Image inspection method and image inspection device

Abstract

To provide an image inspection method using an image inspection device (for example, an X-ray inspection device) that transfers an image of a faulty part of a certain component to an image of the other component to generate and display a pseudo image of a faulty part and a measured value, and thereby can visually and numerically discriminate the difference between a non-defective product and a defective product.SOLUTION: An image inspection method using an image inspection device has a transfer step of transferring an image of a faulty part to a transfer destination in an image in a non-defective product to create a transfer image, as a part of all steps.SELECTED DRAWING: Figure 6

Description

[Technical Field]

[0001] The present invention relates to an image inspection method and an image inspection device for determining whether an object to be inspected is good or bad by inspecting an image of the object to be inspected. [Background technology]

[0002] It has been known that, when the number of defective images required for quality control cannot be obtained in an actual manufacturing process, pseudo-failure images are created based on images of non-defective products. For example, an automatic pseudo-failure image creation device capable of automatically creating a large number of pseudo-failure images required for initial learning is known. In this automatic pseudo-failure image creation device, non-defective product images are input from a non-defective product input unit as learning data for a neural network, and the device learns by inputting defective images from a defective image input unit. Furthermore, a defective image extraction unit extracts difference data from non-defective products, and a pseudo-data condition setting unit creates multiple defect creation conditions, such as defect combination positions, based on random numbers from a random number generator. Based on these defect creation conditions, the pseudo-failure image creation unit combines the difference data with non-defective product images to create multiple pseudo-failure images, which are input as learning data for the neural network (see, for example, Patent Document 1).

[0003] A learning device capable of accurately learning a model for discriminating between good and defective products is also known. The learning device includes an intermediate image generation unit, an intermediate image display unit, a boundary acceptance unit, and a teacher image identification unit. The intermediate image generation unit generates multiple intermediate images from good product images that represent good products and defective product images that represent defective products. The intermediate image display unit arranges the multiple intermediate images between the good product images and the defective product images and displays them on a display device. The boundary acceptance unit accepts a user's designation of a boundary between the good product images and the defective product images. The teacher image identification unit identifies good product images and defective product images based on the designated boundary (see, for example, Patent Document 2). An image processing device capable of easily generating good product images from defective product images is also known (see, for example, Patent Document 3).

[0004] According to the invention disclosed in the above Patent Document 1, pseudo-failure images are created based on data relating to images of non-defective products and data relating to images of defective products, and the pseudo-failure images are input as learning data for a neural network, thereby improving the accuracy of pass / fail judgment of the pseudo-failure image automatic creation device as an inspection device. However, it has not been possible to efficiently create pseudo-failure images and their measurement values ​​using previously accumulated defective images.

[0005] Furthermore, according to the invention disclosed in Patent Document 2, when generating multiple intermediate images based on images of non-defective products and images of defective products, a boundary accepting unit accepts a user's designation of the boundaries of the intermediate images as the boundaries between the non-defective and defective images. However, if sufficient defective images are not obtained when designating the boundaries of the intermediate images, the boundaries of the intermediate images must be designated based only on the non-defective images, which may require designation based on experience. This designation based on experience is undesirable because it may cause variations in the inspection quality of the learning device. Furthermore, it has not been possible to efficiently create new pseudo-defective images using previously accumulated defective images. [Prior art documents] [Patent documents]

[0006] [Patent Document 1] Japanese Patent Application Laid-Open No. 2005-156334 [Patent Document 2] Patent No. 6780769 [Patent Document 3] Japanese Patent Application Publication No. 2020-008488 Summary of the Invention [Problem to be solved by the invention]

[0007] The present invention has been made in consideration of the above-mentioned problems, and has as its ultimate object to provide an image inspection method and an image inspection device that can efficiently create images of pseudo-defective areas by transferring images of defective areas previously obtained onto images of good products, and that can be used for quality control. [Means for solving the problem]

[0008] To solve the above problems, the present invention provides: An image inspection method that enables discrimination between good and bad products in an inspection object using an image inspection device, comprising: an image display step of displaying an image of the non-defective product; a defect image display step of displaying images of a plurality of defect locations in an inspection object of the same type as the non-defective product; a selection step of selecting a transfer destination in the image of the non-defective product and one or more images of defective parts from the images of the plurality of defective parts corresponding to the transfer destination; a transfer step of transferring the image of one or more defective parts from the images of the plurality of defective parts selected in the selection step onto the transfer destination of the image of the non-defective product, thereby generating a transferred image; The image inspection method includes the steps of:

[0009] According to the present invention, in the transfer step, images of defective areas are transferred onto the transfer destination of the image of a non-defective product, thereby making it possible to efficiently generate images of pseudo-defective areas. These images of pseudo-defective areas can be used to distinguish between non-defective and defective products in the manufacturing process, thereby facilitating the task of teaching, which is to register the differences between non-defective and defective products in the image inspection device. These transferred images can also be provided as a standard for distinguishing between non-defective and defective products. Furthermore, the more images of defective areas transferred in the transfer step, the more images of pseudo-defective areas can be obtained.

