Inspection apparatus, inspection method, and recording medium for recording a program

Abstract

In the inspection apparatus (1), a plurality of trial inspection images (431) representing a part of objects of one manufacturing lot, and a confirmation image group (432) representing a plurality of defects that should be detected for the objects are stored in the storage section (43). In the subsidiary inspection section (42), defects are detected by performing inspection processing using a defect detection condition on images representing the objects. In the trial inspection control section (41), the subsidiary inspection section (42) is caused to perform inspection processing using the defect detection condition before adjustment on the plurality of trial inspection images (431) as trial inspection, and the display section (35) is caused to display the result of the trial inspection. After input of adjustment of the defect detection condition is accepted in the input section (36), the subsidiary inspection section (42) is caused to perform inspection processing using the defect detection condition after adjustment on the confirmation image group (432) as confirmation inspection, and the display section (35) is caused to display the result of the confirmation inspection. Thereby, it is possible to easily confirm whether or not the adjustment of the defect detection condition is appropriate.

Description

[0001] [Reference to relevant applications]

[0002] This application claims priority to Japanese Patent Application JP2022-097437, filed on June 16, 2022, the entire disclosure of which is incorporated herein by reference. Technical Field

[0003] This invention relates to a technique for inspecting images of objects that have been captured. Background Technology

[0004] Conventional inspection apparatuses utilize images acquired by photographing a patterned substrate and then use these images to detect defects (see, for example, Japanese Patent Application Publication No. 2002-310928). In these apparatuses, defect detection conditions are adjusted (i.e., the various parameters involved in defect detection are adjusted) to reduce the omission of genuine defects or false positives. For example, in the manufacture of the same type of substrate, when inspecting a new batch of substrates, a portion of the batch is used for trial inspection, and the defect detection conditions are adjusted accordingly. Then, all substrates in the batch are inspected using the adjusted defect detection conditions. This reduces false positives specific to that batch.

[0005] However, from the perspective of inspection stability, even when using adjusted defect detection conditions matched to the new manufacturing batch, it is necessary to be able to detect true defects that would have been detected under the original defect detection conditions. Therefore, a method is needed to easily verify whether such true defects can be detected, i.e., whether the adjustment of the defect detection conditions is appropriate. Summary of the Invention

[0006] The purpose of this invention is to easily confirm whether the adjustment of defect detection conditions is appropriate.

[0007] Embodiment 1 of the present invention is an inspection apparatus for inspecting images obtained by photographing an object, comprising: a storage unit storing multiple test inspection images representing a portion of the objects in a manufacturing batch, and a set of confirmation images representing multiple defects to be detected in the objects; an inspection unit for detecting defects by performing inspection processing on the images representing the objects using defect detection conditions; a display unit for displaying the results of the inspection processing; an input unit for receiving input for adjusting the defect detection conditions; and a test inspection control unit that causes the inspection unit to perform the inspection processing on the multiple test inspection images using the defect detection conditions before adjustment as a test inspection, and causes the display unit to display the results of the test inspection; and after receiving input for adjusting the defect detection conditions on the input unit, causes the inspection unit to perform the inspection processing on the set of confirmation images using the defect detection conditions after adjustment as a confirmation inspection, and causes the display unit to display the results of the confirmation inspection.

[0008] According to the present invention, it is easy to confirm whether the adjustment of defect detection conditions is appropriate.

[0009] Embodiment 2 of the present invention is an inspection apparatus according to Embodiment 1, wherein, when the test inspection control unit causes the display unit to display the result of the confirmation inspection, it displays the presence of a defect that was not detected by the confirmation inspection among the plurality of defects represented by the confirmation image group.

[0010] The third aspect of the present invention is an inspection apparatus according to aspect 1 or 2, wherein when the input unit receives an input that a defect to be displayed on the display unit as the result of the trial inspection is a true defect, the trial inspection control unit appends the image of the defect to the confirmation image group.

[0011] The fourth embodiment of the present invention is an inspection apparatus according to any one of embodiments 1 to 3, wherein the confirmation image group includes an image group of a first defect category and an image group of a second defect category that is different from the first defect category.

[0012] The fifth embodiment of the present invention is an inspection apparatus according to any one of embodiments 1 to 4, wherein it further comprises: an imaging unit that acquires a plurality of inspection images representing a plurality of objects included in the manufacturing batch, wherein the plurality of test inspection images and the confirmation image set are images acquired by the imaging unit, and the inspection unit performs inspection processing on the plurality of inspection images using adjusted defect detection conditions as a mass production inspection.

[0013] The sixth aspect of the present invention is an inspection apparatus according to aspect 5, wherein, when the input unit receives an input that a defect detected in the mass production inspection is a true defect, the test inspection control unit appends an image of the defect to the confirmation image group.

