KR20220130577A - Training data creation assistance apparatus and training data creation assistance method - Google Patents

Abstract

An abnormal data acquisition part acquires abnormal data representing an image of an inspection object that is determined to be defective in advance. A normal data acquisition part acquires normal data indicating an image of a normal inspection target to correspond to the abnormal data acquired by the abnormal data acquisition part. A difference data generation part generates difference data representing a difference between the abnormal data acquired by the abnormal data acquisition part and the normal data acquired by the normal data acquisition part to correspond to the abnormal data. A presentation part presents an image of a portion of the inspection object based on the difference data generated by the difference data generation part.

Description

TRAINING DATA CREATION ASSISTANCE APPARATUS AND TRAINING DATA CREATION ASSISTANCE METHOD

The present invention relates to a teacher data creation support device and a teacher data creation support method that support creation of teacher data.

Inspection for determining whether a product or a commodity such as a food product is a good product is appropriately performed in each step from the middle of manufacture to before distribution. For example, in Unexamined-Japanese-Patent No. 2011-119471, the defect inspection apparatus for test|inspecting various defects which generate|occur|produce in the manufacturing process of a semiconductor wafer is described.

In this defect inspection apparatus, several SEM (scanning electron microscope) images which show the wafer of several inspection object are produced|generated. From a plurality of generated SEM images, an SEM image representing a wafer of good quality is designated as a template by the user. By calculating the difference between each of a plurality of SEM images (inspection images) other than the template and the template, a defect on the circuit pattern of the wafer indicated by the inspection image is detected.

In a defect inspection apparatus, even if it is an inspection object without a defect, it may be determined that there exists a defect. In this case, although there is no defect, the inspection object is discarded because an erroneous inspection result is obtained, and a yield falls. Therefore, it is desired that the inspection be performed with higher precision.

An object of the present invention is to provide a teacher data creation support device and a teacher data creation support method capable of easily creating teacher data for performing an examination with high precision.

(1) A teacher data creation support apparatus according to an aspect of the present invention is a teacher data creation support apparatus that supports creation of teacher data used for re-inspection of an examination object, and provides an image of an examination object determined in advance to be defective. an abnormality data acquisition unit for acquiring the abnormal data indicated by the abnormal data acquisition unit; Based on the difference data generated by the difference data generation unit and a difference data generation unit that generates difference data indicating a difference between the acquired abnormal data and the normal data acquired by the normal data acquisition unit so as to correspond to the abnormal data , a presentation unit for presenting an image of a portion of the inspection object.

In this teacher data creation support apparatus, based on the difference data indicating the difference between abnormal data indicating the image of the inspection object determined in advance to be defective and normal data indicating the image of the normal inspection object, the part of the inspection object is An image is presented. The part of the inspection object in the image that appears based on the difference data is highly likely to require re-inspection. Therefore, by confirming the presented image, the user can create teacher data for re-inspecting the part. In this way, it is possible to easily create teacher data for performing an examination with high precision.

(2) The teacher data creation support apparatus may further include a reception unit for accepting selection of the difference data presented by the presentation unit, and a registration unit for registering the difference data for which the selection is accepted by the reception unit as teacher data. In this case, the difference data selected by the user is registered as the teacher data. Thereby, teacher data can be more easily created.

(3) The acceptance unit may further accept correction of the difference data presented by the presentation unit, and the registration unit may register the corrected difference data as teacher data. In this case, it becomes possible to correct more appropriately the part which requires re-inspection of the inspection object in the image based on the difference data. In this way, it is possible to create teacher data for performing the examination with higher precision.

(4) The normal data acquisition unit acquires a plurality of normal data so as to correspond to the abnormal data, and the difference data generation unit generates a plurality of difference data based on the abnormal data and the plurality of normal data corresponding to the abnormal data. do. In this case, a plurality of difference data is generated from one abnormal data. Thereby, it is possible to improve the work efficiency of creating teacher data.

(5) The normal data acquisition unit acquires a plurality of normal data so as to correspond to the abnormal data, and the difference data generation unit generates difference data based on the average of the abnormal data and the plurality of normal data corresponding to the abnormal data. do. According to this configuration, even when a noise component unrelated to a defect is accidentally mixed in any of the plurality of normal data, since the plurality of normal data are averaged, the noise component has almost no effect on the pixel value of the normal data after averaging. don't give Therefore, it is possible to create teacher data for performing the examination with higher precision.