[0010] Furthermore, the present invention may be an image inspection method further comprising a transfer image display step of displaying the transfer image, a measurement step of measuring a predetermined feature amount in the transfer image, and a measurement result display step of displaying the measurement results obtained in the measurement step or the measurement results obtained in the measurement step and the measurement results of the predetermined feature amount in another inspection object. This makes it possible to visually and numerically distinguish between good and bad products, and the discrimination criteria become clearer, making teaching easier to carry out.

[0011] Furthermore, the present invention may be an image inspection method characterized in that, in the image display step and the defect image display step, the image of the non-defective product and the images of the plurality of defect locations are displayed as cross-sectional images from three directions of X, Y, and Z. This can prevent the risk of overlooking defect locations in the defective product due to blind spots when the defective product is three-dimensional.

[0012] Furthermore, in the present invention, the image inspection method may be such that, in the transfer step, if the size of the transfer destination and the size of the image of the defective portion are different, the size of the image of the defective portion can be adjusted so that they are the same size. This makes it possible to transfer regardless of the size of the transfer destination.

[0013] Furthermore, the present invention may be an image inspection method characterized in that, in the measurement result display step, the measurement results are displayed in the form of a histogram. This makes it easy to check the frequency of defective products based on the measurement values.

[0014] In the present invention, the inspection object is a circuit board on which electronic elements are mounted, the transfer destination in the image of the non-defective product is a connection portion between the electronic element and the circuit board, The image inspection method may be characterized in that the boundaries of the connection portions in the non-defective product images in the X and Y directions are automatically determined by binarization, thereby clearly determining the transfer destination.

[0015] The present invention may also be an image inspection method characterized in that the boundaries of the connection portion in the Z direction are both ends of the connection portion and are automatically set by capturing the positions of both ends of the connection portion. This allows the transfer destination to be clearly determined even when the non-defective product is three-dimensional.

[0016] Furthermore, the present invention may also be a management method for images of a plurality of defect locations in the above-mentioned image inspection method, characterized in that images of the plurality of defect locations acquired in past inspections are compiled into a database, and each of the images of the plurality of defect locations is associated with a numerical defect level representing the type of the inspection object, the type of defect, and the degree of defect, and the numerical defect level is determined based on measurement results measured in the measurement step in the past or based on results of visual inspection in the past.This makes it possible to grasp more detailed information about the defect locations.It is also possible to provide this more detailed information about the defect locations.

[0017] In addition, in the present invention, An image inspection device that can distinguish between good and bad products in an inspection object, a database that stores data on images of the non-defective products; a defect database that stores image data of a plurality of defect locations in an inspection object of the same type as the non-defective product; a transfer unit that transfers, onto a transfer destination in the image of the non-defective product acquired from the database, one or more images of defective parts among the images of the plurality of defective parts acquired from the defect database corresponding to the transfer destination, thereby generating a transferred image; a display unit that displays the image of the non-defective product acquired from the database and the images of the plurality of defective locations acquired from the defect database; The image inspection device may include the following.

[0018] According to the present invention, it is possible to transfer an image of a defective part onto the transfer destination of an image of a good product with a simple device configuration, which makes it possible to distinguish between good and defective products, and by being able to distinguish between good and defective products, it becomes easier to carry out teaching.

[0019] Furthermore, the present invention may be an image inspection device further comprising a measurement unit that measures predetermined feature quantities in the transfer image, and the display unit displays the transfer image obtained by the transfer unit, the measurement results obtained by the measurement unit, and the measurement results of the predetermined feature quantities in other inspection objects. This makes it possible to visually and numerically distinguish between good and bad products, and the discrimination criteria become clearer, making teaching easier to carry out.

[0020] Furthermore, the present invention may be an image inspection device characterized in that the image of the non-defective product and the images of the plurality of defective locations are displayed as cross-sectional images from three directions of X, Y and Z on the display unit. The display unit can display images of good products and images of multiple defective areas as cross-sectional images from all directions, including the XY, YZ, and XZ directions, making it easy to grasp the overall picture of good products and defective areas.

