Inspection device, inspection method, and program

Abstract

To easily confirm the propriety of adjustment of a defect detection condition.SOLUTION: In an inspection device 1, a plurality of trial inspection images 431 showing a partial object in one production lot and a confirmation image set 432 showing a plurality of defects to be detected for the object are stored in a storage unit 43. An auxiliary inspection unit 42 detects a defect by executing inspection processing using a defect detection condition to the image showing the object. A trial inspection control unit 41 causes a display unit 35 to display a result of a trial inspection by causing the auxiliary inspection unit 42 to execute the inspection processing using the defect detection condition before adjustment to the plurality of trial inspection images 431 as a trial inspection, causes the auxiliary inspection unit 42 to execute the inspection processing using the defect detection condition after adjustment to the confirmation image set 432 as the confirmation inspection after an input unit 36 receives an input of adjustment of the defect detection condition and causes the display unit 35 to display the result of the confirmation inspection, and thereby the propriety of adjustment of the defect detection condition can be easily confirmed.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to a technique for inspecting an image of an object. [Background technology]

[0002] Conventionally, inspection devices have been used that capture images of substrates on which patterns are formed, and then use the images to detect defects (see, for example, Patent Document 1). In the inspection device, defect detection conditions are adjusted (i.e., various parameters related to defect detection are adjusted) to reduce overlooking of true defects and false reports. For example, in the manufacture of the same type of substrates, when inspecting substrates in a new production lot, a trial inspection is performed using some of the substrates in the production lot, and the defect detection conditions are adjusted. Then, all of the substrates in the production lot are inspected using the adjusted defect detection conditions. This makes it possible to reduce false reports specific to that production lot. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Laid-Open No. 2002-310928 Summary of the Invention [Problem to be solved by the invention]

[0004] From the viewpoint of inspection stability, it is necessary that true defects that were detected under the pre-adjustment defect detection conditions can be detected even when the post-adjustment defect detection conditions are used, and therefore there is a need for a method for easily checking whether true defects can be detected, i.e., whether the adjustment of the defect detection conditions is appropriate.

[0005] The present invention has been made in view of the above-mentioned problems, and has as its object to easily check whether adjustments to defect detection conditions are appropriate. [Means for solving the problem]

[0006] A first aspect of the present invention is an inspection device that inspects images of an object, the inspection device comprising: a storage unit that stores a plurality of test inspection images showing some objects in a single production lot and a confirmation image set showing a plurality of defects to be detected in the object; an inspection unit that detects defects by executing an inspection process using defect detection conditions on the images showing the object; a display unit that displays results of the inspection process; an input unit that accepts input for adjusting the defect detection conditions; and a test inspection control unit that causes the inspection unit to execute the inspection process using the defect detection conditions before adjustment on the plurality of test inspection images as a test inspection and displays results of the test inspection on the display unit; and, after the input unit accepts input for adjusting the defect detection conditions, causes the inspection unit to execute the inspection process using the defect detection conditions after adjustment on the confirmation image set as a confirmation inspection and displays results of the confirmation inspection on the display unit. , the confirmation image set indicates true defects detected when the inspection process is performed using the defect detection conditions before adjustment. .

[0007] A second aspect of the present invention is an inspection device of the first aspect, wherein when the trial inspection control unit displays the results of the confirmation inspection on the display unit, it displays the presence of defects among the multiple defects indicated by the confirmation image set that were not detected by the confirmation inspection.

[0008] Aspect 3 of the present invention is an inspection device of aspect 1 (which may be aspect 1 or 2), in which, when the input unit receives an input indicating that a defect displayed on the display unit as a result of the trial inspection is a true defect, the trial inspection control unit adds an image of the defect to the confirmation image set.

[0009] Aspect 4 of the present invention is an inspection apparatus of aspect 1 (which may be any one of aspects 1 to 3), in which the confirmation image set includes an image set of a first defect type and an image set of a second defect type different from the first defect type.

[0010] A fifth aspect of the present invention is an inspection device according to any one of aspects 1 to 4, further comprising an imaging unit that acquires a plurality of inspection images showing a plurality of objects included in the production lot, wherein the plurality of trial inspection images and the confirmation image set are images acquired by the imaging unit, and the inspection unit performs the inspection process using the adjusted defect detection conditions on the plurality of inspection images as a mass production inspection.

[0011] A sixth aspect of the present invention is an inspection device according to the fifth aspect, in which, when the input unit receives an input indicating that a defect detected in the mass production inspection is a true defect, the trial inspection control unit adds an image of the defect to the confirmation image set.

[0012] A seventh aspect of the present invention is an inspection device according to the fifth aspect (which may be either fifth or sixth aspect), wherein the inspection unit comprises a first inspection unit that performs the trial inspection and the confirmation inspection, and a second inspection unit that performs the mass production inspection, and the device main body including the imaging unit and the second inspection unit, and an auxiliary unit including the memory unit, the first inspection unit, the display unit, the input unit, and the trial inspection control unit are provided separately.

