Visual inspection equipment

Abstract

To provide a visual inspection device that extracts imaging obstacles such as damage, or contamination and the like of a carrier, and can calculate a level of the imaging obstacle.SOLUTION: A visual inspection device 100 comprises: a carrier 1; a supply unit 2 that supplies an inspection object 20 onto a second principal plane of the carrier 1; a driving unit 3 that drives the carrier 1 to thereby convey the inspection object 20 on the carrier 1; a first imaging unit that, for performing visual inspection of the inspection object 20, can image the inspection object 20 on the carrier 1 by imaging light having a wavelength transmitting the carrier 1; an imaging obstacle extraction unit that extracts an imaging obstacle included in an image captured by the first imaging unit on the basis of an optical characteristic value regarding the imaging obstacle included in the carrier 1; and a level calculation unit that calculates a level of the imaging obstacle extracted by the imaging obstacle extraction unit. The level calculation unit calculates the level of the imaging obstacle on the basis of a cumulative value of a plurality of datum on the imaging obstacle.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to a visual inspection apparatus for inspecting the visual appearance of an object to be inspected. [Background technology]

[0002] 2. Description of the Related Art There is known an apparatus that inspects the appearance of an inspection object by capturing an image of the inspection object with an imaging device while the inspection object is placed on a conveying body such as a conveying table and conveyed.

[0003] As such an appearance inspection device, Patent Document 1 discloses an appearance inspection device in which an object to be inspected is placed on a circular conveying table made of a transparent glass body, and the conveying table is rotated to convey the object to be inspected while a camera captures images of each surface of the object to be inspected. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Application Laid-Open No. 2011-133458 Summary of the Invention [Problem to be solved by the invention]

[0005] However, the visual inspection device described in Patent Document 1 may mistake scratches or stains on the conveying table for scratches or stains on the inspection object, resulting in the incorrect determination of a non-defective inspection object as a defective one. That is, when an image of the inspection object on a transparent conveying table is captured by a bottom camera positioned on the opposite side of the conveying table from the inspection object, scratches or stains on the conveying table that overlap with the inspection object may be mistaken for scratches or stains on the inspection object. Therefore, to prevent the above-mentioned incorrect determination of the visual inspection, it is preferable to clean or replace the conveying table depending on the level of imaging obstacles, such as scratches or stains on the conveying table. However, Patent Document 1 does not disclose a method for calculating the level of imaging obstacles.

[0006] The present invention has been made to solve the above-mentioned problems, and has as its object to provide a visual inspection device that can extract obstacles to be imaged, such as scratches and dirt on a conveyed body, and calculate their level. [Means for solving the problem]

[0007] The visual inspection apparatus of the present invention is an visual inspection apparatus for performing a visual inspection of an inspection object, a carrier having a first main surface and a second main surface opposite to the first main surface; a supply unit that supplies the inspection object onto the second main surface of the transport body; a driving unit that drives the conveying body to convey the inspection object on the conveying body; a first imaging unit capable of imaging the inspection object on the conveyance body using imaging light having a wavelength that passes through the conveyance body in order to perform a visual inspection of the inspection object; an image capturing obstacle extracting unit that extracts an image capturing obstacle included in an image captured by the first image capturing unit based on an optical characteristic value related to the image capturing obstacle included in the transport body; a level calculation unit that calculates a level of the obstacle extracted by the obstacle extraction unit; and Equipped with The level calculation unit calculates the level of the obstacle to be imaged based on a cumulative value of data on the plurality of obstacles to be imaged extracted by the obstacle extraction unit to be imaged. [Effects of the Invention]

[0008] According to the appearance inspection device of the present invention, image-capturing obstacles included in a captured image are extracted, and the level of the image-capturing obstacles is calculated based on the cumulative value of the data of the extracted plurality of image-capturing obstacles, so that the level of the image-capturing obstacles, such as scratches and dirt on the conveyance body, can be appropriately calculated. The level of the image-capturing obstacles can be used as an index for the maintenance of the conveyance body, for example. Therefore, depending on the calculated level of the image-capturing obstacles, cleaning or replacement of the conveyance body can be performed at an appropriate time, for example. [Brief explanation of the drawings]

[0009] [Figure 1] FIG. 1 is a diagram schematically illustrating a configuration of a visual inspection apparatus according to an embodiment. [Figure 2] 1 is a perspective view showing the external shape of a multilayer ceramic capacitor, which is an example of an object to be inspected; [Figure 3] 1 is a diagram showing the positions of a first imaging unit for imaging a first main surface of a multilayer ceramic capacitor, which is an example of an object to be inspected, and a second imaging unit for imaging a second main surface thereof. [Figure 4] 10 is a diagram showing the positions of a third imaging unit for imaging a first end face of a multilayer ceramic capacitor, which is an example of an object to be inspected, and a fourth imaging unit for imaging a second end face of the multilayer ceramic capacitor. FIG. [Figure 5] 10 is a diagram showing the positions of a fifth imaging unit for imaging a first side surface of a multilayer ceramic capacitor, which is an example of an object to be inspected, and a sixth imaging unit for imaging a second side surface of the multilayer ceramic capacitor. FIG. [Figure 6] FIG. 2 is a block diagram schematically illustrating the functions of a processing unit. [Figure 7] FIG. 2 is a diagram showing the range of the image captured by the first imaging unit, excluding the range where the inspection object is placed. [Figure 8] 10A and 10B are diagrams for explaining an example of a method for separating extracted obstacles into scratches and dirt. [Figure 9] 10A and 10B are diagrams for explaining an example of a method for distinguishing between scratches and stains based on coordinate positions on an image. [Figure 10] (a) is a diagram showing a schematic diagram of the luminance distribution of the R image, G image, and B image when the optical axis of the first imaging unit and the optical axis of the first illumination unit are aligned, (b) is a diagram showing a schematic diagram of the luminance distribution of the R image, G image, and B image when the optical axis of the green illumination light of the first illumination unit is misaligned, and (c) is a diagram showing a schematic diagram of the luminance distribution of the R image, G image, and B image when the optical axis of the first imaging unit is misaligned. DETAILED DESCRIPTION OF THE INVENTION

[0010] The features of the present invention will be specifically described below by showing embodiments of the present invention.

[0011] FIG. 1 is a diagram schematically illustrating the configuration of an appearance inspection apparatus 100 according to one embodiment. The appearance inspection apparatus 100 according to one embodiment is an apparatus for performing an appearance inspection of an inspection target object 20, and includes a conveyance body 1, a supply unit 2, a drive unit 3, a processing unit 4, and a first imaging unit 11. The first imaging unit 11 is disposed on the opposite side of the conveyance body 1 from the second imaging unit 12 (see FIG. 3). The appearance inspection apparatus 100 according to this embodiment further includes an alert unit 5, an alignment unit 6, a discharge unit 7, the second imaging unit 12, the third imaging unit 13, the fourth imaging unit 14, the fifth imaging unit 15, and a sixth imaging unit 16.

[0012] The inspection object 20 is, for example, an electronic component such as a multilayer ceramic capacitor, an inductor, a thermistor, or a module substrate, or a semi-finished product in the middle of manufacturing an electronic component, but the inspection object 20 is not limited to an electronic component or a semi-finished product.

[0013] Fig. 2 is a perspective view showing the external shape of a multilayer ceramic capacitor 20X, which is an example of the inspection object 20. As shown in Fig. 2, the multilayer ceramic capacitor 20X has a ceramic body 21, a first external electrode 22a, and a second external electrode 22b.

[0014] The multilayer ceramic capacitor 20X has a hexahedral shape, that is, the multilayer ceramic capacitor 20X has a first end face 23a and a second end face 23b facing each other, a first main face 24a and a second main face 24b facing each other, and a first side face 25a and a second side face 25b facing each other.