(6) The normal data acquisition unit may acquire normal data so as to correspond to a plurality of abnormal data, and the difference data generation unit may generate difference data based on each abnormal data and the normal data corresponding to the abnormal data. In this case, teacher data can be created at high speed using common normal data.

(7) The normal data acquired by the normal data acquisition part may contain image data which shows the image of the inspection object which has not previously been judged as defective. In this case, normal data representing an image of a normal inspection object can be easily acquired.

(8) The normal data acquired by the normal data acquisition part may contain the master data which shows the design drawing of an inspection object. In this case, normal data representing an image of a normal inspection object can be easily acquired.

(9) The normal data acquisition unit may acquire the master data corrected based on the processing precision of an inspection object as normal data. According to this configuration, even when the inspection subject region is fine, it is possible to easily acquire normal data representing an image of a normal inspection subject.

(10) A non-inspection target region is set in the abnormal data acquired by the abnormal data acquisition unit and the normal data acquired by the normal data acquisition unit, and the difference data generating unit generates difference data except for the set non-inspection target region. You can create In this case, it is prevented that a portion other than the inspection subject area is included in the image indicated by the difference data. In this way, it is possible to create teacher data for performing the examination with higher precision.

(11) The abnormality data acquisition unit further acquires defect information indicating the type of a defect on the inspection object corresponding to the acquired abnormality data, and the difference data generation unit generates the defect information acquired by the abnormality data acquisition unit. You may provide to difference data. In this case, the user does not need to perform the task of providing defect information to the teacher data. Accordingly, it is possible to reduce the burden on the user and improve the work efficiency of creating teacher data. Moreover, since a mistake accompanying the user's work does not occur, more accurate teacher data can be created.

(12) The abnormal data acquisition unit may acquire the binarized abnormal data, and the normal data acquisition unit may acquire the binarized normal data. In this case, since the data amount of abnormal data and normal data is reduced, teacher data can be created at high speed.

(13) A teacher data creation support method according to another aspect of the present invention is a teacher data creation support method that supports creation of teacher data used for re-inspection of an inspection object, wherein an image of an inspection object determined in advance to be defective is provided. A difference between the acquired abnormal data and the normal data acquired to correspond to the abnormal data, the step of acquiring the abnormal data shown, and the step of acquiring the normal data which shows the image of a normal inspection object in correspondence with the acquired abnormal data It includes a step of generating difference data representing

According to this teacher data creation support method, based on the difference data indicating the difference between abnormal data indicating an image of an inspection object determined in advance to be defective and normal data indicating an image of a normal inspection object, An image is presented. The part of the inspection object in the image that appears based on the difference data is highly likely to require re-inspection. Therefore, by confirming the presented image, the user can create teacher data for re-inspecting the part. In this way, it is possible to easily create teacher data for performing an examination with high precision.

BRIEF DESCRIPTION OF THE DRAWINGS It is a figure which shows the structure of the processing system which includes the support apparatus which concerns on 1st Embodiment of this invention.
FIG. 2 is a diagram showing the configuration of the support device of FIG. 1 .
Fig. 3 is a diagram showing various types of data used to create teacher data.
Fig. 4 is a diagram showing an example of a display screen of a display device in creation of teacher data.
FIG. 5 is a flowchart showing support processing by the support apparatus of FIG. 2 .
Fig. 6 is a diagram showing various types of data used for creating teacher data in the first modification.
Fig. 7 is a diagram showing various types of data used for creation of teacher data in the second modification.
Fig. 8 is a diagram showing various types of data used for creating teacher data in the third modification.
Fig. 9 is a diagram showing various types of data used for creating teacher data in the second embodiment.
Fig. 10 is a diagram showing various types of data used for creating teacher data in the third embodiment.
Fig. 11 is a diagram showing various types of data used to create teacher data in the fourth embodiment.

[1] First embodiment

(1) processing system

Hereinafter, a teacher data creation support apparatus and a teacher data creation support method according to an embodiment of the present invention will be described with reference to drawings. In the following description, the teacher data creation support device is abbreviated as a support device. BRIEF DESCRIPTION OF THE DRAWINGS It is a figure which shows the structure of the processing system which includes the support apparatus which concerns on 1st Embodiment of this invention. 1 , the processing system 100 includes a processing device 10 , an inspection device 20 , and a database storage device 30 .