[0021] Furthermore, in the present invention, the image inspection device may be configured such that, when the size of the transfer destination and the size of the image of the defective portion are different, the transfer unit can adjust the size of the image of the defective portion so that they are the same size. This makes it possible to transfer regardless of the size of the transfer destination.

[0022] The present invention may also be an image inspection device characterized in that the measurement results are displayed as a histogram on the display unit. By displaying the results as a histogram, the frequency of defective products can be easily confirmed according to the measurement values. Furthermore, if the transfer image and the histogram can be displayed simultaneously on the display unit, it becomes easier to visually and numerically distinguish between good and defective products.

[0023] Furthermore, the present invention may be an image inspection device characterized in that the object to be inspected is a circuit board on which electronic elements are mounted, the transfer destination in the image of the non-defective product is a connection portion between the electronic element and the circuit board, and the boundary in the XY direction of the connection portion in the image of the non-defective product is automatically determined by binarization. This allows the transfer destination to be clearly determined.

[0024] Furthermore, in the present invention, the image inspection device may be characterized in that the boundaries of the connection portion in the Z direction are both ends of the connection portion and are automatically set by capturing the positions of both ends of the connection portion. With this, the transfer destination can be clearly determined even when the non-defective product is three-dimensional.

[0025] Furthermore, in the present invention, the image inspection device may be characterized in that the defect database stores images of the plurality of defect locations acquired in past inspections, and each of the images of the plurality of defect locations is associated with a numerical defect level representing the type of the inspection object, the type of defect, and the degree of defect, and the numerical defect level is determined based on the measurement results previously measured by the measurement unit or the results of previous visual judgment. This makes it possible to obtain more detailed information about the defect locations.

[0026] The above means for solving the problems can be used in combination with each other whenever possible. [Effects of the Invention]

[0027] According to the present invention, by transferring an image of a defective part of a part onto an image of a good product, it is possible to efficiently create images of pseudo-defective parts and use them for quality control. As a result, it is possible to generate and display images of pseudo-defective parts and measurement values, and to visually and numerically distinguish between good and defective products. In addition, it is possible to secure sufficient images of defective parts, making it easier to carry out teaching. [Brief explanation of the drawings]

[0028] [Figure 1] FIG. 1 is a functional block diagram showing an example of an X-ray inspection apparatus according to an embodiment of the present invention. [Figure 2] FIG. 2 is an explanatory diagram showing an example of a method for managing images of a plurality of defective locations in an image inspection method using an X-ray inspection apparatus according to an embodiment of the present invention. [Figure 3] Fig. 3A is a first diagram illustrating an example of the flow of content displayed on a display unit in an image inspection method using an X-ray inspection apparatus according to an embodiment of the present invention. Fig. 3B is a second diagram illustrating an example of the flow of content displayed on a display unit in an image inspection method using an X-ray inspection apparatus according to an embodiment of the present invention. [Figure 4] Fig. 4A is a third diagram illustrating an example of the flow of content displayed on the display unit in an image inspection method using the X-ray inspection apparatus according to an embodiment of the present invention. Fig. 4B is a fourth diagram illustrating an example of the flow of content displayed on the display unit in an image inspection method using the X-ray inspection apparatus according to an embodiment of the present invention. [Figure 5] FIG. 5 is a fifth diagram illustrating an example of the flow of content displayed on the display unit in the image inspection method using the X-ray inspection apparatus according to the embodiment of the present invention. [Figure 6] FIG. 6 is a flowchart showing the procedure of an image inspection method using an X-ray inspection apparatus according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0029] [Application example] An outline of an application example of the present invention will be explained below with reference to some of the drawings. The present invention can be applied to an X-ray inspection apparatus 1 as shown in Fig. 1. Furthermore, by using the X-ray inspection apparatus 1, the present invention can be applied to processing as shown in the flowchart of Fig. 6.

[0030] FIG. 1 is a functional block diagram showing an example of an X-ray inspection apparatus 1 to which the present invention can be applied. As shown in FIG. 1, the X-ray inspection apparatus 1 is broadly configured to include an imaging unit 10, a calculation unit 20, and a display unit 30. The imaging unit 10 is configured to include a stage 11, an imaging condition storage unit 12, an X-ray generator 13, and an X-ray detector 14. An object to be inspected by the X-ray inspection apparatus 1 (e.g., a circuit board with electronic components soldered thereon) is placed on the stage 11, and is imaged by an imaging camera (not shown) based on imaging conditions (e.g., imaging distance, brightness, etc.) read from the imaging condition storage unit 12. Furthermore, the three-dimensional structure, etc. of the object to be inspected placed on the stage 11 is analyzed using X-rays generated by the X-ray generator 13. The X-ray detector 14 detects the intensity of X-rays irradiated from the X-ray generator 13 and transmitted through the object to be inspected.

