JP2008026149A - Visual examination device - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide a visual examination device capable of accurately detecting the flaw formed in a curved surface, especially even the flaw formed in the curved surface in the vicinity of a ridge line comprising a curved line. <P>SOLUTION: The visual examination device 1 is equipped with an illumination means 4, an imaging means 5 and an image processing device 6. The illumination means 4 is constituted so as to irradiate the part formed of the curved surface in the surface of an inspection target 3 with light at every predetermined region with respect to the whole of an inspection target region of the curved surface. The imaging means 5 takes the image of the curved surface so that the normal part of the curved surface becomes a bright part to appear and an imaging region is set to a range wherein the whole of the inspection target region of the curved surface is housed. The image processing device 6 is equipped with an image processing part for forming a synthetic image by superposing a plurality of the photographed images taken by the imaging means 5 one upon another so that a bright part continuously appears to synthesize one image and a judge part for comparing the bright part region of the synthetic image with a preset reference bright part region to judge the presence of the flaw formed on the surface of an inspection target. <P>COPYRIGHT: (C)2008,JPO&INPIT

Description

  The present invention relates to an appearance inspection apparatus for detecting a defect generated in a portion formed by a curved surface on the surface of an object to be inspected. In particular, the present invention relates to an appearance inspection apparatus that detects, by image processing, defects generated on a curved surface near an outer peripheral edge formed by two continuous surfaces on the surface of an object to be inspected, such as a throw-away tip used as a cutting tool.

  As a method for inspecting a shape defect of a throw-away tip used as a cutting tool, a visual inspection using a magnifying glass has been generally performed. The throw-away tip is a cutting tool, and if there is a chip in the cutting edge, it will lead to problems such as reduced cutting performance or shortened life. Therefore, in order to guarantee the quality of the throw-away chip, an inspection for detecting defects such as a chip is always necessary.

  However, when performing a visual inspection for humans, it is easy to miss and misjudgment from fatigue due to tension, and rely on sensual sensations. The detection capability cannot be guaranteed over the whole number.

  In addition, in order to find minute defects generated near the ridgeline at the tip of the blade edge, skill is required, which imposes a burden on the operator and cannot perform efficient inspection.

  In addition, an apparatus for automatically inspecting a surface defect generated on an outer peripheral ridge line of an object has been proposed (see, for example, Patent Document 1).

  The appearance inspection apparatus described in Patent Document 1 uses a displacement meter to measure the displacement on the scanning line with a line that enters a minute amount inside the outer peripheral ridge line along the outer peripheral ridge line of the object (object). I am trying to measure.

  In the appearance inspection apparatus of Patent Document 1, the shape defect of the outer peripheral ridge line of the object to be inspected is detected and distinguished from the foreign matter and dirt based on the amount of displacement.

JP 09-218030 A

  In the appearance inspection apparatus described in Patent Document 1, a line entering a minute amount with respect to the outer peripheral ridge line of the object to be inspected is used as a scanning line, and the amount of displacement on this scanning line is detected by a displacement meter, whereby the object to be inspected is detected. The shape defect is detected. Therefore, if a shape defect occurs in a portion that is out of the displacement measurement region with the scanning line as the center line, that is, a portion that is inward of the scanning line, even if the defect occurs near the outer peripheral edge line This defect cannot be detected.

  Also, image processing for binarizing the captured image so that the inspection target portion is irradiated with light and the image of the object to be inspected is captured by the imaging means, and the normal portion becomes a bright portion and the defective portion becomes a dark portion. It is also conceivable to go and detect defects near the ridgeline.

  By the way, although the tip of the throw-away tip is pointed, the tip portion thereof is formed by a curved surface, so that the ridge line formed by this curved surface also draws a curve. In particular, the negative land, which is a curved surface, is oriented in all directions, so that the entire curved surface is irradiated with light so that the light is reflected in the same direction, and the entire curved surface is illuminated at once, in the vicinity of the ridgeline. It is conceivable to detect defects generated on the curved surface at once. In order to shine the entire curved surface of the cutting edge in this way, imaging is performed in a state where light is irradiated from all directions of 360 ° using ring illumination or the like.

