In other words, it is desirable that only the areas on the film F8 that are irradiated with light from the light source 91 (irradiated areas) appear bright.

[0066] The contrast is expressed as the difference or ratio between two values ​​to be processed (here, the signal value corresponding to the irradiated portion and the signal value corresponding to the non-irradiated portion), and the more different the two values ​​are, the greater the contrast. In order to increase the contrast between the irradiated portion and the non-irradiated portion, it is desirable to use a light source 91 that is powerful and has high directivity.

[0067] 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. Also, "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.

[0068] The analysis unit 93 is composed of a CPU, RAM, etc., and reads out various processing programs stored in the storage unit 94, loads them into the RAM, and performs various processes in cooperation with the programs.

[0069] The storage unit 94 is configured with an HDD, SSD (Solid State Drive), etc., and stores various processing programs, data necessary for executing the 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 feeding conditions (e.g., 30 m / min) of the film F8 in the product manufacturing apparatus 2000. These winding speeds and feeding conditions may be included in the inspection list of the inspection DB (see FIG. 5A ).

[0070] The analysis unit 93 detects defects (position and intensity) in the film F8 by performing data processing on the output signal of the camera 92 (optical sensor). The data processing includes image processing of image data obtained from the output signal of the camera 92, a defect determination process for determining defects based on the image-processed data, and a quantitative evaluation process for quantitatively evaluating the defects based on the image-processed data.

[0071] (Relative Positions of Camera 92 and Light Source 91) The camera 92 may be positioned so as to receive specularly reflected light emitted from the light source 91 (in the case of a bright-field inspection method that receives non-scattered light).

[0072] The camera 92 may be positioned to avoid receiving specularly reflected light from the light source 91 (in the case of a dark-field inspection method that receives scattered light). In other words, it is preferable to position the camera 92 at a position where it receives diffused light reflected from the object under inspection.

[0073] 7C shows an example of a transmission-type inspection device 90. In this manner, a transmission-type inspection device 90 in which the light source 92 is disposed opposite the camera 92 with the film F8 sandwiched therebetween may be employed.

[0074] (Step S13) The analysis unit 93 performs image processing described below on the image data to generate a plurality of feature points.

[0075] (Image Processing for Generating Feature Points) The analysis unit 93 acquires two-dimensional image data generated by the camera 92 and stored in the storage unit 94 .

[0076] The analysis unit 93 performs data processing on the image data (inspection data) acquired from the camera 92 .

[0077] The analysis unit 93 divides the image data into a plurality of regions. For example, the 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).

[0078] Next, the analysis unit 93 acquires image data of one area a1 and performs mathematical processing on the image data of area a1 (step S103). Appropriate mathematical processing is prepared depending on the type of defect to be detected (gauge band, vertical wrinkle, diagonal wrinkle, etc.).

[0079] The mathematical processing includes preprocessing, enhancement processing, signal processing, image feature extraction, and the like.

[0080] Preprocessing includes the following: Image trimming, 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 / shaky images, mask processing, Hough transform, projection transformation, etc.

[0081] Examples of enhancement processing include a Sobel filter, a Scharr filter, a Laplacian filter, a Gabor filter, and a Canny method.

[0082] Signal processing includes the following: Basic statistics (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.

[0083] Examples of image feature extraction include template matching and SIFT features.

[0084] Next, the analysis unit 93 performs threshold processing on the values ​​(feature amounts) calculated by mathematical processing of the image data of the area a1. The threshold processing is a process for determining whether or not the defect is a target defect based on a predetermined threshold, and for determining the rank (intensity) of the defect.

[0085] In the threshold processing, determining the presence and type of defects corresponds to the “defect determination processing.” In the threshold processing in step S104, classifying defects into a plurality of ranks according to the thresholds corresponds to the “quantitative evaluation processing.”

[0086] For example, defects are classified into multiple ranks for a parameter (feature) that takes a value between 1 and 100. For example, the ranks are classified according to the size (diameter or area) of the defect. Alternatively, the ranks classified by size may be further subdivided according to the parameter value.

[0087] The analysis unit 93 performs the same process on areas other than the area a1.

[0088] After processing each of the regions a1 to an, the analysis unit 93 integrates the results for each of the regions a1 to an, and data processing ends. Specifically, the analysis unit 93 generates data that associates the rank of the detected defect with the occurrence position (x and y coordinates) for each region (each position in the width direction of the film F8).

[0089] After the data processing, the analysis unit 93 stores the results of the data processing in the storage unit 94. The analysis unit 93 obtains processing results by performing this type of data processing on each of the multiple image data obtained by inspecting one film roll 80. By aggregating these processing results, the inspection data shown in FIG. 5B is generated.

[0090] (Step S14) Terminal device 70 in the first manufacturing process sends inspection data including the plurality of feature point information obtained in the processes up to step S13 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 first inspection data.

[0091] (Generation Process of Second Inspection Data) FIG. 8 is a flowchart showing the generation process of second inspection data performed in the second manufacturing process.

[0092] (Step S21) In the second manufacturing process, the product manufacturing apparatus 2000 performs post-processing using the film roll 80 to manufacture a product using the film F8.

[0093] (Step S22) The inspection device 90 photographs the surface of the film F8 before, during, or after post-processing, and stores the image data. This inspection device 90 is composed of, for example, a light source 91, a camera 92, an analysis unit 93, a storage unit 94, and the like, as shown in FIG.

[0094] (Step S23) The analysis unit 93 stores the generated inspection data including the feature point information of the plurality of feature points in the storage unit 94 by the same process as in step S13.

[0095] (Step S24) Terminal device 70 in the second manufacturing process sends the inspection data including the plurality of feature point information obtained in the processes up to step S23 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.