[0031] The calculation unit 20 includes a three-dimensional data creation unit 21, a database 22, a defect database 23, a transfer unit 24, and a measurement unit 25. The three-dimensional data creation unit 21 creates three-dimensional data based on an image of the inspection object captured by an imaging camera. The three-dimensional data refers to a tomographic image viewed from three directions (X, Y, and Z). It is often difficult to obtain three-dimensional data of defective products from the inspection object because defects rarely occur during the manufacturing process of the inspection object. Therefore, the three-dimensional data of the inspection object is often created as data of a non-defective product. The created three-dimensional data is stored in the database 22. For example, if the inspection object is a planar structure or if data on only the surface of the inspection object is to be obtained, the calculation unit 20 may be configured to create two-dimensional data instead of the three-dimensional data creation unit 21. The defect database 23 stores three-dimensional data of multiple defect locations in parts of the same type as the inspection object. The data stored in the defect database 23 may also be two-dimensional data.

[0032] The display unit 30 displays the three-dimensional data created by the three-dimensional data creation unit 21 (hereinafter, this three-dimensional data will be referred to as "images of good products" in order to clearly distinguish it from the three-dimensional data of defective parts), and the three-dimensional data of defective parts stored in the defect database 23 (hereinafter, referred to as "images of defective parts"). The defect database 23 stores images of defective parts previously acquired in past inspections in a database. By selecting a partial area of ​​the image of a good product and an image of the defective part on the display unit 30, the transfer unit 24 transfers the image of the defective part onto the partial area of ​​the image of the good product. This updates the image of the good product and generates a transferred image including pseudo-defective parts. Here, transfer refers to the process of cutting and pasting an image without making it look unnatural, by combining a general image processing method (for example, a binarization method). This means (the same applies to the transfer described in the following examples). Furthermore, the transfer destination means the area where the process of cutting and pasting the image is performed (the same applies to the transfer destination described in the following examples). The display unit 30 displays this transferred image, and the measurement unit 25 measures the displayed transferred image. When the measurement is completed, the display unit 30 displays the measurement result (not shown). This measurement result makes it possible to confirm the frequency of defects occurring in the object being inspected.

[0033] The details of the calculation process executed by the calculation unit 20 and the content displayed by the display unit 30 will be explained in the following examples with reference to FIGS. 3A, 3B, 4A, 4B, and 5.

[0034] 6 is a flowchart showing the procedure of an image inspection method using an X-ray inspection apparatus 1 to which the present invention is applicable. Only an outline of the flow will be explained in this application example, and details will be explained in the following examples.

[0035] In the image inspection method using the X-ray inspection apparatus 1 in this application example, as described above, first, an image of a non-defective product created by the three-dimensional data creation unit 21 is displayed on the display unit 30, and then images of defective areas obtained from the defect database 23 are also displayed on the display unit 30. Next, any point is selected as a transfer destination from the image of the non-defective product displayed on the display unit 30, and one or more images of defective areas are selected from the images of the multiple defective areas displayed on the display unit 30. Once the transfer destination is determined, the image of the selected defective area is transferred to the transfer destination. In this way, the image of the non-defective product is processed to generate a transferred image including pseudo-defective areas. Next, this transferred image is displayed on the display unit 30, and predetermined feature quantities are measured by the measurement unit 25. Finally, the measurement results are displayed on the display unit 30.

[0036] As described above, according to the image inspection method using the X-ray inspection apparatus 1 in this application example, even if no defects occur in the manufacturing process of the object to be inspected and data on the defective part in the object to be inspected cannot be acquired from the three-dimensional data creation unit 21, it is possible to generate a transferred image including a pseudo-defective part by the transfer unit 24. Furthermore, by measuring the transferred image by the measurement unit 25, it becomes possible to visually and numerically distinguish between a good product and a defective product. This transferred image can also be provided as a standard for distinguishing between a good product and a defective product.

[0037] [Example] An image inspection method using an X-ray inspection device 1 according to an embodiment of the present invention will be described in more detail below with reference to the drawings (including the drawings that were explained in the application example above). Note that the X-ray inspection device according to the present invention is not intended to be limited to the following configuration. Also, in the embodiment, the X-ray inspection device 1 is exemplified as an example of an image inspection device, but this is not intended to be limiting and other types of devices may be used.

[0038] <Device configuration> Now, let us return to the explanation of Fig. 1. The X-ray inspection apparatus 1 according to this embodiment has the same configuration as the X-ray inspection apparatus 1 described in the application example, and therefore detailed explanation of the contents described in the application example will be omitted. Furthermore, in this specification, the same components will be described using the same reference numerals.