The processing unit 10 includes a CPU (Central Processing Unit) 11 , a RAM (Random Access Memory) 12 , a ROM (Read Only Memory) 13 , a storage device 14 , an operation unit 15 , and a display. It is constituted by a device 16 and an input/output I/F (interface) 17 . The CPU 11 , the RAM 12 , the ROM 13 , the storage device 14 , the operation unit 15 , the display device 16 , and the input/output I/F 17 are connected to the bus 18 .

The RAM 12 is used as a work area of the CPU 11 . The ROM 13 stores a system program. The storage device 14 includes a storage medium such as a hard disk or a semiconductor memory, and stores a teacher data creation support program (hereinafter, abbreviated as support program). The support program may be stored in the ROM 13 or another external storage device. A support device 40 for executing teacher data creation support processing (hereinafter, abbreviated as support processing) is constituted by the CPU 11 , the RAM 12 , and the ROM 13 . In the support process, creation of teacher data is supported.

The operation unit 15 is an input device such as a keyboard, a mouse, or a touch panel. The user can give a predetermined instruction to the support device 40 by operating the operation unit 15 . The display apparatus 16 is a display device, such as a liquid crystal display apparatus, and displays GUI (Graphical User Interface) etc. for accepting the instruction|indication by a user. The input/output I/F 17 is connected to the inspection device 20 .

The inspection apparatus 20 is an AOI (automatic optical inspection) apparatus, for example, by sequentially imaging the inspection object to generate a plurality of image data respectively representing images of the plurality of inspection objects, and each generated image data remember Each stored image data is assigned a unique identification number.

Hereinafter, although the test|inspection apparatus 20 is demonstrated using a board|substrate as an example of a test|inspection object, the test|inspection object is not limited to a board|substrate. In addition, the substrate is a semiconductor substrate, a substrate for a flat panel display (FPD) such as a liquid crystal display device or an organic EL (Electro Luminescence) display device, a substrate for an optical disk, a substrate for a magnetic disk, a substrate for a magneto-optical disk, a substrate for a photomask It refers to a substrate, a ceramic substrate, or a substrate for solar cells.

The inspection apparatus 20 inspects the substrate corresponding to each image data by performing a process based on a predetermined algorithm on each stored image data. The inspection apparatus 20 may test|inspect the board|substrate corresponding to each image data based on deep learning. In the inspection, it is determined whether or not there is a defect in the substrate. In addition, about the board|substrate determined as having a defect, the type of the said defect is determined.

In the inspection apparatus 20, even if it is a board|substrate without a defect, it may determine with a defect. If the substrate is discarded due to an erroneous judgment being made despite the absence of defects, the yield is lowered. Then, about the board|substrate judged to have a defect, the re-inspection by teacher presence learning is implemented. The support device 40 supports creation of teacher data used for retesting. The database storage device 30 includes a large-capacity storage device such as a server. In the database storage device 30, the created teacher data is registered. Hereinafter, the detail of the support apparatus 40 is demonstrated.

(2) Supported devices

FIG. 2 is a diagram showing the configuration of the support device 40 of FIG. 1 . Fig. 3 is a diagram showing various types of data used to create teacher data. 4 is a diagram showing an example of a display screen of the display device 16 in creation of teacher data. As shown in FIG. 2 , the support device 40 is a functional unit, and includes an abnormal data acquisition unit 41 , a normal data acquisition unit 42 , a difference data generation unit 43 , a presentation unit 44 , and an acceptance unit 45 . ) and a register 46 . When the CPU 11 in FIG. 1 executes the support program stored in the ROM 13 or the storage device 14 or the like, the functional portion of the support device 40 is realized. Some or all of the functional units of the support device 40 may be realized by hardware such as an electronic circuit.

The abnormality data acquisition part 41 acquires from the inspection apparatus 20 the image data (henceforth called abnormality data) which shows the image of each board|substrate which was previously determined by the inspection apparatus 20 to have a defect. The image data may represent the image of the whole board|substrate, and may represent the partial image of a board|substrate as long as it is the same area|region. In the upper left part of FIG. 3, a part of the image of the board|substrate based on the abnormality data acquired by the abnormality data acquisition part 41 appears.