[0013] An eighth aspect of the present invention is an inspection method for inspecting images of an object using an inspection device, the method comprising the steps of: a) preparing a plurality of trial inspection images showing some objects in a single production lot, and a confirmation image set showing a plurality of defects to be detected in the object; b) in the inspection device, defects can be detected by executing an inspection process using defect detection conditions on images showing the object, and executing the inspection process using predetermined defect detection conditions on the plurality of trial inspection images as a trial inspection; c) displaying results of the trial inspection on a display unit; d) accepting input for adjustment of the defect detection conditions; e) executing the inspection process using the adjusted defect detection conditions on the confirmation image set as a confirmation inspection; and f) displaying results of the confirmation inspection on the display unit. , the confirmation image set indicates true defects detected when the inspection process is performed using the predetermined defect detection conditions. .

[0014] A ninth aspect of the present invention is an inspection method according to the eighth aspect, wherein in the f) step, when the results of the confirmation inspection are displayed on the display unit, the presence of defects not detected by the confirmation inspection among the plurality of defects indicated by the confirmation image set is displayed.

[0015] Aspect 10 of the present invention is an inspection method of aspect 8 (which may be aspect 8 or 9), in which, in step c), when an input is received indicating that a defect displayed on the display unit as a result of the trial inspection is a true defect, an image of the defect is added to the confirmation image set.

[0016] Aspect 11 of the present invention is an inspection method of aspect 8 (which may be any one of aspects 8 to 10), in which the confirmation image set includes an image set of a first defect type and an image set of a second defect type different from the first defect type.

[0017] A twelfth aspect of the present invention is an inspection method according to any one of aspects 8 to 11, further comprising the steps of: g) acquiring a plurality of inspection images showing a plurality of objects included in the production lot using an imaging unit; and h) performing the inspection process on the plurality of inspection images using the adjusted defect detection conditions as a mass production inspection, wherein the plurality of test inspection images and the confirmation image set are images acquired by the imaging unit.

[0018] A thirteenth aspect of the present invention is an inspection method according to the twelfth aspect, in which, when an input is received indicating that a defect detected in the mass production inspection is a true defect, an image of the defect is added to the confirmation image set.

[0019] A fourteenth aspect of the present invention is a program for causing a computer to inspect an image of an object, wherein execution of the program by the computer causes the computer to execute the following steps: a) preparing a plurality of trial inspection images showing some objects in a production lot, and a confirmation image set showing a plurality of defects to be detected in the objects; b) executing an inspection process using predetermined defect detection conditions on the images showing the object, where defects can be detected, on the computer, and executing the inspection process using predetermined defect detection conditions on the plurality of trial inspection images as a trial inspection; c) displaying the results of the trial inspection on a display unit; d) accepting input for adjustment of the defect detection conditions; e) executing the inspection process using the adjusted defect detection conditions on the confirmation image set as a confirmation inspection; and f) displaying the results of the confirmation inspection on the display unit. , the confirmation image set indicates true defects detected when the inspection process is performed using the predetermined defect detection conditions. . [Effects of the Invention]

[0020] According to the present invention, it is possible to easily check whether adjustment of defect detection conditions is appropriate. [Brief explanation of the drawings]

[0021] [Figure 1] FIG. 1 is a diagram illustrating a configuration of an inspection device. [Figure 2] FIG. 1 illustrates the configuration of a computer. [Figure 3] FIG. 10 is a diagram showing a captured image of a printed circuit board. [Figure 4A] FIG. 1 is a diagram showing a flow of inspection of a printed circuit board by an inspection device. [Figure 4B] FIG. 1 is a diagram showing a flow of inspection of a printed circuit board by an inspection device. [Figure 5] FIG. 10 is a diagram showing a defect displayed on a display unit. [Figure 6] FIG. 10 is a diagram showing the results of the confirmation test displayed on the display unit. [Figure 7] 10A and 10B are diagrams illustrating another example of inspection of a printed circuit board by the inspection device. [Figure 8]FIG. 10 is a diagram showing the configuration of a confirmation image set. DETAILED DESCRIPTION OF THE INVENTION

[0022] FIG. 1 is a diagram showing the configuration of an inspection device 1 according to one embodiment of the present invention. The inspection device 1 inspects an image of a printed circuit board, which is an object. The inspection device 1 includes a device main body 2 and an auxiliary unit 4. The device main body 2 and the auxiliary unit 4 are connected to each other so as to be able to communicate with each other via a network 8 such as a LAN or the Internet.