  However, since defects due to shape defects occur three-dimensionally in an arbitrary direction, even if a defect occurs on the ridgeline, light entering from an arbitrary angle in the circumferential direction of the ring illumination hits a part of the defect. The reflected light may be input to the imaging means. As described above, when the light reflected by the defect is imaged by the imaging unit, it becomes difficult to detect the defect by image processing, and the defect cannot be detected accurately.

  Therefore, the present invention has been made in view of the above problems, and an object thereof is to provide an appearance inspection apparatus that can accurately detect defects generated on a curved surface, particularly defects generated on a curved surface in the vicinity of a curved ridgeline. To do.

  The appearance inspection apparatus of the present invention includes illumination means, imaging means, and image processing means. The illumination means irradiates a portion formed by a curved surface on the surface of the object to be inspected with respect to the entire inspection target area of the curved surface for each predetermined area. The imaging means receives light reflected upon the surface of the object to be inspected, and the imaging area is within a range in which the entire inspection target area is curved. The image processing means performs image processing on a plurality of picked-up images with different irradiation areas picked up by the image pick-up means, and detects the defect by determining the presence or absence of a defect generated on the surface of the inspection object based on the plurality of picked-up images. To do.

  The object to be inspected is a non-black three-dimensional object having a curved surface on its surface, such as a throw-away tip used for a cutting tool.

  It is preferable that the illumination means can perform illumination from multiple directions in three dimensions. In addition, it is preferable that switching can be performed so that light is emitted for each predetermined irradiation region. In this case, it is preferable that the illumination means irradiates light for each predetermined area sequentially so as to determine an irradiation area along the curved surface and to be continuous along the curved surface.

  In order to irradiate light for each predetermined irradiation region, for example, a ring illumination device or a dome illumination device can be used. The illumination means is preferably arranged coaxially with the imaging means above the sample stage.

  In the case of using a ring illumination device, two or more ring illumination devices having different diameters may be arranged in the vertical direction on the sample stage so as to be illuminated in a three-dimensional surface emission state. In this case, it is possible to irradiate light for each predetermined irradiation region by controlling these ring illumination devices individually and for each predetermined region.

  In addition, an illuminating means can be configured by arranging a large number of LEDs so as to obtain a three-dimensional surface emission. In this case, it is preferable to use a dome illumination device using a large number of LEDs. In the case of this LED dome illumination device, each LED can be lit in every direction and region in the vertical direction, in the circumferential direction, or in the form of dots.

  When the illumination means is an LED dome illumination device, there is no need to physically move the illumination device three-dimensionally or to physically move the object to be inspected three-dimensionally to an arbitrary angle. In addition, since the irradiation area can be changed simply by switching on / off the LED, the processing time for changing the irradiation area can be shortened.

  Examples of the imaging means include a two-dimensional camera such as a CCD camera that receives light reflected by the surface of the object to be inspected. The imaging means obtains a two-dimensional image using the visual field size as an imaging region. This imaging region is a range in which the entire inspection target region on the curved surface of the object to be inspected fits. This two-dimensional image is sent to the image processing means. It is preferable that the imaging unit captures an image so that a normal portion of the curved surface appears as a bright portion.

  By the way, when irradiating light on the entire inspection region of the object to be inspected, the light reflected by the defective portion may be input to the imaging means, and the defect may appear as a bright portion.

  Therefore, in the present embodiment, the entire inspection region is divided into a plurality of regions, the irradiation region is determined, and the inspected object is imaged for each irradiation region, so that the captured image has a defect in any irradiation region The defect appears clearly as a dark part. Thus, by dividing the irradiation area into a plurality of areas, it is possible to increase the directivity of illumination and illuminate from one direction, so that it is possible to reduce the reflection of useless light upon hitting the defect, and there is a defect in each captured image. It appears clearly as a dark part.

  The image processing unit includes an image processing unit that performs image processing on a plurality of captured images with different irradiation areas captured by the imaging unit by binarization processing and the like, and a defect that has occurred on the surface of the inspection object based on the plurality of captured images It is set as the structure provided with the determination part which determines the presence or absence of. The image processing means is constituted by a computer, for example.