[0015] The conveying body 1 has a first main surface 1a and a second main surface 1b opposite to the first main surface 1a (see FIGS. 3 to 5). There are no particular restrictions on the structure or shape of the conveying body 1, as long as it can convey the inspection object 20 when used in the visual inspection device 100. The conveying body 1 in this embodiment is an electrostatic induction adsorption type conveying body that adsorbs and conveys the inspection object 20 to the second main surface 1b, which is the conveying surface, by electrostatic force due to electrostatic induction. However, the conveying body 1 may also be one that conveys the inspection object 20 without adsorbing it.

[0016] The conveyance body 1 in this embodiment is transparent at least in the area where the inspection object 20 is placed, and has a shape that is rotatable around a central axis X1 that is perpendicular to the first principal surface 1a and the second principal surface 1b. Specifically, the conveyance body 1 has a transparent, rotatable circular table-like shape, and its diameter is, for example, 100 mm or more and 1000 mm or less.

[0017] In this embodiment, the conveyance body 1 is made of a transparent insulating material, for example, a transparent glass material such as borosilicate glass, quartz glass, or float glass, or a transparent resin material such as polyethylene terephthalate resin or acrylic resin. However, the entire conveyance body 1 does not need to be made of a transparent insulating material, as long as at least the area where the inspection object 20 is placed is made of a transparent insulating material. Note that, as will be described later, "transparent" here means having a transmittance that can transmit imaging light irradiated when inspecting the inspection object 20, and does not necessarily need to be transparent to visible light.

[0018] The carrier 1 may have a single layer structure or a multi-layer structure. When the carrier 1 is an electrostatic induction adsorption type carrier, it may include a conductive layer. In this case, the conductive layer can be configured as a transparent electrode made of indium tin oxide (ITO), antimony-doped tin oxide (ATO), titanium oxide, graphene, or the like.

[0019] In this embodiment, as will be described later, the inspection object 20 placed on the second main surface 1b of the conveyance body 1 is imaged by the first imaging unit 11 from the first main surface 1a side for visual inspection. Therefore, at least the region of the conveyance body 1 on which the inspection object 20 is placed has a transmittance that can transmit imaging light irradiated when inspecting the inspection object 20. To improve the accuracy of the visual inspection, a high transmittance is preferable.

[0020] When the transport body 1 is an electrostatic induction adsorption type transport body, the first main surface 1a is positively or negatively charged by a charging device or the like. Here, the first main surface 1a is assumed to be positively charged. In this case, within the transport body 1, a negative charge appears on the first main surface 1a side, and a positive charge appears on the second main surface 1b side. Furthermore, a negative charge appears on the first main surface 24a side of the inspection object 20 placed on the second main surface 1b of the transport body 1. As a result, an electrostatic adsorption force is generated between the inspection object 20 and the transport body 1, and the inspection object 20 is adsorbed to the second main surface 1b of the transport body 1.

[0021] The supply unit 2 supplies the inspection objects 20 onto the second main surface 1b of the conveyance body 1. However, "on the second main surface 1b" does not mean an upward direction in the vertical direction, but rather refers to the surface of the second main surface 1b, and the direction does not matter. As the supply unit 2, for example, a vibration-type parts feeder that supplies the inspection objects 20 by vibration, a rotary-type parts feeder that supplies the inspection objects 20 while rotating, an air-type parts feeder that supplies the inspection objects 20 by air force, a belt conveyor-type parts feeder that supplies the inspection objects 20 by a belt conveyor, a one-by-one loading mechanism that supplies the inspection objects 20 one by one, etc. can be used.

[0022] The supply unit 2 supplies the inspection objects 20 onto the conveyance body 1 at regular time intervals, for example. The supply amount by the supply unit 2 is, for example, 50 to 30,000 per minute. The supply unit 2 may supply the inspection objects 20 in a single row, or in two or more rows.

[0023] In this embodiment, the inspection objects 20 supplied onto the conveying body 1 are attracted to the conveying body 1 by electrostatic induction and aligned in a line by the alignment unit 6, as shown in FIG. 1. That is, the inspection objects 20 are aligned in a line with their orientations aligned by coming into contact with the alignment unit 6. Here, the orientation of the multilayer ceramic capacitors 20X, which are the inspection objects 20, is aligned so that the direction in which the first external electrode 22a and the second external electrode 22b face each other coincides with the conveying direction.

[0024] As described above, the conveying body 1 in this embodiment has a rotatable circular table-like shape and conveys the inspection object 20 on the second main surface 1b by rotating. At this time, centrifugal force is applied to the inspection object 20. Therefore, in order to prevent the inspection object 20 from shifting position or falling off the second main surface 1b, the rotation speed of the conveying body 1 cannot be made very high. However, the inspection object 20 is conveyed while adsorbed to the second main surface 1b of the conveying body 1 by electrostatic force due to electrostatic induction. This prevents the inspection object 20 from shifting position or falling off the second main surface 1b during conveyance. Therefore, the rotation speed of the conveying body 1 can be made higher. In other words, it is preferable that the inspection object 20 be conveyed while adsorbed to the conveying body 1.

[0025] In the method of transporting the inspection object 20 while it is attracted by electrostatic induction, the transport body 1 can be used not in a horizontal state but in a state inclined relative to the horizontal plane.

[0026] The driving unit 3 drives the conveying body 1 to convey the inspection object 20 on the conveying body 1. The driving unit 3 is, for example, an electromagnetic motor such as a DC motor, servo motor, stepping motor, or linear motor, an ultrasonic motor, or compressed air. The conveying body 1 may be driven continuously or intermittently. When the conveying body 1 is driven continuously, the speed is, for example, 100 mm / s or more and 2000 mm / s or less, and one example is 800 mm / s. The driving unit 3 can be provided at any position.

[0027] The appearance inspection device 100 is configured to perform an appearance inspection of the inspection object 20 when the inspection object 20 is transported by the transport body 1. The appearance inspection of the inspection object 20 is performed by the first imaging unit 11 to the sixth imaging unit 16 and the processing unit 4.

[0028] The first to sixth imaging units 11 to 16 each capture an image of the inspection object 20 on the conveyance body 1. There are no particular restrictions on the first to sixth imaging units 11 to 16 as long as they can capture an image of the inspection object 20, and for example, a CCD camera or a CMOS camera can be used. The imaging speed of the first to sixth imaging units 11 to 16 is, for example, 10 to 400 images per second, for example, 150 images per second. The imaging range is, for example, 1 mm x 1 mm to 10 mm x 10 mm, for example, 5 mm x 5 mm. The distance traveled by the conveyance body 1 when two images are captured consecutively is, where Wa is the dimension of the image along the traveling direction of the conveyance body 1, a distance of 0.5 Wa to 5 Wa.

[0029] Here, the description will be made assuming that the inspection object 20 is the above-mentioned multilayer ceramic capacitor 20X, and that CCD cameras are used as the first imaging unit 11 to the sixth imaging unit 16. Note that Fig. 1 shows the second imaging unit 12 to the sixth imaging unit 16, which are located above the conveying body 1 (on the second main surface 1b side of the conveying body 1), but does not show the first imaging unit 11, which is located below the conveying body 1 (on the first main surface 1a side of the conveying body 1).

[0030] 1, a first imaging area SA1 is an area for imaging the first side surface 25a and the second side surface 25b of the multilayer ceramic capacitor 20X. A second imaging area SA2 is an area for imaging the first end surface 23a and the second end surface 23b of the multilayer ceramic capacitor 20X. A third imaging area SA3 is an area for imaging the first main surface 24a and the second main surface 24b of the multilayer ceramic capacitor 20X.

