Solder inspection device and solder inspection method

Abstract

The present invention makes it possible to reduce labor and burden for obtaining an identification means serving as an AI model, and to enable the identification means to be used in common even when the sizes of lands are different. Image data for inspection, which is based on image data acquired by a camera 32d, is inputted to an AI model 101-103 generated by training a prescribed neural network using only image data relating to non-defective cream solder as training data, and reconstructed image data is acquired. The image data for inspection and the reconstructed image data are compared to determine the quality of cream solder. The training data is obtained by providing one solder region image showing the cream solder corresponding to one land to an image frame having a size greater than the size of the one solder region image. The image data for inspection is obtained by providing one solder region image extracted from the image data acquired by the camera 32d to an image frame of the same size as the image frame for the training data.

Description

Solder inspection device and solder inspection method

[0001] The present invention relates to a solder inspection device and a solder inspection method for inspecting solder provided on a substrate.

[0002] Generally, in a board manufacturing line where electronic components are mounted on a printed circuit board, cream solder is first printed on the lands of the printed circuit board (solder printing process). Next, the electronic components are temporarily attached to the printed circuit board using the viscosity of the cream solder (mounting process). After that, the printed circuit board is introduced into a reflow furnace, where the cream solder is heated and melted to complete the soldering (reflow process). Such board manufacturing lines may be equipped with an inspection device that inspects the printed circuit board.

[0003] Recently, inspection devices using AI models have been proposed for inspecting printed circuit boards. For example, an inspection device using an AI model is known that inspects the presence or absence of foreign matter on a printed circuit board by comparing inspection image data (original image data) of an inspection area on the printed circuit board with reconstructed image data generated by inputting the inspection image data into an AI model (identification means) (see, for example, Patent Document 1).

[0004] Furthermore, in the inspection of printed circuit boards, cream solder may be inspected by determining, for example, the shape (two-dimensional or three-dimensional shape) of the cream solder, whether or not foreign matter is attached to the cream solder, etc. Therefore, it is conceivable to inspect cream solder using the AI ​​model described above.

[0005] The configuration of printed circuit boards varies depending on the type of board. To enable the AI ​​model to inspect a wider variety of printed circuit boards, it is effective to acquire inspection image data related to the cream solder for each land and use this inspection image data for inspection. This is because the configuration (shape, size, etc.) of the land and the cream solder printed on the land often do not vary significantly between various types of printed circuit boards.

[0006] When acquiring inspection image data of the cream solder for each land, it is preferable that the size (width and height) of the acquired inspection image data does not extend beyond the land. For example, as shown in Figures 31 and 32, it is preferable that the size of the inspection image data matches the size of the land 3 (e.g., the size of the rectangle indicated by the thick line in Figures 31 and 32). In Figure 31, etc., a scattered dot pattern is applied to the cream solder 5. By using such inspection image data, the influence of the cream solder, circuit pattern, resist, etc. present around the land can be reduced.

[0007] Furthermore, in terms of improving inspection accuracy, it is preferable to match the size (width and height) of the training data with the size of the inspection image data. While it is possible to match the sizes of the training data and the inspection image data by enlarging or reducing the image data, for example, the standard land size for a typical component size "0603" is 0.25 to 0.35 mm wide x 0.30 to 0.40 mm high. Therefore, because the diameter of the particles that make up the cream solder (e.g., an average particle size of approximately 30 μm) is relatively large, matching the sizes of the two image data by enlarging or reducing them may result in a decrease in inspection accuracy. Therefore, in terms of improving inspection accuracy, it is possible to match the size of both image data with the size of the land, prepare multiple AI models that learn different training data for each land size (i.e., the size of both image data), and then select an appropriate AI model from the multiple AI models during inspection based on the size of the inspection image data (i.e., the size of the land), and use the selected AI model to determine the quality of the cream solder.

[0008] Japanese Patent Application Laid-Open No. 2022-88818

[0009] However, even lands on which the same type of component is mounted may not have uniform sizes but may vary slightly. For example, two types of printed circuit boards each having lands on which the same component is mounted may have slightly different land sizes. Therefore, preparing different AI models for each land size requires complex work, which may require a great deal of effort and time.

[0010] The present invention has been made in consideration of the above circumstances, and its purpose is to provide a solder inspection device or the like that can reduce the effort and burden involved in obtaining an identification means as an AI model, and that allows the identification means to be used in common even when the land sizes are different.

[0011] The following describes each of the means suitable for achieving the above object, with specific effects of the corresponding means added as necessary.

[0012] Means 1. A solder inspection device for inspecting cream solder printed on a printed circuit board, comprising: image data acquisition means capable of acquiring image data of a predetermined inspection area on the printed circuit board including the cream solder printed portion; discrimination means which generates training data by having a neural network having an encoding unit which extracts feature amounts from input image data and a decoding unit which reconstructs image data from the feature amounts learn only image data relating to good cream solder; inspection image data acquisition means which acquires inspection image data including an image of the cream solder to be inspected based on the image data acquired by the image data acquisition means; reconstructed image data acquisition means which is capable of inputting the inspection image data to the discrimination means and acquiring reconstructed image data as reconstructed image data; and comparison means which is capable of comparing the inspection image data and the reconstructed image data, and is configured to be able to determine the quality of the cream solder based on the comparison result by the comparison means, and the training data consists of one solder area image showing cream solder corresponding to one land, arranged in an image frame larger than the size of the one solder area image, The solder inspection device is characterized in that the inspection image data acquisition means acquires the inspection image data of the same size as the learning data, in which the one solder area image extracted from the image data acquired by the image data acquisition means is placed in an image frame of the same size as the image frame of the learning data.

[0013] Note that one solder area image may be an image showing the entire cream solder lump portion, at least a portion of which is located on one land (images of means 2 and 3 described below), or an image showing only the portion of the cream solder lump portion that is present on one land. The former image will be an image of the entire cream solder including the protruding portion if the cream solder protrudes from one land. On the other hand, the latter image will be an image of only a portion of the cream solder excluding the protruding portion if the cream solder protrudes from one land. Furthermore, one solder area image may be one that corresponds to one land, and may include not only an image consisting of one lump portion, but also an image consisting of multiple lump portions.

[0014] In addition, one solder area image constituting the learning data may be extracted from image data (actual image data) obtained by capturing an image of a printed circuit board on which good cream solder has been printed (i.e., an image of the actual cream solder), or may be a virtually generated image of good cream solder. Examples of the actual image data include image data accumulated in previous inspections and image data of good printed circuit boards visually selected by an operator after cream solder has been printed.

[0015] Furthermore, the "neural network" includes, for example, a convolutional neural network having multiple convolutional layers. The "learning" includes, for example, deep learning. The "identification means (generative model)" includes, for example, an autoencoder and a convolutional autoencoder.

[0016] In addition, the "identification means" is generated by learning only image data relating to good cream solder (learning data consisting of one solder area image relating to good cream solder arranged in an image frame). Therefore, the reconstructed image data generated when inspection image data relating to defective cream solder is input to the identification means will be approximately identical to the inspection image data in which the defective part has been corrected (for example, foreign matter has been removed, or the shape, size, etc. have been corrected). In other words, when there is a defective part in the cream solder, virtual image data relating to the cream solder assuming that there is no defective part is generated as the reconstructed image data relating to the cream solder.

[0017] According to the above-mentioned means 1, the inspection image data is formed by placing one solder area image extracted from the image data acquired by the image data acquisition means in an image frame. Therefore, the size (width and height) of the inspection image data does not vary depending on the land size, but remains constant. This eliminates the need to prepare multiple different identification means for each land size, reducing the labor and time required to obtain the identification means. Furthermore, the identification means can be used in common even when the land sizes are different.

[0018] Furthermore, according to the above-mentioned means 1, the image frame of the learning data and the image frame of the test image data are the same size, and the sizes of the learning data and the test image data are the same. Therefore, when the test image data is input to the identification means, appropriate reconstructed image data corresponding to the test image data can be more reliably output, and ultimately the quality of the cream solder can be more accurately determined. This makes it possible to more reliably obtain good test accuracy.

[0019] In addition, according to the above-mentioned method 1, the inspection image data is compared with reconstructed image data obtained by inputting the inspection image data into the identification means and reconstructing the image data, and the quality of the cream solder is determined based on the comparison results. Therefore, both sets of compared image data relate to the same cream solder. Therefore, unlike a method of determining quality by comparison with a separately prepared standard, it is not necessary to set relatively loose inspection conditions to prevent false detection, and stricter inspection conditions can be set. Furthermore, the imaging conditions of the printed circuit board to be inspected (e.g., the position, angle, and deflection of the printed circuit board) and the imaging conditions of the inspection device (e.g., lighting conditions, camera angle, etc.) can be matched between the two sets of compared image data. This combination allows for more accurate quality determination of the cream solder.

[0020] Means 2. The solder inspection device according to Means 1, further comprising a solder area image extraction means for extracting the one solder area image constituting the inspection image data from the image data acquired by the image data acquisition means, wherein the solder area image extraction means is capable of identifying an area occupied by cream solder in the image data acquired by the image data acquisition means, and extracting an image of connected components in the identified area as the one solder area image constituting the inspection image data.

[0021] According to the above-mentioned means 2, the solder area image extraction means identifies the area occupied by the cream solder in the image data acquired by the image data acquisition means, and extracts an image of the connected components in the identified area as one solder area image constituting the inspection image data. Therefore, one solder area image includes not only an image of the part of the cream solder located on the land, but also an image of the part of the cream solder that protrudes from the land. In other words, even if the cream solder 5 protrudes from the land 3 as shown in Figures 33 and 34, one solder area image Ih will include this protruding part as shown in Figures 35 and 36. This makes it possible to properly determine the quality of cream solder that has partially protruded from the land, further improving inspection accuracy.