The normal data acquisition unit 42 acquires image data (hereinafter referred to as normal data) representing an image of a normal substrate so as to correspond to each abnormal data acquired by the abnormal data acquisition unit 41 . In this example, normal data is acquired from the inspection apparatus 20 as predetermined image data which shows the image of the board|substrate which has not previously been judged as defective by the inspection apparatus 20 . In the lower left of FIG. 3 , a part of the image of the substrate based on the normal data acquired by the normal data acquisition unit 42 is shown.

Abnormal data and normal data correspond to each other. For example, when abnormal data is acquired by the abnormal data acquisition unit 41, image data having an identification number one previous to the identification number of the abnormal data and representing an image of a normal substrate is acquired as normal data. It may be acquired by the unit 42 . Alternatively, when abnormal data is acquired by the abnormal data acquisition unit 41, image data having an identification number after one of the identification numbers of the abnormal data and representing an image of a normal substrate is used as normal data by the normal data acquisition unit ( 42) may be obtained.

The difference data generation unit 43 calculates the difference between the pixel values of the abnormal data acquired by the abnormal data acquisition unit 41 and the normal data acquired by the normal data acquisition unit 42 so as to correspond to the abnormal data. By calculating, new image data is generated. The image data generated by the difference data generating unit 43 is called difference data. In the right part of FIG. 3 , an image of the substrate based on the difference data generated by the difference data generating unit 43 appears. The difference data represents an image of a portion of the substrate that is likely to require re-inspection. Therefore, the difference data can be a label indicating a portion of the substrate that requires re-inspection.

The presentation unit 44 displays, on the display device 16, a GUI 50 (FIG. 4) including an image based on each difference data generated by the difference data generation unit 43, thereby displaying each difference data to the user. present to As shown in FIG. 4 , GUI 50 includes an image display area 51 , a registration button 52 , and a correction button 53 . A plurality of images of the measurement target are displayed in the image display area 51 . In this example, the image based on the difference data is displayed on the image display area 51 so that it overlaps with the image based on the abnormal data, but only the image based on the difference data may be displayed on the image display area 51 .

The accepting unit 45 accepts an instruction to register difference data. Specifically, the accepting unit 45 accepts from the operation unit 15 the selection of difference data to be registered as teacher data in the GUI 50 displayed by the presenting unit 44 . The user selects an arbitrary image using the operation unit 15 while visually recognizing the image displayed on the image display area 51 , and operates the registration button 52 to select difference data representing the image as teacher data. instruction can be given to the reception unit 45 . The registration unit 46 registers, in the database storage device 30, the difference data whose selection is accepted by the accepting unit 45 as teacher data.

In addition, the accepting unit 45 can accept correction of the difference data. The user selects an arbitrary image in the image display area 51 using the operation unit 15 and operates the correction button 53 to instruct the accepting unit 45 to correct the difference data corresponding to the image in question. can do. Further, in the selected image, the user can use the operation unit 15 to designate, such as filling in the entire portion that requires re-inspection.

When the designation is accepted by the accepting section 45, the difference data generating section 43 gives the selected difference data a label indicating the portion for which the designation has been accepted. Thereby, the difference data is corrected. When the registration button 52 is operated after the correction of the difference data is performed, the registration unit 46 registers the corrected difference data as teacher data in the database storage device 30 .

(3) Support processing

FIG. 5 is a flowchart showing support processing by the support device 40 in FIG. 2 . The support processing in FIG. 5 is performed by the CPU 11 in FIG. 1 executing the support program stored in the ROM 13 or the storage device 14 or the like on the RAM 12 . Hereinafter, the support process will be described using the support device 40 in FIG. 2 and the flowchart in FIG. 5 .

First, the abnormality data acquisition part 41 acquires each abnormality data from the inspection apparatus 20 (step S1). Next, the normal data acquisition part 42 acquires normal data corresponding to each abnormal data acquired in step S1 from the inspection apparatus 20 (step S2). Steps S1 and S2 may be executed simultaneously.

Then, the difference data generation unit 43 generates each difference data based on the abnormal data and the normal data corresponding to each other obtained in steps S1 and S2, respectively (step S3). Thereafter, the presentation unit 44 presents each difference data to the user by displaying an image based on each difference data generated in step S3 on the display device 16 (step S4).

Next, the accepting unit 45 determines which difference data correction among the difference data presented in step S4 has been accepted (step S5). If the correction of the difference data is not accepted, the accepting unit 45 proceeds to step S7. When correction of a certain difference data is accepted, the difference data generation unit 43 corrects the difference data by giving the difference data a label indicating the part for which the specification of correction has been accepted (step S6), and proceeds to step S7. do.

