Additional inspection device and inspection system

Abstract

To reduce the number of defect images that an operator checks in a defect verification device.SOLUTION: An additional inspection device 12 which is added to an inspection device 11 that inspects the appearance of a printed wiring board comprises: a reception unit 31 that receives a defect image indicating a defect of a printed wiring board detected by the inspection device 11; an image processing unit 33 that applies image processing to the defect image and acquires a processed image; a reinspection unit 34 that reinspects the defect image to determine whether it indicates a defect on the basis of the processed image; and an output unit 35 that outputs the defect image to a defect verification device 13 for the operator to verify the defect image when it is determined by the reinspection unit 34 that the defect image indicates a defect.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to a technique for inspecting the appearance of a printed wiring board. [Background technology]

[0002] Conventionally, in the manufacture of printed wiring boards, inspection devices that capture images of printed wiring boards to detect defects have been used. Known examples of such visual inspection devices include an intermediate inspection device called AOI (Automated Optical Inspection) and a final visual inspection device called AVI (Automated Final Visual Inspection). These visual inspection devices inspect each part of the printed wiring board, divided by material or function. For example, the inspection device disclosed in Patent Document 1 detects defects in the plated and silk sections of the printed wiring board based on captured color images, and detects defects in the solder resist section based on black-and-white images. Examples of defects that can be detected include those caused by the material of the silk section adhering to the plated section and those caused by minute particles of dust adhering to the solder resist section. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Laid-Open No. 2015-143656 Summary of the Invention [Problem to be solved by the invention]

[0004] However, visual inspection devices may detect defects that are not actually defects as defects called "false reports" or "pseudo defects." For this reason, images of defects detected by visual inspection devices are sent to a defect confirmation device (a so-called verify device). The defect confirmation device displays the defect image and a master image without any defects side by side, and workers can view these images to confirm whether the defect image is a false report. If the defect image indicates a defect, they discard or repair the printed wiring board.

[0005] False alarms occur due to variations in the manufacturing process of printed wiring boards or low detection standards to prevent true defects from being overlooked. For example, if variations in the manufacturing process cause differences in the color or shape of the entire or partial printed wiring board, these differences will be detected as defects by a visual inspection device. Furthermore, if solder resist peeling is reliably detected using color differences, foreign matter that does not affect the functionality of the board will be detected as a defect with a certain probability. Defects that do not affect the functionality of the printed wiring board will then be judged as false alarms by a worker's visual reconfirmation.

[0006] When false reports occur frequently, the number of images that workers must judge as genuine increases, which increases the incidence and number of human errors and the possibility of misjudging genuine defects as false reports.

[0007] The present invention has been made in view of the above-mentioned problems, and has as its object to reduce the number of defect images that an operator checks using a defect checking device. [Means for solving the problem]

[0008] A first aspect of the present invention is an additional inspection device that is added to an inspection device that inspects the appearance of a printed wiring board, and includes: a receiving unit that receives defect images that indicate defects in the printed wiring board detected by the inspection device; an image processing unit that performs image processing on the defect images to obtain processed images; a re-inspection unit that re-inspects the processed images to determine whether the defect images indicate defects; and an output unit that, when the re-inspection unit determines that the defect images indicate defects, outputs the defect images to a defect confirmation device for an operator to check the defect images.

[0009] A second aspect of the present invention is the additional inspection device of the first aspect, wherein the defect image is an image of one defect and its surrounding area cut out from an image of the printed wiring board.

[0010] Aspect 3 of the present invention is an additional inspection device of aspect 1 (which may be aspect 1 or 2), in which the reception unit receives from the inspection device, along with the defect image, an inspection type, which is information indicating the type of inspection performed by the inspection device when the defect was detected, the image processing unit applies image processing selected in accordance with the inspection type to the defect image, and the re-inspection unit re-inspects the defect image using a method selected in accordance with the inspection type.

[0011] A fourth aspect of the present invention is an additional inspection device of the first aspect (which may be any one of the first to third aspects), in which the defect image received by the reception unit is at least a part of an image that has been determined to exhibit a defect based on whether the target image to be inspected in the inspection device satisfies the inspection criteria.

[0012] A fifth aspect of the present invention is an additional inspection device according to the fourth aspect (which may be any one of the first to fourth aspects), in which the re-inspection unit determines whether the defect image indicates a defect based on whether the processed image satisfies the inspection criteria.

[0013] A sixth aspect of the present invention is an additional inspection device according to the first aspect (which may be any one of the first to fifth aspects), in which the image processing unit calculates a threshold based on pixel values ​​of the defect and its surrounding area in the defect image, and obtains the processed image by binarizing the defect image using the threshold, and the re-inspection unit determines whether the defect image indicates a defect by comparing the processed image with a reference binary image.