[0096] (Feature Point Extraction Processing) The feature point extraction processing executed by the information processing system 50 will be described below with reference to Figs. 9 to 11. Fig. 9 is a flowchart showing the feature point extraction processing. Fig. 10 is a schematic diagram for explaining the feature point extraction processing. Fig. 11 is a subroutine flowchart showing the alignment processing of step S34.

[0097] (Step S31) The information processing system 50 starts the processing from step S31 onwards in response to a start instruction from the user via the terminal device 70, or when the second test data is registered in the test data DB of the memory unit 52 and a pair of first and second test data is obtained.

[0098] 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.

[0099] (Steps S32 and S33) The alignment unit 512 performs preprocessing on the first test data under the first condition, and performs preprocessing on the second test data under the second condition. In the following description, the XY coordinate system of each feature point in the second test data is aligned with the XY coordinate system of the first test data. However, this is not limiting, and conversely, the XY coordinate system of the first test data may be aligned with the XY coordinate system of the second test data.

[0100] 10 , as preprocessing for the second condition, the alignment unit 512 performs preprocessing of inverting the Y coordinate (up and down) of the second inspection data to account for the difference between winding (first manufacturing process) and unwinding (second manufacturing process). Furthermore, in the second manufacturing process, the alignment unit 512 performs preprocessing of inverting the X coordinate (left and right) of the second inspection data (or the first inspection data) depending on information indicating whether the image capture area of ​​the camera 92 is set to the front or back side of the film F8. Furthermore, in the second manufacturing process, if the film F8 expands or contracts due to the settings of the heating temperature and tension in post-processing, and if the expansion / contraction rate can be estimated in advance, the second inspection data may be coordinate-converted using that expansion / contraction rate.

[0101] Furthermore, the alignment unit 512 performs at least one of the following noise removal processes on the first and second inspection data, which are included in the first and second conditions: (1) Removal of low-rank feature points. (2) Removal of extremely small feature points. (3) Removal of continuous dots. (4) Removal of concentrated dots in the width direction. This occurs particularly at the leading and trailing edges of film F8.

[0102] (Step S34) The alignment unit 512 executes a process of aligning the coordinate system. Fig. 11 is a subroutine flowchart showing the alignment process of step S34.

[0103] (Coarse Adjustment: Steps S401 to S403) The alignment unit 512 performs coarse adjustment in steps S401 to S403. The alignment unit 512 shifts the coordinate position of the second test data by a predetermined amount in the X and Y directions, calculates the distances L1 to Lm between corresponding feature points at that time, and selects the shift amount (x1, y1) with the smallest sum. Here, an average value may be used instead of the sum. The closest feature points are extracted as corresponding feature points. Furthermore, if no feature points are found in one test data that correspond to the other test data (i.e., first and second type feature points), the distance may become a value at infinity. The alignment unit 512 may exclude distance values ​​equal to or greater than a predetermined threshold and use the sum or average of the distance values ​​after excluding them.

[0104] Specifically, the alignment unit 512 sequentially shifts the coordinate position of the second inspection data from (-shift_x, -shift_y) to (+shift_x, +shift_y) around the central shift amount (0, 0) in increments of a fixed coarse adjustment shift amount a. Then, for each of feature points 1 to m in the first inspection data at that time, the alignment unit 512 calculates the distances L1 to Lm to the adjacent feature points in the second inspection data. Then, from among (-shift_x, -shift_y) to (+shift_x, +shift_y), the shift amount (x1, y1) with the smallest total distance is selected.

[0105] For example, when the coarse adjustment shift amount a = 1.0 mm, (-shift_x, -shift_y) = (-10 mm, -10 mm) and (-shift_x, +shift_y) = (+10 mm, +10 mm). As another example, since there is a large difference in the X and Y directions, which is an order of magnitude (approximately three digits), the X and Y shift amounts may be adjusted to match the order. For example, the Y direction may be in the order of mm (millimeters) to m (meters), with (-shift_x, -shift_y) = (-10 mm, -10 m) and (-shift_x, +shift_y) = (+10 mm, +10 m) (the same applies to the fine adjustments below).

[0106] (Fine Adjustment: Steps S404 to S406) In steps S404 to S406, the alignment unit 512 performs fine adjustment and selects a shift amount (x2, y2). The processing here is similar to that of steps S401 to S403, but differs from the coarse adjustment in steps S401 to S403 in the following respects. The fine adjustment shift amount b is smaller than the coarse adjustment shift amount a, and the central shift amount is not (0, 0), but is set to the shift amount (x1, y1) selected in step S403. For example, the fine adjustment shift amount b is sufficiently smaller than the coarse adjustment shift amount a, for example, 0.1 mm, which is one order of magnitude smaller.

[0107] (Step S407) The alignment unit 512 performs coordinate conversion processing on the second inspection data using the shift amount (x2, y2) selected in step S406.

[0108] (Step S408) After the coordinate transformation, the alignment unit 512 calculates the distances L1 to Lm and checks whether the sum is less than a predetermined threshold. If the sum is equal to or greater than the predetermined threshold, the alignment unit 512 may determine that the alignment performed in step S407 is inappropriate.

[0109] (Step S409) If the alignment is inappropriate (YES), the control unit 51 ends the process (END). If the alignment is inappropriate, an error message may be displayed or a message indicating that calculation is not possible may be recorded in the test data DB. On the other hand, if the alignment is appropriate (NO), the control unit 51 ends the process of FIG. 11, returns to the process of FIG. 9 (RETURN), and executes the processes from step S35 onwards.

[0110] (Steps S35 and S36) The comparison extraction unit 513 compares the feature point information of the first test data and the second test data. The second test data here is the data after the alignment process in step S34. Through the comparison, the comparison extraction unit 513 extracts feature points that are present in only one of the first and second test data and not in the other. The comparison extraction unit 513 also extracts feature points that are present in both data. Through this process, the comparison extraction unit 513 generates extracted data in which the feature points are classified into first to third type feature points (see FIGS. 2 and 5C).

