Inspection program and inspection device

Abstract

A threshold value (221) for identifying whether the object is normal or abnormal depending on the abnormality level in the object is set in a computer that inspects the object, and the abnormality level in the object is determined using a machine learning model for a captured image of the object. For each of a plurality of types of abnormalities that may occur in the same part of the object, an object that includes a part where the determined abnormality level is equal to or higher than the set threshold value (221) is identified as an abnormal item.

Description

[Technical field]

[0001] The present invention relates to an inspection program and an inspection device. [Background technology]

[0002] When inspecting a workpiece, artificial intelligence (AI) is sometimes used to detect anomalies (in other words, any peculiar areas) that exist in the captured image of the workpiece.

[0003] Anomaly detection using AI outputs the probability that an anomaly exists and, if an anomaly exists, the type of anomaly. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Patent Publication No. 2021-182225 [Patent Document 2] JP 2021-131364 A Summary of the Invention [Problem to be solved by the invention]

[0005] However, there are cases where it is necessary to flexibly classify workpieces as abnormal or normal not only based on the presence or absence of an abnormality and the type of abnormality, but also based on the level of the abnormality (in other words, its severity).

[0006] FIG. 1 is a diagram showing the level of almond deflation.

[0007] FIG. 1 shows images of three almonds, with the levels of shrinkage of the almonds' surfaces increasing in the order of A1, A2, and A3.

[0008] For example, as shown by reference symbol A2, there are almonds that are shriveled all over but only slightly so can be treated as normal, while there are almonds that are significantly shriveled all over and should be treated as abnormal, as shown by reference symbol A3.

[0009] The level of abnormality that is considered to be normal may differ depending on the purpose of the workpiece sorting, and there is a risk that multiple machine learning data will need to be prepared depending on the purpose of the workpiece sorting.

[0010] For example, almonds may be used as snacks to accompany alcoholic beverages, etc., or as a single piece placed on top of pastries. When used as snacks to accompany alcoholic beverages, etc., it is expected that even slight shrinkage will be tolerated and the almonds will be selected, whereas when used as a single piece on top of pastries, even slight shrinkage will not be tolerated and the almonds will be selected.

[0011] In one aspect, the technology described in this specification aims to provide an inspection program and an inspection device that are capable of flexibly sorting workpieces regardless of the purpose of the workpiece sorting. [Means for solving the problem]

[0012] In one aspect, the inspection program includes a computer that inspects an object, and sets a predetermined value for each of a plurality of types of abnormality that may occur in the same part of the object, for determining whether the object is normal or abnormal according to an abnormality level in the object, and performs a machine learning model on the captured image of the object. Using the first map in The object Each part determining the level of abnormality in Using a plurality of second maps for each of the plurality of abnormality types, which are different from the first map, From the plurality of abnormality types In each of the above locations determining one or more anomaly types; outputting a plurality of degrees of abnormality representing a probability that an abnormality exists in each portion of the object using a third map different from the first map and the plurality of second maps, and based on a correspondence relationship between the first map, the plurality of second maps, and the third map, For each of the one or more determined abnormality types, Among the parts whose output abnormality degree is equal to or greater than a threshold value, A process is executed to identify the object including a portion where the determined abnormality level is equal to or higher than the set predetermined value as the abnormal product. Effect of the Invention

[0013] According to the disclosed technology, it is possible to provide an inspection program and an inspection device that are capable of flexibly selecting works regardless of the purpose of the work selection. [Brief description of the drawings]