[0031] 3 is a diagram showing the positions of a first imaging unit 11 for imaging the first main surface 24a of the multilayer ceramic capacitor 20X and a second imaging unit 12 for imaging the second main surface 24b. The first imaging unit 11 is provided on the first main surface 1a side at a position separated in a direction perpendicular to the first main surface 1a of the conveyance body 1. The second imaging unit 12 is provided on the second main surface 1b side at a position separated in a direction perpendicular to the second main surface 1b of the inspection object 20 of the conveyance body 1.

[0032] 3, the conveyance body 1 is disposed horizontally, the first imaging unit 11 is provided below the conveyance body 1, and the second imaging unit 12 is provided above the conveyance body 1. Therefore, the first imaging unit 11 images the first main surface 24a of the multilayer ceramic capacitor 20X placed on the second main surface 1b of the conveyance body 1 from below, that is, the side of the first main surface 1a of the conveyance body 1. Furthermore, the second imaging unit 12 images the second main surface 24b of the multilayer ceramic capacitor 20X from above, that is, the side of the second main surface 1b of the conveyance body 1.

[0033] In this embodiment, a first illumination unit 31 is provided to illuminate the first main surface 24a of the multilayer ceramic capacitor 20X with light, and a second illumination unit 32 is provided to illuminate the second main surface 24b with light. The first illumination unit 31 and the second illumination unit 32 are, for example, hemispherical dome lights, and have a hole near the center to allow imaging light to pass through.

[0034] 4 is a diagram showing the positions of a third imaging unit 13 for imaging the first end face 23a of the multilayer ceramic capacitor 20X and a fourth imaging unit 14 for imaging the second end face 23b. The third imaging unit 13 and the fourth imaging unit 14 are provided on the conveyance body 1 at positions spaced apart in a direction perpendicular to the second main surface 1b of the inspection object 20. In this embodiment, as shown in FIG. 4, the conveyance body 1 is disposed horizontally, and therefore the third imaging unit 13 and the fourth imaging unit 14 are provided above the conveyance body 1.

[0035] In this embodiment, a third illumination unit 33 is provided for illuminating the first end face 23a of the multilayer ceramic capacitor 20X with light, and a fourth illumination unit 34 is provided for illuminating the second end face 23b with light. The third illumination unit 33 and the fourth illumination unit 34 may have the same structure as the first illumination unit 31 and the second illumination unit 32.

[0036] 4, the imaging surface of the third imaging unit 13 faces vertically downward. A first reflector 41 for changing the optical path is provided vertically below the imaging surface of the third imaging unit 13. The first reflector 41 is, for example, a mirror or a prism. The third imaging unit 13 receives the light whose optical path has been changed by the first reflector 41, thereby capturing an image of the first end face 23a of the multilayer ceramic capacitor 20X.

[0037] 4, the imaging surface of the fourth imaging unit 14 faces vertically downward. A second reflector 42 for changing the optical path is provided vertically below the imaging surface of the fourth imaging unit 14. The second reflector 42 is, for example, a mirror or a prism. The fourth imaging unit 14 receives the light whose optical path has been changed by the second reflector 42, thereby capturing an image of the second end face 23b of the multilayer ceramic capacitor 20X.

[0038] 5 is a diagram showing the positions of a fifth imaging unit 15 for imaging the first side surface 25a of the multilayer ceramic capacitor 20X and a sixth imaging unit 16 for imaging the second side surface 25b. The fifth imaging unit 15 is provided on the conveyance body 1 at a position away from the second main surface 1b of the inspection object 20 in a direction perpendicular to the second main surface 1b. In this embodiment, as shown in FIG. 5, the conveyance body 1 is disposed horizontally, and therefore the fifth imaging unit 15 is provided above the conveyance body 1. The sixth imaging unit 16 is provided radially outward from the conveyance body 1 and at approximately the same height as the multilayer ceramic capacitor 20X.

[0039] In this embodiment, a fifth illumination unit 35 is provided to illuminate the first side surface 25a of the multilayer ceramic capacitor 20X with light, and a sixth illumination unit 36 ​​is provided to illuminate the second side surface 25b with light. The fifth illumination unit 35 and the sixth illumination unit 36 ​​may have the same structure as the first illumination unit 31 and the second illumination unit 32.

[0040] 5, the imaging surface of the fifth imaging unit 15 faces vertically downward. A third reflector 43 for changing the optical path is provided vertically below the imaging surface of the fifth imaging unit 15. The third reflector 43 is, for example, a mirror or a prism. The fifth imaging unit 15 captures an image of the first side surface 25a of the multilayer ceramic capacitor 20X by receiving light whose optical path has been changed by the third reflector 43.

[0041] 5, the imaging surface of the sixth imaging unit 16 faces the second side surface 25b of the multilayer ceramic capacitor 20X. That is, the sixth imaging unit 16 directly receives imaging light and captures an image of the second side surface 25b of the multilayer ceramic capacitor 20X.

[0042] The visual inspection of the inspection object 20 is performed by the processing unit 4 based on the images captured by the first imaging unit 11 to the sixth imaging unit 16. The processing unit 4 is, for example, a personal computer or a dedicated image processing controller. In the visual inspection based on the captured images, for example, the external dimensions of the inspection object 20, the dimensions of specific parts, the presence or absence of surface irregularities, the presence or absence of foreign matter attached, the presence or absence of damage, the presence or absence of discoloration, etc. are checked.

[0043] Of the first imaging unit 11 to the sixth imaging unit 16, the second imaging unit 12 to the sixth imaging unit 16 may be omitted, or the third imaging unit 13 to the sixth imaging unit 16 may be omitted. Also, an imaging unit other than the first imaging unit 11 to the sixth imaging unit 16 may be provided.

[0044] The inspection object 20, after being imaged for visual inspection, is discharged from the second main surface 1b of the conveyance body 1 by the discharge unit 7. The length of the conveyance path from when the inspection object 20 is supplied onto the second main surface 1b of the conveyance body 1 until when it is discharged is, for example, not less than 300 mm and not more than 2500 mm.

[0045] In this embodiment, the discharge unit 7 includes an air blowing unit 71. That is, the air blowing unit 71 blows air toward the inspection object 20, thereby discharging the inspection object 20 from the second main surface 1b of the conveying body 1. However, the method of discharging the inspection object 20 is not limited to the method using air blowing, and for example, the inspection object 20 may be discharged by suction using a suction mechanism (not shown). Also, the inspection objects 20 may be picked up and discharged one by one. Also, depending on the results of the visual inspection, non-defective products and defective products may be discharged so as to be collected in separate containers.

[0046] FIG. 6 is a block diagram illustrating the functions of the processing unit 4. FIG. 6 also illustrates an alert unit 5 (described later) along with the processing unit 4. The processing unit 4 functions as an imaged obstacle extraction unit 4a that extracts imaged obstacles included in the image captured by the first imaging unit 11 based on optical characteristic values ​​of the imaged obstacles included in the conveyance body 1, and a level calculation unit 4c that calculates the level of the imaged obstacles extracted by the imaged obstacle extraction unit 4a. The processing unit 4 may also function as a sorting unit 4b and a non-defective product rate determination unit 4d (described later). The processing unit 4 may further include a storage unit 4e that stores images captured by the first imaging unit 11. However, the imaged obstacle extraction unit 4a may be provided separately from the processing unit 4, and the level calculation unit 4c may be provided separately from the processing unit 4. The sorting unit 4b may be provided separately from the processing unit 4, and the non-defective product rate determination unit 4d may be provided separately from the processing unit 4.