[0023] The device main body 2 includes an imaging unit 21, a movement mechanism 22, a main body inspection unit 23, and a main body control unit 24. The imaging unit 21 has an imaging element such as a CCD sensor or a CMOS sensor, and captures an image of the printed circuit board. In this processing example, the captured image acquired by the imaging unit 21 is a color image. The captured image may also be a grayscale image. The movement mechanism 22 has, for example, a motor, a ball screw, etc., and moves the printed circuit board relative to the imaging unit 21. The main body inspection unit 23 performs an inspection process using defect detection conditions on the captured image output from the imaging unit 21 and detects defects from the captured image. The defect detection conditions include information such as the color ranges determined to be normal in various areas of the printed circuit board. The main body control unit 24 is responsible for overall control of the device main body 2. The main body inspection unit 23 and the main body control unit 24 are realized, for example, by a computer and / or an electric circuit.

[0024] The auxiliary unit 4 is realized by a computer 3. FIG. 2 shows the configuration of the computer 3. The computer 3 has a typical computer system configuration including a CPU 31, a ROM 32, a RAM 33, a fixed disk 34, a display unit (display) 35, an input unit 36, a reading device 37, a communication unit 38, a GPU 39, and a bus 30. The CPU 31 performs various arithmetic operations. The GPU 39 performs various arithmetic operations related to image processing. The ROM 32 stores basic programs. The RAM 33 and the fixed disk 34 store various types of information. The display unit 35 displays various types of information, such as images. The input unit 36 ​​includes a keyboard 36a and a mouse 36b for receiving input from an operator. The reading device 37 reads information from a computer-readable recording medium 81, such as an optical disk, a magnetic disk, a magneto-optical disk, or a memory card. The communication unit 38 transmits and receives signals to and from the device main body 2, etc. The bus 30 is a signal circuit that connects the CPU 31, the GPU 39, the ROM 32, the RAM 33, the fixed disk 34, the display unit 35, the input unit 36, the reading device 37, and the communication unit 38. The computer 3 may be provided with a touch panel, and the input unit 36 ​​and the display unit 35 may be realized by the touch panel.

[0025] In computer 3, program 811 is read in advance from recording medium 81 via reader 37 and stored on fixed disk 34. Program 811 may be stored on fixed disk 34 via network 8. CPU 31 and GPU 39 execute arithmetic processing using RAM 33 and fixed disk 34 in accordance with program 811. CPU 31 and GPU 39 function as a computing unit in computer 3. Other components functioning as a computing unit may be employed in addition to CPU 31 and GPU 39.

[0026] In the inspection device 1, the computer 3 executes arithmetic processing and the like in accordance with the program 811, thereby realizing the functional configuration shown in FIG. 1. That is, the CPU 31, GPU 39, ROM 32, RAM 33, fixed disk 34, and their peripheral configuration of the computer 3 realize the auxiliary unit 4. All or part of the functions of the auxiliary unit 4 may be realized by a dedicated electric circuit, or each function may be realized by an individual program. The auxiliary unit 4 may also be realized by multiple computers. In this processing example, the auxiliary inspection section 42, which will be described later, includes a dedicated image processing circuit (image processing board).

[0027] The auxiliary unit 4 includes a trial inspection control unit 41, an auxiliary inspection unit 42, a memory unit 43, a display unit 35, and an input unit 36. Similar to the main inspection unit 23, the auxiliary inspection unit 42 performs an inspection process using defect detection conditions on an image showing a printed circuit board, and detects defects from the image. The trial inspection control unit 41 controls the auxiliary inspection unit 42 to perform a trial inspection and a confirmation inspection, which will be described later. The trial inspection control unit 41 also controls the entire auxiliary unit 4. The memory unit 43 stores (data of) a trial inspection image 431 used in the trial inspection, and (data of) a confirmation image set 432 used in the confirmation inspection.

[0028] Here, an example of the inspection process in the auxiliary inspection unit 42 will be described. As described above, a similar inspection process is also performed in the main inspection unit 23. FIG. 3 is a diagram showing a multi-tone captured image obtained by capturing an image of a portion of a printed circuit board using the imaging unit 21. As described above, the captured image in this processing example is a color image. Multiple types of regions are provided on the main surface of the printed circuit board. Specifically, the following regions are provided: a plated region plated with a metal such as copper; a solder resist region (hereinafter also referred to as an "SR region") where a solder resist is provided on the surface; a silk region where characters or symbols are printed on the solder resist; and a through-hole region where a through-hole is opened. The SR regions can be distinguished into a first SR region where the solder resist is covered with copper foil and a second SR region where the solder resist is covered with a base material of the printed circuit board, and the two regions have different colors. As described above, each position on the main surface of the printed circuit board belongs to one of multiple region types, including a plated region, a first SR region, a second SR region, a silk region, etc.

[0029] 3 includes region 61 indicating a plated region and region 62 indicating an SR region, and region 62 includes region 621 indicating a first SR region and region 622 indicating a second SR region. In the following description, regions 61, 62, 621, and 622 will be similarly referred to as "plated region 61," "SR region 62," "first SR region 621," and "second SR region 622." For other types of regions on the printed circuit board, the corresponding regions in the captured image will be referred to by the same names.