[0014] [Figure 1] FIG. 1 is a diagram showing an image of the level of almond deflation. [Diagram 2] 1 is a block diagram illustrating an example of a hardware configuration and an example of a functional configuration of an inspection system according to an embodiment. [Diagram 3] FIG. 13 is a diagram illustrating an example of an abnormality level setting screen in the embodiment. [Figure 4] FIG. 10 is a diagram illustrating a map of an input image in the embodiment. [Diagram 5] (a) is a diagram illustrating a map of abnormality degree, (b) is a diagram illustrating a map of abnormality level, (c) is a diagram illustrating a map of abnormality type #1, (d) is a diagram illustrating a map of abnormality type #2, and (e) is a diagram illustrating a map of abnormality type #3. [Figure 6] FIG. 1A is a diagram for explaining the evaluation process of the anomaly degree map, FIG. 1B is a diagram for explaining the selection process of the anomaly type, and FIG. 1C is a diagram for explaining the process of determining the final evaluation according to the anomaly level. [Figure 7] 11 is a flowchart illustrating an abnormality inspection process in the embodiment. [Figure 8] 11 is a flowchart illustrating pre-processing of an input image in an embodiment. [Figure 9] 1 is a flowchart illustrating a machine learning process in an embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0015] An embodiment will be described below with reference to the drawings. However, the embodiment described below is merely an example, and is not intended to exclude various modifications and application of techniques not clearly stated in the embodiment. This embodiment can be implemented with various modifications without departing from the spirit of the invention.

[0016] Furthermore, each figure is not intended to include only the components shown in the figure, but may include other functions, etc.

[0017] Hereinafter, in the drawings, parts given the same reference numerals indicate similar parts.

[0018] [A] Example of embodiment [A-1] System configuration example FIG. 2 is a block diagram illustrating an example of a hardware configuration and a functional configuration of an inspection system 100 according to an embodiment.

[0019] The inspection system 100 includes an inspection device 1, a camera 21, a display 22, and a conveying device 23.

[0020] The camera 21 captures an image of a workpiece (object; not shown) that is an object to be inspected by the inspection device 1, and inputs the captured image to the inspection device 1. The inspection system 100 may be provided with one or more cameras 21. The workpiece may be, for example, a plant such as a fruit or vegetable, an animal, or an industrial product.

[0021] The display 22 displays various information for an operator of the inspection device 1. The display 22 displays, for example, a setting screen 220, which will be described later with reference to FIG.

[0022] The conveying device 23 conveys the workpiece to a position where it can be photographed by the camera 21. The conveying device 23 may also include a discharge mechanism for discharging a defective workpiece.

[0023] The conveying device 23 may be equipped with an air blowing unit when the workpiece is lightweight and not easily damaged. The conveying device 23 photographs the workpiece with the camera 21 while blowing and conveying the workpiece with the air blowing unit. The air blowing unit may realize the function as a discharge mechanism by blowing normal workpieces and abnormal workpieces to different positions (in other words, distances) by adjusting the output air volume. In addition, when the conveying device 23 is equipped with an air blowing unit for conveying and an air blowing unit for exhausting, the air blowing unit for exhausting may blow air in a different direction from the air blowing unit for conveying, thereby blowing normal workpieces and abnormal workpieces to different positions, thereby realizing the function as a discharge mechanism.

[0024] Furthermore, the transport device 23 may include a conveyor, and the work may be photographed by the camera 21 while the work is transported by the conveyor. In this case, the defective work may be discharged by a blower unit that blows air in a direction perpendicular to the transport direction of the conveyor, or by a robot arm for gripping the work or a flap for flicking the work.

[0025] The transport device 23 may include an abnormality notification unit instead of the discharge mechanism. When a defective workpiece is detected, the abnormality notification unit may notify the operator of the inspection system 100 of the detection. The abnormality notification unit may notify the operator of the inspection system 100 of the abnormality, for example, by displaying the screen on the display 22, sounding an alert, emitting a lamp, or the like.

[0026] The inspection device 1 includes a Central Processing Unit (CPU) 11 , a memory 12 , and a storage device 13 .

[0027] The storage device 13 is, for example, a device that stores data in a readable and writable manner, and may be, for example, a hard disk drive (HDD), a solid state drive (SSD), or a storage class memory (SCM). The storage device 13 stores a machine learning model for executing the anomaly inspection process in the embodiment.