[0039] The three-dimensional data creation unit 21 can acquire images of non-defective products that have been stored in the database 22 in the past from the database 22. Therefore, even if an inspection object is not placed on the stage 11, the transfer unit 24 can transfer an image of a defective part onto an image of a non-defective product of the inspection object. Therefore, the three-dimensional data creation unit 21 can generate a transferred image as a function independent of the imaging function of the X-ray inspection device 1. Also, as shown in FIG. 2, for example, the defect database 23 stores a database of images of multiple defective parts that have been acquired in advance in past inspections, and for each of the images of multiple defective parts, the type of the inspection object and the defect are stored. The type and the defect stage represented by a numerical value indicating the degree of defect are associated. And an ID is assigned with the four items of the image of the defective part, the type of the part, the type of the defect, and the defect stage represented by a numerical value as one set. The display unit 30 may be configured to display the information of the four items. Also, it is possible to search for one of the four items by a filter function or a sort function. When the inspection object is, for example, a circuit board on which an electronic element is soldered, examples of the type of defect include non-wetting, voids, etc. (In FIG. 2, as an image of the defective part, an image of a defective pin 51 (details will be described below) at the soldered part is illustrated). The defect stage represented by a numerical value is a numerical value determined based on the measurement result measured by the measurement unit 25 in the past or based on the result determined visually in the past. As detailed information related to the image of the defective part, it is also possible to provide information in which the above four items are managed as one set. The management method shown in FIG. 2 corresponds to the management method of the image of the defective part in the present invention.

[0040] <Image Inspection Method Using an X-ray Inspection Device> Hereinafter, based on FIGS. 3A, 3B, 4A, 4B, and 5, a flow of an example of the content displayed by the display unit 30 in the image inspection method using the X-ray inspection device 1 according to the present embodiment will be described. The content displayed by the display unit 30 is based on the arithmetic processing executed by the arithmetic unit 20. Also, hereinafter, as an example, it is assumed that the inspection object is a plurality of pins 50 in a chip 40 which is an electronic element on a circuit board.

[0041] FIG. 3A shows an example of the content displayed on the display unit 30 when the three-dimensional data creation unit 21 creates an image of a non-defective chip 40. The display unit 30 displays images of one chip 40 as cross-sectional images, each viewed from the XY direction (directions in a plan view), the YZ direction (directions in a side view), and the XZ direction (directions in a front or rear view). To clarify the direction from which the image is viewed, each image may be labeled with an "XY," "YZ," or "XZ." Furthermore, in the case of a non-defective chip, the pin 50 has a circular shape with high roundness when viewed from the XY direction, and the pin 50 has an elliptical shape when viewed from the YZ and XZ directions. The display unit 30 also displays buttons indicating commands to the calculation unit 20, such as "Transfer Settings," "Transfer Execution," and "Measurement." When a user presses one of these buttons, the calculation unit 20 starts calculation processing.

[0042] FIG. 3B shows an example of the content displayed on the display unit 30 when images of multiple defective locations (hereinafter referred to as "faulty pins 51") are acquired from the defect database 23. Images of multiple defective pins 51 are displayed in a list when the user presses the "Transfer Settings" button. Images of the defective pin 51 as seen from the XY direction, the YZ direction, and the XZ direction are also displayed as a set of cross-sectional images. Furthermore, the defective pin 51 may also be labeled with "XY," "YZ," or "XZ." In this embodiment, the defective pin 51 refers to, for example, a pin whose shape is deformed from a perfect circle or ellipse.

[0043] FIG. 4A is an example of the content displayed on the display unit 30 when selecting a portion of the image of the chip 40 that will be the transfer destination and an image of the defective pin 51 that will be the transfer source. When determining the transfer destination and the transfer source, an arbitrary point is selected from the image of the chip 40 displayed in FIG. 3A, and an image of one defective pin 51 is selected from the images of the multiple defective pins 51 displayed in FIG. 3B. Each selected point is displayed, for example, as shown in FIG. 4A, as a black dot. When an arbitrary point is selected from the image of the chip 40, the transfer destination is determined based on that point. Specifically, with regard to the pin 50 that will be the transfer destination, the boundaries in the X and Y directions are automatically determined by binarization, or an area is manually set and then the image within that area is automatically determined by binarization. The boundaries in the Z direction are both ends of the pin 50, and are automatically set by capturing the positions of both ends of the pin 50. The image of the chip 40 is processed by capturing the characteristics of the chip 40 and the pin 50 so that the boundaries in the Z direction can be automatically set. As a result, the image of the chip 40 that will be the transfer destination is automatically determined. The image of the defective pin 51 that is the transfer source is determined in correspondence with the image portion and the transfer destination. Note that an area may be selected in the image of the chip 40 so that multiple images of the pins 50 are included, and multiple images of the defective pins 51 may be selected corresponding to each of the multiple pins 50. Here, the transfer destination corresponds to the pin 50 that serves as the connection portion between the electronic element and the circuit board.