[0030] The auxiliary inspection unit 42, for example, refers to design data (CAM data, etc.) to identify the region type to which each position in the captured image belongs. Furthermore, a normal range of gradation values ​​for each color component is set for each region type. In other words, thresholds for the abnormal and normal ranges of gradation values ​​for each color component are stored as defect detection conditions. The gradation values ​​at each position in the captured image are compared with the thresholds for each color component, and a group of pixels that fall within the abnormal range is detected as a defective region. In the example of FIG. 3, a region 71 that is darker than its surroundings exists in the first SR region 621, and this region 71 is detected as a defect.

[0031] As described above, the auxiliary inspection unit 42 detects defects by performing an inspection process using defect detection conditions that indicate the above thresholds. The auxiliary inspection unit 42 may perform other inspection processes, and the defect detection conditions may include values ​​other than the thresholds for the gradation values ​​of each color component. For example, the defect detection conditions may include the minimum distance between two adjacent plating areas (pads) or the minimum width of a plating area (land) in which a through-hole is formed. Furthermore, the defect detection conditions may include values ​​other than the defect detection thresholds, and may include, for example, values ​​such as the size of a mask area when a mask area is set for defect detection.

[0032] Printed circuit boards are typically manufactured sequentially in production lots. A production lot is a collection of multiple printed circuit boards manufactured under the same conditions. Variations in the materials used in the production process, as well as the effects of temperature and humidity, can cause unique variations in each production lot. For example, variations in the solder resist and silk ink can cause the color of the SR area and silk area to vary from production lot to production lot. Furthermore, the size of the exposed plated area can vary from production lot to production lot due to the effects of temperature and humidity during the formation of the solder resist layer. When variations unique to each production lot occur, there is a risk of false alarms (detection of false defects) increasing during the inspection process. Therefore, it is preferable to adjust the defect detection conditions to match the unique variations in each production lot. Below, we will explain the process of inspecting printed circuit boards while adjusting the defect detection conditions for each production lot.

[0033] 4A and 4B are diagrams showing the flow of inspection of printed circuit boards by the inspection device 1. Here, a large number of printed circuit boards of the same type are manufactured sequentially as multiple production lots, and the second or subsequent production lot is set as the inspection target, and the process of inspecting the printed circuit boards included in that production lot (hereinafter referred to as the "target production lot") will be described.

[0034] In the inspection device 1 of FIG. 1, some of the printed circuit boards included in a target production lot (for example, 10 to 30 printed circuit boards) are carried into the device main body 2, and a plurality of captured images showing the some of the printed circuit boards are acquired by the imaging unit 21. In this processing example, each captured image shows the entire printed circuit board (all of one or both sides), but may also be an image showing a portion of the printed circuit board. As will be described later, each of the plurality of captured images is for trial inspection, and therefore will be referred to as a "trial inspection image" hereinafter. The plurality of trial inspection images are transmitted from the device main body 2 to the auxiliary unit 4 via the network 8 and stored in the storage unit 43. In FIG. 1, only one trial inspection image 431 is shown as a block, but in reality, a plurality of trial inspection images 431 are stored.

[0035] The memory unit 43 also stores a confirmation image set 432. The confirmation image set 432 is a collection of images identified as true defects by an operator during inspection of a production lot prior to the target production lot. In this processing example, each image in the confirmation image set 432 is an image showing the true defect (an image showing a portion of the printed circuit board), but may also be an image showing the entire printed circuit board. As described above, in the inspection of the printed circuit board of the target production lot, a plurality of trial inspection images 431 and the confirmation image set 432 are stored and prepared in the memory unit 43 (step S11).

[0036] Next, under the control of the trial inspection control unit 41, the auxiliary inspection unit 42 executes an inspection process on the plurality of trial inspection images 431 as a trial inspection (step S12). The auxiliary inspection unit 42 stores defect detection conditions (defect detection conditions in mass production inspection, described below) for a production lot inspected immediately before the target production lot for the same type of printed circuit board, and these defect detection conditions are used in the trial inspection. In step S16, described below, the defect detection conditions are adjusted, so the defect detection conditions in the trial inspection are the defect detection conditions before the adjustment. When the trial inspection on the plurality of trial inspection images 431 is completed, the results of the trial inspection are displayed on the display unit 35 (step S13).

[0037] FIG. 5 is a diagram showing defects displayed on the display unit 35. The results of the trial inspection include, for example, images of defects detected by the trial inspection. In the example of FIG. 5, an area including the detected defect (enclosed by a white rectangle 51 in FIG. 5) is displayed on the left, and an area in the master image that is the same as the detected defect (i.e., the master image area corresponding to the defect) is displayed on the right. The master image is an image generated using images of multiple printed circuit boards during the inspection of the first production lot, for example, and is an image that does not contain defects or has reduced defects. The number of defects detected for each printed circuit board may also be displayed as a result of the trial inspection.