[0028] The memory 12 is a storage device including, for example, a Read Only Memory (ROM) and a Random Access Memory (RAM). The RAM may be, for example, a Dynamic RAM (DRAM). Programs such as a Basic Input / Output System (BIOS) may be written in the ROM of the memory 12. The software programs in the memory 12 may be appropriately read and executed by the CPU 11. The RAM of the memory 12 may be used as a primary recording memory or a working memory.

[0029] The CPU 11 is an example of a processor, and is illustratively a processing device that performs various controls and calculations, and realizes various functions by executing an Operating System (OS) and programs read by the memory 12. That is, the CPU 11 may function as a learning model acquisition unit 111, an abnormality level setting unit 112, an abnormality level determination unit 113, and a discharge processing unit 114, as shown in FIG.

[0030] The programs for implementing the functions of the learning model acquisition unit 111, the abnormality level setting unit 112, the abnormality level determination unit 113, and the discharge processing unit 114 may be provided in a form recorded on a computer-readable recording medium such as a flexible disk, a CD (CD-ROM, CD-R, CD-RW, etc.), a DVD (DVD-ROM, DVD-RAM, DVD-R, DVD+R, DVD-RW, DVD+RW, HD DVD, etc.), a Blu-ray disk, a magnetic disk, an optical disk, a magneto-optical disk, etc. Then, the computer (CPU 11 in this embodiment) may read the program from the above-mentioned recording medium via a reading device not shown, transfer it to an internal recording device or an external recording device, and store it for use. Also, the program may be recorded in a storage device (recording medium) such as a magnetic disk, an optical disk, a magneto-optical disk, etc., and provided to the computer from the storage device via a communication path.

[0031] When realizing the functions of the learning model acquisition unit 111, the abnormality level setting unit 112, the abnormality level determination unit 113, and the discharge processing unit 114, a program stored in an internal storage device (memory 12 in this embodiment) may be executed by a computer (CPU 11 in this embodiment). Also, a program recorded on a recording medium may be read and executed by a computer.

[0032] The learning model acquisition unit 111 generates a machine learning model for executing the anomaly inspection process in the embodiment and stores it in the storage device 13. The learning model acquisition unit 111 also acquires the machine learning model stored in the storage device 13. In this embodiment, a single machine learning model that can be used for a plurality of selection applications is implemented by appropriately adjusting the threshold value.

[0033] The abnormality level setting unit 112 sets information on the judgment threshold, the test result threshold, and the ambiguous discharge rate based on input by the operator using a setting screen 220, which will be described later with reference to FIG.

[0034] The abnormality level determination unit 113 determines the abnormality level when an abnormality exists in each work, based on the machine learning model acquired by the learning model acquisition unit 111 and the input from the camera 21.

[0035] The discharge processing unit 114 discharges a workpiece that is a defective product based on the setting by the abnormality level setting unit 112 and the abnormality level determination result by the abnormality level determination unit 113.

[0036] In addition, the rejection processing unit 114 may reject some of the works that are unclear as to whether they are abnormal or normal. For example, if it is acceptable for up to 10% of the almonds to be mixed with large chips, abnormal levels 1 and 2 are deemed normal, abnormal levels 2 and 3 are deemed ambiguous and 90% are rejected, and abnormal levels 3 and above are all rejected as abnormal.

[0037] FIG. 3 is a diagram illustrating an example of an abnormality level setting screen 220 in the embodiment.

[0038] An operator of the inspection system 100 inputs values ​​into the setting screen 220 shown in FIG. 3 using a keyboard and mouse (not shown).

[0039] The setting screen 220 displays a judgment threshold, a judgment result threshold, and an ambiguous discharge rate for each label indicating the type of abnormality.

[0040] In the example shown in FIG. 3, the label indicates "shrunk", "wormhole", "chipped" and "foreign object".

[0041] The judgment threshold is set as the probability that each workpiece is a defective item for each label.

[0042] The threshold value of the inspection result is set based on the abnormality level of each work, and determines whether each work is normal, ambiguous, or abnormal for each label.