[0014] A seventh aspect of the present invention is an additional inspection device according to the first aspect (which may be any one of the first to fifth aspects), in which the image processing unit acquires a processed image in which a specific type of area is extracted from the defect and its surrounding area in the defect image, and the re-inspection unit calculates a degree of variation indicating the variation in pixel values ​​in the specific type of area, and compares the degree of variation with a predetermined threshold value to determine whether the defect image indicates a defect.

[0015] Aspect 8 of the present invention is an additional inspection device of aspect 1 (which may be any one of aspects 1 to 5), in which the image processing unit acquires a processed image in which the defect and its surrounding area in the defect image are aligned with a reference area image, and the re-inspection unit determines whether the defect image indicates a defect by comparing the processed image with the reference area image.

[0016] A ninth aspect of the present invention is an inspection system for inspecting the appearance of a printed wiring board, comprising an additional inspection device described in any one of aspects 1 to 8, and the inspection device that outputs a defect image showing defects in the printed wiring board to the additional inspection device. [Effects of the Invention]

[0017] According to the present invention, it is possible to reduce the number of defect images that an operator checks using a defect checking device. [Brief explanation of the drawings]

[0018] [Figure 1] FIG. 10 is a diagram showing the configuration of an inspection system including an additional inspection device. [Figure 2] FIG. 10 is a diagram showing the configuration of a computer that is an additional inspection device. [Figure 3] FIG. 2 is a diagram showing the flow of operations of the inspection device. [Figure 4] FIG. 10 is a diagram showing the flow of operations of the additional inspection device. [Figure 5A] FIG. 10 is a diagram showing a defect image. [Figure 5B] FIG. 10 is a diagram showing a part of a reference binary image. [Figure 5C] FIG. 1 is a diagram showing a part of a target binary image. [Figure 5D] FIG. [Figure 5E] FIG. 10 is a diagram showing a target binary image that is a processed image. [Figure 6A] FIG. 10 is a diagram showing a defect image. [Figure 6B] FIG. 10 is a diagram showing a part of a reference image. [Figure 6C] FIG. 10 is a diagram showing a target processed image that is a processed image. [Figure 6D] FIG. 10 is a diagram showing a reference processed image. [Figure 6E] FIG. [Figure 7] FIG. 10 is a diagram illustrating a distribution of pixel values. [Figure 8A] FIG. 10 is a diagram showing a defect image. [Figure 8B] FIG. 10 is a diagram showing a part of a reference image. [Figure 8C] FIG. [Figure 8D] FIG. 10 shows a processed image. DETAILED DESCRIPTION OF THE INVENTION

[0019] FIG. 1 is a diagram showing the configuration of an inspection system 1 including an additional inspection device 12 according to one embodiment of the present invention. The inspection system 1 inspects the appearance of a printed wiring board, which is an object. "Inspecting the appearance" means acquiring an image of the printed wiring board and determining whether the printed wiring board has a defect based on the image. The inspection system 1 includes an appearance inspection device (hereinafter simply referred to as "inspection device") 11 that captures an image of the printed wiring board and inspects its appearance, an additional inspection device 12, and a defect confirmation device 13, which are connected via a communication network 14. The inspection device 11 may be an intermediate inspection device called AOI or a final appearance inspection device called AVI. The printed wiring board is the board inspected by these devices, and may be a printed wiring board in the process of being manufactured or a completed printed wiring board.

[0020] The inspection device 11 includes an image acquisition unit 21 and an inspection unit 22. The image acquisition unit 21 includes an imaging unit and a movement mechanism. The imaging unit has a so-called line sensor in which multiple imaging elements are arranged in a line. The movement mechanism moves the printed wiring board relative to the imaging unit. The imaging unit repeatedly acquires line images while the printed wiring board moves relative to the imaging unit, thereby acquiring a two-dimensional image of the printed wiring board. The imaging unit that acquires the image of the printed wiring board can be modified in various ways. For example, the imaging unit may acquire a two-dimensional image of the printed wiring board using an image sensor in which imaging elements are arranged two-dimensionally.

[0021] The inspection unit 22 is realized by, for example, a computer and / or a dedicated electric circuit. The inspection unit 22 detects defects from an image of the printed wiring board and acquires an image including the defect and its vicinity as a defect image. The defect image at this stage is an image showing a defect that the inspection device 11 has determined to be a defect. In this way, "defective" means that the defect has been determined to be a defect according to the determining entity. Defect image data 81, which is data on the defect image, is stored in the memory unit 221 of the inspection unit 22. The inspection unit 22 performs various inspections, i.e., defect detection processes, on the image of the printed wiring board.