[0111] (Step S37) The output unit 514 registers the extraction result (extraction data) generated in step S36 in the test data DB, and transmits the extraction result to the terminal device 70. This completes the feature point extraction process shown in FIG. 9 (END).

[0112] In this embodiment, the first feature information of the film in the first inspection data is compared with the second feature information of the film in the second inspection data. Based on the comparison results, feature points that are present in one of the first and second inspection data but not in the other, or feature points that are determined to be defective in one inspection data but not in the other, are extracted. This allows for efficient collection of information useful for process improvement and setting shipping standards both during the production of film rolls and in the manufacturing process where post-processing is performed using the film.

[0113] (Modification) FIG. 12 is a flowchart showing the process of setting shipping standards in the first manufacturing process.

[0114] (Step S51) A user such as a manager managing the first manufacturing process refers to the extraction result using the terminal device 70 of the first manufacturing process. This process corresponds to step S37 in FIG.

[0115] (Step S52) The user can review the shipping standard z for the first manufacturing process by referring to the first type feature points, i.e., feature points that are present in the first inspection data but not in the second inspection data. For example, by reviewing the shipping standard z for the first type feature points in the first manufacturing process, an improvement in yield can be expected.

[0116] Second Embodiment Next, an information processing system 50 according to a second embodiment will be described with reference to FIGS. 13 and 14. In the information processing system 50 according to the second embodiment, kernel density estimation is used for the alignment process of the coordinate systems. In this respect, it differs from the alignment process of the first embodiment (FIGS. 10 and 11). However, the other configurations can be applied in common to the configuration examples of the first embodiment shown in FIGS. 1 to 9. FIG. 13 is a subroutine flowchart showing the alignment process of step S34 in the second embodiment.

[0117] (Step S451) The alignment unit 512 obtains a probability density function by performing kernel density estimation on the first inspection data. Kernel density estimation is performed two-dimensionally, using a Gaussian kernel as the kernel function. A predetermined value is used as the bandwidth. For example, a table correlating each product name (type) with a bandwidth may be stored in the storage unit 52, and a bandwidth value for each product name may be used. Alternatively, different bandwidth values ​​may be used depending on the number of feature points. The alignment unit 512 calculates density for each feature point by taking into account the surrounding data. The alignment unit 512 then sums the densities calculated for each data set to obtain a probability density function. FIG. 14 shows an example of a probability density function indicating the position and intensity (density) of feature points calculated by kernel density estimation. In FIG. 14, the vertical and horizontal axes represent X and Y coordinates, and higher density indicates higher density.

[0118] (Step S452) The alignment unit 512 performs kernel density estimation on the second inspection data by the same process as in step S451 to obtain a probability density function.

[0119] (Steps S453 to S455) The alignment unit 512 compares the two obtained probability density functions and associates them based on the density distributions (position and intensity information). Then, the alignment unit 512 calculates a transformation matrix based on the association result and performs coordinate transformation of the X and Y coordinates on the second inspection data.

[0120] (Steps S456 to S457) The processing here is the same as steps S406 to S407 in FIG. 11. Using the inspection data after coordinate transformation, the alignment unit 512 calculates distances L1 to Lm from feature points 1 to m in one inspection data to the corresponding feature points in the other inspection data, and checks whether the sum is less than a predetermined threshold. If the sum is equal to or greater than the predetermined threshold, the alignment unit 512 determines that the alignment in step S455 was inappropriate and ends the processing (END). On the other hand, if the alignment is appropriate (NO), the control unit 51 ends the processing in FIG. 13, returns to the processing in FIG. 9 (RETURN), and executes the processing from step S35 onward.

[0121] In this way, in the second embodiment, the film is aligned by calculating the probability density function of the feature points using kernel density estimation and comparing the calculated probability density functions, which also achieves the same effect as in the first embodiment.

[0122] 13, kernel density estimation is performed on both the first and second inspection data to calculate the probability density function of the feature points, but this is not limiting. For example, kernel density estimation may be performed on only one of the inspection data (e.g., the second inspection data), and the resulting probability density function may be compared with the feature point information of the other inspection data to align the film.

[0123] Third Embodiment FIG. 15 is a schematic diagram illustrating an application example of an information processing system 50 according to a third embodiment. FIG. 16 is a table illustrating the relationship between the multiple inspection devices 90a1-90b3 in FIG. 15 and the inspection positions. FIG. 15 corresponds to FIG. 1, but some components, such as the terminal device 70, are omitted. The first and second embodiments described above illustrate an example in which first inspection data is acquired in the first manufacturing process and second inspection data is acquired in the second manufacturing process. Hereinafter, inspection data is acquired at multiple inspection positions in each of the first and second manufacturing processes, and a combination of the first and second inspection data is selected from the acquired multiple inspection data. The inspection positions are positions before or after multiple sub-processes that make up the manufacturing process. For example, suppose n and m pieces of inspection data are acquired in the first and second manufacturing processes, respectively (total p = n + m), and two arbitrary pieces of inspection data are selected from these p pieces of inspection data. In this case, of the selected inspection data, the inspection data at the upstream inspection position in the process flow direction is referred to as first inspection data, and the inspection data at the downstream inspection position is referred to as second inspection data.

[0124] There is one inspection device 90 that inspects for failures and defects that occur in one sub-process. The inspection device 90 may be composed of multiple inspection units. For example, it may be composed of an inspection unit (camera) for detecting scratches on the surface of the film F8 and another inspection unit (camera) for detecting foreign matter inside the film F8. In this case, one of the analysis results obtained by analyzing the photographed data obtained from the two inspection units may be used, or the two analysis results may be combined (by arithmetic processing such as addition) and used as the inspection data.