In step S7, the accepting unit 45 determines whether registration of which difference data has been instructed among the difference data presented in step S4 or the difference data corrected in step S6 (step S7). When registration of difference data is not instructed, the accepting unit 45 proceeds to step S9. When registration of a certain difference data is instructed, the registration unit 46 registers the instructed difference data as teacher data in the database storage device 30 (step S8), and proceeds to step S9.

In step S9, the registration unit 46 determines whether an end has been instructed (step S9). The user can instruct the end or continuation by performing a predetermined operation using the operation unit 15 . If the end is not instructed, the registration unit 46 returns to step S5. In the case of additionally registering difference data, the user instructs continuation without instructing the end. When the end is instructed, the registration unit 46 ends the support process.

(4) effect

In the support apparatus 40 which concerns on this embodiment, the abnormality data which shows the image of the test|inspection object judged in advance to have a defect is acquired by the abnormality data acquisition part 41. As shown in FIG. Normal data representing an image of a normal inspection object is acquired by the normal data acquisition unit 42 so as to correspond to the abnormal data acquired by the abnormal data acquisition unit 41 . Difference data indicating a difference between the abnormal data acquired by the abnormal data acquiring unit 41 and the normal data acquired by the normal data acquiring unit 42 so as to correspond to the abnormal data is generated by the difference data generating unit 43 is created The part of the inspection object in the image that appears based on the difference data is highly likely to require re-inspection.

Therefore, based on the difference data generated by the difference data generation unit 43 , the image of the portion of the inspection object is presented by the presentation unit 44 . The selection of the difference data presented by the presenting unit 44 is accepted by the accepting unit 45 . The difference data for which the selection is accepted by the accepting unit 45 is registered in the database storage device 30 by the registering unit 46 as teacher data. In this case, the user can register the selected difference data as teacher data by selecting the difference data corresponding to the desired image while viewing the presented image. Thereby, teacher data can be more easily created.

In addition, the accepting unit 45 further accepts correction of the difference data presented by the presenting unit 44 . The registration unit 46 registers the corrected difference data as teacher data. In this case, it becomes possible for a user to correct more appropriately the part which requires re-inspection of the inspection object in the image based on the difference data. In this way, it is possible to create teacher data for performing the examination with higher precision.

(5) Modifications

Fig. 6 is a diagram showing various types of data used for creating teacher data in the first modification. In the first modification, the user can register in advance a non-inspection target area indicating outside the examination target area with the examination apparatus 20 . When the non-inspection target area is registered, the inspection apparatus 20 sets the non-inspection target area in the generated image data.

Therefore, as shown in the upper left part of FIG. 6, a non-inspection target area|region is set in the abnormality data acquired by the abnormality data acquisition part 41. As shown in FIG. Similarly, as shown in the lower left part of FIG. 6, a non-inspection target area|region is set in the normal data acquired by the normal data acquisition part 42. As shown in FIG. In this case, as shown in the right part of FIG. 6 , the difference data generating unit 43 is a difference between the abnormal data and each pixel value of the normal data corresponding to the abnormal data in a state excluding the set non-inspection target region. By calculating , difference data is generated. The pixel value of the non-inspection target region in the difference data may be 0.

In this case, it is prevented that a label indicating a portion requiring re-inspection is attached to a portion other than the area to be inspected. In this way, it is possible to create teacher data for performing the examination with higher precision. In addition, since parts other than the area to be inspected are not re-inspected, by using the created teacher data, the board can be re-inspected at high speed.

Fig. 7 is a diagram showing various types of data used for creation of teacher data in the second modification. As shown in the upper left part of FIG. 7, the abnormality data acquisition part 41 acquires defect information which shows the type of the defect of the board|substrate in the image which the said abnormality data shows with abnormality data. The difference data generation part 43 gives the defect information acquired by the abnormality data acquisition part 41 to the produced|generated difference data, as shown in the right part of FIG. In the image display area 51 of GUI50, the image based on difference data may appear in the aspect (for example, color) which shows the type of a defect.

In this case, the user does not need to perform the task of providing defect information to the teacher data. Accordingly, it is possible to reduce the burden on the user and improve the work efficiency of creating teacher data. Moreover, since a mistake accompanying the user's work does not occur, more accurate teacher data can be created.