[0043] In FIG. 3, for example, for the label “Shrunk,” the threshold values ​​of the test results indicate that an abnormality level of less than 1.5 indicates a normal product (see the white area of ​​indicator 221), an abnormality level of 1.5 or more and less than 3.5 indicates an ambiguous product (see the diagonal area of ​​indicator 221), and an abnormality level of 3.5 or more indicates an abnormal product (see the black area of ​​indicator 221).

[0044] In addition, an ambiguous product may be referred to as an intermediate product having a quality intermediate between a normal product and an abnormal product.

[0045] For the threshold value of the test result, a value of “1.5” (second threshold value) or “3.5” (first threshold value) may be directly input into the input box, or the value may be adjusted by operating the indicator 221.

[0046] Also, in FIG. 3, for example, for the label “wormhole”, the threshold value of the inspection result is that an abnormality level of less than 2.5 is a normal product (see the white area of ​​indicator 221), and an abnormality level of 2.5 or more is an abnormal product (see the black area of ​​indicator 221), so there is no need to set an ambiguous product.

[0047] The ambiguous rejection rate is set to indicate what percentage of the workpieces determined to be ambiguous are to be rejected.

[0048] FIG. 4 is a diagram illustrating a map of an input image in the embodiment.

[0049] In Fig. 4, the luminance of a monochrome image normalized to [0,1] is represented as a 9 × 9 map. Note that the input image may be a color image.

[0050] In the example shown in Figure 4, 0 represents an area where no workpiece is present, 0.25 represents a normal area of ​​the workpiece, 0.8 represents abnormal area A, 0.65 represents abnormal area B, and 0.9 represents abnormal area C.

[0051] (a) of Figure 5 is a diagram illustrating a map of abnormality degree, (b) of Figure 5 is a diagram illustrating a map of abnormality level, (c) of Figure 5 is a diagram illustrating a map of abnormality type #1, (d) of Figure 5 is a diagram illustrating a map of abnormality type #2, and (e) of Figure 5 is a diagram illustrating a map of abnormality type #3.

[0052] In the examples shown in Figures 5(a) to (e), the cell resolution is 3 x 3, which is one third of the map of the input image shown in Figure 4. Note that the cell resolution of each map in Figures 5(a) to (e) is not limited to 3 x 3, and may be lower or higher than 3 x 3, or may be the same as the map of the input image (9 x 9 in the example shown in Figure 4).

[0053] In Fig. 5(a), the degree of anomaly represents the probability that an image has an anomaly as a result of machine learning evaluation. In the example shown in Fig. 5(a), the degree of anomaly is 0.71 at the location of anomalous part A, 0.8 at the location of anomalous part B, and 0.55 at the location of anomalous part C.

[0054] In Fig. 5(b), the abnormality level indicates the degree of abnormality when an abnormality is found as a result of evaluating an image using machine learning. In the example shown in Fig. 5(b), the abnormality level is 0.6 at the location of abnormal part A, 0.1 at the location of abnormal part B, and 0.9 at the location of abnormal part C.

[0055] In (c) to (e) of FIG. 5, the anomaly types correspond to the labels shown in FIG.

[0056] In the example shown in FIG. 5(c), for abnormality type #1, the location where abnormality portion A is located reacts as 0.51, the location where abnormality portion B is located reacts as 0.2, and the location where abnormality portion C is located reacts as 0.05.

[0057] In the example shown in FIG. 5(d), for abnormality type #2, the location where abnormal part A is located reacts as 0.6, the location where abnormal part B is located reacts as 0.55, and the location where abnormal part C is located reacts as 0.25.

[0058] In the example shown in FIG. 5(c), for anomaly type #3, the location where anomalous part A is located reacts as 0.1, the location where anomalous part B is located reacts as 0.05, and the location where anomalous part C is located reacts as 0.45.

[0059] FIG. 6(a) is a diagram explaining the evaluation process of the anomaly degree map, FIG. 6(b) is a diagram explaining the selection process of the anomaly type, and FIG. 6(c) is a diagram explaining the determination process of the final evaluation according to the anomaly level.