[0022] In the storage unit 221, together with the defect image data 81, an inspection type 82, which is information indicating the type of inspection performed when the defect image data 81 was acquired, is stored in association with the defect image data 81. The "inspection type" typically refers to the type of inspection algorithm, and in principle corresponds to an individual inspection algorithm. However, a general concept that encompasses multiple inspection algorithms may also be treated as a single inspection type. Apart from the concept of an inspection algorithm, for example, a method of inspecting specific functional elements or materials using machine learning may also be considered as a single inspection type.

[0023] The storage unit 221 may be provided outside the inspection unit 22. For example, a computer or NAS (Network Attached Storage) provided outside the housing of the inspection device 11 may function as the storage unit 221.

[0024] The inspection unit 22 is usually arranged inside the housing of the inspection device 11. The inspection unit 22 may be arranged outside the housing of the inspection device 11, or may be connected to the main body of the inspection device 11 via the communication network 14.

[0025] In the following description, defect image data will also be simply referred to as a "defect image." Similarly, data of other images may also be simply referred to by the name of the image. Furthermore, processing that is actually performed on image data may also be simply described as processing that is performed on the image. For example, binarization that is actually performed on defect image data may also be simply described as binarization of the defect image.

[0026] The additional inspection device 12 performs an additional inspection on the defect image acquired by the inspection device 11 and determines whether the defect image indicates a defect or a false report indicating a false defect. The additional inspection device 12 includes a reception unit 31, a memory unit 32, an image processing unit 33, a reinspection unit 34, and an output unit 35. In the following description, the additional inspection by the additional inspection device 12 is also referred to as a "reinspection." The additional inspection device 12 is a device added to the inspection device 11, and "addition" here means that the inspection device 11 has an independent function of outputting defect images and that the additional inspection device 12 has a function of performing additional inspection on the defect images. In other words, if the inspection device 11 can function as a device that performs inspection independently, the additional inspection device 12 does not need to be physically added later. For example, the additional inspection device 12 may be installed at the same time as the inspection device 11 is installed in a predetermined location.

[0027] Furthermore, the additional inspection device 12 may be provided inside the housing of the inspection device 11 without going through the communication network 14, or may be directly connected to the inspection device 11, or conversely, the additional inspection device 12 may be installed remotely from the inspection device 11 via the communication network 14. Furthermore, the additional inspection device 12 may be realized by a computer that realizes the inspection unit 22 in the inspection device 11. In this way, the additional inspection device 12 may be provided in various modes as long as it is added to the inspection device 11 as a function.

[0028] The additional inspection device 12 re-inspects the defect image to determine whether it is a false alarm. The additional inspection device 12 re-inspects the defect image by, for example, having a computer execute a program. Only when the re-inspection determines that the defect image is not a false alarm does the additional inspection device 12 send the defect image to the defect confirmation device 13. The defect image at this stage is an image that has been determined by the inspection device 11 and the additional inspection device 12 to show a defect.

[0029] The defect confirmation device 13 is a device that allows an operator to confirm a defect image when the additional inspection device 12 determines that the defect image indicates a defect. The defect confirmation device 13 is also a device that is realized by a computer executing a program. The defect confirmation device 13 displays a defect image and an image (hereinafter referred to as a "master image") in which no defect corresponding to the defect image exists on a display unit. The operator visually compares the two images to determine whether the defect image indicates a defect or is a false report indicating a spurious defect, and inputs the determination result into the defect confirmation device 13 via an input unit such as a mouse or keyboard. The defect confirmation device 13 is not limited to the above form as long as it is a device that allows an operator to confirm defects.

[0030] Defects in printed wiring board inspection include "functional defects" that affect the function of the printed wiring board, and "visual defects" that do not affect the function but do not meet the appearance standard. Defects in the present invention may be either functional defects or visual defects, but since defect images that are determined to be false reports by the defect confirmation device 13 are mainly images that show defects that do not affect the function, defects in the present invention may be interpreted as being limited to functional defects.