[0022] Means 3. The solder inspection device according to Means 2, wherein the solder area image extraction means is capable of extracting, from among the connected components, an entire image of an element that at least partially overlaps with one land in the design data or manufacturing data, as the one solder area image that constitutes the inspection image data.

[0023] According to the above-mentioned means 3, when the cream solder printed on one land is separated into multiple pieces, the first solder area image includes an image of the entire cream solder separated into multiple pieces. Therefore, for example, when the cream solder 5 printed on one land 3 is separated into two pieces as shown in Fig. 37, the first solder area image Ih is an image that includes the entire cream solder 5 separated into two pieces as shown in Fig. 38. This makes it possible to more appropriately judge the quality of the cream solder even if the cream solder printed on one land is separated into multiple pieces.

[0024] Means 4. A solder inspection device according to Means 1, characterized in that it comprises second discrimination means generated by having a neural network having an encoding unit that extracts feature amounts from input image data and a decoding unit that reconstructs image data from the feature amounts learn only image data relating to non-defective cream solder as second learning data, the second learning data having the one solder area image arranged in a second image frame that is larger than the size of the one solder area image but smaller than the size of the image frame of the learning data, when the size of the one solder area image extracted from the image data acquired by the image data acquisition means is smaller than the size of the second image frame, the inspection image data acquisition means acquires the inspection image data of the same size as the second learning data, the one solder area image arranged in the second image frame, the reconstructed image data acquisition means inputs the inspection image data to the second discrimination means to acquire the reconstructed image data, and the comparison means is configured to compare the inspection image data and the reconstructed image data.

[0025] According to the above-mentioned means 4, when the size of one solder area image is relatively small, the inspection image data acquisition means acquires inspection image data of a relatively small size, in which one solder area image is arranged in a relatively small second image frame. Then, the reconstructed image data acquisition means inputs this relatively small inspection image data to the second identification means, which outputs the reconstructed image data, and the comparison means compares the relatively small inspection image data and the reconstructed image data. Therefore, compared to when the image frame of the inspection image data is always a fixed size, the process for acquiring the reconstructed image data and the comparison process by the comparison means can be speeded up, and ultimately the inspection speed can be further improved.

[0026] Means 5. A solder inspection device according to Means 1, characterized in that it comprises a circular correspondence discrimination means generated by having a neural network having an encoding unit that extracts feature amounts from input image data and a decoding unit that reconstructs image data from the feature amounts learn only image data pertaining to non-defective cream solder printed on circular lands as circular correspondence learning data, the circular correspondence learning data being formed by providing the one solder area image pertaining to non-defective cream solder printed on circular lands in a circular correspondence image frame that is larger than the size of the one solder area image, when the one solder area image extracted from the image data obtained by the image data obtaining means corresponds to a circular land, the inspection image data obtaining means obtains the inspection image data of the same size as the circular correspondence learning data, the one solder area image being provided in the circular correspondence image frame, the reconstructed image data obtaining means inputs the inspection image data to the circular correspondence discrimination means to obtain the reconstructed image data, and the comparison means is configured to compare the inspection image data and the reconstructed image data.

[0027] Regarding the number of learning data used for training the identification means, typically, the number of data relating to cream solder printed on rectangular lands is overwhelmingly greater than the number of data relating to cream solder printed on circular lands. Therefore, when test image data K1 (e.g., see FIG. 39 ) relating to circular cream solder 5 printed on circular lands is input to the identification means, there is a risk that an image showing a rectangular cream solder 5 (e.g., see FIG. 41 ) will be output as the reconstructed image data S1, just as when test image data K2 (e.g., see FIG. 40 ) relating to rectangular cream solder 5 with rounded corners is input. If such reconstructed image data is output, there is a risk that a good cream solder will be erroneously determined to be defective.

[0028] In this regard, the above-mentioned means 5 is provided with a circle-specific identification means that is generated by learning only image data related to good-quality cream solder printed on circular lands and is dedicated to inspecting cream solder printed on circular lands. Therefore, it is possible to accurately determine whether circular cream solder printed on circular lands is good or bad. This makes it possible to further improve inspection accuracy.

[0029] Means 6. The solder inspection device according to Means 1, wherein the learning data and the inspection image data are set so that the center or center of gravity of the one solder area image coincides with the center of the image frame, and the long side or short side of the one solder area image extends in a predetermined direction.

[0030] The technical matters related to the above-mentioned means 6 may be applied to the above-mentioned means 4 and 5. That is, the second learning data and the learning data for circular correspondence may be set so that the center or center of gravity of one solder area image coincides with the center of the second image frame or the image frame for circular correspondence, and the long side or short side of the one solder area image extends along a predetermined direction. Of course, the same setting may be applied to the inspection image data related to the above-mentioned means 4 and 5.

[0031] According to the above-mentioned means 6, the orientation and position of the cream solder in the training data and the test image data can be roughly aligned. Therefore, even if the training data used to generate the identification means is relatively small, the quality of the cream solder can be accurately determined. In other words, it is possible to obtain good inspection accuracy while more effectively reducing the labor and time required to obtain the identification means.

[0032] Means 7. The solder inspection device according to Means 1, wherein the comparison means is configured to be able to compare the inspection image data and the reconstructed image data, with only the one solder region image in the inspection image data being the comparison target.

[0033] According to the above-mentioned means 7, the comparison means compares the inspection image data and the reconstructed image data, using only one solder area image in the inspection image data as the comparison target. In other words, when comparing the two image data, the comparison means does not compare any portion of the inspection image data other than the one solder area image. Therefore, compared to comparing the entirety of both image data, the processing load associated with comparing the two image data can be reduced, and inspection can be performed more quickly and efficiently. Furthermore, it is possible to more reliably prevent portions of the inspection image data other than the one solder area image, i.e., portions unrelated to the cream solder, from affecting the pass / fail judgment, thereby further improving inspection accuracy.

[0034] Means 8. A solder inspection method for inspecting cream solder printed on a printed circuit board, comprising: an image data acquisition step capable of acquiring image data of a predetermined inspection area on the printed circuit board including a cream solder printed portion; an inspection image data acquisition step acquiring inspection image data including an image of the cream solder to be inspected based on the image data acquired in the image data acquisition step; a reconstructed image data acquisition step using a discrimination means generated by having a neural network having an encoding unit that extracts feature amounts from input image data and a decoding unit that reconstructs image data from the feature amounts learn only image data related to good cream solder as learning data, and inputting the inspection image data acquired in the inspection image data acquisition step into the discrimination means to acquire reconstructed image data as reconstructed image data; and a comparison step comparing the inspection image data and the reconstructed image data, and judging the quality of the cream solder based on the comparison result in the comparison step, wherein the learning data comprises one solder area image showing cream solder corresponding to one land, arranged in an image frame larger than the size of the one solder area image, A solder inspection method characterized in that in the inspection image data acquisition process, the one solder area image extracted from the image data acquired by the image data acquisition process is placed in an image frame of the same size as the image frame of the learning data, and the inspection image data of the same size as the learning data is acquired.

[0035] According to the above-mentioned means 8, the same effects as those of the above-mentioned means 1 can be achieved.

[0036] The technical matters relating to the above means may be combined as appropriate. For example, the technical matters relating to the above means 2 may be combined with the technical matters relating to the above means 4. Furthermore, for example, at least one of the technical matters relating to the above means 2 to 7 may be applied to the above means 8.

[0037] 1 is a partially enlarged plan view of a portion of a printed circuit board. FIG. 2 is a block diagram showing the configuration of a printed circuit board manufacturing line. FIG. 3 is a schematic configuration diagram showing a solder inspection device. FIG. 4 is a block diagram showing the functional configuration of a solder inspection device. FIG. 5 is a schematic diagram for explaining the structure of a neural network. FIG. 6 is a flowchart showing the flow of a learning process of a neural network. FIG. 7 is a flowchart showing the flow of an inspection process. FIG. 8 is a schematic diagram showing original learning image data. FIG. 9 is a schematic diagram showing an area occupied by cream solder in the original learning image data. FIG. 10 is a schematic diagram showing one solder area image extracted from the original learning image data. FIG. 11 is a schematic diagram showing a first image frame and first learning data Ga. FIG. 12 is a schematic diagram showing a first image frame and first learning data Gb. FIG. 13 is a schematic diagram showing a second image frame and second learning data Gc. FIG. 14 is a schematic diagram showing a second image frame and second learning data Gd. FIG. 15 is a schematic diagram showing a third image frame and third learning data Ge. FIG. 16 is a schematic diagram showing an example of original inspection image data. FIG. 17 is a schematic diagram showing an area occupied by cream solder in the original inspection image data. FIG. 18 is a schematic diagram showing an example of one solder area image extracted from the original inspection image data. FIG. 1 is a schematic diagram showing an example of one solder region image extracted from the original inspection image data. FIG. 2 is a schematic diagram showing an example of first inspection image data Ka and a first image frame. FIG. 3 is a schematic diagram showing an example of first inspection image data Ka and a first image frame. FIG. 4 is a schematic diagram showing an example of first inspection image data Kb and a first image frame. FIG. 5 is a schematic diagram showing an example of first inspection image data Kb and a first image frame. FIG. 6 is a schematic diagram showing second inspection image data Kc and a second image frame. FIG. 7 is a schematic diagram showing second inspection image data Kd and a second image frame. FIG. 8 is a schematic diagram showing second inspection image data Ke and a third image frame. FIG. 9 is a schematic diagram showing reconstructed image data output from a first AI model when first inspection image data Ka is input to the first AI model. FIG. 10 is a schematic diagram showing reconstructed image data output from a first AI model when first inspection image data Kb is input to the first AI model. FIG. 11 is a schematic diagram showing reconstructed image data output from a second AI model when second inspection image data Kc is input to the second AI model. A schematic diagram showing reconstructed image data output from the second AI model when second inspection image data Kd is input to the second AI model.1 is a schematic diagram for explaining the size of a land in a two-dimensional image. FIG. 1 is a schematic diagram for explaining the size of a land in a three-dimensional image. FIG. 2 is a schematic diagram showing cream solder protruding from a land in a two-dimensional image. FIG. 3 is a schematic diagram showing cream solder protruding from a land in a three-dimensional image. FIG. 4 is a schematic diagram showing an example of a solder area image relating to cream solder protruding from a land. FIG. 5 is a schematic diagram showing an example of a solder area image relating to cream solder protruding from a land. FIG. 6 is a schematic diagram showing cream solder printed on a land in a separated state in two. FIG. 7 is a schematic diagram showing one solder area image relating to cream solder printed on a land in a separated state in two. FIG. 8 is a schematic diagram showing inspection image data relating to circular cream solder printed on a circular land. FIG. 9 is a schematic diagram showing inspection image data relating to rectangular cream solder with rounded corners. FIG. 10 is a schematic diagram showing inappropriate reconstructed image data output from an identification means when inspection image data relating to circular cream solder printed on a circular land is input to the identification means.