[0060] It is assumed that the threshold of the degree of abnormality of abnormality type #1 is 0.7, the threshold of the degree of abnormality of abnormality type #2 is 0.6, and the threshold of the degree of abnormality of abnormality type #3 is 0.51.

[0061] In the anomaly degree map shown in (a) of Figure 6, cells that exceed the minimum value of the threshold value for each anomaly type (in this example, 0.51 for anomaly type #3) are selected. The point of 0.71 is cell #1, the point of 0.8 is cell #5, and the point of 0.55 is cell #9.

[0062] In the selection of anomaly types shown in Fig. 6(b), maps of anomaly types #1 to #3 are arranged, and a value (0.5 in this example) exceeding the threshold value at the same coordinates as the coordinates of the cell selected in Fig. 6(a) in each map is selected. In the example shown in Fig. 6(b), 0.51 is selected as a value exceeding the threshold value of 0.5 in the map of anomaly type #1, and 0.6 and 0.55 are selected as values ​​exceeding the threshold value of 0.5 in the map of anomaly type #2. On the other hand, in the map of anomaly type #3, there is no value exceeding the threshold value of 0.5 at the same coordinates as the coordinates of the cell selected in Fig. 6(a), so the maximum value of 0.45 is selected.

[0063] In determining the final evaluation according to the abnormality level shown in Figure 6 (c), if for abnormality type #1, an abnormality level of 0.5 or more is abnormal, for abnormality type #2, 0.05 to 0.56 is ambiguous and anything above that is abnormal, and for abnormality type #3, anything below 0.75 is normal, then cell #1 will be judged as abnormal for both abnormality types #1 and #2, cell #5 will be judged as ambiguous for abnormality type #2, and cell #9 will be judged as normal for abnormality type #3.

[0064] [A-2] Example of operation The abnormality inspection process in this embodiment is shown in the flowchart of FIG. 3 The following description will be given with reference to the flowchart shown in FIG.

[0065] The abnormality level determination unit 113 performs inference on the image using AI (step S1).

[0066] The abnormality level determination unit 113 determines whether there is a cell having an abnormality degree exceeding the smallest abnormality degree among the thresholds for each abnormality type (step S2).

[0067] If there is no cell having an abnormality degree exceeding the smallest abnormality degree among the thresholds of each abnormality type (see No route in step S2), the abnormality inspection process ends.

[0068] On the other hand, if there is a cell with an abnormality degree exceeding the smallest abnormality degree threshold for each abnormality type (see the Yes route in step S2), steps S4 to S11 ,S13 The process is repeated to start evaluation of all cells having an abnormality degree exceeding the minimum threshold (step S3). Note that evaluation may also be performed on all cells other than the cells having an abnormality degree exceeding the minimum threshold.

[0069] The abnormality level determination unit 113 determines the abnormality type of the cell (step S4).

[0070] The abnormality level determination unit 113 determines whether the degree of abnormality is equal to or greater than the threshold value of any one of the determined types of abnormality (step S5).

[0071] If the degree of abnormality is not equal to or greater than the threshold value of any of the determined types of abnormality (see No route in step S5), The abnormality level determination unit 113 adopts the maximum value among the values ​​in the abnormality type map (step S13). The process proceeds to step S12.

[0072] On the other hand, if the degree of abnormality is equal to or greater than the threshold value of any of the determined abnormality types (see the Yes route in step S5), the processes in steps S7 to S10 are repeatedly executed, and evaluation of all the determined abnormality types is started (step S6).

[0073] The abnormality level determination unit 113 determines whether the abnormality level is ambiguous or higher (step S7).

[0074] If the abnormality level is not ambiguous or higher (see the No route from step S7), the process proceeds to step S11.

[0075] On the other hand, if the abnormality level is equal to or higher than ambiguous (see the Yes route in step S7), it is determined whether the abnormality level is equal to or higher than abnormal (step S8).

[0076] If the abnormality level is abnormal or higher (see the Yes route from step S8), the process proceeds to step S10.