[0031] FIG. 2 is a diagram showing the configuration of a computer serving as the additional inspection device 12. The additional inspection device 12 has the configuration of a typical computer system, including a CPU 301, a GPU 302, a ROM 303, a RAM 304, a fixed disk 305, a display 306, an input unit 307, a reading device 308, a communication unit 309, and a bus 30. The CPU 301 performs various arithmetic operations. The GPU 302 performs various arithmetic operations related to image processing. The ROM 303 stores basic programs. The RAM 304 and the fixed disk 305 store various types of information. The display 306 displays various types of information, such as images. The input unit 307 includes a keyboard 307a and a mouse 307b for receiving input from an operator. The reading device 308 reads information from a computer-readable recording medium 9, such as an optical disk, a magnetic disk, a magneto-optical disk, or a memory card. The communication unit 309 transmits and receives signals to and from other components of the additional inspection device 12 and external devices. The bus 30 is a signal circuit that connects the CPU 301, the GPU 302, the ROM 303, the RAM 304, the fixed disk 305, the display 306, the input unit 307, the reading device 308, and the communication unit 309.

[0032] In the additional inspection device 12, the program 91 is read in advance from the recording medium 9 via the reading device 308 and stored on the fixed disk 305. The program 91 may be stored on the fixed disk 305 via a communication network. The CPU 301 and the GPU 302 execute arithmetic processing using the RAM 304 and the fixed disk 305 in accordance with the program 91. The CPU 301 and the GPU 302 function as a calculation unit in the additional inspection device 12. Other components that function as a calculation unit may be employed in addition to the CPU 301 and the GPU 302.

[0033] In the additional inspection device 12, the computer executes arithmetic processing and the like in accordance with the program 91, thereby realizing the functional configuration shown in Fig. 1. That is, the CPU 301, GPU 302, ROM 303, RAM 304, fixed disk 305, communication unit 309, and their peripheral components realize a reception unit 31, a storage unit 32, an image processing unit 33, a re-inspection unit 34, and an output unit 35. All or part of these functions may be realized by dedicated electrical circuits, or these functions may be realized by individual programs. Furthermore, these functions may be realized by multiple computers.

[0034] Receiving unit 31 receives defect images (more precisely, defect image data) from inspection device 11 and stores them in storage unit 32. For example, receiving unit 31 is a communication unit 309 such as an interface that communicates with communication network 14 and a functional configuration that controls this, and defect images are stored in fixed disk 305 in FIG. 2 that functions as storage unit 32. Receiving unit 31 receives defect image data from inspection device 11 as well as an inspection type, which is information indicating the type of inspection when the defect was detected, and stores the inspection type in fixed disk 305 as well.

[0035] The image processing unit 33 performs image processing on the defect image and obtains a processed image. The re-inspection unit 34 determines whether the defect image is a false alarm based on the processed image and the inspection type. If the re-inspection determines that the defect image is an image that indicates a defect, the defect image data and inspection type are sent to the defect confirmation device 13 via the output unit 35 and the communication network 14. If the re-inspection determines that the defect image does not indicate a defect, the defect image data and inspection type are not sent to the defect confirmation device 13. The output unit 35 is a communication unit 309, such as an interface that communicates with the communication network 14, and a functional configuration that controls this.

[0036] Next, a specific example of the operation of the inspection device 11 and the additional inspection device 12 will be described with reference to FIGS.

[0037] First, a printed wiring board is carried into the inspection device 11, and the image acquisition unit 21 acquires a two-dimensional image of the entire printed wiring board (hereinafter referred to as a "board image") (step S11). The board image may be a color image or a monochrome image, or both images may be acquired. Next, the inspection unit 22 performs processing to detect defects on the printed wiring board based on the board image (step S12). The inspection unit 22 performs various processes on the board image depending on the type of defect to be detected. In a typical example of the inspection device 11, defects in the board image (more precisely, areas indicating defects) are identified based on whether each area, which is an inspection unit of the board image, satisfies the inspection criteria.

[0038] 5A is a diagram showing an example of a defect image that is an image showing a defect detected by inspection unit 22. In defect image 811, the area indicated by symbol 813 within a circular bright area 812 is slightly dark, and area 813 has been detected as a defect. Such defects are detected due to changes in color across the entire printed wiring board or differences in color in parts of the board.

[0039] The operation of the inspection unit 22 when a defect image 811 is detected is as follows. First, an image of the area to be inspected in the substrate image (hereinafter referred to as the "target image") and an image of an area corresponding to the target image in a defect-free master image (hereinafter referred to as the "reference image") are prepared in advance. The area to be inspected is larger than the defect image 811 that will ultimately be obtained. Then, a reference binary image is obtained by binarizing the reference image using a predetermined threshold value. FIG. 5B is a diagram showing only the area of ​​the reference binary image that corresponds to FIG. 5A, and the fact that it is actually a larger image is indicated by the dashed outline (the same applies hereinafter).