[0038] The operator confirms the results of the trial inspection displayed on the display unit 35. If the operator determines that any of the defects displayed on the display unit 35 is a true defect, the operator inputs an indication that the defect is a true defect via the input unit 36 ​​(step S14). For example, the operator can easily register the defect as a true defect by selecting the defect on the display unit 35, right-clicking the mouse 36b, and selecting "Register True Defect" from the displayed menu. In this way, when the input unit 36 ​​receives an input indicating that a defect is a true defect, the trial inspection control unit 41 adds an image of the defect (true defect) to the confirmation image set 432, and the confirmation image set 432 is updated (step S15). If no defect is determined to be a true defect by the operator, the input unit 36 ​​does not receive the input, and the confirmation image set 432 is not updated (step S14).

[0039] 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 are located in the SR region and are false alarms, the threshold value of the gradation value of each color component in the SR region is changed in the defect detection conditions. Then, the inspection process is executed again on the multiple trial inspection images 431 using the changed defect detection conditions, and the results of the inspection process are displayed on the display unit 35. If the results of the inspection process show that false alarms have not been sufficiently reduced, the defect detection conditions are further changed, and the results of the inspection process performed using the changed defect detection conditions are obtained.

[0040] As described above, by repeatedly changing the defect detection conditions and executing the inspection process as necessary, the defect detection conditions are adjusted, and adjusted defect detection conditions that can reduce false alarms are obtained. In other words, an input for adjusting the defect detection conditions is accepted by the input unit 36, and the adjusted defect detection conditions are obtained. Note that, when adjusting the defect detection conditions, the processes of steps S14 and S15 described above may be performed, and defect images may be added to the confirmation image set 432. On the other hand, if the operator determines that adjustment of the defect detection conditions is not necessary (step S16), the defect detection conditions are not adjusted, and the process proceeds to step S21, which will be described later.

[0041] When the defect detection conditions are adjusted and the adjusted defect detection conditions are acquired, the auxiliary inspection unit 42 executes an inspection process on the confirmation image set 432 as a confirmation inspection under the control of the trial inspection control unit 41 (step S17). The adjusted defect detection conditions are used in the confirmation inspection. When the confirmation inspection on the confirmation image set 432 is completed, the results of the confirmation inspection are displayed on the display unit 35 (step S18).

[0042] FIG. 6 is a diagram showing the results of the confirmation inspection displayed on the display unit 35. In the example of FIG. 6, images 56 of multiple true defects indicated by the confirmation image set 432 are displayed in an array. Furthermore, a master image area 57 corresponding to each true defect is arranged adjacent to the right side of the image 56 of the true defect. At this time, if there is a true defect (hereinafter referred to as an "undetected true defect") that is not detected as a defect in the confirmation inspection among the multiple true defects indicated by the confirmation image set 432 (step S19), the presence of the undetected true defect is displayed on the display unit 35 and reported to the operator. In the example of FIG. 6, the presence of the undetected true defect is emphasized by surrounding the image 56 of the undetected true defect and the corresponding master image area 57 with a thick rectangle 52. In step S18, the presence of the undetected true defect may be indicated by, for example, displaying only the image 56 of the undetected true defect on the display unit 35.

[0043] If an undetected true defect exists, the operator readjusts the defect detection conditions via the input unit 36 ​​(step S20). In readjusting the defect detection conditions, the operator changes the defect detection conditions via the input unit 36 ​​(i.e., changes them from the defect detection conditions after the adjustment described above). Then, the inspection process is executed again on the confirmation image set 432 using the changed defect detection conditions, and the results of the inspection process are displayed on the display unit 35. If an undetected true defect exists as a result of the inspection process, the defect detection conditions are further changed, and the results of the inspection process performed using the changed defect detection conditions are obtained.

[0044] As described above, by repeatedly changing the defect detection conditions and executing the inspection process as necessary, the defect detection conditions are readjusted, and readjusted defect detection conditions are acquired that can detect all true defects indicated by the confirmation image set 432. In other words, an input for readjusting the defect detection conditions is accepted by the input unit 36, and the readjusted defect detection conditions are acquired. The readjusted defect detection conditions become defect detection conditions for the mass production inspection described below for the target production lot. Note that the readjusted defect detection conditions are stricter than the above-mentioned adjusted defect detection conditions used in the confirmation inspection, because they can detect the above-mentioned undetectable true defects.

[0045] On the other hand, if the results of the confirmation inspection show that there are no undetected true defects (step S19), the defect detection conditions are not readjusted, and the defect detection conditions after the above-mentioned adjustment become the defect detection conditions for mass production inspection of the target production lot.