[0077] On the other hand, if the abnormality level is not abnormal or higher (see the No route from step S8), the discharge processing unit 114 determines whether or not discharge has been selected with a predetermined probability (step S9).

[0078] If discharge is not selected with a predetermined probability (see the No route in step S9), the process proceeds to step S11.

[0079] On the other hand, if the discharge is selected with a predetermined probability (see the Yes route of step S9), the discharge processing unit 114 executes the discharge process (step S10).

[0080] When the evaluation of all the determined abnormality types has been repeatedly performed in steps S7 to S10, the evaluation of all the determined abnormality types is completed (step S11).

[0081] All cell evaluations are performed in steps S4 to S11. ,S13 When the process is repeated in step S12, evaluation of all cells having an abnormality degree exceeding the minimum threshold is completed (step S12), and the abnormality inspection process is terminated.

[0082] Next, the pre-processing of an input image in this embodiment will be described with reference to the flowchart shown in FIG. 8 (steps S21 to S23).

[0083] The abnormality level determination unit 113 functions as an image input unit that processes an input image as necessary (step S21).

[0084] The abnormality level determination unit 113 functions as a latent space projection unit that projects the input into a low-dimensional latent space to enable high-speed processing (step S22).

[0085] The abnormality level determination unit 113 functions as an output unit that interprets the information in the latent space, converts it into a predetermined format, and outputs it (step S23). Then, the pre-processing of the input image is completed.

[0086] Next, the machine learning process in the embodiment will be described with reference to the flowchart (steps S31 to S38) shown in FIG.

[0087] When a learning sample is imaged by placing the sample in the inspection system 100 and imaging it with the camera 21, the learning model acquisition unit 111 performs instruction on the imaged data (step S31). Specifically, the learning model acquisition unit 111 instructs the abnormality type and abnormality level to the abnormal portion of the image, and performs processing called Semantic Segmentation and Bounding Box only on the abnormal portion.

[0088] The learning model acquisition unit 111 converts the image and teaching data into a format suitable for learning, such as a [0,1] map (step S32).

[0089] The processes of steps S34 to S37 are repeatedly executed, and learning is started until sufficient accuracy is obtained (step S33).

[0090] The learning model acquisition unit 111 inputs the converted image to the AI ​​(step S34).

[0091] The learning model acquisition unit 111 acquires the output of the AI ​​(step S35).

[0092] The learning model acquisition unit 111 evaluates the output of the AI ​​against the converted teaching data (step S36).

[0093] The learning model acquisition unit 111 back-propagates the evaluation result and updates the AI ​​parameters (step S37).

[0094] When the learning is repeated in steps S34 to S37 until sufficient accuracy is obtained, the learning is completed (step S38), and the machine learning process is terminated.

[0095] [A-3] Effect According to the inspection program and the inspection device 1 in the example of the embodiment described above, for example, the following advantageous effects can be achieved.

[0096] The abnormality level setting unit 112 sets a threshold value for determining whether the object is normal or abnormal according to the abnormality level of the object. The abnormality level determination unit 113 determines the abnormality level of the object using a machine learning model for a captured image of the object. The abnormality level determination unit 113 identifies the object including a portion where the determined abnormality level is equal to or higher than the set threshold value for each of a plurality of abnormality types that may occur in the same portion of the object as an abnormal item.

[0097] This enables flexible work sorting using one machine learning model regardless of the purpose of work sorting, and also enables appropriate work sorting according to the abnormality level for each of multiple anomaly types.

[0098] The states of the object include not only normal and abnormal products, but also intermediate products having intermediate quality between normal and abnormal products. The thresholds include a first threshold for identifying whether the object is an abnormal product or an intermediate product, and a second threshold for identifying whether the object is an intermediate product or normal product. The abnormality level determination unit 113 identifies an object including a part whose determined abnormality level is equal to or higher than the first threshold as an abnormal product, identifies an object including a part whose determined abnormality level is equal to or higher than the second threshold and lower than the first threshold and not identified as an abnormal product as an intermediate product, and identifies an object including a part whose determined abnormality level is equal to or higher than the second threshold and not identified as an abnormal product or an intermediate product as an abnormal product.