[0040] Next, the target image is also binarized using the same threshold value, and a target binary image is obtained. FIG. 5C is a diagram showing only the region of the target binary image corresponding to FIG. 5A. Inspection unit 22 obtains a difference image between the target binary image and the reference binary image, and detects the difference region as a defect region 814 as shown in FIG. 5D. Furthermore, inspection unit 22 cuts out defect region 814 and its surrounding region from the target image, and obtains defect image 811 as shown in FIG. 5A. As described above, in the examples shown in FIGS. 5A to 5D, defects are detected by the above-mentioned "comparison inspection" (algorithm).

[0041] In practice, many types of inspections are performed on each region of a substrate image, and when one or more defects are detected, defect image data 81 and an inspection type 82, which is information indicating the type of inspection performed by inspection device 11 when the defect image was detected, are associated and stored in storage unit 221, as shown in Fig. 1. In the examples of Figs. 5A to 5D, the inspection type is information indicating "comparative inspection." Then, when inspection of one substrate image is completed, the combination of defect image data 81 and inspection type 82 is output to additional inspection device 12 (step S13).

[0042] The combination of defect image data and inspection type is accepted by accepting unit 31 of additional inspection device 12 and stored in storage unit 32 (step S21). Next, image processing unit 33 processes the defect image according to the inspection type (step S22). For example, in the example shown in FIGS. 5A to 5D, image processing unit 33 determines a binarization threshold from defect image 811 in FIG. 5A and binarizes defect image 811 using this threshold. The threshold is determined, for example, using the K-means algorithm.

[0043] In determining the threshold using the K-means method, the pixels in an image are first divided into two appropriate classes, (1) the average value of each class is calculated, (2) the pixels are reassigned to the class with the closest average value, (3) (1) and (2) are repeated until no more pixels are reassigned, and (4) the pixel value between the two classes is determined as the threshold. Figure 5E shows an example of a target binary image, which is a processed image binarized in this way. Because the threshold is determined based on the defect image 811, the influence of the dark area 813 in Figure 5A is suppressed in the target binary image.

[0044] Meanwhile, additional inspection device 12 stores a master image of the printed wiring board in advance, extracts an area of ​​the master image corresponding to defect image 811, and binarizes it in the same way as inspection device 11 to obtain a reference binary image. Then, as a re-inspection, it obtains a difference image between the target binary image and the reference binary image, and since no difference area exists in the difference image, it determines that defect image 811 is a false alarm (step S23). In this way, re-inspection unit 34 re-inspects whether the defect image shows a result based on the image of the defect image processed by image processing unit 33.

[0045] The threshold value used for binarizing the defect image by image processing unit 33 does not need to be the pixel values ​​of the entire defect image, and only part of the pixel values ​​of the defect image may be used as long as it is determined based on the pixel values ​​of the defect in the defect image (more precisely, the area indicating the defect; the same applies below) and its surrounding area (including the case where the area is the defect image itself). Image processing unit 33 performs binarization using a threshold value different from that used in inspection device 11, and reinspection unit 34 compares the processed image with the reference binary image to determine whether the defect image indicates a defect, thereby enabling appropriate reinspection to be performed even if a board image is acquired with a color different from that of the master image due to slight differences in manufacturing conditions, imaging conditions, etc.

[0046] If the defect image is determined to be a false alarm, the processing of the defect image by the additional inspection device 12 is terminated (step S24). On the other hand, if the defect image is also determined to indicate a defect in the reinspection, the output unit 35 outputs the defect image (data) and the corresponding inspection type to the defect confirmation device 13 (step S25). In the defect confirmation device 13, an operator visually confirms whether the defect image indicates a defect, as described above.

[0047] By providing the additional inspection device 12 in the inspection system 1, the number of defect images that the operator must check using the defect confirmation device 13 is reduced. As a result, the probability of human error occurring due to operator fatigue can be reduced, and printed wiring boards with real defects can be appropriately prevented from being used as products.

[0048] Fig. 6A is a diagram showing another example of a defect image. Defect image 821 in Fig. 6A has a solder resist area 822, a substantially circular plating area 823, and an external area 824 outside the printed wiring board. In defect image 821, there is a slightly bright area 825 in solder resist area 822, and this area 825 has been detected as a defect by inspection device 11.

[0049] The operation of the inspection unit 22 when the defect image 821 is acquired is as follows. First, a target image indicating the area to be inspected in the substrate image and a reference image indicating the area in the master image corresponding to the target image are prepared in advance. As described above, the area to be inspected is larger than the defect image 821 that will ultimately be obtained. FIG. 6B is a diagram showing only the area of ​​the reference image that corresponds to FIG. 6A.