[0014] Embodiment 7 of the present invention is an inspection apparatus according to Embodiment 5 or 6, wherein the inspection unit comprises: a first inspection unit for performing the trial inspection and the confirmation inspection; and a second inspection unit for performing the mass production inspection. A device main body and an auxiliary unit are independently provided. The device main body includes the imaging unit and the second inspection unit, and the auxiliary unit includes the storage unit, the first inspection unit, the display unit, the input unit, and the trial inspection control unit.

[0015] The present invention, embodiment 8, is an inspection method that inspects an image obtained by photographing an object using an inspection device, comprising: a) a step of preparing multiple test inspection images representing a portion of an object in a manufacturing batch, and a set of confirmation images representing multiple defects to be detected in the object; b) a step of performing a test inspection on the multiple test inspection images using predetermined defect detection conditions in the inspection device to detect defects; c) a step of displaying the result of the test inspection on a display unit; d) a step of receiving input for adjusting the defect detection conditions; e) a step of performing a confirmation inspection on the set of confirmation images using the adjusted defect detection conditions; and f) a step of displaying the result of the confirmation inspection on the display unit.

[0016] The present invention, in aspect 9, is an inspection method according to aspect 8, wherein, in step f), when the result of the confirmation inspection is displayed on the display unit, the presence of a defect that was not detected by the confirmation inspection is displayed among the plurality of defects represented by the confirmation image group.

[0017] The present invention, in aspect 10, is an inspection method according to aspect 8 or 9, wherein, in step c), when an input is received that a defect to be displayed on the display unit as a result of the trial inspection is a true defect, the image of the defect is appended to the confirmation image group.

[0018] The present invention, embodiment 11, is an inspection method according to any one of embodiments 8 to 10, wherein the confirmation image set includes an image set of a first defect category and an image set of a second defect category different from the first defect category.

[0019] The present invention, embodiment 12, is an inspection method according to any one of embodiments 8 to 11, further comprising: a step of acquiring multiple inspection images representing multiple objects included in the manufacturing batch by means of an imaging unit; and a step of performing an inspection process on the multiple inspection images using adjusted defect detection conditions as a mass production inspection, wherein the multiple test inspection images and the confirmation image set are images acquired by the imaging unit.

[0020] In the inspection method according to the present invention, in the case of receiving input that a defect detected in the mass production inspection is a true defect, the image of the defect is appended to the confirmation image group.

[0021] The present invention, embodiment 14, is a recording medium recording a program that enables a computer to inspect images obtained by photographing an object. By executing the program, the computer performs the following steps: a) preparing multiple test inspection images representing a portion of an object in a manufacturing batch, and a set of confirmation images representing multiple defects to be detected in the object; b) performing a test inspection on the multiple test inspection images using predetermined defect detection conditions, in the computer, to detect defects; c) displaying the results of the test inspection on a display unit; d) receiving input for adjusting the defect detection conditions; e) performing a confirmation inspection on the set of confirmation images using the adjusted defect detection conditions; and f) displaying the results of the confirmation inspection on the display unit.

[0022] The above-mentioned objects, as well as other objects, features, methods, and advantages, will become clear from the following detailed description of the invention with reference to the accompanying drawings. Attached Figure Description

[0023] Figure 1 This is a diagram showing the structure of the inspection device.

[0024] Figure 2 It is a diagram representing the structure of a computer.

[0025] Figure 3 This is a diagram showing an image captured on a printed circuit board.

[0026] Figure 4A This is a diagram illustrating the process of inspecting printed circuit boards using an inspection device.

[0027] Figure 4B This is a diagram illustrating the process of inspecting printed circuit boards using an inspection device.

[0028] Figure 5 It is a diagram showing the defects displayed by the display unit.

[0029] Figure 6 This is a graph showing the results of the confirmation check displayed on the display unit.

[0030] Figure 7 This is another example of an inspection of a printed circuit board performed by an inspection device.

[0031] Figure 8 It is a diagram representing the structure of the image group used for confirmation.

[0032] Explanation of reference numerals in the attached figures

[0033] 1. Inspection device

[0034] 2. Main body of the device

[0035] 3. Computer

[0036] 4 Auxiliary Units

[0037] 21 Filming Department

[0038] 23 Main Inspection Department

[0039] 35 Display Section

[0040] 36 Input Section

[0041] 41. Trial inspection control department

[0042] 42. Auxiliary Inspection Department

[0043] 43 Storage Department

[0044] 431 Test image

[0045] 432 Confirmation using image group

[0046] 433 Defect Image Set in Plating Area

[0047] 434 SR region defect image group

[0048] 811 program

[0049] Steps S11 to S25 Detailed Implementation

[0050] Figure 1 This diagram illustrates the structure of an inspection apparatus 1 according to an embodiment of the present invention. The inspection apparatus 1 inspects images obtained by photographing a printed circuit board, which is the object of the inspection. The inspection apparatus 1 includes a main body 2 and an auxiliary unit 4. The main body 2 and the auxiliary unit 4 are communicatively connected via a network 8 such as a LAN or the Internet.