[0044] FIG. 4B is an example of the content displayed on the display unit 30 when an image of a defective pin 51 is transferred onto a part of the image of the chip 40. When the user presses the "Execute Transfer" button, the transfer unit 24 transfers the image of the defective pin 51 selected in FIG. 4A onto a part of the image of the chip 40. As a result of this transfer, the pins 50 on the chip 40 are replaced with defective pins 51 (hereinafter, the pins 50 replaced by this transfer are referred to as "transfer pins 52"), and a transferred image is generated. During transfer, the sizes of the transfer destination image and the transfer source image often differ, so the size of the image of the defective pin 51 to be transferred can be adjusted by enlarging or reducing it so that these sizes are the same. 4A, for example, if a partial area of ​​the image of the chip 40 viewed from the XY direction is selected, that area is defined not only in the XY direction but also in the YZ and XZ directions. Therefore, when a transfer image is generated in FIG. 4B, the transfer pins 52 are displayed in all directions, namely, the XY direction, the YZ direction, and the XZ direction (i.e., when the transfer pins 52 viewed from the XY direction are displayed, the transfer pins 52 viewed from the YZ and XZ directions corresponding to those transfer pins 52 are also displayed). The transfer pins 52 are displayed, for example, surrounded by a square, as shown in FIG. 4B. Furthermore, as described above, it is possible to select a portion of the image of the chip 40 in multiple locations in FIG. 4A and select multiple images of defective pins 51 corresponding to each of those multiple locations. In this case, multiple defective pins 51 can be transferred to obtain images of more transfer pins 52 (i.e., images of defective locations).

[0045] FIG. 5 shows an example of the content displayed on the display unit 30 when a transfer image is measured. The transfer image includes pins 50 and transfer pins 52. When the user presses the "Measure" button, the measurement unit 25 measures predetermined feature values ​​for all pins 50 and transfer pins 52 on the transfer image and all pins 50 and transfer pins 52 on other chips 40 that are not included in the transfer image. Once the measurement is performed, the display unit 30 displays the measurement results 60. The measurement results 60 are displayed, for example, as a histogram, with the horizontal axis representing the measurement value and the vertical axis representing the frequency, as shown in FIG. 5. In this case, a histogram of the measurement values ​​of the predetermined feature values ​​of the object being measured in the process can be displayed based on the measurement values ​​of the predetermined feature values ​​in the newly created transfer image and images of other chips 40. Alternatively, a histogram of the measurement values ​​of all pins 50 and transfer pins 52 on the chip 40 related to the transfer image currently displayed can be displayed. The predetermined feature values ​​can be, for example, the roundness and area of ​​the surfaces of the pins 50 and transfer pins 52. The pins 50 and transfer pins 52 are roughly classified as non-defective or defective based on a predetermined threshold value for these measurement values.

[0046] <Flowchart> Returning now to the explanation of FIG. 6 , the procedure of the image inspection method using the X-ray inspection apparatus 1 according to this embodiment will be described in detail below with reference to FIG. 6 . In this flowchart, first, the three-dimensional data creation unit 21 creates an image of the chip 40 as viewed from the XY, YZ, and XZ directions, and the display unit 30 displays the image of the chip 40 as a tomographic image (S101). Here, S101 corresponds to the image display step in the present invention and to FIG. 3A in this embodiment. Furthermore, the display unit 30 displays images of a plurality of defective pins 51 as viewed from the XY, YZ, and XZ directions, acquired from the defect database 23, alongside the image of the chip 40 (S102). Here, S102 corresponds to the defect image display step in the present invention and to FIG. 3B in this embodiment. Next, an arbitrary point is selected from the image of the chip 40 displayed on the display unit 30, and one or more images of defective pins 51 corresponding to the arbitrary point are selected from the images of the plurality of defective pins 51. When an arbitrary point is selected from the image of the chip 40, the boundary in the XY direction and the boundary in the Z direction are determined based on the arbitrary point, and the transfer destination is determined (S10 3). Here, S103 corresponds to the selection step in the present invention and FIG. 4A in this embodiment. Once the transfer destination is determined, an image of the selected defective pin 51 is transferred to the transfer destination. This processes the image of the chip 40, generating a transfer image including the transfer pin 52 as a pseudo-defective location (S104). Here, S104 corresponds to the transfer step in the present invention and FIG. 4B in this embodiment. The display unit 30 displays the transfer image (S105), and the measurement unit 25 measures, for example, the roundness and area of ​​the surfaces of all pins 50 and transfer pins 52 on the chip 40 other than the transfer image (S106). Here, S105 corresponds to the transfer image display step in the present invention and FIG. 5 in this embodiment. Also, S106 corresponds to the measurement step in the present invention and FIG. 5 in this embodiment. The measurement result 60 in S106 is displayed on the display unit 30, for example, as a histogram (S107). Here, S107 corresponds to the measurement result display step in the present invention and to FIG. 5 in this embodiment.