[0050] Next, in the target image and the reference image, areas other than the solder resist area are masked with reference to the design information of the printed wiring board, and a target processed image, which is a processed image of the target image shown in FIG. 6C, and a reference processed image, which is a processed image of the reference image shown in FIG. 6D, are obtained. Then, by binarizing the differential image between the target processed image and the reference processed image, an image showing the defect area 826 shown in FIG. 6E is obtained. Furthermore, the inspection unit 22 cuts out the defect area 826 and its surrounding area from the target image, and obtains the defect image 821 shown in FIG. 6A. In the examples shown in FIGS. 6A to 6E, defects are detected by the above-mentioned "unevenness inspection" (algorithm).

[0051] When the combination of defect image data and inspection type obtained by "unevenness inspection" is output from the inspection device 11 and accepted by the additional inspection device 12, the image processing unit 33 of the additional inspection device 12 first performs the same processing as that of the inspection device 11 on the defect image and the corresponding area of ​​the master image to obtain a defect area 826 similar to that shown in Figure 6E. Note that the defect area 826 may be stored in advance in the storage unit 221 of the inspection device 11 and sent to the additional inspection device 12 together with the defect image data.

[0052] Next, the re-inspection unit 34 acquires pixel values ​​in the defective area 826 of the defective image to obtain a distribution of pixel values. FIG. 7 is a diagram illustrating this distribution. The re-inspection unit 34 acquires a standard deviation, which is a value indicating the variation in pixel values, from the distribution of pixel values. The re-inspection unit 34 then compares the standard deviation with a predetermined threshold value. If the standard deviation is greater than the threshold value, i.e., if the pixel values ​​in the defective area vary greatly and the colors are unstable, the re-inspection unit 34 determines that the defective image is an image indicating a mura defect. In this way, the re-inspection unit 34 re-inspects the defective image based on the image processed by the image processing unit 33 to determine whether the defective image indicates a defect. After the defective image is determined to be an image indicating a defect or a false alarm, the additional inspection device 12 operates as described with reference to FIG. 4.

[0053] 6A to 6E and 7 are not limited to defect detection in solder resist regions. Similar processing may be performed on other specific types of regions, such as copper regions, plated regions, and silk-screened regions. Furthermore, the entire defect image does not need to be the target of region extraction. Generally speaking, the image processing unit 33 acquires a processed image in which specific types of regions are extracted from the defect and its surrounding region in the defect image (including the case where the region is the defect image itself).

[0054] The re-inspection unit 34 may also calculate a value other than the standard deviation as the degree of variation indicating the variation in pixel values ​​in the specific type of region. The re-inspection unit 34 compares the degree of variation with a predetermined threshold value to determine whether the defective image indicates a defect.

[0055] Fig. 8A is a diagram showing yet another example of a defect image. A defect image 831 in Fig. 8A has a solder resist area 832, a linear copper area 833, and a silk-screened area 834 where silk-screen printing has been performed.

[0056] The operation of the inspection unit 22 when the defect image 831 is acquired is as follows. First, a target image indicating the area to be inspected in the board image and a reference image indicating the area in the master image corresponding to the target image are prepared in advance. As described above, the area to be inspected is larger than the defect image 831 that will ultimately be obtained. FIG. 8B is a diagram showing only the area of ​​the reference image that corresponds to FIG. 8A. In the inspection device 11, the area shown in FIG. 8B is used as the area corresponding to FIG. 8A, and the position of the pattern in FIG. 8A is shifted from the position of the pattern in FIG. 8B. The position shift occurs due to distortion or warpage of the printed wiring board.

[0057] Next, the inspection unit 22 obtains a difference image between the target image and the reference image and binarizes the difference image to obtain an image showing the defect area 835 shown in FIG. 8C. The difference image may be obtained by other methods, or, as in FIGS. 5A to 5D, the target image and the reference image may be binarized and then a difference image between these binary images may be obtained. The inspection unit 22 cuts out the defect area 835 and its surrounding area from the target image to obtain the defect image 831 shown in FIG. 8A. However, in the case of FIG. 8C, since the defect area 835 appears over a wide area, a defect image of a predetermined size is appropriately cut out from the target image. In the examples shown in FIGS. 8A to 8C, defects are detected by the above-mentioned "comparison inspection" (algorithm).