[0125] In the example shown in Figures 15 and 16, the inspection device 90a1 is located at the final stage of the first manufacturing process 1000 (immediately upstream of the winding process). The first manufacturing process is followed by a storage or transportation process for the film roll 80. This is followed by a plurality of first to third sub-processes and a winding process in the second manufacturing process 2000. In the example shown in Figure 15, the first to third sub-processes are the first to third coating processes, respectively. The first to third coating processes coat the raw film F8 with first and second layers, respectively (see the enlarged cross-sectional view of the bubble in Figure 15). Each sub-process may include not only a coating process for applying a coating liquid, but also other auxiliary processes such as a drying process. Furthermore, each sub-process is not limited to a coating process, and may also include a bonding process (lamination) for adhering and attaching another film, as in the example described below.

[0126] 17A is a diagram showing findings obtained by an extraction process when any two combinations of the test data (Data A to Data B3) shown in FIG. 16 are selected and used as the first and second test data. This extraction process is executed by the information processing system 50, and any of the extraction processes described in the first and second embodiments may be applied. This selection may be made by the user via the terminal device 70, or the information processing system 50 may perform the extraction process for all combinations and output the results.

[0127] FIG. 17B is a table for explaining the first to third type feature points extracted by the feature point extraction process in the third embodiment.

[0128] The first type of feature points are feature points that have disappeared by the time the second inspection data is acquired (hereinafter referred to as the second inspection position). These feature points may be subject to relaxation of standards for a manufacturing process or sub-manufacturing process upstream of the inspection position where the first inspection data is acquired (hereinafter referred to as the first inspection position). The second type of feature points are feature points originating from an intermediate process (manufacturing process or sub-process) between the first inspection position and the second inspection position. These second type of feature points can be used to improve the intermediate process. The third type of feature points are feature points originating from an upstream process (manufacturing process or sub-process) upstream of the first inspection position and require management. These third type of feature points can be used to improve the upstream process. The information processing system 50 can provide feedback to users at factories A and B on the results of feature point extraction obtained from such multiple combinations.

[0129] As described above, in this embodiment, first inspection data is acquired in a first manufacturing process for manufacturing a film or in a second manufacturing process for post-processing using the manufactured film, which is performed after the first manufacturing process. Second inspection data is acquired in a second manufacturing process or at an inspection position after a sub-process downstream from the inspection position where the first inspection data was acquired in the second manufacturing process. That is, two sets of inspection data are selected from the multiple sets of inspection data acquired in the first and second manufacturing processes, and the inspection data from the upstream process is used as the first inspection data and the inspection data from the downstream process is used as the second inspection data. First feature point information of the film in the first inspection data is then compared with second feature point information of the film in the second inspection data. Based on the comparison results, feature points that are present in one set of inspection data but not in the other, or that are determined to be defective in one set of inspection data but not in the other, are extracted. This allows for efficient collection of information useful for process improvement and setting shipping standards both when manufacturing film rolls and during the manufacturing process (including sub-processes) where post-processing is performed using the film.

[0130] EXAMPLES Hereinafter, with reference to FIGS. 18 to 20, examples of a process for manufacturing a film roll (first manufacturing process) and a process for manufacturing a product using the manufactured film roll (second manufacturing process) will be described.

[0131] 18 produces an optical film by a solution casting method. The produced film roll 80 of the optical film is inspected by an inspection device 90 during product inspection.

[0132] In the solution casting method, a raw material resin is dissolved in a solvent, and various additives such as plasticizers, UV absorbers, anti-degradants, slip agents, and release promoters are added as needed to prepare a dope, which is then extruded from a die onto an endless metal support (e.g., a belt or drum) that moves endlessly. After casting, the solvent is removed to a certain extent on the endless support, and the film is peeled off from the support, passed through a drying section by various conveying means to remove the solvent, and wound up on a take-up shaft.

[0133] 18 , a film roll manufacturing apparatus 1000 includes a casting section 01, a first drying section 02, a stretching section 03, a second drying section 04, a knurling section 05, and a winding / collecting section 06 (also referred to as a winding device). In the film roll manufacturing apparatus 1000, an inspection device 90 is disposed in the winding / collecting section 06. The inspection device 90 optically inspects the film surface side of the film roll 80 and generates first inspection data. The configuration of the inspection device 90 is as described above ( FIG. 7 , etc.).

[0134] The casting unit 01 includes a mirror-finished metal casting belt (hereinafter referred to as the belt) 01a, which is an endless support that runs endlessly (in the direction of the arrow in the figure), and a die 01b that casts a dope, which is a resin dissolved in a solvent, onto the belt 01a. In order to stabilize the dope film flowing out from the die 01b, a decompression chamber (not shown) may be provided upstream of the die 01b in the belt transport direction, and a pressurization chamber (not shown) may be provided downstream of the die 01b.

[0135] The casting section 01 has a peeling roll 01d. The peeling roll 01d peels off the casting film 01c formed by casting on the belt 01a. The casting film 01c peeled off by the peeling roll 01d constitutes an unstretched film F8a.

[0136] The first drying section 02 (first drying process) has a drying box 02a having a dry air intake 02b and an exhaust 02c, and a pair of conveying rolls 02d, each consisting of an upper and lower set for conveying the unstretched film F8a, which are made up of multiple sets.

[0137] The first drying section 02 is capable of adjusting the amount of solvent contained in the unstretched film F8a before it enters the stretching section 03 (stretching step), and can be installed as needed.

[0138] The stretching section 03 includes an MD (Machine Direction) stretching section 03a and a TD (Transverse Direction) stretching section 03b. The stretching section 03 stretches the unstretched film F8a conveyed from the first drying section 02.

[0139] The second drying section 04 (second drying step) has the same basic configuration as the first drying section 02, so a description thereof will be omitted.