[0047] <Appendix 1> An image inspection method that enables discrimination between good products (50) and defective products (51, 52) in an inspection object (40) using an image inspection device (1), an image display step (S101) of displaying an image of the non-defective product; a defect image display step (S102) for displaying images of a plurality of defect locations (51) in an inspection object of the same type as the non-defective product; a selection step (S103) of selecting a transfer destination in the image of the non-defective product and one or more images of defective parts from the images of the plurality of defective parts corresponding to the transfer destination; a transfer step (S104) of transferring an image of one or more defective parts from the images of the plurality of defective parts selected in the selection step onto the transfer destination in the image of the non-defective product, thereby generating a transferred image; An imaging inspection method comprising:

[0048] <Appendix 2> An image inspection device (1) that can distinguish between good products (50) and defective products (51, 52) in an inspection object (40), a database (22) for storing data on images of the non-defective products; a defect database (23) that stores image data of a plurality of defect locations (51) in an inspection object of the same type as the non-defective product; a transfer unit (24) that transfers one or more images of defective parts among the images of the plurality of defective parts obtained from the defect database corresponding to the transfer destination onto a transfer destination in the image of the non-defective product obtained from the database, thereby generating a transferred image; a display unit (30) that displays the image of the non-defective product acquired from the database and the images of the plurality of defective locations acquired from the defect database; An image inspection device (1) comprising: [Explanation of symbols]

[0049] 1: X-ray inspection equipment 10: Imaging unit 11: Stage 12: Imaging condition storage unit 13: X-ray generator 14: X-ray detector 20: Arithmetic section 21: 3D data creation department 22: Database 23: Bad database 24: Transfer unit 25: Measurement section 30:Display section 40: Tip 50: Pin 51: Bad pin 52: Transfer pin 60: Measurement results

Claims

1. An image inspection method that enables discrimination between good and bad products in an inspection object using an image inspection device, comprising: an image display step of displaying a screen simultaneously showing a non-defective inspection image display area for displaying an image of the non-defective product, and a defective image display area for displaying images of a plurality of defective locations in an inspection object of the same type as the non-defective product, the images of the plurality of defective locations being narrowed down or arranged based on at least one of the type of the inspection object, the type of defect, or the degree of defect; a selection step of selecting a transfer destination in the image of the non-defective product and one or more images of defective parts from the images of the plurality of defective parts corresponding to the transfer destination; a transfer step of transferring the image of one or more defective parts from the images of the plurality of defective parts selected in the selection step onto the transfer destination of the image of the non-defective product, thereby generating a transferred image; An imaging inspection method comprising:

2. a transfer image display step of displaying the transfer image; a measuring step of measuring a predetermined feature amount in the transfer image; a measurement result display step of displaying the measurement result obtained in the measurement step, or the measurement result obtained in the measurement step and other measurement results of the predetermined feature amount of the inspection object; The image inspection method of claim 1 , further comprising:

3. 3. The image inspection method according to claim 1, wherein in the image display step, the image of the non-defective product and the images of the plurality of defective locations are displayed as cross-sectional images from three directions of X, Y and Z.

4. In the transfer step, if the size of the transfer destination and the size of the image of the defective portion are different, the size of the image of the defective portion is adjusted so that the sizes are the same. The image inspection method according to claim 1 , wherein the image inspection method is capable of:

5. 3. The image inspection method according to claim 2, wherein in said measurement result display step, said measurement result is displayed in the form of a histogram.

6. the inspection object is a circuit board on which electronic elements are mounted, the transfer destination in the image of the non-defective product is a connection portion between the electronic element and the circuit board, 6. The image inspection method according to claim 1, wherein the boundaries of the connection portions in the image of the non-defective product in the X and Y directions are automatically determined by binarization.