[0058] Next, the operation of the additional inspection device 12 corresponding to the defect image in FIG. 8A will be described. The defect in FIG. 8A is a defect caused by "misalignment." Defects caused by "misalignment" are detected, for example, when a region where solder resist is formed on a fine line pattern is inspected in detail. Note that defects caused by "misalignment" can also cause the detection of various types of defects, so the operation of the additional inspection device 12 described below may be performed for other inspection types. In other words, the reinspection of a defect detected by the inspection device 11 is not limited to one type of reinspection, but multiple reinspections may be performed. In this case, depending on the inspection type, the reinspection unit 34 may conclude that the defect is a "false alarm" if at least one of the multiple reinspections is determined to be a "false alarm." Alternatively, the reinspection unit 34 may conclude that the defect is a "false alarm" only if all of the reinspections are determined to be "false alarm."

[0059] When re-inspecting defects caused by "misalignment," image processing unit 33 first performs image alignment processing on the defect image and the corresponding area of ​​the master image. For example, while shifting the position of the defect image relative to the master image, the sum of the differences in pixel values ​​between the defect image and the master image is repeatedly calculated, and the position of the defect image where the sum of the differences in pixel values ​​is minimum is obtained. FIG. 8D is a diagram showing a processed image 836 that has been subjected to image alignment processing by image processing unit 33. The position of the pixel at the top left vertex of FIG. 8B corresponds to the position of the pixel at the top left vertex of FIG. 8D.

[0060] The re-inspection unit 34 acquires a difference image of the overlapping portion between the processed image 836 and the master image in this state and binarizes the difference image. If a difference region exists in the difference image, the defect image 831 is determined to have a defect, and if no difference region exists, the defect image 831 is determined to be a false alarm.

[0061] Note that the alignment process (e.g., image processing to change the coordinate values ​​of each pixel) between the defect image and the corresponding area of ​​the master image (hereinafter referred to as the "reference area image") may be achieved by processing only the reference area image without processing the defect image. Because the relationship between the defect image and the reference area image in alignment is relative, processing the reference area image is essentially processing the defect image, and processing of the defect image in the image processing unit 33 is defined to include processing of the reference area image.

[0062] In this case, the reinspection unit 34 compares the processed image with the reference area image to determine whether the defect image indicates a defect, and this includes not only the use of a processed image obtained by directly processing the defect image, but also the use of indirect processing of the defect image by processing the reference area image. Furthermore, the entire defect image does not need to be used for alignment; generally speaking, the processed image after alignment is obtained by aligning the defect in the defect image and its surrounding area (including the case where the area is the defect image itself) with the reference area image.

[0063] The defect images in FIGS. 5A, 6A, and 8A are images obtained by cutting out one defect detected from a board image showing a printed wiring board and its surrounding area. This makes it easy to limit the scope of processing during reinspection to the scope of the defect image. Note that "one defect" means that there is one defect of interest, and includes cases where multiple defect areas are perceived as one defect. The defect image may take any other form as long as it is an image showing a defect detected by inspection device 11. For example, the defect image may be a combination of a board image and coordinates indicating the position of the defect. Alternatively, the target image in the above description, i.e., an image of the area of ​​the board image used for inspection by inspection device 11, may be used as the defect image.

[0064] Furthermore, although the defect image is an image showing one defect detected by the inspection device 11, the defect image does not have to be an image showing only one defect, and one defect image may include multiple defects, i.e., the defect of interest and other defects, because multiple defects are close to each other.

[0065] In the above description, the receiving unit 31 of the additional inspection device 12 receives the defect image and the inspection type from the inspection device 11 (step S21), and the image processing unit 33 performs image processing selected according to the inspection type on the defect image to obtain a processed image (step S22). Furthermore, the reinspection unit 34 reinspects the defect image using the method selected according to the inspection type (step S23). By having the additional inspection device 12 receive the inspection type from the inspection device 11, an appropriate reinspection can be performed promptly. However, the content of the reinspection may be selected based on the defect image, regardless of the inspection type.

[0066] For example, the type of defect may be identified from the defect image, and the type of image processing and reinspection may be selected based on the identified type of defect. Alternatively, the type of image processing and reinspection may be selected from the defect image based on the functional components of the printed wiring board (e.g., lands, wiring, through-holes, etc.) indicated by the defect image or the material of the printed wiring board (e.g., solder resist, silk printing, copper, plating, etc.). In this way, the inspection type does not need to be sent from the inspection device 11 to the additional inspection device 12. Furthermore, instead of the inspection type, the type of defect, the functional components of the printed wiring board indicated by the defect image, the material of the printed wiring board indicated by the defect image, etc. may be sent from the inspection device 11 to the additional inspection device 12 together with the defect image.