[0047] The above-mentioned "imaging obstacle included in the conveying body 1" refers to an object that obstructs imaging for visual inspection of the inspection target 20, such as scratches or dirt on the conveying body 1. Furthermore, the "optical characteristic value related to the imaging obstacle included in the conveying body 1" refers to, for example, the brightness of the imaging obstacle in the captured image. Using the obtained brightness information, it is possible to use the brightness area, brightness coordinates, maximum brightness, minimum brightness, differential value (amount of change in brightness per distance), color information, brightness difference from the background average brightness, brightness difference from an arbitrary specified brightness, etc.

[0048] In this embodiment, the imaged obstacle extraction unit 4a extracts imaged obstacles based on optical characteristic values ​​contained in images captured by the first imaging unit 11 and stored in the storage unit 4e. That is, the first imaging unit 11 is used not only to perform the appearance inspection of the inspection target object 20 but also to extract imaged obstacles. Therefore, there is no need to provide a new device for extracting imaged obstacles, which can prevent the appearance inspection apparatus 100 from becoming larger.

[0049] Furthermore, since the first imaging unit 11 images the inspection object 20 on the conveyance body 1 from the side of the first main surface 1a of the conveyance body 1, an image focused on the first main surface 1a can be obtained as an image for extracting an imaging obstacle. That is, since the second imaging unit 12 performs imaging while focusing on the second main surface 24b of the inspection object 20 on the conveyance body 1, depending on the height of the inspection object 20, the second main surface 1b of the conveyance body 1 may not be accurately focused. However, since the first imaging unit 11 performs imaging while focusing on the first main surface 24a of the inspection object 20 on the conveyance body 1, an image focused on the first main surface 1a of the conveyance body 1, which is at approximately the same distance from the first imaging unit 11, can also be obtained.

[0050] The detailed method for extracting obstacles to be captured will be explained below.

[0051] In order to extract the imaged obstacles, the first imaging unit 11 captures an image of a range wider than the range in which the inspection object 20 is placed on the conveyance body 1. As shown in Fig. 7, the imaged obstacle extractor 4a extracts the imaged obstacles within a range 51 excluding the range in which the inspection object 20 is placed from the image 50 captured by the first imaging unit 11. However, if the inspection object 20 is not captured in the image 50 captured by the first imaging unit 11, it is possible to extract the imaged obstacles within the entire range of the captured image 50.

[0052] That is, when the first imaging unit 11 images only the range where the inspection object 20 is placed on the conveying body 1, if the inspection object 20 is placed on the conveying body 1, it is difficult to determine whether an imaged obstacle in an image captured from the first main surface 1a of the conveying body 1 originates from the conveying body 1 or the inspection object 20. However, by having the first imaging unit 11 image a range wider than the range where the inspection object 20 is placed on the conveying body 1, even when the inspection object 20 is placed on the conveying body 1, it is possible to image an imaged obstacle present within the range 51 excluding the range where the inspection object 20 is placed. Furthermore, the processing unit 4 extracts the imaged obstacle within the range 51 excluding the range where the inspection object 20 is placed from the image captured by the first imaging unit 11, so that it is possible to accurately extract the imaged obstacle included in the conveying body 1.

[0053] In this embodiment, the average brightness of an area 51 excluding the area where the inspection object 20 is placed is calculated from the image 50 captured by the first imaging unit 11 and stored in the storage unit 4e, and an area where the brightness is higher than the calculated average brightness by a predetermined value or more and the area is equal to or larger than a predetermined area is extracted as an imaging obstacle. The predetermined value is, for example, 10, and the predetermined area is, for example, 10 μm 2 Here, the difference between the luminance of the imaged obstacle and the average luminance of the range 51 excluding the range where the inspection object 20 is placed is called the luminance difference of the imaged obstacle.

[0054] The selection unit 4b separates the image capturing obstacles extracted by the image capturing obstacle extraction unit 4a into scratches on the conveyance body 1 and dirt adhering to the conveyance body 1. For example, as shown in FIG. 8, the selection unit 4b selects an elongated image capturing obstacle 30a from among the image capturing obstacles 30 extracted by the image capturing obstacle extraction unit 4a as a scratch. That is, the elongated image capturing obstacle 30a is distinguished from dirt as a scratch caused when the surface of the conveyance body 1 is wiped clean. Specifically, when the elongated direction is defined as a first direction and the direction perpendicular to the first direction is defined as a second direction, the selection unit 4b selects an image capturing obstacle 30a for which the ratio L1 / L2 of the dimension L1 in the first direction to the dimension L2 in the second direction of the image capturing obstacle 30 is 3 or more as a scratch on the conveyance body 1. Furthermore, the sorting unit 4b sorts out the extracted image capturing obstacles 30b that have not been sorted out as scratches as dirt adhering to the conveyance body 1.

[0055] The method for separating extracted imaged obstacles into scratches and dirt is not limited to the above-described method. For example, imaged obstacles that remain even after wiping the surface of the conveying body 1 may be separated as scratches. Alternatively, images may be captured using illumination of multiple colors, and the captured images may be separated by color, such as R images, G images, and B images, to separate scratches and dirt. In other words, if it is known in advance that scratches or dirt are more easily detected in images of specific colors, such as R images, G images, and B images, scratches and dirt can be separated from the images of the specific colors.

[0056] It is also possible to distinguish between scratches and stains based on coordinate positions on the image. For example, as shown in Fig. 9, if scratches tend to occur more easily at the edge positions of the inspection object 20 along the conveyance direction among the positions where the inspection object 20 is placed, an imaged obstacle 30a at that coordinate position is selected as a scratch. In this case, an imaged obstacle 30a that is located at the edge position of the inspection object 20 along the conveyance direction and has an elongated shape may be selected as a scratch.

[0057] Furthermore, when capturing images to extract imaging obstacles, a dedicated lighting unit other than the first lighting unit 31 used for the appearance inspection may be used. That is, if it is known in advance that scratches or stains are easily detected in images captured using lighting of a specific color, capturing images using dedicated lighting makes it possible to accurately distinguish between scratches and stains.

[0058] Furthermore, after cleaning the surface of the transport body 1, a dedicated inspection for screening out scratches may be performed without transporting the inspection object 20. After cleaning the surface of the transport body 1, the transport body 1 is in a state where there is no or almost no dirt, so it becomes possible to accurately screen out the imaged obstacles extracted by the imaged obstacle extraction unit 4a as scratches.

[0059] In this way, the sorting unit 4b sorts the imaged obstacles extracted by the imaged obstacle extraction unit 4a into scratches on the conveying body 1 and dirt adhering to the conveying body 1, thereby making it possible to appropriately clean and replace the conveying body 1. In other words, if the conveying body 1 contains scratches, it needs to be replaced, but if it does not contain scratches, it is possible to deal with the problem by simply cleaning the conveying body 1 without replacing it.

[0060] As described above, the level calculation unit 4c calculates the level of an obstacle to be imaged based on the cumulative value of data on multiple obstacles extracted by the obstacle extraction unit 4a. The level of an obstacle to be imaged means the degree of the obstacle to be imaged, such as the quantity and size of the obstacle. In this embodiment, the level calculation unit 4c calculates the level of the obstacle to be imaged for each of scratches and stains selected by the selection unit 4b.

[0061] Here, multiple imaged obstacles are extracted from multiple images captured by the first imaging unit 11, and the level of the imaged obstacles is calculated. It is preferable to use a large number of images to calculate the level of the imaged obstacles, for example, 100 to 10,000 images, inclusive, such as 1,000 images. This number is, for example, the number of images captured by the first imaging unit 11 while the conveying body 1 makes one revolution in the rotational direction. However, when calculating the level of the imaged obstacles, it is not necessary to use all of the images captured by the first imaging unit 11 while the conveying body 1 makes one revolution in the rotational direction; the captured images may be selected by a method such as periodically sampling the captured images. The level of the imaged obstacles can be calculated accurately by calculating the level of the imaged obstacles based on the cumulative value of the data of multiple imaged obstacles extracted from multiple images captured while the conveying body 1 makes one revolution.