[0140] The knurling forming section 05 forms knurls on both ends of the stretched film F8 conveyed from the second drying section 04 before the stretched film F8 is wound around a winding shaft in the winding and collecting section 06 (winding and collecting step). Regarding the position at which the knurls are formed, it is preferable to form knurls on both ends of the stretched film F8 gripped by the TD stretching section 03b disposed upstream of the knurling forming section 05 after cutting off both ends of the stretched film F8.

[0141] The winding and recovery section 06 includes a winder 06a that winds up the stretched film F8, both ends of which have been knurled by the knurling forming section 05, an entrained air amount control device 06b, a contact or non-contact linear encoder 06c that detects the running speed of the stretched film F8, a winding shaft rotation speed measuring device 06d, a tension control device 06e, and a thickness measuring device 06f.

[0142] As shown in this figure, in the casting section 01, a raw resin is dissolved in a solvent, and various additives such as plasticizers, UV absorbers, anti-degradants, slip agents, and release promoters are added as needed to prepare a dope. The dope is extruded from a die 01b onto an endless belt 01a that moves endlessly. The cast film is then peeled off from the belt after the solvent has been removed to a certain extent on the endless support. The film is then passed through a drying section and a stretching section 03 by various conveying means, whereby knurling is formed on both ends. After that, the film is wound around a take-up shaft in a winding and collecting section 06 to produce an optical film.

[0143] The width of the optical film produced as shown in FIGS. 18 and 19 is preferably 1000 mm to 2500 mm, taking into consideration productivity, quality, and the like.

[0144] The thickness is preferably 15 μm to 50 μm in consideration of quality, handling, etc.

[0145] The length of the optical film F8 in the film roll 8 wound around the winding shaft 82 (see FIG. 19 ; the winding shaft is also called a core) is preferably 2000 m to 8000 m, taking into consideration productivity, winding quality, etc. The winding length indicates a value calculated from the speed and time.

[0146] FIG. 19 is an enlarged schematic view showing the knurling forming section 05 and the winding and collecting section 06.

[0147] The knurling device 05a is configured with a pair of a knurling roll 501a having an uneven surface with a pressing means 501c and a receiving roll 501b. In the knurling device 05a, the stretched film F8 is sandwiched between the knurling roll 501a and the receiving roll 501b, thereby forming knurls on both ends of the stretched film F8. The knurling roll 501a can be moved in the vertical direction (in the direction of the arrow in the figure) by the pressing means 501c. The amount of movement (pressing amount) of the pressing means 501c is controlled by the control device 07.

[0148] The control device 07 has a memory, a CPU, and an input / output I / F. The control device 07 performs arithmetic processing between information input to the CPU and information previously input to the memory, determines the movement amount (pressure amount) of the pressing means 501c, and determines the movement amount (pressure amount) of the knurling forming roll 501a. As the movement amount (pressure amount) of the knurling forming roll 501a increases, the height of the knurling formed increases, and as the movement amount (pressure amount) of the knurling forming roll 501a decreases, the height of the knurling formed decreases.

[0149] In addition, if a TD stretching section (not shown) is located upstream of the knurling forming section 05 in the conveying direction of the stretched film F8, it is preferable to form knurling on both ends of the stretched film F8 held in the TD stretching section (not shown) after cutting off both ends of the stretched film F8.

[0150] In the drawing, the knurling forming device 05a is shown as a system using a pressure roll and a receiving roll, but other than this system, for example, an inkjet system, a laser system, etc. can be used.

[0151] In the present invention, the knurling forming device can be of any type, for example, in the case of an inkjet system, the amount of knurling forming material discharged from an inkjet head is controlled, and in the case of a laser system, the laser output is controlled.

[0152] The entrained air amount control device 06b has a touch roll 602a that contacts and presses the stretched film F8 being taken up around the take-up shaft 82, and a pressure amount control device 602b that controls the amount of pressure of the touch roll 602a. The amount of entrained air can be adjusted by adjusting the amount of pressure. The pressure amount control devices 602b are disposed on both ends of the touch roll 602a.

[0153] The relationship between the touch roll and tension control (transport tension) is described in a document (J. K. Good, Modeling Nip Induced Tension in Wound Rolls, Proceedings of Forth International Conference on Web Handling, 1997).

[0154] Based on the idea of ​​TW (winding tension) = Th (transport tension) + μN (μ: friction coefficient, N: touch pressure), it is possible to set the optimum radial and circumferential stresses during winding that will prevent breakdowns.

[0155] The material can be metal, or a metal roll wrapped with resin, rubber, etc. Alternatively, a crown roll with a diameter that varies from the center to the sides can be used. Aluminum, iron, or CFRP (carbon fiber reinforced plastics) can be used as the core material.

[0156] The tension control device 06e has a tension controller 605a and a moving means 605b for the tension controller 605a. The tension control device 06e is capable of moving the position of the tension controller 605a (in the direction of the arrow in the figure) in accordance with changes in the stretched film F8 being wound around the winding shaft 82 in the recovery unit 6. Generally, when the initial tension setting value t1 is set, the tension is low at the beginning of winding (setting value t1) and is set so that the tension increases as the winding diameter increases (setting value t1 + α). The tension setting value t1 is changed depending on the winding conditions set by the winding condition setting unit 315.

[0157] Although the drawing explains the stretched film F8, it is of course applicable to unstretched film when no stretching device is provided.

[0158] (Second Manufacturing Process for Product Using Film Roll) Next, with reference to Figure 20, a manufacturing process for a product (hereinafter simply referred to as product) equipped with film roll 80 for acquiring second inspection data in this embodiment will be described. In the manufacturing process for the product, when film F8 is unwound from film roll 80 and the product is manufactured, an inspection device 90 optically inspects the film surface side of film roll 80 and generates inspection data. The inspection device 90 used in this second manufacturing process has substantially the same inspection performance as the first inspection device 90 used when manufacturing film roll 80 in Figure 18.