[0051] The main body 2 of the device includes an imaging unit 21, a moving mechanism 22, a main inspection unit 23, and a main control unit 24. The imaging unit 21 has an imaging element, such as a CCD sensor or a CMOS sensor, to capture images of the printed circuit board. In this processing example, the image captured by the imaging unit 21 is a color image. The captured image may also be a grayscale image. The moving mechanism 22 includes, for example, an electric motor or a ball screw, to move the printed circuit board relative to the imaging unit 21. The main inspection unit 23 performs inspection processing on the captured image output from the imaging unit 21 using defect detection conditions, detecting defects from the captured image. The defect detection conditions include information such as the range of colors deemed normal in various areas of the printed circuit board. The main control unit 24 performs overall control of the main body 2 of the device. The main inspection unit 23 and the main control unit 24 are implemented, for example, by a computer and / or circuitry.

[0052] Auxiliary unit 4 is implemented by computer 3. Figure 2 This diagram illustrates the structure of computer 3. Computer 3 has the general structure of a computer system, including CPU 31, ROM 32, RAM 33, solid-state drive 34, display unit (monitor) 35, input unit 36, reading device 37, communication unit 38, GPU 39, and bus 30. CPU 31 performs various arithmetic operations. GPU 39 performs various arithmetic operations related to image processing. ROM 32 stores basic programs. RAM 33 and solid-state drive 34 store various information. Display unit 35 displays various information such as images. Input unit 36 ​​includes a keyboard 36a and a mouse 36b for accepting input from the user. Reading device 37 reads information from computer-readable recording media 81 such as optical discs, magnetic disks, optical disc drives, and memory cards. Communication unit 38 transmits and receives signals between itself and the main body 2, etc. Bus 30 is a signal circuit connecting CPU 31, GPU 39, ROM 32, RAM 33, solid-state drive 34, display unit 35, input unit 36, reading device 37, and communication unit 38. In computer 3, a touch panel may also be provided, through which the input unit 36 ​​and the display unit 35 are implemented.

[0053] In computer 3, program 811 is read from recording medium 81 beforehand via reading device 37 and stored in solid-state drive 34. Program 811 can be stored in solid-state drive 34 via network 8. CPU 31 and GPU 39 perform arithmetic processing using RAM 33 and solid-state drive 34 according to program 811. CPU 31 and GPU 39 function as arithmetic units in computer 3. In addition to CPU 31 and GPU 39, other structures that function as arithmetic units may also be used.

[0054] In the inspection device 1, the computer 3 performs calculations and other processes according to the program 811, thereby achieving... Figure 1The functional structure shown is as follows: The auxiliary unit 4 is implemented by the CPU 31, GPU 39, ROM 32, RAM 33, solid-state drive 34, and their peripheral structures in the computer 3. All or part of the functions of the auxiliary unit 4 can be implemented by dedicated circuitry, and each function can also be implemented by a separate program. Alternatively, the auxiliary unit 4 can be implemented by multiple computers. In this processing example, the auxiliary inspection unit 42, described later, includes a dedicated image processing circuit (image processing board).

[0055] The auxiliary unit 4 includes a test inspection control unit 41, an auxiliary inspection unit 42, a storage unit 43, a display unit 35, and an input unit 36. The auxiliary inspection unit 42, similar to the main inspection unit 23, performs inspection processing on an image representing the printed circuit board using defect detection conditions, detecting defects from the image. The test inspection control unit 41 controls the auxiliary inspection unit 42 to perform the test inspection and confirmation inspection described later. The test inspection control unit 41 is also responsible for the overall control of the auxiliary unit 4. The storage unit 43 stores the test inspection image (data) 431 used in the test inspection and the confirmation image set (data) 432 used in the confirmation inspection.

[0056] Here, an example of the inspection process in the auxiliary inspection unit 42 will be described. As described above, the same inspection process is also performed in the main inspection unit 23. Figure 3 This diagram shows a multi-tone image obtained by photographing a portion of a printed circuit board using the imaging unit 21. As described above, the image captured in this processing example is a color image. Various types of areas are provided on the main surface of the printed circuit board. Specifically, these include plating areas where a metal such as copper is plated, solder resist areas (hereinafter also referred to as "SR areas") where solder resist is applied to the surface, screen printing areas for text, markings, etc., printed on the solder resist, and through-hole areas for via openings. Furthermore, the SR areas can be distinguished into a first SR area where the solder resist is underlying copper foil and a second SR area where the solder resist is underlying the printed circuit board substrate; the two have different colors. As described above, each position on the main surface of the printed circuit board belongs to any one of several area categories, including plating areas, first SR areas, second SR areas, and screen printing areas.

[0057] Figure 3 Examples include region 61, representing a plating area, and region 62, representing an SR area. Region 62 includes region 621, representing a first SR area, and region 622, representing a second SR area. In the following description, regions 61, 62, 621, and 622 will be referred to as "plating area 61," "SR area 62," "first SR area 621," and "second SR area 622," respectively. Other types of areas on the printed circuit board will also be referred to by the same names in the captured images.