[0038] An embodiment of the present invention will now be described with reference to the accompanying drawings. First, the configuration of a printed circuit board will be described. Fig. 1 is a partially enlarged plan view of a portion of the printed circuit board.

[0039] 1, the printed circuit board 1 has a wiring pattern (not shown) made of copper foil and a plurality of lands 3 formed on the surface of a flat base substrate 2 made of glass epoxy resin or the like. A resist film 4 is coated on the surface of the base substrate 2 except for the lands 3.

[0040] Furthermore, cream solder 5 made by kneading solder particles with flux is printed on the lands 3. For convenience, in Fig. 1 and other figures, a scattered dot pattern is applied to the portion showing the cream solder 5. In this embodiment, the cream solder 5 includes relatively large rectangular solder pieces 5a and 5b printed on the relatively large lands 3, relatively small rectangular solder pieces 5c and 5d printed on the relatively small lands 3, and a circular solder piece 5e printed on the circular land 3.

[0041] Next, a manufacturing line (manufacturing process) for manufacturing the printed circuit board 1 will be described with reference to Fig. 2. Fig. 2 is a block diagram showing the configuration of a manufacturing line 10 for the printed circuit board 1. As shown in Fig. 2, the manufacturing line 10 is equipped with, in order from the upstream side (upper side in Fig. 2), a solder printer 12, a solder inspection device 13, a component mounter 14, a reflow device 15, and a post-reflow inspection device 16.

[0042] The solder printer 12 performs a solder printing process for printing cream solder 5 on each land 3 of the printed circuit board 1. In the solder printing process, the cream solder 5 is printed by, for example, screen printing. In screen printing, first, the bottom surface of a screen mask is brought into contact with the printed circuit board 1, and cream solder 5 is supplied to the top surface of the screen mask. The screen mask has a plurality of openings formed therein that correspond to each land 3 of the printed circuit board 1. Next, a predetermined squeegee is moved while being brought into contact with the top surface of the screen mask, thereby filling the openings with the cream solder 5. Thereafter, the printed circuit board 1 is separated from the bottom surface of the screen mask, and the cream solder 5 is printed on each land 3 of the printed circuit board 1.

[0043] The solder inspection device 13 inspects the shape of the cream solder 5 printed on the lands 3 and whether or not any foreign matter has adhered to the cream solder 5. The solder inspection device 13 will be described in detail later.

[0044] The component mounter 14 mounts an electronic component 25 (see FIG. 1) on the land 3 on which the cream solder 5 is printed. The electronic component 25 has a plurality of electrodes (not shown), and each of the electrodes is temporarily fixed to a predetermined cream solder 5.

[0045] The reflow device 15 performs a reflow process in which the cream solder 5 is heated and melted to solder the lands 3 to the electrodes of the electronic component 25 .

[0046] The post-reflow inspection device 16 checks whether the solder joints have been properly made in the reflow process by checking for the presence or absence of misalignment in the electronic components 25 using, for example, brightness image data.

[0047] In addition, although not shown, the production line 10 is equipped with conveyors or the like for transporting the printed circuit board 1 between the above-mentioned devices, such as between the solder printer 12 and the solder inspection device 13. Branching devices are also provided between the solder inspection device 13 and the component mounter 14 and downstream of the post-reflow inspection device 16. The printed circuit boards 1 that have been determined to be non-defective by the solder inspection device 13 or the post-reflow inspection device 16 are guided directly downstream, while the printed circuit boards 1 that have been determined to be defective are discharged by the branching devices to a defective product storage area.

[0048] Next, the configuration of the solder inspection device 13 will be described in detail with reference to Figures 3 and 4. Figure 3 is a schematic diagram showing the configuration of the solder inspection device 13. Figure 4 is a block diagram showing the functional configuration of the solder inspection device 13.

[0049] The solder inspection device 13 includes a transport mechanism 31 that transports and positions the printed circuit board 1, an inspection unit 32 that obtains image data of the printed circuit board 1, and a control device 33 (see Figure 4) that controls the drive of the transport mechanism 31 and the inspection unit 32, as well as performs various controls, image processing, and arithmetic processing in the solder inspection device 13.

[0050] The transport mechanism 31 includes a pair of transport rails 31a arranged along the direction in which the printed circuit board 1 is carried in and out, and an endless conveyor belt 31b rotatably disposed on each of the transport rails 31a. Although not shown, the transport mechanism 31 also includes a driving means such as a motor for driving the conveyor belt 31b, and a chucking mechanism for positioning the printed circuit board 1 at a predetermined position. The transport mechanism 31 is driven and controlled by a control device 33 (a transport mechanism control unit 79 described later).

[0051] With the above configuration, the printed circuit board 1 carried into the solder inspection device 13 has both side edges in the width direction perpendicular to the carrying-in / out direction inserted into the conveyor rails 31a, and is placed on the conveyor belt 31b. The conveyor belt 31b then starts operating, transporting the printed circuit board 1 to a predetermined inspection position. When the printed circuit board 1 reaches the inspection position, the conveyor belt 31b stops and the chucking mechanism is activated. The operation of this chucking mechanism pushes up the conveyor belt 31b, and both side edges of the printed circuit board 1 are clamped between the conveyor belt 31b and the upper edge of the conveyor rail 31a. This positions and fixes the printed circuit board 1 at the inspection position. When the inspection is completed, the chucking mechanism releases the fixation, and the conveyor belt 31b starts operating. The printed circuit board 1 is then carried out of the solder inspection device 13. Of course, the configuration of the transport mechanism 31 is not limited to the above, and other configurations may be employed.

[0052] The inspection unit 32 is disposed above the transport rail 31a (the transport path for the printed circuit board 1). The inspection unit 32 includes a first lighting device 32a, a second lighting device 32b, a third lighting device 32c, and a camera 32d. In this embodiment, the camera 32d constitutes the "image data acquisition means."

[0053] The inspection unit 32 also includes an X-axis movement mechanism 32e (see FIG. 4) that allows movement in the X-axis direction (left-right direction in FIG. 3), and a Y-axis movement mechanism 32f (see FIG. 4) that allows movement in the Y-axis direction (front-back direction in FIG. 3). These movement mechanisms 32e and 32f are driven and controlled by the control device 33 (a movement mechanism control section 76, which will be described later).

[0054] When performing three-dimensional measurement of the printed circuit board 1, the first illumination device 32a and the second illumination device 32b each irradiate a predetermined inspection area on the printed circuit board 1 from diagonally above with predetermined light for three-dimensional measurement (pattern light having a striped light intensity distribution).

[0055] Specifically, the first lighting device 32a includes a first light source 32a1 that emits a predetermined light, and a first liquid crystal shutter 32a2 that forms a first grating that converts the light from the first light source 32a1 into a first pattern light having a striped light intensity distribution, and is driven and controlled by the control device 33 (the lighting control unit 72 described later).

[0056] The second lighting device 32b includes a second light source 32b1 that emits a predetermined light, and a second liquid crystal shutter 32b2 that forms a second grating that converts the light from the second light source 32b1 into a second pattern light having a striped light intensity distribution, and is driven and controlled by a control device 33 (an illumination control unit 72 described later).

[0057] With the above configuration, the light emitted from each light source 32a1, 32b1 is guided to a condenser lens (not shown), where it is converted into parallel light, and then guided to a projection lens (not shown) via liquid crystal shutters 32a2, 32b2, and projected as patterned light onto printed circuit board 1. In this embodiment, switching control of liquid crystal shutters 32a2, 32b2 is performed so that the phase of each patterned light is shifted by a quarter pitch.

[0058] Furthermore, by using the liquid crystal shutters 32a2 and 32b2 as the grating, it is possible to irradiate pattern light that is close to an ideal sine wave. This improves the measurement resolution of three-dimensional measurement. In addition, the phase shift of the pattern light can be electrically controlled, which allows for a more compact device.