[0159] FIG. 20 is a schematic diagram showing the manufacturing process of a laminated polarizing film 1 including a film roll 80 and the inspection position of an inspection device 90 for the second inspection data.

[0160] The laminated polarizing film manufacturing apparatus 2000 shown in FIG. 20 performs a series of steps on a single manufacturing line, from manufacturing a polarizer to bonding a protective film to obtain a laminated polarizing film.

[0161] As shown in FIG. 20 , a product manufacturing apparatus 2000 for manufacturing a laminated polarizing film 1 including film F8 includes, in order from upstream, a wet-type processing apparatus 204, a drying apparatus 205, and a laminating apparatus 206. The product manufacturing apparatus 2000 also includes a payout unit 202. The film roll 80 manufactured by the film roll manufacturing apparatus 1000 of FIGS. 18 and 19 is loaded into the third roll unit 63 of the payout unit 202, and film F8 paid out from the film roll 80 is used as the second protective film 13. In the product manufacturing apparatus 2000, an inspection device 90 is disposed in the third roll unit 63 of the payout unit 202. The inspection device 90 optically inspects the film surface side of the film roll 80 loaded into the third roll unit 63 and generates first inspection data. In FIG. 18 , the arrow indicates the transport direction of the film, etc. (The same applies to FIGS. 19 and 20 ).

[0162] The wet treatment device 204 includes a first roll unit 41 around which a long strip of untreated hydrophilic polymer film 1a is wound, a transport unit 42 for transporting the hydrophilic polymer film 1a, and a treatment unit that treats the untreated hydrophilic polymer film 1a with a dichroic substance to convert the hydrophilic polymer film 1a into a polarizer 1b.

[0163] The drying device 205 has a transport section 501 that transports the long strip-shaped polarizer 1b, and a heating section that applies heat to the polarizer 1b to dry the polarizer 1b.

[0164] The laminating device 206 has a conveying section 61 that conveys the dried polarizer 1c and protective film 12, an adhesive coating section 64, a bonding section 67, and a chamber 69 that surrounds the adhesive coating section 64 and the bonding section 67.

[0165] <Wet Treatment Apparatus> The wet treatment apparatus 204 includes a treatment section that dyes and stretches the long strip-shaped hydrophilic polymer film 1 a with a dye treatment solution. The wet treatment includes a process of stretching the hydrophilic polymer film 1 a while applying a plurality of treatment solutions, including the dye treatment solution, to the hydrophilic polymer film 1 a.

[0166] Wet-type treatment devices are well known in the art, and the wet-type treatment device 204 of the present invention can also employ a well-known configuration.

[0167] The processing section includes, for example, a swelling processing tank 4A, a dyeing processing tank 4B, a crosslinking processing tank 4C, a stretching processing tank 4D, and a washing processing tank 4E in this order from the upstream side.

[0168] The transport unit 42 of the wet treatment device 204 has a plurality of guide rolls and the like, and pulls out the long strip-shaped hydrophilic polymer film 1a wound around the first roll unit 41 and transports it to the treatment unit.

[0169] The swelling treatment tank 4A is a treatment tank containing a swelling treatment liquid. The swelling treatment liquid swells the hydrophilic polymer film 1a. The dyeing treatment tank 4B is a treatment tank containing a dyeing treatment liquid. The dyeing treatment liquid dyes the hydrophilic polymer film 1a. The crosslinking treatment tank 4C is a treatment tank containing a crosslinking treatment liquid. The crosslinking treatment liquid crosslinks the dyed hydrophilic polymer film 1a. The stretching treatment tank 4D is a treatment tank containing a stretching treatment liquid. The stretching treatment liquid is not particularly limited, but for example, a solution containing a boron compound as an active ingredient can be used. The cleaning treatment tank 4E is a treatment tank containing a cleaning treatment liquid. The cleaning treatment liquid cleans the hydrophilic polymer film 1a after stretching. The cleaning treatment liquid is a treatment liquid for cleaning treatment liquids such as the dyeing treatment liquid and the crosslinking treatment liquid that have adhered to the hydrophilic polymer film 1a. Typical cleaning treatment liquids used are water such as ion-exchanged water, distilled water, and pure water.

[0170] <Drying Device> The drying device 205 is provided downstream of the wet treatment device 204 and upstream of the laminating device 206. In the illustrated example, the drying device 205 is provided downstream of the cleaning treatment tank 4E.

[0171] The number of drying devices 205 may be one, or two or more drying devices 205 may be provided side by side in the transport direction of the polarizer. In the illustrated example, for example, one drying device 205 is provided on the transport path of the polarizer. The drying device 205 includes a transport unit 501 having guide rolls that transport the long strip-shaped polarizer 1b manufactured by the wet-processing device 204, and a heating unit that applies heat to the polarizer 1b being transported in the longitudinal direction (MD direction) in the transport unit 501 to dry it.

[0172] The heating unit includes, for example, a chamber 502 and a heat source (not shown). The chamber 502 has a space 503 therein that can carry a polarizer.

[0173] <Laminating Device> The conveying unit 61 of the laminating device 206 has a guide roll and the like. The conveying unit 61 conveys the long strip-shaped polarizer 1c dried by the drying device 205 to the bonding unit 67. The conveying unit 61 also conveys the long strip-shaped protective film 12 and the like to the bonding unit 67.

[0174] The illustrated laminated polarizing film manufacturing apparatus 2000 is capable of laminating a first protective film 12 and a second protective film 13 on both sides of a polarizer 1c. This apparatus produces a laminated polarizing film 1 having a layer structure of first protective film 12 / adhesive layer 31 / polarizer 11 / adhesive layer 32 / second protective film 13, as shown in Fig. 20 (the balloon area at the lower left of Fig. 20).