[0067] The inspection performed by the inspection device 11 may be an inspection using machine learning, but is preferably performed based on whether the target image to be inspected satisfies the inspection criteria. In other words, the inspection device 11 performs so-called "rule-based" inspection. "Based on whether the inspection criteria are satisfied" typically means that the presence or absence of a defect is determined by comparing values ​​derived from the target image (such as the area of ​​a difference region or the number of pixels of a specific color) with a predetermined value. Then, at least a portion of the target image determined to exhibit a defect is used as a defect image. The above processing enables the inspection device 11 to quickly perform a large amount of processing.

[0068] The reinspection in the reinspection unit 34 of the additional inspection device 12 may also be an inspection based on machine learning, but preferably, it determines whether a defective image indicates a defect based on whether the processed image satisfies the inspection criteria. This allows for stable reinspection. From the perspective of "reinspection," preferably, the type of inspection (inspection type) of the inspection process for the target image in the inspection device 11 and the inspection process for the processed image in the additional inspection device 12 are the same, except for the fact that image processing is performed. In this case, the inspection process in the inspection device 11 and the inspection process in the additional inspection device 12 are also rule-based inspections. Of course, as illustrated with reference to Figures 6A to 6E and 7, the inspection process in the inspection device 11 and the inspection process in the additional inspection device 12 may be significantly different.

[0069] The above-mentioned examples of inspection by the inspection device 11 and the examples of re-inspection by the additional inspection device 12 are only a few examples, and in reality, many types of inspections are performed on various parts of the board image. For example, various inspections are performed such as checking for pattern bending, pattern shorts, pattern opens, through-hole abnormalities, silk printing abnormalities, peeling of solder resist on copper, peeling of solder resist on the base material, foreign matter on copper, foreign matter on solder resist, foreign matter on the pattern, unevenness in the solder resist, copper pattern abnormalities, and abnormalities in the plated area.

[0070] The configurations in the above-described embodiment and each modification may be combined as appropriate as long as they are not mutually contradictory. [Explanation of symbols]

[0071] 1. Inspection system 11 Inspection equipment 12 Additional testing equipment 13 Defect checking device 31 Reception 33 Image processing section 34 Re-examination Department 35 Output section 81 Defect image data 82 Test Types 811,821,831 Defective images 815,836 processed images

Claims

1. An additional inspection device to be added to an inspection device that inspects the appearance of a printed wiring board, a receiving unit that receives a defect image showing a defect in the printed wiring board detected by the inspection device; an image processing unit that performs image processing on the defect image to obtain a processed image; a re-inspection unit that re-inspects the defect image based on the processed image to determine whether the defect image indicates a defect; an output unit that outputs the defect image to a defect confirmation device for an operator to confirm the defect image when the re-inspection unit determines that the defect image indicates a defect; Additional inspection equipment.

2. The additional inspection device according to claim 1, An additional inspection device in which the defect image is an image obtained by cutting out one defect and its surrounding area from the image of the printed wiring board.

3. The additional inspection device according to claim 1, the receiving unit receives, from the inspection device, the defect image and an inspection type, which is information indicating the type of inspection performed by the inspection device when the defect was detected; the image processing unit performs image processing selected in accordance with the inspection type on the defect image; The re-inspection unit re-inspects the defect image by a method selected according to the inspection type.

4. The additional inspection device according to claim 1, An additional inspection device in which the defect image received by the reception unit is at least a part of an image that has been determined to exhibit a defect based on whether or not the target image to be inspected in the inspection device satisfies an inspection standard.

5. The additional inspection device according to claim 4, An additional inspection device in which the re-inspection unit determines whether the defect image indicates a defect based on whether the processed image meets inspection criteria.

6. The additional inspection device according to claim 1, the image processing unit obtains a threshold value based on pixel values ​​of the defect and its surrounding area in the defect image, and binarizes the defect image using the threshold value to obtain the processed image; The re-inspection unit determines whether the defect image indicates a defect by comparing the processed image with a reference binary image.

7. The additional inspection device according to claim 1, the image processing unit acquires a processed image in which a specific type of area is extracted from the defect and its surrounding area in the defect image; The re-inspection unit determines a degree of variation that indicates the variation in pixel values ​​in the specific type of region, and compares the degree of variation with a predetermined threshold value to determine whether the defect image indicates a defect.

8. The additional inspection device according to claim 1, the image processing unit acquires a processed image in which the defect and its surrounding area in the defect image are aligned with a reference area image; The re-inspection unit determines whether the defect image indicates a defect by comparing the processed image with the reference area image.

9. An inspection system for inspecting the appearance of a printed wiring board, comprising: An additional inspection device according to any one of claims 1 to 8; the inspection device that outputs a defect image showing a defect in the printed wiring board to the additional inspection device; An inspection system comprising:

Images