[0058] In the auxiliary inspection unit 42, for example, the region category to which each location in the captured image belongs is determined by referring to design data (CAM data, etc.). Furthermore, a normal range for the grayscale values ​​of each color component is set for each region category. In other words, thresholds for abnormal and normal ranges of grayscale values ​​for each color component are stored as defect detection conditions. In the captured image, the grayscale values ​​of each location are compared with the aforementioned thresholds for each color component, and the set of pixels within the abnormal range is detected as a defective region. Figure 3 In the example, there is a darker area 71 on the first SR region 621 than the surrounding area, and this area 71 is detected as a defect.

[0059] As described above, in the auxiliary inspection unit 42, defects are detected by performing inspection processing using defect detection conditions that represent the aforementioned thresholds. In the auxiliary inspection unit 42, other inspection processing can be performed, and the defect detection conditions can include values ​​other than the threshold values ​​for the grayscale values ​​of each color component. For example, the shortest distance between two adjacent plating areas (pads), the minimum width of a plating area (land) with vias formed, etc., can also be included in the defect detection conditions. Furthermore, the defect detection conditions can include values ​​other than the defect detection threshold; for example, if a mask area is set in the defect detection, values ​​such as the size of that mask area can also be included.

[0060] However, printed circuit boards (PCBs) are typically manufactured sequentially in batches. A batch is a collection of multiple PCBs manufactured under identical conditions. Within these batches, variations can occur due to batch-to-batch deviations in materials used, as well as the effects of temperature and humidity. For example, variations in solder resist or screen printing ink can cause variations in the color of the SR (solder resist) area and the screen printing area in each batch. Furthermore, variations in temperature and humidity during solder resist formation can cause variations in the size of the exposed plating area in each batch. Thus, the possibility of false positives (detection of false defects) increases during inspection. Therefore, it is preferable to adjust defect detection conditions to accommodate the specific variations of each batch. The following describes the process of adjusting defect detection conditions for each batch and inspecting the PCBs.

[0061] Figure 4A and Figure 4B This diagram illustrates the process of inspecting printed circuit boards by inspection apparatus 1. Here, multiple printed circuit boards of the same type are manufactured sequentially as multiple manufacturing batches, and the second and subsequent manufacturing batches are designated as inspection targets. The processing of the printed circuit boards included in the inspection of this manufacturing batch (hereinafter referred to as the "target manufacturing batch") will be described.

[0062] exist Figure 1 In the inspection apparatus 1, a portion of the printed circuit boards (e.g., 10 to 30 printed circuit boards) included in the batch being manufactured is loaded into the apparatus body 2, and multiple images representing this portion of the printed circuit boards are acquired by the imaging unit 21. Each image in this processing example is an image representing the entire printed circuit board (both sides or one side), but it can also be an image representing a portion of the printed circuit board. As described later, each of these multiple images is for trial inspection and is therefore referred to below as a "trial inspection image." The multiple trial inspection images are transmitted from the apparatus body 2 to the auxiliary unit 4 via the network 8 and stored in the storage unit 43. Figure 1 In the block diagram, only one test image 431 is represented, but in reality, multiple test images 431 are stored.

[0063] Additionally, a set of confirmation images 432 is stored in the storage unit 43. The set of confirmation images 432 is a collection of images identified as true defects by the operator during the inspection of a manufacturing batch prior to the target manufacturing batch. In this processing example, each image in the set of confirmation images 432 represents the true defect (an image representing a portion of the printed circuit board), but it could also be an image representing the entire printed circuit board. As described above, during the inspection of the printed circuit board of the target manufacturing batch, multiple test inspection images 431 and the set of confirmation images 432 are stored in the storage unit 43 for preparation (step S11).

[0064] Next, under the control of the test inspection control unit 41, the auxiliary inspection unit 42 performs inspection processing on multiple test inspection images 431 as a test inspection (step S12). The auxiliary inspection unit 42 stores defect detection conditions (defect detection conditions in mass production inspection described later) for the same type of printed circuit board, specifically for manufacturing batches that have been inspected before the target manufacturing batch. These defect detection conditions are used during the test inspection. In step S16 described later, since the defect detection conditions are adjusted, the defect detection conditions during the test inspection are the same as before the adjustment. When the test inspection of the multiple test inspection images 431 is completed, the test inspection results are displayed on the display unit 35 (step S13).

[0065] Figure 5 This is a diagram showing the defects displayed by the display unit 35. The results of the test inspection may include, for example, images of defects detected through the test inspection. Figure 5 In the example, it includes detected defects (in Figure 5The area enclosed by a rectangle 51 with a white line is displayed on the left, and the area in the same master image (i.e., the master image area corresponding to the defect) is displayed on the right. The master image is, for example, an image generated using images of multiple printed circuit boards during the initial inspection of the manufacturing batch, and is an image that does not contain defects or has reduced defects. As a result of trial inspection, the number of defects detected on each printed circuit board may also be displayed.