Fig. 8 is a diagram showing various types of data used for creating teacher data in the third modification. In the third modification, the user can set in advance in the inspection apparatus 20 that image data is subjected to binarization processing. When performing the binarization process is set, the inspection apparatus 20 produces|generates binarized image data.

Therefore, as shown in the upper left part of FIG. 8, the abnormal data acquisition part 41 acquires the binarization-processed abnormal data. Similarly, as shown in the lower left part of FIG. 8, the normal data acquisition part 42 acquires the normal data by which the binarization process was carried out. The difference data generation unit 43 generates difference data by calculating the difference between the pixel values of the binarized abnormal data and the binarized normal data corresponding to the abnormal data, as shown in the right part of Fig. 8 . do.

In this case, since the data amount of image data is reduced, teacher data can be created at high speed. In addition, by using the created teacher data, it is possible to perform re-inspection of the board at high speed.

[2] Second embodiment

In the first embodiment, the normal data acquisition unit 42 acquires normal data so that one normal data corresponds to one abnormal data, but the embodiment is not limited to this. Hereinafter, a point different from the support process in 1st Embodiment is demonstrated about the support process in 2nd - 4th embodiment.

Fig. 9 is a diagram showing various types of data used for creating teacher data in the second embodiment. In this embodiment, as shown in the lower left part of FIG. 9, some normal data is acquired so that some normal data may correspond with respect to one abnormal data. The difference data generation unit 43 generates difference data by calculating the difference between each pixel value of one abnormal data and each normal data corresponding to the abnormal data. Therefore, as shown in the right part of FIG. 9, a plurality of difference data is generated corresponding to one abnormal data.

According to this configuration, a plurality of difference data is generated from one abnormal data. Thereby, it is possible to improve the work efficiency of creating teacher data.

[3] Third embodiment

Fig. 10 is a diagram showing various types of data used for creating teacher data in the third embodiment. In this embodiment, as shown in the lower left part of FIG. 10, some normal data is acquired so that some normal data may correspond with respect to one abnormal data. The difference data generation unit 43 generates difference data by calculating the difference between each pixel value of the average of one abnormal data and a plurality of normal data corresponding to the abnormal data. Accordingly, as shown in the right part of FIG. 10 , one piece of difference data is generated corresponding to one piece of abnormal data.

According to this configuration, even when a noise component unrelated to a defect is accidentally mixed in any of the plurality of normal data, since the plurality of normal data are averaged, the noise component has almost no effect on the pixel value of the normal data after averaging. don't give Therefore, by using the normal data after averaging, it is possible to create teacher data for testing with higher precision.

[4] Fourth embodiment

Fig. 11 is a diagram showing various types of data used to create teacher data in the fourth embodiment. In this embodiment, as shown in the upper left part of FIG. 11, normal data is acquired so that one normal data may correspond to a plurality of abnormal data. The difference data generation unit 43 generates difference data based on each abnormal data and normal data corresponding to the abnormal data. Therefore, as shown in the right part of FIG. 11, a plurality of difference data respectively corresponding to a plurality of abnormal data are generated.

According to this configuration, since it is not necessary to acquire normal data each time abnormal data is acquired, it is possible to create teacher data at high speed using common normal data. In the present embodiment, image data representing an image of a normal substrate prepared in advance may be acquired by the normal data acquisition unit 42 as normal data. In this case, step S2 in the support process may be executed before step S1.

The image data prepared in advance may be any of the image data generated by the inspection apparatus 20, but may be master data such as CAD data showing a design drawing of the substrate. Here, depending on the processing precision of the board|substrate by etching etc., the pattern width of the board|substrate in an image, the curvature radius of the edge part of a pattern, etc. differ between the image data and master data generated by the inspection apparatus 20. FIG. Then, the master data may be corrected based on the processing precision of a board|substrate so that the pattern width in an image, the curvature radius of the edge part of a pattern, etc. may be changed.

In addition, also in the first to third embodiments, image data representing an image of a substrate not previously determined to be defective by the inspection apparatus 20 is acquired from the inspection apparatus 20 as normal data, but in the embodiment It is not limited to this. At least one of the normal data may be master data prepared in advance or master data corrected.

[5] Another embodiment

In the above embodiment, the support device 40 includes the reception unit 45 and the registration unit 46, but the embodiment is not limited to this. The support device 40 does not need to include the reception unit 45 and the registration unit 46 . Also in this case, by confirming the image presented on the GUI 50, the user becomes possible to create the teacher data for re-inspecting the said part. In this way, it is possible to easily create teacher data for performing an examination with high precision.