[0059] When performing two-dimensional measurement of the printed circuit board 1, the third illumination device 32c irradiates a predetermined inspection area on the printed circuit board 1 with predetermined light for two-dimensional measurement (e.g., uniform light). The third illumination device 32c is equipped with a ring light capable of irradiating blue light, a ring light capable of irradiating green light, and a ring light capable of irradiating red light. Note that the third illumination device 32c has a configuration similar to that of known technology, and therefore detailed description thereof will be omitted.

[0060] The camera 32d captures an image of a predetermined inspection area of ​​the printed circuit board 1 from directly above. The camera 32d has an imaging element such as a CCD (Charge Coupled Device) image sensor or a CMOS (Complementary Metal Oxide Semiconductor) image sensor, and an optical system (lens unit, diaphragm, etc.) that forms an image of the printed circuit board 1 on the imaging element, and is arranged so that its optical axis is aligned in the vertical direction (Z-axis direction). Of course, the imaging element is not limited to these, and other imaging elements may be used.

[0061] The camera 32d is driven and controlled by the control device 33 (camera control unit 73, described later). More specifically, the control device 33 executes an image capturing process by the camera 32d in synchronization with the irradiation process by each of the lighting devices 32a, 32b, and 32c. As a result, light irradiated from one of the lighting devices 32a, 32b, and 32c and reflected by the printed circuit board 1 is captured by the camera 32d. As a result, image data of the inspection area of ​​the printed circuit board 1, including the printed portion of the cream solder 5, is acquired. Note that the "inspection area" of the printed circuit board 1 is one area out of multiple areas preset on the printed circuit board 1, with the size of the imaging field of view (imaging range) of the camera 32d being one unit.

[0062] Furthermore, the camera 32d in this embodiment is configured as a color camera, which makes it possible to simultaneously capture images of the light of each color that is simultaneously irradiated from the ring lights of each color of the third illumination device 32c and reflected by the printed circuit board 1.

[0063] The image data captured and generated by the camera 32d is converted into a digital signal inside the camera 32d and then transferred in the form of a digital signal to the control device 33 (an image acquisition unit 74 described below). The control device 33 then stores the transferred image data and performs various image processing, arithmetic processing, and the like based on the image data.

[0064] The control device 33 is composed of a computer including a CPU (Central Processing Unit) that executes predetermined arithmetic processing, a ROM (Read Only Memory) that stores various programs and fixed value data, a RAM (Random Access Memory) that temporarily stores various data when executing various arithmetic processing, and peripheral circuits for these.

[0065] The control device 33 functions as various functional units such as a main control unit 71, a lighting control unit 72, a camera control unit 73, an image acquisition unit 74, a data processing unit 75, a movement mechanism control unit 76, a learning unit 77, an inspection unit 78, and a transport mechanism control unit 79, as the CPU operates in accordance with various programs.

[0066] However, the various functional units are realized by the cooperation of various hardware such as the CPU, ROM, RAM, etc., and there is no need to clearly distinguish between functions realized by hardware and functions realized by software, and some or all of these functions may be realized by hardware circuits such as ICs.

[0067] Furthermore, the control device 33 is provided with an input unit 55 consisting of a keyboard, mouse, touch panel, etc., a display unit 56 with a display screen consisting of a liquid crystal display, etc., a memory unit 57 capable of storing various data, programs, calculation results, test results, etc., and a communication unit 58 capable of sending and receiving various data to and from the outside.

[0068] Here, the above-mentioned various functional units that constitute the control device 33 will be described in detail.

[0069] The main control unit 71 is a functional unit that controls the entire solder inspection device 13 and is configured to be able to send and receive various signals to and from other functional units such as the illumination control unit 72 and camera control unit 73 .

[0070] The illumination control unit 72 is a functional unit that controls the driving of the illumination devices 32 a , 32 b , and 32 c , and performs switching control of the illumination light based on a command signal from the main control unit 71 .

[0071] The camera control unit 73 is a functional unit that controls the driving of the camera 32 d, and controls the timing of image capture based on a command signal from the main control unit 71 .

[0072] The image acquisition unit 74 is a functional unit for capturing image data captured and acquired by the camera 32d.

[0073] The data processing unit 75 is a functional unit that performs predetermined image processing on the image data captured by the image acquisition unit 74, and performs two-dimensional measurement processing, three-dimensional measurement processing, and the like using the image data.

[0074] The movement mechanism control unit 76 is a functional unit that drives and controls the X-axis movement mechanism 32 e and the Y-axis movement mechanism 32 f, and controls the position of the inspection unit 32 based on a command signal from the main control unit 71. By controlling and driving the X-axis movement mechanism 32 e and the Y-axis movement mechanism 32 f, the movement mechanism control unit 76 can move the inspection unit 32 to a position above any inspection area of ​​the printed circuit board 1 that is positioned and fixed at the inspection position. Then, the inspection unit 32 is moved sequentially to a plurality of inspection areas set on the printed circuit board 1, and inspections of the inspection areas are performed, thereby inspecting the entire printed circuit board 1.

[0075] The learning unit 77 is a functional unit that uses learning data to train a deep neural network 90 (hereinafter simply referred to as the "neural network 90"; see Figure 5) and constructs a first AI (Artificial Intelligence) model 101 as an "identification means," a second AI model 102 as a "second identification means," and a third AI model 103 as a "circular correspondence identification means."

[0076] In addition, each of the AI ​​models 101, 102, and 103 in this embodiment (hereinafter, sometimes simply referred to as "AI models 101 to 103") is a generative model constructed by deep learning a neural network 90 using only image data relating to good cream solder 5 as training data, as will be described later, and has the structure of a so-called autoencoder.

[0077] The structure of the neural network 90 will now be described with reference to Fig. 5. Fig. 5 is a schematic diagram conceptually illustrating the structure of the neural network 90. ​​As shown in Fig. 5, the neural network 90 has a convolutional auto-encoder (CAE) structure that includes an encoder unit 91 serving as an "encoding unit" that extracts a feature (latent variable) TA from input image data GA, and a decoder unit 92 serving as a "decoding unit" that reconstructs image data GB from the feature TA.

[0078] The structure of a convolutional autoencoder is well known, and therefore a detailed description thereof will be omitted. However, the encoder unit 91 has a plurality of convolution layers 93, and in each convolution layer 93, a convolution operation is performed on input data using a plurality of filters (kernels) 94, and the result is output as input data for the next layer. Similarly, the decoder unit 92 has a plurality of deconvolution layers 95, and in each deconvolution layer 95, a deconvolution operation is performed on input data using a plurality of filters (kernels) 96, and the result is output as input data for the next layer. Then, in the learning process described below, the weights (parameters) of each filter 94, 96 are updated.

[0079] The inspection unit 78 is a functional unit that inspects the cream solder 5. In this embodiment, the inspection unit 78 inspects whether the cream solder 5 has been printed properly in terms of size, shape, and the presence or absence of foreign matter.

[0080] The transport mechanism control unit 79 is a functional unit that controls the drive of the transport mechanism 31 , and controls the position of the printed circuit board 1 based on a command signal from the main control unit 71 .

[0081] The memory unit 57 is composed of a hard disk drive (HDD) or a solid state drive (SSD), and has a predetermined memory area for storing, for example, each AI model 101 to 103 (neural network 90 and learning information acquired by its learning).

[0082] The communication unit 58 includes a wireless communication interface conforming to communication standards such as a wired LAN (Local Area Network) or a wireless LAN, and is configured to be able to transmit and receive various data to and from the outside. For example, the results of the inspection performed by the inspection unit 78 are output to the outside via the communication unit 58, and the results of the inspection performed by the post-reflow inspection device 16 are input via the communication unit 58.

[0083] Next, the learning process of the neural network 90 performed by the solder inspection device 13 will be described with reference to the flowchart of FIG.

[0084] When the learning process is started based on the execution of a predetermined learning program, the main control unit 71 first performs pre-processing for learning the neural network 90 in step S101.

[0085] In this pre-processing, first, inspection information of a large number of printed circuit boards 1 stored in the post-reflow inspection device 16 is obtained via the communication unit 58. Next, based on the inspection information, original learning image data Ig, which is image data relating to non-defective cream solder 5 that has passed the post-reflow inspection, is obtained from the storage unit 57 (see, for example, FIG. 8).

[0086] This training original image data Ig pertains to the printed circuit board 1 after the printing of the cream solder 5 and before the mounting of the electronic components 25, and is used to obtain the later-described training data Ga, Gb, Gc, Gd, and Ge (hereinafter, sometimes abbreviated as "training data Ga-Ge") used for training the neural network 90. ​​The training original image data Ig also includes three-dimensional data, which is image data obtained by imaging the printed circuit board 1 with the camera 32d while irradiating it with patterned light from the first illumination device 32a or the second illumination device 32b, and two-dimensional data, which is image data obtained by imaging the printed circuit board 1 with the camera 32d while irradiating it with uniform light from the third illumination device 32c.

[0087] The original learning image data Ig may be image data obtained by the camera 32d without any special processing (for example, monochrome luminance image data or RGB luminance image data), or it may be image data obtained by performing a predetermined processing on the image data obtained by the camera 32d (for example, HLS image data obtained by converting RGB image data, or height image data obtained by converting image data).

[0088] Next, first learning data Ga and Gb, second learning data Gc and Gd, and third learning data Ge are created from the acquired original learning image data Ig (see FIGS. 11 to 15 for the learning data Ga to Ge). In this embodiment, the first learning data Ga and Gb correspond to "learning data," and the third learning data Ge corresponds to "circular correspondence learning data." The first learning data Ga and Gb are used to generate the first AI model 101, the second learning data Gc and Gd are used to generate the second AI model 102, and the third learning data Ge is used to generate the third AI model 103.