[0066] The results of the trial inspection displayed on the display unit 35 are confirmed by the operator. If the operator determines that a defect among the defects displayed on the display unit 35 is a genuine defect, the operator inputs this information via the input unit 36 ​​(step S14). For example, the operator selects the defect on the display unit 35 and right-clicks the mouse 36b, then selects "Register Genuine Defect" from the displayed menu, thus easily registering the defect as a genuine defect. When the input unit 36 ​​receives an input indicating a defect as a genuine defect, the trial inspection control unit 41 adds the image of the defect (genuine defect) to the confirmation image group 432 and updates the confirmation image group 432 (step S15). If no defect is determined to be a genuine defect by the operator, the input unit 36 ​​does not accept the input and therefore does not update the confirmation image group 432 (step S14).

[0067] Furthermore, if the operator determines that the defect detection conditions need to be adjusted, the operator adjusts the defect detection conditions via the input unit 36 ​​(step S16). For example, if most of the defects displayed on the display unit 35 exist in the SR region and are false alarms, the threshold of the grayscale value of each color component in the SR region is changed in the defect detection conditions. Then, the inspection processing of multiple test images 431 is performed again using the changed defect detection conditions, and the result of the inspection processing is displayed on the display unit 35. If the false alarms are not sufficiently reduced in the inspection processing results, the defect detection conditions are further changed to obtain the result of the inspection processing performed using the changed defect detection conditions.

[0068] As described above, by repeatedly changing the defect detection conditions and performing inspection processes as needed, the defect detection conditions are adjusted to obtain adjusted defect detection conditions that reduce false alarms. In other words, the input unit 36 ​​receives the input for adjusting the defect detection conditions and obtains the adjusted defect detection conditions. Furthermore, when adjusting the defect detection conditions, the processes described in steps S14 and S15 can also be performed to append the defect image to the confirmation image group 432. On the other hand, if the operator determines that adjustment of the defect detection conditions is unnecessary (step S16), no adjustment of the defect detection conditions is performed, and the process proceeds to step S21, which will be described later.

[0069] After adjusting the defect detection conditions and obtaining the adjusted defect detection conditions, the auxiliary inspection unit 42 performs an inspection process for the confirmation image group 432 as a confirmation inspection (step S17) under the control of the test inspection control unit 41. During the confirmation inspection, the adjusted defect detection conditions are used. When the confirmation inspection of the confirmation image group 432 is completed, the result of the confirmation inspection is displayed on the display unit 35 (step S18).

[0070] Figure 6 This is a diagram showing the results of the confirmation check displayed on display unit 35. In Figure 6 In this example, images 56 representing multiple true defects shown in image group 432 are arranged for display. Furthermore, the main image region 57 corresponding to each true defect is arranged adjacent to the right side of the image 56 representing that true defect. At this time, if a true defect (hereinafter referred to as a "non-detected true defect") exists among the multiple true defects shown in image group 432 that was not detected as a defect during the confirmation inspection (step S19), the presence of the non-detected true defect is displayed on display unit 35 and reported to the operator. Figure 6 In the example, the presence of the undetected true defect is emphasized by surrounding the image 56 of the undetected true defect and the corresponding main image area 57 with a thick rectangle 52. In step S18, the presence of the undetected true defect can also be displayed by displaying only the image 56 of the undetected true defect on the display unit 35, etc.

[0071] If a true defect is found that is not detected, the operator readjusts the defect detection conditions via input unit 36 ​​(step S20). In this readjustment, the operator changes the defect detection conditions via input unit 36 ​​(i.e., changes them from the previously adjusted conditions). Then, the inspection process for the confirmation image group 432 is performed again using the changed defect detection conditions, and the results are displayed on display unit 35. If a true defect is found that is not detected in the inspection results, the defect detection conditions are further changed, and the results of the inspection process using the changed defect detection conditions are obtained.

[0072] As described above, by repeatedly changing the defect detection conditions and executing inspection processes as needed, the defect detection conditions are readjusted to obtain readjusted defect detection conditions capable of detecting all true defects shown in the confirmation image group 432. In other words, the input unit 36 ​​receives the input of the readjusted defect detection conditions and obtains the readjusted defect detection conditions. The readjusted defect detection conditions become the defect detection conditions for mass production inspection of the target manufacturing batch, as described later. Furthermore, since the readjusted defect detection conditions can detect the aforementioned undetected true defects, they become stricter conditions than the readjusted defect detection conditions used in the confirmation inspection.

[0073] On the other hand, if no undetected true defects are found in the results of the inspection (step S19), the defect detection conditions are not readjusted, and the above-mentioned adjusted defect detection conditions become the defect detection conditions for mass production inspection of the target manufacturing batch.