[0062] In this embodiment, the level calculation unit 4c calculates the level of the imaging obstacle based on the brightness of the imaging obstacle included in the image captured by the first imaging unit 11 and the area of ​​the imaging obstacle. Specifically, the level calculation unit 4c calculates the level of the imaging obstacle based on the cumulative value of the product of the brightness difference and the area of ​​each extracted imaging obstacle. For example, if 100 imaging obstacles are extracted from 1000 images, and each imaging obstacle has a brightness difference of 10 and an area of ​​1000 μm 2 In this case, the cumulative value of the product of the brightness difference and area of ​​each obstacle is 10 x 1000 x 100, or 1,000,000. The more obstacles there are and the larger their areas are, the larger this cumulative value becomes. When 1,000 images are used, the cumulative value is, for example, between 1,000 and 1,000,000.

[0063] Since the cumulative value of the product of the brightness difference and the area of ​​each obstacle varies depending on the size of the captured image, it is preferable to normalize the product of the brightness difference and the area of ​​each obstacle by the size of the captured image, more specifically, by the area of ​​the region from which the obstacle is extracted. By performing normalization, it becomes possible to extract the cumulative value of the obstacle per unit area regardless of the image size.

[0064] The level calculation unit 4c calculates the level of the obstacle to be imaged based on the brightness and area of ​​the obstacle to be imaged, so that the level of the obstacle to be imaged can be determined with higher accuracy.

[0065] For example, if a predetermined number of inspection objects 20 undergoing visual inspection are called one lot, the cumulative value may be calculated using a predetermined number of images from the start of the visual inspection of one lot, or after the visual inspection of one lot is completed, the cumulative value may be calculated using a predetermined number of images going back to the end of the visual inspection. Furthermore, since the rotation of the conveying body 1 is controlled by the rotation angle around the central axis X1, the cumulative value may be calculated based on the rotation angle using images captured while the conveying body 1 makes one revolution. Furthermore, multiple images may be acquired and recombined into a single image based on the maximum brightness of the same pixel in each image to create a cumulative value, or the cumulative value may be calculated by adding up the brightness of each pixel in multiple images and dividing the sum by the number of images.

[0066] Next, the level calculation unit 4c calculates an average value by dividing the cumulative value per image based on the number of images used when calculating the level of the obstacle to be imaged, and sets the calculated average value as the level of the obstacle to be imaged. The level of the obstacle to be imaged increases as the amount of obstacle to be imaged, such as scratches or dirt, increases, and as the size of the obstacle to be imaged increases. In the above example, 1,000 images are used, so the level of the obstacle to be imaged is 1,000,000 / 1,000=1,000. This allows the level of the obstacle to be imaged for the entire conveyance 1 to be quantified.

[0067] As described above, the level calculation unit 4c in this embodiment calculates the level of the imaging obstacle for each scratch and stain selected by the selection unit 4b, but it may also be configured to calculate the level of the imaging obstacle including scratches and stains, rather than for each scratch and stain.

[0068] Next, the yield rate determination unit 4d calculates the yield rate of the inspection objects 20 based on the visual inspection. As an example, the yield rate of the inspection objects 20 can be calculated by (1 - number of defectives / number of inspections) × 100. The number of defectives here refers to the number of inspection objects 20 for which at least one of the first end face 23a, the second end face 23b, the first main face 24a, the second main face 24b, the first side face 25a, and the second side face 25b of the inspection object 20 is determined to be "defective" in the visual inspection performed based on the images captured by the first imaging unit 11 to the sixth imaging unit 16. However, the yield rate of any of the first end face 23a, the second end face 23b, the first main face 24a, the second main face 24b, the first side face 25a, and the second side face 25b of the inspection object 20 may be calculated based on an image captured of that surface.

[0069] In this embodiment, the yield rate determination unit 4d determines the yield rate of the inspection object 20 based on the image of the inspection object 20 captured by the first imaging unit 11 and the image of the inspection object 20 captured by the second imaging unit 12, which are stored in the storage unit 4e. Specifically, the yield rate determination unit 4d calculates the yield rate of the first main surface 24a of the inspection object 20 (hereinafter referred to as the bottom surface yield rate) based on the image of the inspection object 20 captured by the first imaging unit 11, and calculates the yield rate of the second main surface 24b of the inspection object 20 (hereinafter referred to as the top surface yield rate) based on the image of the inspection object 20 captured by the second imaging unit 12. The bottom surface yield rate and the top surface yield rate are both examples of the yield rate of the inspection object 20. When an imaging obstacle is present, the bottom surface yield rate tends to be lower than the top surface yield rate because it is affected by the imaging obstacle. It should be noted that the criteria for distinguishing between good and bad products used to determine the top surface yield rate and bottom surface yield rate do not necessarily have to be the same as the criteria used for visual inspection of the object 20 to be inspected, and different criteria may be used to obtain information about the obstacles being imaged.

[0070] The bottom surface pass rate is calculated by (1 - number of bottom surface defects / number of bottom surface inspections) × 100. The number of bottom surface inspections is the number of inspections performed on the first main surface 24a of the inspection objects 20, and the number of bottom surface defects is the number of inspections determined to be defective in the inspection of the first main surface 24a. The top surface pass rate is calculated by (1 - number of top surface defects / number of top surface inspections) × 100. The number of top surface inspections is the number of inspections performed on the second main surface 24b of the inspection objects 20, and the number of top surface defects is the number of inspections determined to be defective in the inspection of the second main surface 24b. For example, if visual inspections are performed on 1,000 inspection objects 20 and the first main surfaces 24a of 20 inspection objects 20 are determined to be defective based on images captured by the first imaging unit 11, the bottom surface pass rate is 98%. Furthermore, if the second main surfaces 24b of 10 of the 1,000 inspection objects 20 are judged to be defective based on the images captured by the second imaging unit 12, the top surface yield rate is 99%.

[0071] The alert unit 5 issues an alert based on the level of the imaged obstacle calculated by the level calculation unit 4c. The level of the imaged obstacle used by the alert unit 5 to determine whether to issue an alert may be the level of scratches on the imaged obstacle, the level of dirt, or the level of the imaged obstacle including scratches and dirt. By having the alert unit 5 issue an alert based on the level of the imaged obstacle calculated by the level calculation unit 4c, it becomes possible, for example, to clean or replace the conveyed body 1 at an appropriate time.

[0072] In this embodiment, the alert unit 5 issues an alert based on the yield rate determined by the yield rate determination unit 4d and the level of the imaged obstacle calculated by the level calculation unit 4c. By having the alert unit 5 issue an alert based on the yield rate determined by the yield rate determination unit 4d and the level of the imaged obstacle calculated by the level calculation unit 4c, the alert can be issued at a more appropriate timing.

[0073] Specifically, the alert unit 5 issues an alert when the level of the imaging obstacle is equal to or greater than a first threshold and the difference between the bottom surface defect rate and the top surface defect rate is equal to or greater than a second threshold. The first threshold is, for example, 1000, and the second threshold is, for example, 3%. In this case, the alert unit 5 issues an alert when the level of the imaging obstacle is equal to or greater than 1000 and the difference between the bottom surface defect rate and the top surface defect rate is equal to or greater than 3%. As described above, when an imaging obstacle is present, the bottom surface pass rate is affected by the imaging obstacle and becomes lower than the top surface pass rate. Therefore, by issuing an alert based on the difference between the bottom surface pass rate and the top surface pass rate and the level of the imaging obstacle, it is possible to issue an alert at a more appropriate time.