[0046] 1 and stored in the main body inspection unit 23. In the main body 2, a plurality of inspection images showing a plurality of printed circuit boards included in the target production lot are sequentially acquired by the imaging unit 21 (step S21). Of the plurality of printed circuit boards included in the target production lot, for those printed circuit boards for which a trial inspection image has been acquired in step S11, the trial inspection image may be treated as the inspection image.

[0047] Further, under the control of the main body control unit 24, the main body inspection unit 23 performs inspection processing on the multiple inspection images as mass production inspection (step S22). In the mass production inspection, the above-described defect detection conditions for mass production inspection are used. Preferably, the mass production inspection is performed in parallel with the acquisition of the multiple inspection images. The results of the mass production inspection are stored in the main body inspection unit 23. The results of the mass production inspection include information on defects detected by the mass production inspection. The defect information includes, for example, an image of the defect, identification information for the printed circuit board containing the defect, and position information of the defect on the printed circuit board. The results of the mass production inspection may also include the number of defects detected for each printed circuit board. Note that the multiple inspection images may be deleted after the inspection processing.

[0048] This completes the inspection of the printed circuit board by the inspection device 1. Information about defects detected in the mass production inspection may be output to, for example, an external defect confirmation device. The defect confirmation device refers to the information about the defect, images the area of ​​the defect on the printed circuit board, and displays it on a display unit. An operator checks the defect contained in the displayed image to determine whether the defect is a real defect or a false report (false defect).

[0049] As described above, in the inspection device 1 of FIG. 1, a plurality of trial inspection images 431 showing some of the printed circuit boards in one production lot and a confirmation image set 432 showing a plurality of defects to be detected on the printed circuit boards are stored in the memory unit 43. The auxiliary inspection unit 42 detects defects by performing an inspection process using defect detection conditions on the images showing the printed circuit boards. The trial inspection control unit 41 causes the auxiliary inspection unit 42 to perform an inspection process using the defect detection conditions before adjustment as a trial inspection on the plurality of trial inspection images 431, and causes the display unit 35 to display the results of the trial inspection. Thereafter, the input unit 36 ​​accepts an input for adjusting the defect detection conditions. In the inspection device 1, by adjusting the defect detection conditions based on the results of the trial inspection, an increase in false alarms due to unique variations that occur for each production lot can be suppressed.

[0050] After receiving the input for adjusting the defect detection conditions, the trial inspection control unit 41 causes the auxiliary inspection unit 42 to execute an inspection process using the adjusted defect detection conditions for the confirmation image set 432 as a confirmation inspection, and displays the results of the confirmation inspection on the display unit 35. If the confirmation image set 432 is not prepared, an operator must memorize or record images containing true defects among the trial inspection images from past production lots, and then execute an inspection process using the adjusted defect detection conditions for those images to confirm whether true defects can be detected using the adjusted defect detection conditions. While it is possible to execute an inspection process for all trial inspection images from past production lots, this would require a large amount of work. In contrast, by preparing the confirmation image set 432, the inspection device 1 can easily confirm whether true defects can be detected using the adjusted defect detection conditions, i.e., whether the adjustment of the defect detection conditions is appropriate. As a result, the efficiency of the work involved in adjusting the defect detection conditions can be improved. Furthermore, since there is no need for a large-capacity storage unit 43 for storing all test inspection images from past production lots, the manufacturing cost of the inspection device 1 can be reduced.

[0051] Preferably, when the trial 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 shown in the confirmation image set 432. This allows the operator to easily and more reliably recognize the presence of undetected true defects, and enables the operator to readjust the defect detection conditions to obtain appropriate defect detection conditions for mass production inspection.

[0052] Preferably, when the input unit 36 ​​receives an input indicating that a defect displayed on the display unit 35 as a result of the trial inspection is a true defect, the trial inspection control unit 41 adds an image of the defect to the confirmation image set 432. This makes it possible to easily add a true defect detected in the trial inspection to the confirmation image set 432, and to create (prepare) a preferable confirmation image set 432.

[0053] Preferably, the inspection device 1 further includes an imaging unit 21 that acquires multiple inspection images showing multiple printed circuit boards included in the production lot. The main inspection unit 23 executes an inspection process for the multiple inspection images using the adjusted defect detection conditions as a mass production inspection. This allows the mass production inspection to be performed appropriately using defect detection conditions that can detect true defects while reducing false alarms. Furthermore, because the multiple trial inspection images 431 and the confirmation image set 432 are images acquired by the imaging unit 21, it is possible to prevent differences in inspection conditions caused by the imaging unit during the trial inspection, confirmation inspection, and mass production inspection.