[0074] Defect detection conditions for mass production inspection are sent to Figure 1 The main body 2 of the device is stored by the main body inspection unit 23. In the main body 2, the imaging unit 21 sequentially acquires multiple inspection images representing multiple printed circuit boards included in the target manufacturing batch (step S21). For the printed circuit boards included in the target manufacturing batch, for which a test inspection image was acquired in step S11, the test inspection image can also be processed as an inspection image.

[0075] Furthermore, under the control of the main control unit 24, inspection processing for multiple inspection images is performed in the main inspection unit 23 as a mass production inspection (step S22). In the mass production inspection, the defect detection conditions for mass production inspection described above are used. Preferably, the mass production inspection and the acquisition of multiple inspection images are performed in parallel. The results of the mass production inspection are stored in the main inspection unit 23. The results of the mass production inspection include information on defects detected by the mass production inspection. Defect information includes, for example, an image of the defect, identification information of the printed circuit board containing the defect, and location information of the defect on the printed circuit board. The results of the mass production inspection may also include the number of defects detected on each printed circuit board. Additionally, multiple inspection images can be deleted after the inspection processing.

[0076] Through the above steps, the inspection device 1 completes the inspection of the printed circuit board. Information about defects detected during mass production inspection can, for example, be output to an external defect confirmation device. In the defect confirmation device, the area of ​​the defect on the printed circuit board is photographed based on the defect information and displayed on a display unit. The operator determines whether the defect is a genuine defect or a false report by reviewing the displayed image.

[0077] As explained above, in Figure 1 In the inspection apparatus 1, multiple test inspection images 431 representing a portion of the printed circuit boards in a manufacturing batch, and a set of confirmation images 432 representing multiple defects to be detected in the printed circuit boards, are stored in the storage unit 43. In the auxiliary inspection unit 42, defects are detected by performing inspection processing using defect detection conditions on the images representing the printed circuit boards. The test inspection control unit 41 causes the auxiliary inspection unit 42 to perform inspection processing on the multiple test inspection images 431 using the unadjusted defect detection conditions as a test inspection, and displays the results of the test inspection on the display unit 35. Then, input for adjusting the defect detection conditions is received in the input unit 36. In the inspection apparatus 1, by adjusting the defect detection conditions based on the results of the test inspection, it is possible to suppress the increase in false alarms caused by unique variations occurring in each manufacturing batch.

[0078] Furthermore, after receiving input indicating an adjustment to the defect detection conditions, the test inspection control unit 41 instructs the auxiliary inspection unit 42 to perform an inspection process using the adjusted defect detection conditions on the confirmation image set 432 as a confirmation inspection, and the display unit 35 displays the result of the confirmation inspection. Here, assuming that the confirmation image set 432 is not prepared, in order to confirm whether a true defect can be detected using the adjusted defect detection conditions, the operator needs to pre-store or record images containing true defects from past batches of test inspection images and perform inspection processing using the adjusted defect detection conditions on those images. Alternatively, while performing inspection processing on all test inspection images from past batches is also considered, this requires considerable time. In contrast, in the inspection device 1, by preparing the confirmation image set 432, it is easy to confirm whether a true defect can be detected using the adjusted defect detection conditions; that is, it is easy to confirm whether the adjustment of the defect detection conditions is appropriate. As a result, the work efficiency related to the adjustment of defect detection conditions can be improved. Furthermore, since a large-capacity storage unit 43 is not required to store all the test inspection images from past manufacturing batches, the manufacturing cost of the inspection device 1 can be reduced.

[0079] Preferably, when the test inspection control unit 41 displays the results of the confirmation inspection on the display unit 35, it displays the presence of defects that were not detected by the confirmation inspection among the multiple defects represented by the confirmation image group 432. This allows the operator to easily and reliably identify the presence of undetected true defects, and enables readjustment of defect detection conditions to obtain appropriate defect detection conditions for mass production inspection.

[0080] Preferably, when the input unit 36 ​​receives an input indicating that a defect to be displayed on the display unit 35 as a result of a trial inspection is a true defect, the trial inspection control unit 41 adds the image of the defect to the confirmation image group 432. Thus, true defects detected through the trial inspection can be easily added to the confirmation image group 432, and a preferred confirmation image group 432 can be prepared.

[0081] Preferably, the inspection apparatus 1 further includes an imaging unit 21 that acquires multiple inspection images representing the multiple printed circuit boards included in the aforementioned manufacturing batch. In the main inspection unit 23, as a mass production inspection, inspection processing using adjusted defect detection conditions is performed on these multiple inspection images. This allows for appropriate mass production inspection by using defect detection conditions that reduce false alarms while detecting genuine defects. Furthermore, since the multiple test inspection images 431 and the confirmation image set 432 are images acquired by the imaging unit 21, differences in inspection conditions caused by the imaging unit can be suppressed during test inspection, confirmation inspection, and mass production inspection.