[0099] This makes it possible to appropriately identify intermediate products having quality intermediate between normal products and abnormal products (in other words, ambiguous products).

[0100] The abnormality level setting unit 112 sets a rejection rate of intermediate products for each of a plurality of abnormality types. The rejection processing unit 114 rejects a part of the intermediate products according to the rejection rate in addition to all of the abnormal products from among the plurality of targets.

[0101] This allows intermediate products to be discharged at an appropriate rate.

[0102] The abnormality level setting unit 112 sets a plurality of thresholds for each abnormality type. The abnormality level determination unit 113 determines a plurality of abnormality levels for each abnormality type. The abnormality level determination unit 113 identifies, as an abnormal product, an object including a portion in which each of the determined abnormality levels is equal to or higher than a corresponding threshold among the set thresholds.

[0103] This allows for more accurate identification of defective products by determining multiple abnormality levels for each type of abnormality.

[0104] [B] Other The disclosed technology is not limited to the above-described embodiment, and various modifications can be made without departing from the spirit of the present embodiment. Each configuration and each process of the present embodiment can be selected as necessary, or can be combined as appropriate. [Explanation of symbols]

[0105] 100: Inspection system 1: Inspection equipment 11: CPU 111: Learning model acquisition unit 112: Abnormal level setting section 113: Abnormality level determination unit 114: Discharge processing section 12: Memory 13:Storage device 21: Camera 22: Display 220: Setting screen 221: Indicator 23:Transportation device

Claims

1. The computer that inspects the object a predetermined value is set for each of a plurality of types of abnormality that may occur in the same portion of the object, the predetermined value being used to specify whether the object is normal or abnormal according to the abnormality level of the object; Using a machine learning model to determine an abnormality level in the captured image of the object; determining one or more abnormality types from among the plurality of abnormality types; identifying, for each of the one or more determined abnormality types, the object including a portion in which the determined abnormality level is equal to or higher than the set predetermined value, as the abnormal product; An inspection program that executes the process.

2. Using a first map, determining the abnormality level in each part of the object; determining the one or more abnormality types in each of the portions using a plurality of second maps for each of the plurality of abnormality types that are different from the first map; identifying the defective product based on a correspondence relationship between the first map and the plurality of second maps; The inspection program according to claim 1 , which causes the computer to execute a process.

3. Using a third map different from the first map and the plurality of second maps, outputting a plurality of abnormality degrees representing the probability that an abnormality exists in each part of the object; extracting one or more degrees of abnormality that are equal to or greater than a minimum first threshold value among the first threshold values ​​for each of the plurality of types of abnormality from the plurality of degrees of abnormality in the third map; extracting, from each of the plurality of second maps, a value equal to or greater than a second threshold value or a maximum value from coordinates corresponding to coordinates at which the one or more degrees of abnormality extracted in the third map exist; Identifying the object including coordinates whose corresponding coordinate values ​​in the first map are equal to or greater than the predetermined value for coordinates of the second threshold value or the maximum value extracted in each of the plurality of second maps as the abnormal product; The inspection program according to claim 2 , which causes the computer to execute a process.

4. The state of the object includes, in addition to the normal product and the abnormal product, an intermediate product having an intermediate quality between the normal product and the abnormal product, the predetermined value includes a first predetermined value for specifying whether the object is the abnormal product or the intermediate product, and a second predetermined value for specifying whether the object is the intermediate product or the normal product, a plurality of the first predetermined values ​​are set for each of the plurality of abnormality types, and a plurality of the second predetermined values ​​are set for each of the plurality of abnormality types, identifying the object including a portion where the determined abnormality level is equal to or greater than the first predetermined value as the abnormal product, identifying the object including a portion where the determined abnormality level is equal to or greater than the second predetermined value and less than the first predetermined value and not identified as the abnormal product as the intermediate product, and identifying the object including a portion where the determined abnormality level is less than the second predetermined value and not identified as the abnormal product or the intermediate product as the normal product. The inspection program according to any one of claims 1 to 3, which causes the computer to execute a process.