[0175] The product manufacturing apparatus 2000 has a second roll unit 62 around which a long strip-shaped first protective film 12 is wound, and a third roll unit 63 around which a long strip-shaped second protective film 13 (film F8) is wound. The first protective film 12 of the second roll unit 62 and the second protective film 13 of the third roll unit 63 are each independently transported by a transport unit 61 from each roll unit 62, 63 to a bonding unit 67.

[0176] The adhesive coating unit 64 has a coating roll 641. The coating roll 641 of the adhesive coating unit 64 coats the film with adhesive. The adhesive coating unit 64 is disposed upstream of the laminating unit 67.

[0177] In the illustrated laminating device 206, adhesive application sections 64 are respectively arranged on one side of the first protective film 12 and one side of the second protective film 13 (film F8).

[0178] One adhesive coating section 64 applies adhesive to one side of the first protective film 12 to form an adhesive layer, and the other adhesive coating section 64 applies adhesive to one side of the second protective film 13 (film F8) to form an adhesive layer.

[0179] If necessary, adhesive-coated portions may be disposed on one side of the polarizer 1c and the other side of the polarizer 1c (not shown). When such adhesive-coated portions (not shown) are provided, adhesive layers can be formed by coating one side of the polarizer 1c and the other side of the polarizer 1c with adhesive, respectively.

[0180] The adhesive-coated portions disposed on one side of the polarizer 1c and on the other side of the polarizer 1c can also be used to coat an easy-adhesion composition, which will be described later.

[0181] The adhesive coating unit 64 includes, for example, a gravure roll 641 which is a coating roll, a container 642 in which an adhesive is stored, and a doctor blade 643. The adhesive coating unit 64 may also include a backup roll as necessary. The backup roll is disposed opposite the gravure roll 641 with the film sandwiched therebetween.

[0182] The gravure roll 641 has a plurality of cells (recesses into which adhesive is placed) formed on its surface. The gravure roll 641 rotates around its axis so that its surface comes into contact with the adhesive 65 stored in a container 642 (the direction of rotation of the gravure roll 641 is indicated by an arrow). As the gravure roll 641 rotates, the adhesive 65 adheres to the surface of the gravure roll 641, including the cells, and excess adhesive 65 is scraped off into the container 642 by a doctor blade 643. When the gravure roll 641, with adhesive in its cells, comes into contact with the film, the adhesive 65 in the cells is transferred to one side of the first protective film 12 and the second protective film 13. In this way, the adhesive 65 is solidly coated from the gravure roll 641 onto one side of each of the first protective film 12 and the second protective film 13.

[0183] The adhesive for bonding the polarizer 1c to the first protective film 12 and the second protective film 13 is not particularly limited, but it is preferable to use an active energy ray-curable adhesive as described above. Any conventionally known active energy ray-curable adhesive can be used. The active energy ray-curable adhesive generally contains an active energy ray-curable component and a polymerization initiator, and optionally contains various additives.

[0184] (Feed-out section 202) The feed-out section 202 includes an easy-adhesion treatment tank 21, a cleaning treatment tank 22, and a heat treatment tank 23. The easy-adhesion treatment tank 21 performs easy-adhesion treatment on the surface of the second protective film 13 (film F8) to which the polarizer 11 is bonded. For example, the easy-adhesion treatment tank 21 performs corona discharge treatment, plasma treatment, or the like. Corona discharge treatment is performed by applying a high voltage to a wire or sawtooth electrode disposed in a chamber facing the second protective film 13 (film F8). The cleaning treatment tank 22 has a configuration similar to the above-described cleaning treatment tank 4E and is a treatment tank containing a cleaning treatment liquid. The cleaning treatment liquid cleans the second protective film 13 (film F8). The heat treatment tank 23 has a configuration similar to the drying device 205 and heats and dries the second protective film 13 (film F8). The drying temperature of the heat treatment tank 23 is changed according to the heat treatment conditions set by the manufacturing management system 3000.

[0185] The information processing system 50 described above is a main configuration used to explain the features of the above embodiment. However, the present invention is not limited to the above configuration and can be modified in various ways within the scope of the claims. Furthermore, configurations of general information processing devices / systems are not excluded. For example, the information processing system 50 may include an inspection device 90 disposed in the first manufacturing process and / or the second manufacturing process. Furthermore, the feature point generation function of the analysis unit 93 of the inspection device 90 may be performed by the control unit 51 of the information processing system 50. In this case, the inspection device 90 sends image data of an image of the film surface and the image capture conditions (information such as transport speed, camera orientation, and angle of view) to the information processing system 50, and the feature point generation process is performed by the control unit 51.

[0186] 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 program may be provided, for example, 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 and stored in a storage unit such as a hard disk. The program may also be provided as standalone application software, or may be incorporated into the software of a device as a function of the device.

[0187] This application is based on a Japanese patent application (Patent Application No. 2023-206655) filed on December 7, 2023, the disclosure of which is incorporated herein by reference in its entirety.

[0188] 50 Information processing system 51 Control unit 511 Acquisition unit 512 Alignment unit 513 Comparison extraction unit 514 Output unit 52 Storage unit 90, 90a1, 90b1, 90b2, 90b3 Inspection device 1000 Film roll manufacturing device 2000 Product manufacturing device

Claims

1. A method for extracting feature points of a film, comprising the steps of: (a) acquiring first inspection data in a first manufacturing process for manufacturing a film; (b) acquiring second inspection data in a second manufacturing process for performing post-processing using the manufactured film, which is performed after the first manufacturing process; (c) comparing first feature point information of the film in the first inspection data with second feature point information of the film in the second inspection data; and (d) extracting, based on a result of the comparison in step (c), feature points that are present in one of the first and second inspection data but not in the other, or that are determined to be defective in one of the inspection data but not determined to be defective in the other inspection data.