[0082] Figure 7 This diagram illustrates another example of the inspection of a printed circuit board performed by inspection apparatus 1, showing... Figure 4B The processing flow following step S22. Figure 7 In the example, the results of the mass production check in step S22 are sent to Figure 1 The auxiliary unit 4 displays the results of the mass production inspection on the display unit 35 (step S23). The results of the mass production inspection displayed on the display unit 35 are confirmed by the operator. If there is a defect among the defects displayed on the display unit 35 that the operator determines to be a true defect, the operator inputs an indication that the defect is a true defect via the input unit 36, similar to step S14 (step S24). As a result, the test inspection control unit 41 adds the image of the defect (true defect) to the confirmation image group 432 and updates the confirmation image group 432 (step S25). If there is no defect that the operator determines to be a true defect, the input unit 36 ​​does not accept the above input, and therefore the confirmation image group 432 is not updated (step S24).

[0083] As mentioned above, in Figure 7 In the processing example, when the input unit 36 ​​receives an input indicating that a defect detected during mass production inspection is a genuine defect, the test inspection control unit 41 adds the image of the defect to the confirmation image group 432. Thus, genuine defects detected during mass production inspection can be easily added to the confirmation image group 432, and a preferred confirmation image group 432 can be prepared.

[0084] exist Figure 1In the inspection device 1, a main body 2 and an auxiliary unit 4 are respectively provided. However, the test inspection control unit 41, auxiliary inspection unit 42, and storage unit 43 of the auxiliary unit 4 can also be implemented by a computer provided in the main body 2. In this case, the main inspection unit 23 and the auxiliary inspection unit 42 are implemented by one inspection unit. In other words, in the inspection device 1, the main body 2 and the auxiliary unit 4 are respectively provided. Figure 1 In the inspection device 1, the inspection unit can be said to have a first inspection unit (auxiliary inspection unit 42) that performs trial inspection and confirmation inspection and a second inspection unit (main inspection unit 23) that performs mass production inspection.

[0085] As in the example above, when a device main body 2, including an imaging unit 21 and a second inspection unit, and an auxiliary unit 4, including a storage unit 43, a first inspection unit, a display unit 35, an input unit 36, and a test inspection control unit 41 are respectively provided, mass production inspections of other types of printed circuit boards can be performed in parallel with the processing of steps S12 to S20 in the auxiliary unit 4. As a result, the operating rate of the device main body 2 can be improved, and the efficiency related to the inspection of printed circuit boards can be improved.

[0086] In the above processing example, the image group 432 is confirmed to include images of various defects. However, the image group 432 can also distinguishably include an image group of a first defect category and an image group of a second defect category that is different from the first defect category. Figure 8 In the example, image group 432 is confirmed to include plating area defect image group 433 and SR area defect image group 434. Defects existing in plating area 61 are designated as "plating area defects," and plating area defect image group 433 contains images of multiple plating area defects that are considered true defects. Similarly, defects existing in SR area 62 are designated as "SR area defects," and SR area defect image group 434 contains images of multiple SR area defects that are considered true defects. Since plating area defects have a significant impact on the operation of the printed circuit board, they are considered high-importance defects. Since SR area defects have a relatively small impact on the operation of the printed circuit board, they are considered low-importance defects.

[0087] exist Figure 4A In step S14, if the input unit 36 ​​receives an input indicating that a defect to be displayed on the display unit 35 as a result of a trial inspection is a true defect, the trial inspection control unit 41, when the defect is a plating area defect, adds the image of the defect to the plating area defect image group 433 (step S15). On the other hand, when the defect is an SR area defect, the image of the defect is not added to the SR area defect image group 434. Figure 7Steps S24 and S25 are the same. As described above, by not adding low-importance defects to the confirmation image group 432, it is possible to suppress the excessive increase in the number of images contained in the confirmation image group 432, that is, it is possible to suppress the excessive increase in the size of the confirmation image group 432. The first and second defect categories can be defect categories other than plating area defects and SR area defects, and the confirmation image group 432 can include image groups of three or more defect categories.

[0088] Various modifications can be performed in the above-mentioned inspection device 1 and inspection method.

[0089] The images included in the image group 432 can be images of defects that should be detected in the printed circuit board, or images of real defects in other types of printed circuit boards.

[0090] In addition to printed circuit boards, the objects inspected in inspection apparatus 1 can also be semiconductor substrates, glass substrates, or other substrates. Furthermore, inspection apparatus 1 can also detect defects in objects other than substrates, such as mechanical parts.

[0091] The structures in the above-described embodiments and their variations can be appropriately combined as long as they do not contradict each other.

[0092] Although the invention has been described and illustrated in detail, the above description is exemplary and not restrictive. Therefore, many modifications or methods can be made without departing from the scope of the invention.