[0054] FIG. 7 is a diagram showing another example of inspection of a printed circuit board by the inspection apparatus 1, illustrating the flow of processing performed after step S22 in FIG. 4B. In the example of FIG. 7, the results of the mass production inspection in step S22 are transmitted to the auxiliary unit 4 in FIG. 1 and displayed on the display unit 35 (step S23). The results of the mass production inspection displayed on the display unit 35 are confirmed by an operator. If any of the defects displayed on the display unit 35 is determined to be a true defect by the operator, the operator inputs an indication that the defect is a true defect via the input unit 36, as in step S14 (step S24). As a result, the trial inspection control unit 41 adds an image of the defect (true defect) to the confirmation image set 432, and the confirmation image set 432 is updated (step S25). If no defect is determined to be a true defect by the operator, the input unit 36 ​​does not receive the input, and the confirmation image set 432 is not updated (step S24).

[0055] 7, when the input unit 36 ​​receives an input indicating that a defect detected in mass production inspection is a true defect, the trial inspection control unit 41 adds an image of the defect to the confirmation image set 432. This makes it possible to easily add a true defect detected in mass production inspection to the confirmation image set 432, and to create (prepare) a desirable confirmation image set 432.

[0056] In the inspection device 1 of Fig. 1, the device main body 2 and the auxiliary unit 4 are provided separately, but the trial inspection control unit 41, auxiliary inspection unit 42, and memory unit 43 of the auxiliary unit 4 may be realized by a computer included in the device main body 2. In this case, the main body inspection unit 23 and the auxiliary inspection unit 42 are realized by a single inspection unit. In other words, in the inspection device 1 of Fig. 1, in which the device main body 2 and the auxiliary unit 4 are provided separately, the inspection unit has a first inspection unit (auxiliary inspection unit 42) that performs trial inspection and confirmation inspection, and a second inspection unit (main body inspection unit 23) that performs mass production inspection.

[0057] As in the above example, when the device main body 2 including the imaging unit 21 and the second inspection unit and the auxiliary unit 4 including the memory unit 43, the first inspection unit, the display unit 35, the input unit 36, and the trial inspection control unit 41 are provided separately, it becomes possible to perform mass production inspections of other types of printed circuit boards in the device main body 2 in parallel with the processing of steps S12 to S20 in the auxiliary unit 4. As a result, it is possible to improve the operating rate of the device main body 2 and improve the efficiency of inspecting printed circuit boards.

[0058] In the above processing example, the confirmation image set 432 includes images of various types of defects. However, the confirmation image set 432 may also include an image set of a first defect type and an image set of a second defect type different from the first defect type. In the example of FIG. 8 , the confirmation image set 432 includes a plating area defect image set 433 and an SR area defect image set 434. Defects present in the plating area 61 are referred to as "plating area defects," and the plating area defect image set 433 includes images of multiple plating area defects that are true defects. Furthermore, defects present in the SR area 62 are referred to as "SR area defects," and the SR area defect image set 434 includes images of multiple SR area defects that are true defects. Plating area defects are high-importance defects because they have a relatively large impact on the operation of the printed circuit board. SR area defects are low-importance defects because they have a relatively small impact on the operation of the printed circuit board.

[0059] In step S14 of FIG. 4A, when the input unit 36 ​​receives an input indicating that a defect displayed on the display unit 35 as a result of the trial inspection is a true defect, if the defect is a plating region defect, the trial inspection control unit 41 adds an image of the defect to the plating region defect image set 433 (step S15). On the other hand, if the defect is an SR region defect, the image of the defect is not added to the SR region defect image set 434. This is similar to steps S24 and S25 of FIG. 7. As described above, by not adding defects of low importance to the confirmation image set 432, an excessive increase in the number of images included in the confirmation image set 432, i.e., an excessive increase in the size of the confirmation image set 432, can be prevented. The first and second defect types may be other than plating region defects and SR region defects, and the confirmation image set 432 may include image sets of three or more defect types.

[0060] The inspection device 1 and the inspection method described above can be modified in various ways.

[0061] The images included in the confirmation image set 432 may be images of defects to be detected on printed circuit boards, or may be images of real defects on other types of printed circuit boards.

[0062] The object to be inspected by the inspection device 1 may be a substrate other than a printed circuit board, such as a semiconductor substrate or a glass substrate. Furthermore, the inspection device 1 may also detect defects in objects other than substrates, such as machine parts.

[0063] 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]

[0064] 1. Inspection equipment 2. Device body 3. Computer 4 Auxiliary Unit 21 Imaging unit 23 Main Unit Inspection Department 35 Display section 36 Input section 41 Trial inspection control section 42 Auxiliary Inspection Department 43 Storage section 431 Trial inspection image 432 Confirmation Image Set 433 Plated Area Defect Image Set 434 SR region defect image set 811 Program S11~S25 steps

Claims

1. An inspection device that inspects an image of an object, a storage unit that stores a plurality of test inspection images showing some objects in one production lot and a set of confirmation images showing a plurality of defects to be detected in the objects; an inspection unit that detects defects by executing an inspection process using defect detection conditions on an image showing an object; a display unit that displays the results of the inspection process; an input unit that receives an input for adjusting the defect detection conditions; a trial inspection control unit that causes the inspection unit to execute the inspection process using the defect detection conditions before adjustment on the plurality of trial inspection images as a trial inspection, causes the display unit to display results of the trial inspection, and, after the input unit receives input for adjusting the defect detection conditions, causes the inspection unit to execute the inspection process using the defect detection conditions after adjustment on the confirmation image set as a confirmation inspection, and displays results of the confirmation inspection on the display unit; Equipped with An inspection apparatus, characterized in that the confirmation image set shows true defects detected when the inspection process is performed using the defect detection conditions before adjustment.