[6] Correspondence between each component of the claim and each part of the embodiment

Hereinafter, although the example of correspondence of each element of a claim and each element of embodiment is demonstrated, this invention is not limited to the following example. As each component of the claim, various other elements having the structure or function described in the claim may be used.

In the above embodiment, the support device 40 is an example of the teacher data creation support device, the abnormal data acquisition unit 41 is an example of the abnormal data acquisition unit, and the normal data acquisition unit 42 is an example of the normal data acquisition unit. . The difference data generating unit 43 is an example of the difference data generating unit, the presenting unit 44 is an example of the presenting unit, the accepting unit 45 is an example of the accepting unit, and the registering unit 46 is an example of the registering unit.

Claims (13)

A teacher data creation support device that supports creation of teacher data used for re-inspection of an object to be tested, comprising:
an abnormality data acquisition unit configured to acquire abnormality data indicating an image of an inspection object determined in advance to have a defect;
a normal data acquisition unit which acquires normal data representing an image of a normal inspection object so as to correspond to the abnormal data acquired by the abnormal data acquisition unit;
a difference data generating unit for generating difference data indicating a difference between the abnormal data acquired by the abnormal data acquiring unit and the normal data acquired by the normal data acquiring unit so as to correspond to the abnormal data;
and a presenting unit for presenting an image of a portion of the test subject based on the difference data generated by the difference data generating unit. The method of claim 1,
a receiving unit for receiving selection of the difference data presented by the presenting unit;
and a registration unit that registers, as teacher data, the difference data for which the selection is accepted by the reception unit. 3. The method of claim 2,
The receiving unit further receives correction of the difference data presented by the presenting unit,
The registration unit registers the corrected difference data as teacher data. 4. The method according to any one of claims 1 to 3,
The normal data acquisition unit acquires a plurality of normal data to correspond to the abnormal data,
The teacher data creation support apparatus, wherein the difference data generation unit generates a plurality of difference data based on the abnormal data and a plurality of normal data corresponding to the abnormal data. 4. The method according to any one of claims 1 to 3,
The normal data acquisition unit acquires a plurality of normal data to correspond to the abnormal data,
The difference data generating unit generates difference data based on an average of the abnormal data and a plurality of normal data corresponding to the abnormal data. 4. The method according to any one of claims 1 to 3,
The normal data acquisition unit acquires normal data to correspond to a plurality of abnormal data,
The difference data generation unit generates difference data based on each abnormal data and normal data corresponding to the abnormal data. 4. The method according to any one of claims 1 to 3,
The normal data acquired by the said normal data acquisition part contains image data which shows the image of the test object which has not previously been judged as defective. 4. The method according to any one of claims 1 to 3,
The normal data acquired by the said normal data acquisition part contains master data which shows the design drawing of an examination object, The teacher data creation support apparatus. 9. The method of claim 8,
The teacher data creation support device, wherein the normal data acquisition unit acquires, as normal data, the master data corrected based on the processing accuracy of the inspection object. 4. The method according to any one of claims 1 to 3,
A non-inspection target area is set in the abnormal data acquired by the abnormal data acquisition unit and the normal data acquired by the normal data acquisition unit;
The difference data generating unit is configured to generate difference data except for a set non-inspection target area. 4. The method according to any one of claims 1 to 3,
The abnormality data acquisition unit further acquires defect information indicating the type of defect on the inspection object corresponding to the acquired abnormality data,
The teacher data creation support apparatus, wherein the difference data generation unit gives the defect information acquired by the abnormality data acquisition unit to the generated difference data. 4. The method according to any one of claims 1 to 3,
The abnormal data acquisition unit acquires binarized abnormal data,
The teacher data creation support device, wherein the normal data acquisition unit acquires normal data that has been binarized. A teacher data creation support method for supporting creation of teacher data used for re-inspection of an object to be inspected, the method comprising:
A step of acquiring abnormal data indicating an image of an inspection object determined in advance to have a defect;
a step of acquiring normal data representing an image of a normal inspection object so as to correspond to the acquired abnormal data;
generating difference data indicating a difference between the acquired abnormal data and the normal data acquired to correspond to the abnormal data;
A teacher data creation support method comprising the step of presenting an image of a portion of an examination object based on the generated difference data.

Images