[0074] There are no particular restrictions on the method by which the alert unit 5 issues an alert, and it can be done by, for example, displaying an alert on a display or issuing an alert sound.

[0075] However, the conditions under which the alert unit 5 issues an alert are not limited to the above-mentioned conditions. For example, the alert unit 5 may issue an alert when the level of the imaged obstacle calculated by the level calculation unit 4c is equal to or higher than a first threshold and the yield rate of the inspection objects 20 is equal to or lower than a third threshold. As described above, the yield rate of the inspection objects 20 can be calculated by (1 - number of defective items / number of inspections) x 100.

[0076] In addition, the alert unit 5 may issue an alert when the level of the imaged obstacle calculated by the level calculation unit 4c is equal to or higher than a first threshold and the lower surface yield rate of the object 20 to be inspected is equal to or lower than a fourth threshold.

[0077] As a method for determining the level of an obstacle to be imaged from the value of the product of the brightness difference and the area of ​​the obstacle to be imaged, instead of determining the average value per image from the cumulative value described above, the values ​​of the product of the brightness difference and the area of ​​the obstacle to be imaged may be collected from all of the multiple images, and the average, median, maximum, quartile, etc., may be determined as the level of the obstacle to be imaged. In this case, the determination to issue an alert may be made by appropriately combining an index such as the non-defective rate of the inspection object 20 over a certain period of time.

[0078] When the alert unit 5 issues an alert, it is preferable to clean or replace the conveying body 1. That is, if the level of imaging obstacles such as scratches or dirt on the conveying body 1 increases, there is a possibility that the appearance inspection cannot be performed accurately, so when an alert is issued, the conveying body 1 is cleaned or replaced. By cleaning or replacing the conveying body 1, it is possible to perform the subsequent appearance inspection of the inspection object 20 with high accuracy.

[0079] According to the appearance inspection device 100 of this embodiment, the level calculation unit 4c calculates the level of the image-captured obstacle based on the cumulative value of the data of the multiple image-captured obstacles extracted by the image-captured obstacle extraction unit 4a, and can therefore appropriately calculate the level of the image-captured obstacle, such as scratches or dirt on the conveyance body 1. Therefore, depending on the calculated image-captured obstacle level, for example, cleaning or replacement of the conveyance body 1 can be performed at an appropriate timing.

[0080] Furthermore, in conventional devices that cannot clean or replace the conveying body in a timely manner, when an inspection object is placed on a scratched or dirty conveying table, the scratches or dirt can cause the inspection object to lose its posture, potentially resulting in an erroneous visual inspection of the inspection object. However, in the visual inspection device 100 of this embodiment, as described above, cleaning or replacing the conveying body 1 can be performed at an appropriate time depending on the level of the imaged obstacle. This prevents the inspection object 20 from losing its posture due to scratches or dirt, thereby enabling accurate visual inspection of the inspection object 20. The alert unit 5 may also issue an alert based on the level of the imaged obstacle calculated by the level calculation unit 4c and the number and percentage of inspection objects 20 that were not properly inspected due to poor posture. Note that an inspection object 20 that was not properly inspected due to poor posture refers to an inspection object 20 that was not properly inspected by image processing due to poor posture. For example, if the length of the inspection object 20 detected by the sensor is shorter than a reference length due to poor posture, the inspection object 20 is determined to be poorly oriented.

[0081] Furthermore, in the visual inspection device 100 of this embodiment, the conveyance body 1 is transparent in at least the area where the inspection object 20 is placed, and has a shape that allows it to rotate around the central axis X1, and the drive unit 3 is configured to drive the conveyance body 1 in a rotational direction around the central axis X1, thereby conveying the inspection object 20 in the rotational direction. Therefore, since the position of the conveyance body 1 is easy to manage, it is easy to identify the position of the extracted imaging obstacle. For example, if the drive unit 3 is a servo motor, the position of the conveyance body 1 can be managed by an encoder.

[0082] Furthermore, when the conveyance body 1 has a rotatable shape, the conveyance path tends to be shorter than when the conveyance body 1 has other shapes such as a linear shape, and therefore a single image-captured obstacle has a greater impact on the appearance inspection. Therefore, the effect of extracting image-captured obstacles and calculating the level of the extracted image-captured obstacles using the appearance inspection device 100 in this embodiment is significant.

[0083] In addition, the information acquired by the visual inspection device 100 in this embodiment (lot name, product name, inspection date and time, equipment number, light intensity setting value, inspection item setting value, etc.), the pass rate and inspection result statistics for each visual inspection device 100, imaging unit, and inspection item, and the output values ​​for all inspection items of the inspected object 20 may be aggregated in a server, database, etc., and the data may be referenced or compared for each of multiple visual inspection devices 100 to calculate the level of imaging obstacles.

[0084] The visual inspection device 100 in this embodiment can be used for the following purposes (i) to (iv) in addition to extracting the obstacle to be imaged included in the transport body 1 described above.

[0085] (i) Detection of foreign matter adhering to the lens of the imaging unit The appearance inspection device 100 in this embodiment can detect foreign matter adhering to the lenses of the first to sixth imaging units 11 to 16.

[0086] As described above, the imaged obstacle extractor 4a extracts imaged obstacles based on optical characteristic values ​​contained in the image captured by the first image capturing unit 11. When detecting foreign matter adhering to the lens, as described above, the imaged obstacles may be extracted from the captured image within a range excluding the range in which the inspection object 20 is placed, or may be extracted from a range including the range in which the inspection object 20 is placed. Here, after the imaged obstacles are extracted, the area, brightness, and coordinates of the extracted imaged obstacles are recorded.

[0087] When an imaging obstacle having approximately the same area and brightness at approximately the same coordinates is present in multiple images captured by the first imaging unit 11, the processing unit 4 determines that the imaging obstacle is a foreign object attached to the lens of the first imaging unit 11. That is, when a foreign object is attached to the lens of the first imaging unit 11, an imaging obstacle having approximately the same area and brightness is reflected in the multiple captured images at approximately the same coordinate position. Therefore, when an imaging obstacle having approximately the same area and brightness at approximately the same coordinates is present in multiple images, it is possible to determine that the imaging obstacle is a foreign object attached to the lens of the first imaging unit 11. Note that the amount of light of the illumination changes each time imaging is performed, and an imaging obstacle combined with other imaging obstacles may be extracted, so the term "imaging obstacle having approximately the same area and brightness at approximately the same coordinates" is used instead of "imaging obstacle having the same area and brightness at the same coordinates."

[0088] A similar judgment can be made based on images captured by imaging units other than the first imaging unit 11, namely, the second imaging unit 12, the third imaging unit 13, the fourth imaging unit 14, the fifth imaging unit 15, and the sixth imaging unit 16, thereby making it possible to detect foreign matter attached to each imaging unit.

[0089] When a foreign object adhering to the lens of the imaging unit is detected by the above-described method, the alert unit 5 may issue an alert. Issuing an alert by the alert unit 5 can prompt the user to clean or replace the lens, making it possible to clean or replace the lens at an appropriate time. Furthermore, by detecting a foreign object adhering to the lens of the imaging unit, it is possible to suppress erroneous determinations in the appearance inspection of the inspection object 20 caused by a foreign object adhering to the lens of the imaging unit. Furthermore, it becomes possible to distinguish whether an obstacle to imaging on the image is caused by the lens of the imaging unit or by the conveyance body 1.

[0090] (ii) Detecting the relative positional deviation between the imaging unit and the lighting unit The visual inspection apparatus 100 of this embodiment can detect the relative positional deviation between the optical axis of the imaging unit and the optical axis of the illumination unit.