[0089] To obtain each of the learning data Ga to Ge, first, the area occupied by the cream solder 5 in the acquired learning original image data Ig is identified (see, for example, FIG. 9 ). If the learning original image data Ig is two-dimensional data, the area occupied by the cream solder 5 is identified using, for example, brightness, hue, saturation, etc. If the learning original image data Ig is three-dimensional data, the area occupied by the cream solder 5 is identified using, for example, height information, etc.

[0090] Next, an image of a connected component (a lump portion) in the region occupied by the identified cream solder 5 is extracted as a single solder region image Ih (see, for example, FIG. 10 ). One solder region image Ih corresponds to one land 3, and in this embodiment, a connected component (a lump portion) located on one land 3 in the design within the region occupied by the cream solder 5 is extracted as a single solder region image Ih. Note that one connected component (a lump portion) may simply be extracted as a single solder region image Ih without considering the position of the land 3.

[0091] Next, an image frame into which the extracted solder region image Ih is to be pasted is selected from the first image frame W1, the second image frame W2, and the third image frame W3 (see Figures 11 to 15 for each of the image frames W1, W2, and W3).

[0092] In this embodiment, the first image frame W1 is a rectangular image having a height (width in the vertical direction of the paper in Figure 11, etc.) of n (pixels) and a width (width in the horizontal direction of the paper in Figure 11, etc.) of n (pixels), and its size (width and height) is set based on design data, etc. to be larger than the size of the extracted solder area image Ih.

[0093] The second image frame W2 is a rectangular image with a height of m (pixels) and a width of m (pixels), and its size (width and height) is set to be smaller than the size of the first image frame W1.

[0094] The third image frame W3 is a rectangular image with a height of l (pixels) and a width of l (pixels), and its size is set to be smaller than the size of the second image frame W2. In this embodiment, the first image frame W1 corresponds to the "image frame," and the third image frame W3 corresponds to the "circular corresponding image frame." Note that n, m, and l are all natural numbers, and n>m>l is satisfied.

[0095] Furthermore, all pixels in each of the image frames W1, W2, and W3 (when nothing is pasted) have the same value. For example, the brightness and height information of each pixel constituting each of the image frames W1, W2, and W3 are set to "0." It is preferable that this same value be relatively significantly different from the value possessed by the constituent pixels of the solder area image Ih of 1. Therefore, it is preferable to use a value other than a normally used value (for example, a negative number) as this same value.

[0096] The image frames W1, W2, and W3 are selected based on the size and shape of the first solder area image Ih. If the size (width and height) of the first solder area image Ih is larger than the size of the second image frame W2, the first image frame W1 is selected. On the other hand, if the size of the first solder area image Ih is smaller than the size of the second image frame W2, the second image frame W2 is selected.

[0097] Furthermore, the third image frame W3 is selected if the first solder area image Ih relates to the cream solder 5 printed on the circular land 3. Whether the first solder area image Ih relates to the cream solder 5 printed on the circular land 3 can be determined based on, for example, the shape of the land 3 in the design data or manufacturing data.

[0098] Next, one solder area image Ih is pasted onto the selected image frames W1, W2, and W3, thereby obtaining each of the learning data Ga to Ge in which one solder area image Ih is provided in the image frames W1, W2, and W3.

[0099] In this embodiment, first learning data Ga (see, for example, Figure 11) is obtained by pasting one solder area image Ih corresponding to solder 5a into the first image frame W1, and first learning data Gb (see, for example, Figure 12) is obtained by pasting one solder area image Ih corresponding to solder 5b into the first image frame W1.

[0100] Furthermore, by pasting one solder area image Ih corresponding to solder 5c into the second image frame W2, second learning data Gc (see, for example, Figure 13) is obtained, and by pasting one solder area image Ih corresponding to solder 5d into the second image frame W2, second learning data Gd (see, for example, Figure 14) is obtained.

[0101] Furthermore, by pasting one solder region image Ih corresponding to the solder 5e in the third image frame W3, third learning data Gd (see, for example, FIG. 15) is obtained.

[0102] By adjusting the pasting position and rotating the solder area image Ih, each of the learning data Ga to Ge is set so that the center or center of gravity of the solder area image Ih coincides with the center of the image frame W1, W2, or W3, and the long or short side of the solder area image Ih extends in a predetermined direction. These long or short sides may be the long or short sides of a rectangle circumscribing the solder area image Ih. Furthermore, among the virtual lines passing through the center or center of gravity of the solder area image Ih, the one with the longest length that overlaps the solder area image Ih may be defined as the long side, and the virtual line perpendicular to the long side may be defined as the short side.

[0103] Then, by repeatedly performing the above process of extracting one solder region image Ih and pasting one solder region image Ih into the selected image frames W1, W2, and W3, each of the training data Ga to Ge is obtained from one training original image data Ig. Furthermore, by using multiple training original image data Ig, the required number of first training data Ga and Gb, second training data Gc and Gd, and third training data Ge are finally obtained. In this embodiment, each of the training data Ga to Ge includes data obtained based on two-dimensional data and data obtained based on three-dimensional data.

[0104] In step S101, the number of pieces of learning data Ga to Ge required for learning is acquired. In the following step S102, the learning unit 77 prepares an unlearned neural network 90 based on a command from the main control unit 71. For example, the learning unit 77 reads out the neural network 90 stored in advance in the storage unit 57 or the like. Alternatively, the neural network 90 is constructed based on network configuration information (e.g., the number of layers of the neural network, the number of nodes in each layer, etc.) stored in the storage unit 57 or the like.

[0105] In this embodiment, three neural networks 90 are constructed: one for learning using the first learning data Ga and Gb, one for learning using the second learning data Gc and Gd, and one for learning using the third learning data Ge. Furthermore, three neural networks 90 are constructed: one for learning using the learning data Ga to Ge acquired based on two-dimensional data, and one for learning using the learning data Ga to Ge acquired based on three-dimensional data. Therefore, a total of six neural networks 90 are constructed in this embodiment.

[0106] In step S103, reconstructed image data is acquired. That is, based on a command from the main control unit 71, the learning unit 77 provides the training data Ga-Ge acquired in step S102 as input data to the input layer of the neural network 90, thereby acquiring reconstructed image data output from the output layer of the neural network 90. ​​More specifically, the learning unit 77 provides the training data Ga-Ge acquired in step S102 that corresponds to the neural network 90 as input data to the input layer of the neural network 90, thereby acquiring reconstructed image data output from the output layer of the neural network 90. ​​For example, the learning unit 77 provides the first training data Ga and Gb obtained from two-dimensional data as input data to the input layer of the neural network 90 that performs training using the first training data Ga and Gb, and acquires the reconstructed image data output from the neural network 90. ​​That is, the learning unit 77 inputs appropriate training data Ga-Ge to each of the six types of neural networks 90, and acquires the output reconstructed image data.

[0107] In the following step S104, the learning unit 77 compares the input learning data Ga to Ge with the reconstructed image data output by the neural network 90, and determines whether the error is sufficiently small (whether it is below a predetermined threshold).

[0108] If the error is sufficiently small, in step S106, the learning unit 77 determines whether the learning termination condition is met. For example, if a positive determination is made in step S104 a predetermined number of times in succession without going through the processing of step S105 described below, or if learning using all of the prepared learning data Ga to Ge is repeated a predetermined number of times, it is determined that the termination condition is met. If the termination condition is met, the neural network 90 and its learning information (such as updated parameters described below) are stored in the storage unit 57 as AI models 101 to 103, and the learning process is terminated.

[0109] In this embodiment, the first AI model 101 ultimately stores an AI model obtained by learning the first learning data Ga, Gb obtained from two-dimensional data, and an AI model obtained by learning the first learning data Ga, Gb obtained from three-dimensional data.

[0110] In addition, as the second AI model 102, an AI model obtained by learning the second learning data Gc, Gd obtained from two-dimensional data and an AI model obtained by learning the second learning data Gc, Gd obtained from three-dimensional data are stored.

[0111] Furthermore, an AI model obtained by learning third learning data Ge acquired from two-dimensional data and an AI model obtained by learning third learning data Ge acquired from three-dimensional data are stored as third AI models 103. Therefore, a total of six types of AI models are stored.

[0112] On the other hand, if the termination condition is not met in step S106, the process returns to step S102, and the neural network 90 is trained again.

[0113] If the error is not sufficiently small in step S104, the network is updated (the neural network 90 is trained) in step S105, and then the process returns to step S103 to repeat the above series of processes.

[0114] Specifically, in the network update process of step S105, a known learning algorithm such as backpropagation is used to update the weights (parameters) of the filters 94, 96 in the neural network 90 to more appropriate ones so that a loss function representing the difference between the training data Ga to Ge and the reconstructed image data is minimized. Note that, for example, BCE (Binary Cross-entropy) can be used as the loss function.

[0115] By repeating the processes of steps S103 to S105 many times, the neural network 90 minimizes the error between the learning data Ga to Ge and the reconstructed image data, and outputs more accurate reconstructed image data.