5. A rejection rate of the intermediate product is set for each of the plurality of abnormality types; Among the plurality of objects, in addition to all of the defective products, a part of the intermediate products according to the rejection rate is rejected. The inspection program according to claim 4 , which causes the computer to execute a process.

6. A plurality of the predetermined values ​​are set for each of the types of abnormality, determining a plurality of abnormality levels for each of the abnormality types; Identifying the object including a portion in which each of the determined abnormal levels is equal to or greater than a corresponding one of the set predetermined values ​​as the abnormal product. The inspection program according to any one of claims 1 to 3, which causes the computer to execute a process.

7. An inspection device for inspecting an object, comprising: a predetermined value is set for each of a plurality of types of abnormality that may occur in the same portion of the object, the predetermined value being used to specify whether the object is normal or abnormal according to the abnormality level of the object; Using a machine learning model to determine an abnormality level in the captured image of the object; determining one or more abnormality types from among the plurality of abnormality types; identifying, for each of the one or more determined abnormality types, the object including a portion in which the determined abnormality level is equal to or higher than the set predetermined value, as the abnormal product; An inspection device comprising a processor.

8. The processor, determining the abnormality level at each site of the object using a first map; determining the one or more abnormality types in each of the portions using a plurality of second maps for each of the plurality of abnormality types that are different from the first map; identifying the defective product based on a correspondence relationship between the first map and the plurality of second maps; 8. The inspection apparatus according to claim 7.

9. The processor, outputting a plurality of anomaly degrees representing the probability that an anomaly exists in each portion of the object by using a third map different from the first map and the plurality of second maps; extracting one or more degrees of abnormality that are equal to or greater than a minimum first threshold value among the first threshold values ​​for each of the plurality of types of abnormality from the plurality of degrees of abnormality in the third map; extracting, from each of the plurality of second maps, a value equal to or greater than a second threshold value or a maximum value from coordinates corresponding to coordinates at which the one or more degrees of abnormality extracted in the third map exist; Identifying the object including coordinates whose corresponding coordinate values ​​in the first map are equal to or greater than the predetermined value for coordinates of the second threshold value or the maximum value extracted in each of the plurality of second maps as the abnormal product; 9. The inspection apparatus according to claim 8.

10. The state of the object includes, in addition to the normal product and the abnormal product, an intermediate product having an intermediate quality between the normal product and the abnormal product, the predetermined value includes a first predetermined value for specifying whether the object is the abnormal product or the intermediate product, and a second predetermined value for specifying whether the object is the intermediate product or the normal product, a plurality of the first predetermined values ​​are set for each of the plurality of abnormality types, and a plurality of the second predetermined values ​​are set for each of the plurality of abnormality types, The processor, identifying the object including a portion where the determined abnormality level is equal to or greater than the first predetermined value as the abnormal product, identifying the object including a portion where the determined abnormality level is equal to or greater than the second predetermined value and less than the first predetermined value and not identified as the abnormal product as the intermediate product, and identifying the object including a portion where the determined abnormality level is less than the second predetermined value and not identified as the abnormal product or the intermediate product as the normal product. The inspection device according to any one of claims 7 to 9.

11. The processor, A rejection rate of the intermediate product is set for each of the plurality of abnormality types; Among the plurality of objects, in addition to all of the defective products, a part of the intermediate products according to the rejection rate is rejected. The inspection apparatus according to claim 10.

12. The processor, A plurality of the predetermined values ​​are set for each of the types of abnormality, determining a plurality of abnormality levels for each of the abnormality types; Identifying the object including a portion in which each of the determined abnormal levels is equal to or greater than a corresponding one of the set predetermined values ​​as the abnormal product. The inspection device according to any one of claims 7 to 9.

Images