[0091] When the first illumination unit 31 emits illumination light of multiple colors, the optical axis of the first imaging unit 11 and the optical axis of the first illumination unit 31 need to be aligned, but they may not be aligned due to reasons such as adjustment errors. When the optical axes of the first imaging unit 11 and the first illumination unit 31 are aligned, the luminance distribution of the captured image will be symmetrical in the vertical and horizontal directions relative to the field of view, but when the optical axes are not aligned, the luminance distribution of the image will be asymmetric.

[0092] FIG. 10(a) is a diagram schematically showing the luminance distributions of the R image, G image, and B image when the optical axis of the first imaging unit 11 and the optical axis of the first illumination unit 31 are aligned. FIG. 10(b) is a diagram schematically showing the luminance distributions of the R image, G image, and B image when the optical axis of the green illumination light of the first illumination unit 31 is misaligned. FIG. 10(c) is a diagram schematically showing the luminance distributions of the R image, G image, and B image when the optical axis of the first imaging unit 11 is misaligned. Note that FIG. 10 shows a state in which the positional relationship between the first imaging unit 11 and the inspection object 20 is upside down compared to the positional relationship shown in FIG. 3.

[0093] As shown in Figure 10(a), when the optical axis of the first imaging unit 11 and the optical axis of the first illumination unit 31 are aligned, the luminance distributions of the R image, G image, and B image are symmetrical left and right, and although not shown, the luminance distributions of the R image, G image, and B image are symmetrical up and down.

[0094] In contrast, when the optical axis of the green illumination light from the first illumination unit 31 is misaligned, the luminance distribution of the G image becomes asymmetrical as shown in Fig. 10(b). Also, when the optical axis of the first imaging unit 11 is misaligned, the luminance distributions of the R, G, and B images all become asymmetrical as shown in Fig. 10(c).

[0095] In this way, if the optical axis of only one of the multiple-color illumination lights is misaligned, only the luminance distribution of that color image will be asymmetric. In contrast, if the optical axis of the first image capture unit 11 is misaligned, the luminance distribution of all color images will be asymmetric. Therefore, based on the luminance distribution of the color images, it is possible to distinguish between a case where the optical axis of the illumination light of a specific color is misaligned and a case where the optical axis of the first image capture unit 11 is misaligned.

[0096] The above-described relative positional deviations of the optical axes can be detected similarly between other image capturing units and other illumination units. That is, by using a similar method, it is possible to detect the positional deviation between the optical axis of the second image capturing unit 12 and the optical axis of the second illumination unit 32, the positional deviation between the optical axis of the third image capturing unit 13 and the optical axis of the third illumination unit 33, the positional deviation between the optical axis of the fourth image capturing unit 14 and the optical axis of the fourth illumination unit 34, the positional deviation between the optical axis of the fifth image capturing unit 15 and the optical axis of the fifth illumination unit 35, and the positional deviation between the optical axis of the sixth image capturing unit 16 and the optical axis of the sixth illumination unit 36.

[0097] (iii) Management of the amount of light emitted by the lighting unit The visual inspection apparatus 100 in this embodiment can manage the light intensities of the first illumination unit 31 to the sixth illumination unit 36. For example, it is possible to calculate the average luminance in the background region of the image captured by the first imaging unit 11, and manage the light intensity of the illumination light of the first illumination unit 31 based on the calculated average luminance. The background region of the image is the entire region of the image excluding the region in which the inspection object 20 is captured.

[0098] Specifically, the average luminance of the background region of the captured image is calculated and recorded. The transition of the average luminance of the background region of the image is observed for each set of images, each set of time interval, or each batch, and it is confirmed whether the newly calculated average luminance of the background region is within a predetermined range. When the light intensity of the first illumination unit 31 is appropriate, the average luminance of the background region of the image falls within the predetermined range. However, when the light intensity is low or high, the average luminance of the background region of the image does not fall within the predetermined range. In such a case, it is determined that the light intensity of the first illumination unit 31 is inappropriate. This determination can be made by the processing unit 4. When it is determined that the light intensity of the first illumination unit 31 is inappropriate, for example, an alert may be issued by the alert unit 5, or the light intensity of the first illumination unit 31 may be controlled to achieve an appropriate light intensity.

[0099] The above-described management of the amount of illumination light can be performed in the same manner for each of the second illumination unit 32 to the sixth illumination unit .

[0100] If the conveyance body 1 includes an imaging obstacle, the imaging obstacle also moves in the image captured by the first imaging unit 11 as the conveyance body 1 is rotated. For this reason, the imaging obstacle may cause a change in the average brightness of the background area of ​​the image, but by understanding the correlation between the level of the imaging obstacle and the average brightness of the background area, it is possible to distinguish between a change in the average brightness of the background area caused by a change in the amount of illumination light and a change in the average brightness of the background area caused by the imaging obstacle.

[0101] (iv) Detection of lighting deterioration The visual inspection device 100 in this embodiment can detect deterioration of the first to sixth illumination units 31 to .

[0102] When the first illumination unit 31 includes multiple LEDs, the degree of deterioration varies depending on the LED. For this reason, the brightness distribution in the background area of ​​the captured image is created as a heat map, and if the brightness in a certain area is reduced, it is determined that the LED corresponding to that area is deteriorated. This determination can be made by the processing unit 4. If it is determined that an LED is deteriorated, an alert can be issued by the alert unit 5, for example, to prompt replacement of the LED. This makes it easy to detect and replace deteriorated LEDs.

[0103] Furthermore, if a specific LED deteriorates, the brightness of the same area will decrease each time. Therefore, by recording the coordinates of the location where the brightness has decreased, it is possible to reduce erroneous judgments in visual inspections caused by LED deterioration.

[0104] The above-described detection of deterioration in illumination can be performed for the second illumination unit 32 to the sixth illumination unit 36 ​​in the same manner.

[0105] The present invention is not limited to the above-described embodiment, and various applications and modifications are possible within the scope of the present invention. For example, in the above-described embodiment, the imaged obstacle extraction unit 4a is described as extracting an imaged obstacle based on optical characteristic values ​​contained in the image captured by the first image capturing unit 11. However, the optical characteristic values ​​are not limited to those contained in the image captured by the first image capturing unit 11. For example, an optical sensor that emits a light beam toward the conveyance body 1 may be provided, and the imaged obstacle may be extracted based on optical characteristic values ​​contained in the light beam emitted from the optical sensor and reflected by the conveyance body 1.

[0106] In the above-described embodiment, the conveyance body 1 has been described as being transparent in at least the area where the inspection object 20 is placed, but the area where the inspection object 20 is placed does not have to be transparent. In this case, the first imaging unit 11 may image the inspection object 20 on the conveyance body 1 using imaging light having a wavelength that passes through the conveyance body 1, such as infrared light.

[0107] In the above-described embodiment, the conveying body 1 has been described as having a transparent, rotatable circular table-like shape, but it may also have a foldable film-like shape or a continuous, endless shape.