[0116] When image data relating to a good cream solder 5 is input, each of the finally obtained AI models 101-103 generates reconstructed image data that approximately matches the image data. Furthermore, when image data relating to a defective cream solder 5 in terms of shape, size, and the presence or absence of foreign matter is input, each of the AI ​​models 101-103 generates reconstructed image data that approximately matches the image data after correcting the shape and size of the cream solder 5 and removing noise portions (portions corresponding to foreign matter). In other words, when the cream solder 5 is defective, virtual image data relating to the cream solder 5, assuming that there are no defective portions, is generated as the reconstructed image data relating to the cream solder 5.

[0117] Next, the inspection process performed by the solder inspection device 13 will be described with reference to the flowchart of Fig. 7. However, the inspection process shown in Fig. 7 is a process that is executed for each area to be inspected on the printed circuit board 1.

[0118] When the printed circuit board 1 is carried into the solder inspection device 13 and positioned at a predetermined inspection position, inspection processing is started based on the execution of a predetermined inspection program.

[0119] When the inspection process starts, an image data acquisition process is first performed in step S301. In the image data acquisition process, original inspection image data Ik (see, for example, FIG. 16 ) related to the printed circuit board 1 to be inspected is acquired. The original inspection image data Ik is image data for obtaining inspection image data Ka, Kb, Kc, Kd, ​​and Ke (hereinafter, sometimes abbreviated as "inspection image data Ka-Ke") described below. Note that in this embodiment, the printed circuit board 1 to be inspected is, as an example, one in which multiple cream solders 5 are printed separately on one land 3, the cream solder 5 protrudes from the land 3, foreign matter X is attached to the cream solder 5, or the size or shape of the cream solder 5 is abnormal.

[0120] The original inspection image data Ik includes three-dimensional data, which is image data obtained by imaging the printed circuit board 1 with the camera 32d while irradiating it with patterned light from the first illumination device 32a or the second illumination device 32b, and two-dimensional data, which is image data obtained by imaging the printed circuit board 1 with the camera 32d while irradiating it with uniform light from the third illumination device 32c. In the image data acquisition process, a three-dimensional data acquisition process and a two-dimensional data acquisition process are performed.

[0121] First, the three-dimensional data acquisition process will be described. In this process, the phase of the first pattern light irradiated from the first illumination device 32a is changed and four imaging processes are performed under the first pattern light with different phases. Then, the phase of the second pattern light irradiated from the second illumination device 32b is changed and four imaging processes are performed under the second pattern light with different phases, thereby acquiring a total of eight sets of three-dimensional data. This will be described in detail below.

[0122] As described above, when the printed circuit board 1 carried into the solder inspection device 13 is positioned and fixed at a predetermined inspection position, based on instructions from the main control unit 71, the movement mechanism control unit 76 first drives and controls the X-axis movement mechanism 32e and the Y-axis movement mechanism 32f to move the inspection unit 32, and aligns the imaging field of view (imaging range) of the camera 32d with the predetermined inspection area of ​​the printed circuit board 1.

[0123] Additionally, the illumination control unit 72 controls the switching of the liquid crystal shutters 32a2, 32b2 of the two illumination devices 32a, 32b, and sets the positions of the first grating and the second grating formed on the two liquid crystal shutters 32a2, 32b2 to predetermined reference positions.

[0124] When the switching between the first and second gratings is complete, the illumination control unit 72 causes the first light source 32a1 of the first illumination device 32a to emit light and irradiate the first pattern light, and the camera control unit 73 drives and controls the camera 32d to perform a first imaging process under the first pattern light. Note that the image data generated by the imaging process is continuously imported into the image acquisition unit 74 (same below). This allows three-dimensional data of the inspection area including the multiple lands 3 (cream solder 5) to be acquired.

[0125] Thereafter, upon completion of the first imaging process under the first pattern light, the illumination control unit 72 turns off the first light source 32a1 of the first illumination device 32a and executes a switching process for the first liquid crystal shutter 32a2. Specifically, the illumination control unit 72 switches the position of the first grating formed on the first liquid crystal shutter 32a2 from the reference position to a second position where the phase of the first pattern light is shifted by a quarter pitch (90°).

[0126] When the first grating setting is complete, the illumination control unit 72 causes the light source 32a1 of the first illumination device 32a to emit light and irradiate the first pattern light, and the camera control unit 73 drives and controls the camera 32d to perform a second imaging process under the first pattern light. Thereafter, by repeating the same process, four sets of three-dimensional data are acquired under the first pattern light, each with a phase difference of 90°.

[0127] Next, the lighting control unit 72 causes the second light source 32b1 of the second lighting device 32b to emit light and irradiate the second pattern light, and the camera control unit 73 drives and controls the camera 32d to perform the first imaging process under the second pattern light.

[0128] Thereafter, at the same time as the completion of the first imaging process under the second pattern light, the illumination control unit 72 turns off the second light source 32b1 of the second illumination device 32b and executes a switching process for the second liquid crystal shutter 32b2. Specifically, the position of the second grating formed on the second liquid crystal shutter 32b2 is switched from the reference position to a second position where the phase of the second pattern light is shifted by a quarter pitch (90°).

[0129] When the second grating setting is complete, the illumination control unit 72 causes the light source 32b1 of the second illumination device 32b to emit light and irradiate the second pattern light, and the camera control unit 73 drives and controls the camera 32d to perform a second imaging process under the second pattern light. Thereafter, by repeating the same process, four sets of three-dimensional data are acquired under the second pattern light, each with a phase difference of 90°.

[0130] Next, the two-dimensional data acquisition process will be described. In this process, based on a command from the main control unit 71, the illumination control unit 72 causes the third illumination device 32c to emit light, irradiating a predetermined inspection area with uniform light, while the camera control unit 73 drives and controls the camera 32d to perform an image capture process under the uniform light. As a result, the predetermined inspection area on the printed circuit board 1 is imaged, and two-dimensional data related to the inspection area is acquired.

[0131] The acquired original inspection image data Ik (three-dimensional data and two-dimensional data) is stored in the storage unit 57.

[0132] The original image data for inspection Ik may be image data obtained by the camera 32d without any special processing (for example, monochrome luminance image data or RGB luminance image data), or it may be image data obtained by performing a predetermined processing on the image data obtained by the camera 32d (for example, HLS image data obtained by converting RGB image data, or height image data obtained by converting image data).

[0133] Next, in step S302, a test image data acquisition step is executed, in which first test image data Ka, Kb, second test image data Kc, Kd, ​​and third test image data Ke, which will be described later, are acquired based on the original test image data Ik obtained in the image data acquisition step.

[0134] To obtain these inspection image data Ka to Ke, first, the area occupied by the cream solder 5 in the acquired original inspection image data Ik is identified (see, for example, FIG. 17). The area occupied by the cream solder 5 can be identified using brightness, hue, saturation, height information, etc.

[0135] Next, one solder area image Ih (see, for example, FIGS. 18 and 19 ) is extracted from the area occupied by the identified cream solder 5. One solder area image Ih corresponds to one land 3. In this embodiment, the entire image of connected components (lump portions) in the identified area that at least partially overlap one land 3 in the design data or manufacturing data is extracted as one solder area image Ih. Therefore, if two or more connected components exist for one land 3 in the design data or manufacturing data, one solder area image Ih is composed of two or more connected components (see, for example, FIG. 18 ). Furthermore, if a portion of a connected component extends beyond the land 3 in the design data or manufacturing data, one solder area image Ih is composed of the entire connected component, including the portion extending beyond the land 3 (see, for example, FIG. 19 ). Note that one connected component may be simply extracted as one solder area image Ih without using design data or the like. In this embodiment, the inspection unit 78 that extracts one solder area image Ih from the original inspection image data Ik constitutes the "solder area image extraction means."

[0136] Then, based on the size and shape of the extracted solder area image Ih, an appropriate image frame is selected from the first image frame W1, the second image frame W2, and the third image frame W3, and the inspection image data Ka to Ke are obtained by placing the one solder area image Ih in the selected image frames W1, W2, and W3 (see Figures 20 to 26 for the inspection image data Ka to Ke).

[0137] That is, if the size of one extracted solder area image Ih is larger than the size of the second image frame W2, the first test image data Ka, Kb (see, for example, FIGS. 20 to 23) are obtained by pasting the one solder area image Ih into the first image frame W1. Therefore, the size (width and height) of the first test image data Ka, Kb is the same as the size of the first learning data Ga, Gb.

[0138] Furthermore, if the size of the extracted solder area image Ih is smaller than the size of the second image frame W2, the second test image data Kc, Kd (see, for example, Figures 24 and 25) are obtained by pasting the extracted solder area image Ih into the second image frame W2. Therefore, the size of the second test image data Kc, Kd is the same as the size of the second learning data Gc, Gd. For reference, in Figures 24 and 25, a cream solder 5 of normal shape and size is virtually shown by a two-dot chain line.

[0139] Furthermore, if the extracted solder area image Ih relates to the cream solder 5 printed on the circular land 3, the third test image data Ke (see, for example, FIG. 26 ) is obtained by pasting the extracted solder area image Ih into the third image frame W3. Therefore, the size of the third test image data Ke is the same as the size of the third learning data Ge. Whether the extracted solder area image Ih relates to the cream solder 5 printed on the circular land 3 can be determined based on, for example, the shape of the land 3 in the design data and manufacturing data.

[0140] Furthermore, when pasting one solder area image Ih to the image frames W1, W2, and W3, adjustment of the pasting position, image rotation processing, etc. As a result, in each of the test image data Ka to Ke, similar to each of the learning data Ga to Ge, the center or center of gravity of one solder area image Ih coincides with the center of the image frame W1, W2, and W3, and the long side or short side of the one solder area image Ih extends along a predetermined direction.