7. An image inspection method that enables discrimination between good and bad products in an inspection object using an image inspection device, comprising: an image display step of simultaneously displaying a screen showing a non-defective inspection image display area for displaying an image of the non-defective product and a defective image display area for displaying images of a plurality of defective locations in an inspection object of the same type as the non-defective product; a selection step of selecting a transfer destination in the image of the non-defective product and one or more images of defective parts from the images of the plurality of defective parts corresponding to the transfer destination; a transfer step of transferring the image of one or more defective parts from the images of the plurality of defective parts selected in the selection step onto the transfer destination of the image of the non-defective product, thereby generating a transferred image; and the inspection object is a circuit board on which electronic elements are mounted, the transfer destination in the image of the non-defective product is a connection portion between the electronic element and the circuit board, The boundary of the connection portion in the image of the non-defective product in the X and Y directions is automatically determined by binarization, An image inspection method, characterized in that the Z-direction boundaries of the connection portion are both ends of the connection portion and are automatically set by capturing the positions of both ends of the connection portion.

8. 3. The image inspection method according to claim 2, wherein the image management method for a plurality of defective locations comprises: Images of the plurality of defective locations acquired in past inspections are stored in a database, A method for managing images of defective parts, characterized in that each of the images of the plurality of defective parts is linked to a numerical defect level that represents the type of the object to be inspected, the type of defect, and the degree of defect, and the numerical defect level is a value that is determined based on measurement results measured in the measurement step in the past or based on results of visual inspection in the past.

9. An image inspection device that can distinguish between good and bad products in an inspection object, a database that stores data on images of the non-defective products; a defect database that stores image data of a plurality of defect locations in an inspection object of the same type as the non-defective product; a transfer unit that transfers, onto a transfer destination in the image of the non-defective product acquired from the database, one or more images of defective parts among the images of the plurality of defective parts acquired from the defect database corresponding to the transfer destination, thereby generating a transferred image; a display unit that displays a screen simultaneously showing a non-defective inspection image display area showing the images of the non-defective products acquired from the database, and a defect image display area showing the images of the plurality of defect locations acquired from the defect database, the images being narrowed down or arranged based on at least one of the type of the inspection object, the type of defect, or the degree of defect; An image inspection device comprising:

10. a measurement unit that measures a predetermined feature amount in the transfer image, 10. The image inspection device according to claim 9, wherein the display unit also displays the transferred image obtained in the transfer unit, the measurement results obtained in the measurement unit, and the measurement results of the predetermined feature amounts in other inspection objects.

11. 11. The image inspection device according to claim 9, wherein the image of the non-defective product and the images of the plurality of defective locations are displayed on the display unit as cross-sectional images from three directions of X, Y and Z.

12. 12. The image inspection device according to claim 9, wherein, when the size of the transfer destination and the size of the image of the defective portion are different, the transfer unit is capable of adjusting the size of the image of the defective portion so that the sizes are the same.

13. 11. The image inspection device according to claim 10, wherein the measurement results are displayed in the form of a histogram on the display unit.

14. the inspection object is a circuit board on which electronic elements are mounted, the transfer destination in the image of the non-defective product is a connection portion between the electronic element and the circuit board, 14. The image inspection device according to claim 9, wherein the boundaries of the connection portions in the image of the non-defective product in the X and Y directions are automatically determined by binarization.

15. An image inspection device that enables discrimination between good and bad products in an inspection object, comprising: a database that stores data on images of the non-defective products; a defect database that stores image data of a plurality of defect locations in an inspection object of the same type as the non-defective product; a transfer unit that transfers, onto a transfer destination in the image of the non-defective product acquired from the database, one or more images of defective parts among the images of the plurality of defective parts acquired from the defect database corresponding to the transfer destination, thereby generating a transferred image; a display unit that displays a screen simultaneously showing a non-defective inspection image display area showing the image of the non-defective product acquired from the database and a defective image display area showing images of the plurality of defective locations acquired from the defective database; Equipped with the inspection object is a circuit board on which electronic elements are mounted, the transfer destination in the image of the non-defective product is a connection portion between the electronic element and the circuit board, The boundary of the connection portion in the image of the non-defective product in the XY direction is automatically determined by binarization, An image inspection device characterized in that the Z-direction boundaries of the connection portion are both ends of the connection portion and are automatically set by capturing the positions of both ends of the connection portion.

16. In the defect database, images of the plurality of defect locations acquired in past inspections are compiled into a database, 11. The image inspection device according to claim 10, wherein each of the images of the plurality of defective areas is associated with a numerical defect level representing the type of the object to be inspected, the type of defect, and the degree of defect, and the numerical defect level is determined based on measurement results previously measured by the measurement unit or based on results previously determined by visual inspection.

Images