2. A method for extracting feature points of a film, comprising the steps of: (a) acquiring first inspection data in a first manufacturing process for manufacturing a film, or in a second manufacturing process for performing post-processing using the film manufactured after the first manufacturing process; (b) acquiring second inspection data in the second manufacturing process, or at an inspection position after a sub-process downstream of the inspection position at which the first inspection data was acquired in the second manufacturing process; (c) comparing first feature point information of the film in the first inspection data with second feature point information of the film in the second inspection data; and (d) extracting, based on a result of the comparison in step (c), feature points that are present in one of the first and second inspection data but not present in the other inspection data, or that are determined to be defective in one of the inspection data but not determined to be defective in the other inspection data.

3. A method for extracting features according to claim 1 or claim 2, wherein the one inspection data is the first inspection data and the other inspection data is the second inspection data, and in step (d), a first type feature is extracted that is present in the first inspection data but not present in the second inspection data, or that is determined to be a defect in the first inspection data but not determined to be a defect in the second inspection data.

4. The feature extraction method according to claim 3, further comprising extracting a second type of feature that is present in the second inspection data but not present in the first inspection data, or that is determined to be a defect in the second inspection data but not determined to be a defect in the first inspection data.

5. A method for extracting feature points according to claim 3, wherein the first inspection data and the second inspection data are inspection data obtained by processing images of the film to extract feature point information, and the feature point information includes size information of the feature points and position information on the film.

6. A method for extracting feature points as claimed in claim 3, further comprising, before step (c), a step (e) of aligning the film in the first inspection data and the second inspection data, wherein step (e) comprises: a step (e1) of not shifting the relative positions of the first inspection data and the second inspection data and / or moving position information of the feature points of the second inspection data; a step (e2) of calculating a distance from each of a plurality of feature points in one of the first and second inspection data to a nearest feature point in the other inspection data; and a step (e3) of repeating step (e1) and step (e2) so that the distance calculated in step (e2) is minimized.

7. The method for extracting feature points according to claim 6, further comprising, after step (e), a step (f) of calculating a distance from each of a plurality of feature points in one of the first and second test data to a nearest feature point in the other of the first and second test data, excluding distance values ​​equal to or greater than a predetermined threshold, and judging whether the processing of step (e) is appropriate based on a sum or average of the distance values ​​calculated from the distance values ​​after excluding the distance values.

8. The method for extracting feature points according to claim 3, further comprising, before step (c), a step (g) of aligning the film in the first inspection data and the second inspection data, wherein in step (g), kernel density estimation is performed on a plurality of feature points in the first inspection data and the second inspection data to calculate probability density functions of the feature points, and the calculated probability density functions are compared to align the film.

9. The method for extracting feature points as described in claim 3, further comprising, before step (c), a step (g) of aligning the film in the first inspection data and the second inspection data, wherein in step (g), kernel density estimation is performed on a plurality of feature points in one of the first inspection data and the second inspection data to calculate a probability density function of the feature points, and the calculated probability density function is compared with position information of the feature points in the other inspection data, thereby aligning the film.

10. A method for extracting feature points as described in claim 3, wherein the post-processing in the second manufacturing process is a coating process for providing a functional layer on the surface of the film manufactured in the first manufacturing process.

11. The method for extracting feature points according to claim 3, further comprising, before step (c), a step (g) of performing pre-processing on the first inspection data and the second inspection data to exclude feature points that do not meet predetermined conditions.

12. A method for extracting features according to claim 1 or claim 2, wherein the one inspection data is the second inspection data and the other inspection data is the first inspection data, and in step (d), a second type of feature is extracted that is present in the second inspection data but not present in the first inspection data, or that is determined to be a defect in the second inspection data but not determined to be a defect in the first inspection data.

13. A method for extracting feature points according to claim 2, wherein each of the first manufacturing process and the second manufacturing process includes a plurality of sub-processes, a plurality of inspection data are acquired at inspection positions upstream and downstream of at least one or more of the sub-processes, and any of the plurality of inspection data is used as first inspection data, and inspection data at an inspection position downstream of the first inspection data is used as second inspection data.

14. The method for extracting feature points according to claim 13, further comprising the step of: (h) accepting a selection of a combination of first and second test data from among the plurality of test data.

15. A method for setting shipping standards, comprising the steps of: setting shipping standards for the first manufacturing process based on the first type of feature points extracted by the feature point extraction method of claim 3.

16. An information processing system comprising: an acquisition unit that acquires first inspection data from a first manufacturing process for manufacturing a film, and second inspection data from a second manufacturing process for performing post-processing using the manufactured film, which is performed after the first manufacturing process; a comparison unit that compares first feature point information of the film in the first inspection data with second feature point information of the film in the second inspection data; and an extraction unit that extracts, based on a comparison result by the comparison unit, of the first and second inspection data, a feature point that is present in one inspection data but not in the other inspection data, or a feature point that is determined to be a defect in one inspection data but not determined to be a defect in the other inspection data.

17. An information processing system comprising: an acquisition unit that acquires first inspection data from a first manufacturing process for manufacturing a film or a second manufacturing process that is carried out after the first manufacturing process and performs post-processing using the manufactured film, and second inspection data from the second manufacturing process or an inspection position after a sub-process downstream of the inspection position where the first inspection data was acquired in the second manufacturing process; a comparison unit that compares first feature point information of the film in the first inspection data with second feature point information of the film in the second inspection data; and an extraction unit that extracts, based on a comparison result by the comparison unit, a feature point that is present in one of the first inspection data and not present in the other of the second inspection data, or a feature point that is determined to be a defect in one of the inspection data and not determined to be a defect in the other of the inspection data.

18. An information processing system as described in claim 16 or claim 17, wherein the extraction unit extracts first type feature points that are present in the first inspection data but not present in the second inspection data, or that are determined to be defects in the first inspection data but not determined to be defects in the second inspection data.

Images