Claims

1. An inspection apparatus that inspects an image obtained by photographing an object, wherein have: The storage unit stores multiple test inspection images representing a portion of objects in a manufacturing batch, as well as a set of confirmation images representing multiple defects that should be detected in the objects. The inspection department detects defects by performing inspection processing on images representing objects using defect detection conditions; The display unit shows the results of the inspection process. The input section accepts input for adjusting the defect detection conditions; as well as The test inspection control unit causes the inspection unit to perform inspection processing on multiple test inspection images using the original defect detection conditions as a test inspection, and causes the display unit to display the result of the test inspection. After the input unit receives input indicating an adjustment to the defect detection conditions, the inspection unit causes the inspection unit to perform inspection processing on the confirmation image group using the adjusted defect detection conditions as a confirmation inspection, and causes the display unit to display the result of the confirmation inspection. When the test inspection control unit causes the display unit to display the result of the confirmation inspection, it confirms whether there is a defect among the multiple defects represented by the confirmation image group that was not detected by the confirmation inspection, i.e., a non-detectable defect. If the non-detectable defect exists, it displays the presence of the non-detectable defect.

2. The inspection device according to claim 1, wherein, When the input unit receives an input that a defect will be displayed on the display unit as a result of the test inspection, the test inspection control unit adds the image of the defect to the confirmation image group.

3. The inspection device according to claim 1, wherein, The confirmation image set includes an image set of a first defect category and an image set of a second defect category that is different from the first defect category.

4. The inspection apparatus according to any one of claims 1 to 3, wherein It also has: The imaging unit acquires multiple inspection images representing multiple objects included in the manufacturing batch. The plurality of test images and the set of confirmation images are images acquired by the imaging unit. The inspection unit performs inspection processing on multiple inspection images using adjusted defect detection conditions as a mass production inspection.

5. The inspection device according to claim 4, wherein, When the input unit receives an input that a defect detected in the mass production inspection is a true defect, the test inspection control unit appends the image of the defect to the confirmation image group.

6. The inspection device according to claim 4, wherein, The inspection unit is equipped with: The first inspection unit performs the trial inspection and the confirmation inspection; and The second inspection department performs the aforementioned mass production inspection. The device body and auxiliary unit are set up independently. The device body includes the imaging unit and the second inspection unit, and the auxiliary unit includes the storage unit, the first inspection unit, the display unit, the input unit and the test inspection control unit.

7. An inspection method of inspecting an image obtained by photographing an object by an inspection apparatus, wherein include: a) Process: Prepare multiple test images representing a portion of an object in a manufacturing batch, and a set of confirmation images representing multiple defects to be detected in the object; b) In the inspection apparatus, defects can be detected by performing inspection processing on an image representing an object using defect detection conditions, and the inspection processing on multiple test inspection images using prescribed defect detection conditions is performed as a test inspection. c) The result of the test inspection is displayed on the display unit; d) The process accepts input for adjusting the defect detection conditions; e) The process involves performing the inspection process for the confirmation image group, using the adjusted defect detection conditions, as a confirmation inspection; f) The result of the confirmation check is displayed on the display unit; In step f), when the result of the confirmation inspection is displayed on the display unit, the inspection device confirms whether there is a defect among the multiple defects represented by the confirmation image group that was not detected by the confirmation inspection, i.e., a non-detectable defect. If the non-detectable defect exists, the presence of the non-detectable defect is displayed.

8. The inspection method according to claim 7, wherein, In step c), if an input is received that a defect will be displayed on the display unit as a result of the test inspection, the image of the defect is added to the confirmation image group.

9. The inspection method according to claim 7, wherein, The confirmation image set includes an image set of a first defect category and an image set of a second defect category that is different from the first defect category.

10. The inspection method of any one of claims 7-9, wherein, Also includes: g) In the process of acquiring multiple inspection images representing multiple objects included in the manufacturing batch through the imaging unit; h) Step, performing the inspection processing on multiple inspection images using the adjusted defect detection conditions as a mass production inspection. The multiple test images and the set of confirmation images are images acquired by the imaging unit.

11. The inspection method according to claim 10, wherein, Upon receiving input that a defect detected during the mass production inspection is a genuine defect, the image of the defect is appended to the confirmation image set.

12. A recording medium containing a program that causes a computer to examine an image of a photographed object, wherein the computer executes the program to perform: a) Process: Prepare multiple test images representing a portion of an object in a manufacturing batch, and a set of confirmation images representing multiple defects to be detected in the object; b) In the computer, defects can be detected by performing inspection processing on an image representing an object using defect detection conditions, and the inspection processing using prescribed defect detection conditions on multiple test inspection images is performed as a test inspection. c) The result of the test inspection is displayed on the display unit; d) The process accepts input for adjusting the defect detection conditions; e) The process involves performing the inspection process for the confirmation image group, using the adjusted defect detection conditions, as a confirmation inspection; f) In the process of confirming the inspection results, the results are displayed on the display unit. In step f), when the result of the confirmation inspection is displayed on the display unit, the computer confirms whether there is a defect among the multiple defects represented by the confirmation image group that was not detected by the confirmation inspection, i.e., a non-detectable defect. If the non-detectable defect exists, the presence of the non-detectable defect is displayed.

Images