[0108] The appearance inspection device in this application is as follows. <1> A visual inspection device for performing a visual inspection of an object to be inspected, a carrier having a first main surface and a second main surface opposite to the first main surface; a supply unit that supplies the inspection object onto the second main surface of the transport body; a driving unit that drives the conveying body to convey the inspection object on the conveying body; a first imaging unit capable of imaging the inspection object on the conveyance body using imaging light having a wavelength that passes through the conveyance body in order to perform a visual inspection of the inspection object; an image capturing obstacle extracting unit that extracts an image capturing obstacle included in an image captured by the first image capturing unit based on an optical characteristic value related to the image capturing obstacle included in the transport body; a level calculation unit that calculates a level of the obstacle extracted by the obstacle extraction unit; and Equipped with The visual inspection device is characterized in that the level calculation unit calculates the level of the obstacle to be imaged based on a cumulative value of data on the plurality of obstacles to be imaged extracted by the obstacle extraction unit. <2> The imaged obstacle extraction unit extracts the imaged obstacle based on the optical characteristic value included in the image captured by the first image capturing unit. <1> The visual inspection apparatus according to claim 1. <3> The optical characteristic value is brightness. <1> or <2> The visual inspection apparatus according to claim 1. <4> The first imaging unit is characterized in that it images the inspection object on the transport body from the first main surface side. <1> ~ <3> 10. The visual inspection apparatus according to claim 9, wherein <5> The first imaging unit is characterized in that it images an area wider than the area in which the inspection object is placed on the conveyance body. <4> The visual inspection apparatus according to claim 1. <6> The imaged obstacle extraction unit extracts the imaged obstacle from the image captured by the first image capturing unit within a range excluding the range in which the inspection object is placed. <5> The visual inspection apparatus according to claim 1. <7> the conveying body is transparent at least in an area where the inspection object is placed, and has a shape that can rotate around a central axis perpendicular to the first main surface and the second main surface, The driving unit drives the transport body in a rotational direction around the central axis, thereby transporting the inspection object on the transport body in the rotational direction. <1> ~ <6> 10. The visual inspection apparatus according to claim 9, wherein <8> The level calculation unit calculates the level of the imaged obstacle based on a cumulative value of data of the plurality of imaged obstacles extracted by the imaged obstacle extraction unit in a plurality of images captured by the first image capturing unit while the conveyor makes one revolution in the rotation direction. <7> The visual inspection apparatus according to claim 1. <9> The level calculation unit calculates the level of the obstacle to be imaged based on the brightness of the obstacle to be imaged included in the image captured by the first image capturing unit and the area of ​​the obstacle to be imaged. <1> ~ <8> 10. The visual inspection apparatus according to claim 9, wherein <10> The present invention is characterized in that the present invention further comprises an alert unit that issues an alert based on the level of the obstacle to be imaged calculated by the level calculation unit. <1> ~ <9> 10. The visual inspection apparatus according to claim 9, wherein <11> The present invention is characterized in that the image capturing device further comprises a sorting unit that sorts the obstacles extracted by the image capturing obstacle extraction unit into scratches on the transport body and dirt attached to the transport body. <1> ~ <10> 10. The visual inspection apparatus according to claim 9, wherein <12> The inspection apparatus further includes a second imaging unit that images the inspection object on the transport body from the second main surface side. <1> ~ <9> 10. The visual inspection apparatus according to claim 9, wherein <13> The apparatus further comprises a product quality determining unit for determining the product quality of the inspection object. <12> The visual inspection apparatus according to claim 1. <14> The non-defective product rate determining unit determines the non-defective product rate of the inspection object based on the image of the inspection object captured by the first imaging unit and the image of the inspection object captured by the second imaging unit. <13> The visual inspection apparatus according to claim 1. <15> The image capturing device further includes an alert unit that issues an alert based on the level of the obstacle calculated by the level calculation unit, The alert unit issues the alert based on the yield rate determined by the yield rate determination unit and the level of the obstacle to be imaged calculated by the level calculation unit. <13> or <14> The visual inspection apparatus according to claim 1. [Explanation of symbols]

[0109] 1. Carrier 2 Supply section 3 Drive unit 4 Processing section 4a Imaged obstacle extraction unit 4b Sorting section 4c Level calculation section 4d Good product rate judgment section 4e storage section 5 Alert section 6 Alignment section 7 Discharge section 11 First imaging unit 12 Second imaging unit 13 Third imaging unit 14 Fourth imaging unit 15 Fifth imaging unit 16 Sixth imaging unit 20 Inspection object 20X Multilayer Ceramic Capacitors 30 Imaging Obstacles 30a Imaging obstacles classified as scratches 30b Imaging obstacles classified as dirt 31 First Lighting Section 32 Second Lighting Section 33 Third Lighting Section 34 Fourth Lighting Section 35 Fifth Lighting Section 36 Sixth Lighting Section 41 First Reflector 42 Second Reflector 43 Third Reflector 50 images 51 The area of ​​the image excluding the area where the object to be inspected is placed 71 Air outlet 100 Visual inspection equipment

Claims

1. An appearance inspection device for performing an appearance inspection of an inspection object, a carrier having a first main surface and a second main surface opposite to the first main surface; a supply unit that supplies the inspection object onto the second main surface of the transport body; a driving unit that drives the conveying body to convey the inspection object on the conveying body; a first imaging unit capable of imaging the inspection object on the conveyance body using imaging light having a wavelength that passes through the conveyance body in order to perform a visual inspection of the inspection object; an image capturing obstacle extracting unit that extracts an image capturing obstacle included in an image captured by the first image capturing unit based on an optical characteristic value related to the image capturing obstacle included in the transport body; a level calculation unit that calculates a level of the obstacle extracted by the obstacle extraction unit; and Equipped with The visual inspection device is characterized in that the level calculation unit calculates the level of the obstacle to be imaged based on a cumulative value of data on the plurality of obstacles to be imaged extracted by the obstacle extraction unit.

2. 2. The visual inspection device according to claim 1, wherein the imaged obstacle extracting section extracts the imaged obstacle based on the optical characteristic value included in the image captured by the first image capturing section.

3. 3. The visual inspection apparatus according to claim 2, wherein the optical characteristic value is luminance.

4. 2. The visual inspection apparatus according to claim 1, wherein the first image capturing unit captures an image of the inspection object on the transport body from the first main surface side.

5. 5. The visual inspection apparatus according to claim 4, wherein the first image capturing unit captures an image of a range wider than a range in which the inspection object is placed on the conveyance body.

6. 6. The visual inspection device according to claim 5, wherein the imaged obstacle extraction unit extracts the imaged obstacle from the image captured by the first imaging unit within a range excluding a range in which the inspection object is placed.

7. the transport body has a transparent area at least where the inspection object is placed, and has a shape that is rotatable around a central axis perpendicular to the first principal surface and the second principal surface; 2. The visual inspection apparatus according to claim 1, wherein the driving unit drives the transport body in a rotational direction about the central axis, thereby transporting the inspection object on the transport body in the rotational direction.

8. The visual inspection device described in claim 7, characterized in that the level calculation unit calculates the level of the imaged obstacle based on a cumulative value of data of the multiple imaged obstacles extracted by the imaged obstacle extraction unit in multiple images captured by the first imaging unit while the conveying body makes one rotation in the rotation direction.

9. 2. The visual inspection device according to claim 1, wherein the level calculation unit calculates the level of the imaging obstacle based on the brightness of the imaging obstacle included in the image captured by the first imaging unit and the area of ​​the imaging obstacle.

10. 2. The visual inspection device according to claim 1, further comprising an alert unit that issues an alert based on the level of the obstacle to be imaged calculated by the level calculation unit.

11. The visual inspection device according to claim 1, further comprising a sorting unit that sorts the imaged obstacles extracted by the imaged obstacle extraction unit into scratches on the transported body and dirt attached to the transported body.

12. 2. The visual inspection apparatus according to claim 1, further comprising a second image capturing unit configured to capture an image of the inspection object on the transport body from the second main surface side.

13. The visual inspection apparatus according to claim 12, further comprising a yield rate determining unit for determining a yield rate of the inspection objects.

14. 14. The visual inspection apparatus according to claim 13, wherein the yield rate determination unit determines the yield rate of the object to be inspected based on an image of the object to be inspected captured by the first imaging unit and an image of the object to be inspected captured by the second imaging unit.

15. an alert unit that issues an alert based on the level of the obstacle to be imaged calculated by the level calculation unit; 15. The visual inspection device according to claim 13, wherein the alert unit issues the alert based on the yield rate determined by the yield rate determination unit and the level of the imaged obstacle calculated by the level calculation unit.

Images