[0141] Then, by repeatedly performing the above process of extracting one solder area image Ih and pasting one solder area image Ih into the selected image frames W1, W2, and W3, each of the test image data Ka-Ke is obtained from one of the original test image data Ik. In this embodiment, each of the test image data Ka-Ke includes data obtained based on two-dimensional data and data obtained based on three-dimensional data. In this embodiment, the inspection unit 78 that obtains the test image data Ka-Ke constitutes the "test image data obtaining means."

[0142] In the following step S303, a reconstructed image data acquisition process is executed. Specifically, based on instructions from the main control unit 71, the inspection unit 78 inputs the inspection image data Ka-Ke acquired in step S302 to the input layers of the AI ​​models 101, 102, and 103 corresponding to the types of the inspection image data Ka-Ke. Therefore, the first inspection image data Ka and Kb are input to the first AI model 101, the second inspection image data Kc and Kd are input to the second AI model 102, and the third inspection image data Ke is input to the third AI model 103. Furthermore, the inspection image data Ka-Ke acquired based on two-dimensional data are input to the AI ​​models 101-103 corresponding to the two-dimensional data, and the inspection image data Ka-Ke acquired based on three-dimensional data are input to the AI ​​models 101-103 corresponding to the three-dimensional data. Then, the image data reconstructed by the AI ​​models 101-103 and output from the output layers is acquired as reconstructed image data. The acquired reconstructed image data is stored in association with the test image data Ka to Ke from which the reconstructed image data was derived.

[0143] Here, when each AI model 101 to 103 receives first inspection image data Kb (see Figure 23) relating to cream solder 5 with foreign matter X attached, or inspection image data Ka, Kc, Kd (see Figures 20, 21, 24, 25) relating to cream solder 5 with an inappropriate shape or size, it outputs, as reconstructed image data S, image data relating to good cream solder 5 from which foreign matter X has been removed or whose shape or size has been corrected, by learning as described above (see, for example, Figures 27 to 30).

[0144] On the other hand, when inspection image data Ka-Ke relating to a good cream solder 5 is input, each of the AI ​​models 101-103 outputs image data relating to the good cream solder 5 that is substantially identical to the inspection image data Ka-Ke as reconstructed image data S. The size (width and height) of the reconstructed image data S is the same as the size of the original inspection image data Ka-Ke. In this embodiment, the inspection unit 78 that acquires the reconstructed image data S constitutes the "reconstructed image data acquisition means."

[0145] In step S304, a quality determination process is performed based on the acquired reconstructed image data S. In the quality determination process, based on instructions from the main control unit 71, the inspection unit 78 compares the entire test image data Ka-Ke acquired in step S302 with the entire reconstructed image data S acquired in step S303 using the test image data Ka-Ke, and calculates the difference between the two sets of image data Ka-Ke and S. For example, dots (pixels) at the same coordinates in the two sets of image data Ka-Ke and S are compared, and the area (number of dots) of a cluster of dots whose brightness difference is equal to or greater than a predetermined value is calculated. In this embodiment, the inspection unit 78, which compares the test image data Ka-Ke and the reconstructed image data S, constitutes a "comparison means." Furthermore, the process of comparing the test image data Ka-Ke and the reconstructed image data S corresponds to a "comparison process."

[0146] Next, the inspection unit 78 determines whether the calculated difference is greater than a predetermined threshold value. If the calculated difference is greater than the predetermined threshold value, the inspection unit 78 determines the product as a "good product," whereas if the difference is smaller than the predetermined threshold value, the inspection unit 78 determines the product as a "defective product."

[0147] Furthermore, the inspection unit 78 makes the above-mentioned judgment for all the test image data Ka to Ke relating to the inspection area of ​​the printed circuit board 1, and if the inspection unit 78 judges all the test image data Ka to Ke to be "good", it judges the inspection area to be "good" and stores this result in the storage unit 57. On the other hand, if the inspection unit 78 makes the above-mentioned judgment for all the test image data Ka to Ke relating to the inspection area and judges at least one of the test image data Ka to Ke to be "defective", it judges the inspection area to be "defective" and stores this result in the storage unit 57.

[0148] Then, if the solder inspection device 13 performs the above inspection process on all inspected areas of the printed circuit board 1 and judges all inspected areas to be "good," it judges the printed circuit board 1 to be free of abnormalities in the cream solder 5 (pass judgment) and stores this result in the memory unit 57.

[0149] On the other hand, if there is even one inspected area that is judged to be "defective," the solder inspection device 13 judges that the printed circuit board 1 has an abnormality in the cream solder 5 (failure judgment), stores this result in the memory unit 57, and notifies the outside world of this via the display unit 56, communication unit 58, etc.

[0150] As described above in detail, according to this embodiment, the inspection image data Ka-Ke are each formed by providing one solder region image Ih in an image frame W1, W2, or W3. Therefore, the size (width and height) of each inspection image data Ka-Ke is constant and does not vary depending on the size of the land 3. This eliminates the need to prepare multiple AI models (identification means) that differ for each land 3 size, reducing the effort and time required to obtain the AI ​​models 101-103. Furthermore, the AI ​​models 101-103 can be commonly used even when the land 3 has a different size.

[0151] Furthermore, the image frames W1, W2, and W3 of the learning data Ga-Ge and the image frames W1, W2, and W3 of the test image data Ka-Ke are the same size, and the sizes of the learning data Ga-Ge and the test image data Ka-Ke are the same. Therefore, when the test image data Ka-Ke are input to the AI ​​models 101-103, appropriate reconstructed image data S corresponding to the test image data Ka-Ke can be more reliably output, and the quality of the cream solder 5 can be more accurately determined. This makes it possible to more reliably obtain good test accuracy.

[0152] In addition, the inspection image data Ka-Ke and the reconstructed image data S to be compared each relate to the same cream solder 5. Therefore, unlike a method of determining pass / fail by comparison with a separately prepared standard, it is not necessary to set relatively loose inspection conditions to prevent erroneous detection, and stricter inspection conditions can be set. Furthermore, the imaging conditions of the printed circuit board 1 to be inspected (e.g., the placement position, placement angle, and deflection of the printed circuit board 1) and the imaging conditions of the solder inspection device 13 (e.g., lighting conditions, camera angle of view, etc.) can be matched for both sets of image data Ka-Ke and S to be compared. This combination allows for more accurate pass / fail determination of the cream solder 5.

[0153] Furthermore, in this embodiment, one solder region image Ih constituting the inspection image data Ka to Ke includes not only an image of the portion of the cream solder 5 located on the land 3, but also an image of the portion of the cream solder 5 that extends beyond the land 3. This makes it possible to properly determine whether the cream solder 5 that has partially extended beyond the land 3 is good or bad, further improving inspection accuracy.

[0154] Furthermore, when the cream solder 5 printed on one land 3 is separated into multiple pieces, one solder area image Ih constituting the inspection image data Ka-Ke includes an image of the entire cream solder 5. Therefore, even if the cream solder 5 printed on one land 3 is separated into multiple pieces, it is possible to more appropriately determine whether the cream solder 5 is good or bad.

[0155] Furthermore, in this embodiment, when the size of one solder region image Ih is relatively small, relatively small inspection image data Kc, Kd are obtained by placing the one solder region image Ih in a relatively small second image frame W2. These relatively small inspection image data Kc, Kd are then input to the second AI model 102, which outputs reconstructed image data S, and the relatively small inspection image data Kc, Kd and the reconstructed image data S are compared. Therefore, compared to when the image frame of the inspection image data is always set to a constant size, the process for obtaining the reconstructed image data S and the comparison process by the inspection unit 78 can be speeded up, and the inspection speed can be further improved.

[0156] Furthermore, in this embodiment, a third AI model 103 is provided to exclusively inspect the cream solder 5 printed on the circular lands 3. Therefore, it is possible to accurately determine whether the circular cream solder 5 printed on the circular lands 3 is good or bad. This makes it possible to further improve inspection accuracy.

[0157] In addition, because the orientation and position of the cream solder 5 in the learning data Ga to Ge and the inspection image data Ka to Ke are roughly aligned, it is possible to accurately determine whether the cream solder 5 is good or bad even if a relatively small amount of learning data Ga to Ge is used to generate the AI ​​models 101 to 103. In other words, it is possible to obtain good inspection accuracy while more effectively reducing the effort and time required to obtain the AI ​​models 101 to 103.

[0158] The present invention is not limited to the above-described embodiment, and may be implemented as follows: Of course, other applications and modifications not exemplified below are also possible.

[0159] (a) In the above embodiment, the entire test image data Ka to Ke is compared with the entire reconstructed image data S in the pass / fail determination process of step S304.

[0160] In contrast to this, it is also possible to configure the system so that only one solder area image Ih in the inspection image data Ka to Ke is used as the comparison target, and to compare the inspection image data Ka to Ke with the reconstructed image data S. In other words, it is also possible to configure the system so that one solder area image Ih in the inspection image data Ka to Ke is compared with an area in the reconstructed image data S that overlaps with the one solder area image Ih.

[0161] In this configuration, since the portions of the test image data Ka-Ke other than the one solder region image Ih are not compared, the processing load associated with comparing the two image data Ka-Ke, S can be reduced compared to when the entire sets of both image data Ka-Ke, S are compared. This allows for faster and more efficient testing. Furthermore, it is possible to more reliably prevent portions of the test image data Ka-Ke other than the one solder region image Ih, i.e., portions unrelated to the cream solder 5, from affecting the pass / fail judgment, thereby further improving the accuracy of the test.