2. The inspection device according to claim 1, An inspection device characterized in that, when the trial inspection control unit displays the results of the confirmation inspection on the display unit, it displays the presence of defects among the multiple defects shown in the confirmation image set that were not detected by the confirmation inspection.

3. The inspection device according to claim 1, An inspection device characterized in that when the input unit receives input indicating that a defect displayed on the display unit as a result of the trial inspection is a true defect, the trial inspection control unit adds an image of the defect to the confirmation image set.

4. The inspection device according to claim 1, An inspection apparatus, wherein the confirmation image set includes an image set of a first defect type and an image set of a second defect type different from the first defect type.

5. 5. The inspection device according to claim 1, an imaging unit that acquires a plurality of inspection images showing a plurality of objects included in the production lot; the plurality of test inspection images and the confirmation image set are images acquired by the imaging unit, The inspection apparatus is characterized in that the inspection unit performs the inspection process using the adjusted defect detection conditions on the plurality of inspection images as a mass production inspection.

6. The inspection device according to claim 5, An inspection device characterized in that when the input unit receives input indicating that a defect detected during the mass production inspection is a true defect, the trial inspection control unit adds an image of the defect to the confirmation image set.

7. The inspection device according to claim 5, The inspection unit a first inspection unit that performs the trial inspection and the confirmation inspection; a second inspection unit that performs the mass production inspection; Equipped with An inspection device characterized in that a device main body including the imaging unit and the second inspection unit, and an auxiliary unit including the memory unit, the first inspection unit, the display unit, the input unit, and the trial inspection control unit are provided separately.

8. An inspection method for inspecting an image of an object using an inspection device, comprising: a) preparing a set of trial inspection images of a portion of a production lot of objects and a set of verification images of the objects that are to be inspected for defects; b) in the inspection device, defects can be detected by executing an inspection process using defect detection conditions on an image showing an object, and a step of executing the inspection process using predetermined defect detection conditions on the plurality of trial inspection images as a trial inspection; c) displaying the results of the trial inspection on a display unit; d) receiving an input for adjusting the defect detection conditions; e) performing the inspection process using the adjusted defect detection conditions on the confirmation image set as a confirmation inspection; f) displaying the result of the confirmation test on the display unit; Equipped with An inspection method, characterized in that the confirmation image set indicates true defects detected when the inspection process is performed using the predetermined defect detection conditions.

9. The inspection method according to claim 8, An inspection method characterized in that in step f), when the results of the confirmation inspection are displayed on the display unit, the presence of defects that were not detected by the confirmation inspection among the multiple defects shown in the confirmation image set is displayed.

10. The inspection method according to claim 8, An inspection method characterized in that in step c), when an input is received that designates a defect displayed on the display unit as a result of the trial inspection as a true defect, an image of the defect is added to the confirmation image set.

11. The inspection method according to claim 8, An inspection method, wherein the confirmation image set includes an image set of a first defect type and an image set of a second defect type different from the first defect type.

12. 12. The inspection method according to claim 8, further comprising: g) acquiring, by an imaging unit, a plurality of inspection images showing a plurality of objects included in the production lot; h) performing the inspection process using the adjusted defect detection conditions on the plurality of inspection images as a mass production inspection; Furthermore, An inspection method characterized in that the plurality of test inspection images and the set of confirmation images are images acquired by the imaging unit.

13. The inspection method according to claim 12, an inspection method characterized in that, when an input is received indicating that a defect detected in the mass production inspection is a true defect, an image of the defect is added to the confirmation image set.

14. A program for causing a computer to inspect an image of an object, the program being executed by the computer by the computer comprising: a) preparing a set of trial inspection images representing a portion of a production lot of objects and a set of verification images representing a plurality of defects to be detected on the objects; b) in the computer, defects can be detected by executing an inspection process using defect detection conditions on an image showing an object, and a step of executing the inspection process using predetermined defect detection conditions on the plurality of trial inspection images as a trial inspection; c) displaying the results of the trial inspection on a display unit; d) receiving an input for adjusting the defect detection conditions; e) performing the inspection process using the adjusted defect detection conditions on the confirmation image set as a confirmation inspection; f) displaying the result of the confirmation test on the display unit; Execute The program, characterized in that the confirmation image set indicates true defects detected when the inspection process is executed using the predetermined defect detection conditions.

Images