[0162] It is also possible to configure the comparison between the inspection image data Ka-Ke and the reconstructed image data S by comparing only the area relating to the cream solder 5 in the reconstructed image data S. In other words, it is also possible to configure the comparison to compare the area relating to the cream solder 5 in the reconstructed image data S with the area in the inspection image data Ka-Ke that overlaps with the area relating to the cream solder 5. Of course, the above two comparison methods may be used in combination.

[0163] (b) In the above embodiment, the learning data Ga to Ge are obtained using the original learning image data Ig of the printed circuit board 1 that passed the post-reflow inspection when training the neural network 90. ​​However, the learning data Ga to Ge may also be obtained using original learning image data of good-quality cream solder 5 that has been visually selected by an operator after the cream solder 5 has been printed.

[0164] The learning unit 77 may also acquire the learning data Ga to Ge using image data of a virtually generated non-defective cream solder 5 .

[0165] (c) In the above embodiment, AI models 101 to 103 are provided separately for two-dimensional data and three-dimensional data, but it is also possible to provide a common AI model that corresponds to both two-dimensional data and three-dimensional data.

[0166] Furthermore, in the above embodiment, the first AI model 101 and the second AI model 102 are provided, but the second AI model 102 may be omitted. In this case, the size of the second test image data Kc, Kd may be the same as the size of the first test image data Ka, Kd, ​​and the first AI model 101 may perform testing based on the test image data Ka, Kb, Kc, Kd. Also, the third AI model 103 may be omitted.

[0167] (d) The configuration and learning method of the AI ​​models 101-103 (neural network 90) are not limited to those described in the above embodiment. For example, the neural network 90 may be configured to perform normalization or other processing on various data as needed during the learning process or the reconstructed image data acquisition process. Furthermore, the structure of the neural network 90 is not limited to that shown in FIG. 5 , and may include, for example, a pooling layer after the convolution layer 93. Of course, the number of layers of the neural network 90, the number of nodes in each layer, and the connection structure of each node may be different.

[0168] Furthermore, in the above embodiment, the AI ​​models 101 to 103 (neural network 90) are generative models having the structure of a convolutional autoencoder (CAE), but this is not limited thereto, and they may also be generative models having the structure of a different type of autoencoder, such as a variational autoencoder (VAE).

[0169] Furthermore, in the above embodiment, the neural network 90 is configured to learn using the error backpropagation method, but this is not limiting, and the neural network 90 may be configured to learn using various other learning algorithms.

[0170] Additionally, neural network 90 may be configured by a dedicated AI processing circuit such as an AI chip. In this case, only learning information such as parameters may be stored in storage unit 57, and the dedicated AI processing circuit may read this information and set it in neural network 90, thereby configuring AI models 101 to 103.

[0171] Additionally, in the above embodiment, the control device 33 is provided with the learning unit 77, and the neural network 90 is configured to be learned within the control device 33, but this is not limiting. For example, the learning unit 77 may be omitted, and the neural network 90 may be configured to be learned outside the control device 33, and the AI ​​models 101 to 103 (trained neural network 90) that have been trained externally may be stored in the storage unit 57.

[0172] (e) In the above embodiment, two-dimensional data and three-dimensional data are acquired as the original inspection image data Ik, but it is also possible to acquire only one of the two-dimensional data and the three-dimensional data. Furthermore, the AI ​​models 101 to 103 may be provided to correspond to only one of the two-dimensional data and the three-dimensional data, depending on the data to be acquired.

[0173] (f) In the above embodiment, the test image data Ka-Ke are obtained by pasting one solder area image Ih into the image frames W1, W2, and W3. Alternatively, the test image data Ka-Ke may be obtained as follows. First, when extracting an image of the connected components (lump portions) in the area occupied by the identified cream solder 5 as one solder area image Ih, the one solder area image Ih and its surrounding area are extracted to obtain an extracted image of the same size as the image frames W1, W2, and W3. Then, the values ​​of each pixel in the surrounding area in the extracted image may be replaced with the same value (for example, brightness or height may be set to "0") to obtain the test image data Ka-Ke. Of course, a similar method may be used to obtain the learning data Ga-Ge.

[0174] 1...Printed circuit board, 3...Land, 5...Cream solder, 13...Solder inspection device, 32d...Camera (image data acquisition means), 78...Inspection unit (inspection image data acquisition means, reconstructed image data acquisition means, comparison means, solder area image extraction means), 90...Neural network, 91...Encoder unit (encoding unit), 92...Decoder unit (decoding unit), 101...First AI model (identification means), 102...Second AI model (second identification means), 103...Third AI model (circular correspondence identification means), Ih...Solder area image of 1, W1...First image frame (image frame), W2...Second image frame, W3...Third image frame (circular correspondence image frame).

Claims

1. A solder inspection device for inspecting cream solder printed on a printed circuit board, comprising: image data acquisition means capable of acquiring image data of a predetermined inspection area on the printed circuit board including the cream solder printed portion; discrimination means for generating learning data generated by having a neural network having an encoding unit that extracts features from input image data and a decoding unit that reconstructs image data from the features learn only image data relating to good cream solder; inspection image data acquisition means for acquiring inspection image data including an image of the cream solder to be inspected based on the image data acquired by the image data acquisition means; reconstructed image data acquisition means for inputting the inspection image data to the discrimination means and acquiring reconstructed image data as reconstructed image data; and comparison means for comparing the inspection image data and the reconstructed image data, and the device is configured to be able to determine the quality of the cream solder based on the comparison result by the comparison means, and the learning data is composed of one solder area image showing cream solder corresponding to one land, arranged in an image frame larger than the size of the one solder area image, The solder inspection device is characterized in that the inspection image data acquisition means acquires the inspection image data of the same size as the learning data, wherein the one solder area image extracted from the image data acquired by the image data acquisition means is placed in an image frame of the same size as the image frame of the learning data.

2. A solder inspection device as described in claim 1, further comprising a solder area image extraction means for extracting the one solder area image constituting the inspection image data from the image data acquired by the image data acquisition means, wherein the solder area image extraction means is capable of identifying an area occupied by cream solder in the image data acquired by the image data acquisition means, and extracting an image of the connected components in the identified area as the one solder area image constituting the inspection image data.

3. The solder inspection device according to claim 2, characterized in that the solder area image extraction means is capable of extracting an entire image of one of the connected components that at least partially overlaps with one land in the design data or manufacturing data as the one solder area image constituting the inspection image data.

4. A solder inspection device as described in claim 1, further comprising a second identification means for generating second learning data by having a neural network having an encoding unit which extracts features from input image data and a decoding unit which reconstructs image data from the features learn only image data relating to good quality cream solder, the second learning data being formed by providing the first solder area image in a second image frame which is larger than the size of the first solder area image but smaller than the size of the image frame of the learning data, and when the size of the first solder area image extracted from the image data obtained by the image data obtaining means is smaller than the size of the second image frame, the inspection image data obtaining means obtains the inspection image data of the same size as the second learning data, in which the first solder area image is provided in the second image frame, the reconstructed image data obtaining means obtains the reconstructed image data obtained by inputting the inspection image data to the second identification means, and the comparison means is configured to compare the inspection image data and the reconstructed image data.

5. A solder inspection device as described in claim 1, further comprising a circular correspondence identification means for generating circular correspondence learning data by having a neural network having an encoding unit which extracts features from input image data and a decoding unit which reconstructs image data from the features learn only image data relating to good quality cream solder printed on circular lands, the circular correspondence learning data being configured to provide the one solder area image relating to good quality cream solder printed on circular lands in a circular correspondence image frame having a size larger than the size of the one solder area image, and when the one solder area image extracted from the image data acquired by the image data acquisition means corresponds to a circular land, the inspection image data acquisition means acquires the inspection image data of the same size as the circular correspondence learning data in which the one solder area image is provided in the circular correspondence image frame, the reconstructed image data acquisition means inputs the inspection image data to the circular correspondence identification means to acquire the reconstructed image data, and the comparison means is configured to compare the inspection image data and the reconstructed image data.

6. The solder inspection device of claim 1, characterized in that the learning data and the inspection image data are set so that the center or center of gravity of the one solder area image coincides with the center of the image frame and the long or short side of the one solder area image extends along a predetermined direction.

7. A solder inspection device as described in claim 1, characterized in that the comparison means is configured to be able to compare the inspection image data and the reconstructed image data by using only the one solder area image in the inspection image data as a comparison object.

8. A solder inspection method for inspecting cream solder printed on a printed circuit board, comprising: an image data acquisition step capable of acquiring image data of a predetermined inspection area on the printed circuit board including a portion where cream solder is printed; an inspection image data acquisition step for acquiring inspection image data including an image of the cream solder to be inspected based on the image data acquired by the image data acquisition step; a reconstructed image data acquisition step for inputting the inspection image data acquired by the inspection image data acquisition step into the identification means and acquiring reconstructed image data as reconstructed image data using an identification means generated by having a neural network having an encoding unit that extracts features from input image data and a decoding unit that reconstructs image data from the features learn only image data relating to good cream solder as learning data; and a comparison step for comparing the inspection image data and the reconstructed image data, and judging whether the cream solder is good or bad based on the comparison result in the comparison step, wherein the learning data is one solder area image showing cream solder corresponding to one land, arranged in an image frame larger than the size of the one solder area image, A solder inspection method characterized in that, in the inspection image data acquisition process, the one solder area image extracted from the image data acquired by the image data acquisition process is arranged in an image frame of the same size as the image frame of the learning data, and the inspection image data of the same size as the learning data is acquired.

Images