  The image processing unit of the image processing unit superimposes a plurality of captured images with different irradiation areas captured by the imaging unit so that a bright portion that is a normal portion of the curved surface appears continuously and combines them into one image. Create a composite image. In this composite image, the entire inspection area of the object to be inspected is represented.

  As a method of creating a composite image, a method of performing OR operation on a plurality of obtained images can be mentioned. In the OR operation, in the image frame of each captured image, when all of the positions in the XY direction do not shine (parts below a predetermined brightness), the positions in the composite image are not lit. When there is even one portion that shines at the same position, an operation is performed to express the shining state in the image at that position.

  Then, the image processing unit binarizes this composite image. By the binarization process, the normal part is represented by the bright part and the other part is represented by the dark part. Further, the image data of the inspection object having no defect is stored in advance in the image processing means as reference data, and the reference data is binarized. The bright portion in the reference data is a normal portion of the curved surface.

  When determining the presence or absence of a defect from the composite image, the determination unit compares the bright area of the composite image with the reference bright area of the reference data set in advance, and the surface of the object to be inspected. It is determined whether or not there is a defect that occurred.

  Specifically, the determination unit compares the light area of the binarized composite image with the reference light area of the reference data to obtain a difference, and this difference (dark area) is a predetermined value. If it is larger, it is determined that this dark part is a defect, and if it is less than a predetermined value, it is determined that it is not a defect.

  In this way, by superimposing a plurality of images and combining them into one image, a dark part that becomes a defect appears clearly in the composite image, and the defective part can be reliably detected. The determination can be made reliably.

  In addition, the illumination unit sequentially irradiates light in predetermined areas along the curved surface, and the imaging unit captures an image so that a normal part of the curved surface appears as a bright part. The processing unit performs image processing on the captured image captured by the imaging unit to recognize the position of the bright part, and the change in the position of the bright part differs from the reference position change according to the imaging order. Sometimes, a determination unit for determining a defect may be provided.

  The image processing unit binarizes each captured image and then obtains the position of the bright portion represented in the image data. For example, the position of the bright part is the position of the center of gravity. When there are two bright parts in one image data, the position of each bright part is obtained.

  The determination unit calculates how the position of the bright part of each image data is changed in the order of imaging, and determines whether the position change is changing regularly or irregularly. judge. In the case of regular changes, it is determined as normal, and in the case of irregular changes, it is determined that there is a defect.

  In this way, by changing the illumination direction continuously, by imaging the object to be inspected, the transition of the position of the bright part (e.g., the center of gravity position) that is the shining part of the object is obtained. Can do. Then, it can be determined that there is no defect if the transition of the position moves in order, and that there is no defect, and that the defect is present if the order is broken.

  Of course, in the appearance inspection apparatus of the present invention, the defect can be detected by imaging so that the defective portion becomes a dark portion as described above, or conversely, only the defective portion can be illuminated to detect the defect.

  In the appearance inspection apparatus of the present invention, it is not necessary to limit the defect occurrence site to a ridge line such as a throw-away tip, and for example, it is possible to detect a shape defect generated on the side surface or negative land portion of the throw-away tip.

  The appearance inspection apparatus according to the present invention captures a plurality of captured images by capturing the inspected object while changing the direction of light irradiating the inspected object to a plurality of directions in a certain imaging region. Since the presence / absence of a defect is determined based on the image, it is possible to automatically and reliably detect the defect generated on the curved surface of the inspection object. As a result, since it is possible to inspect defects in a short time while reducing labor costs, it is possible to stabilize the detection level and provide products with stable quality.

  Embodiments of an appearance inspection apparatus according to the present invention will be described below with reference to the drawings. The appearance inspection apparatus according to the present embodiment is an apparatus that inspects a defect that occurs in the vicinity of a ridge line in an inspection object. In this embodiment, the object to be inspected is a throw-away tip (work) used for a cutting tool.

  As shown in the schematic configuration diagram of FIG. 1, the appearance inspection apparatus 1 inspects the presence or absence of defects in the vicinity of the ridgeline of the negative land portion at the cutting edge of the workpiece 2 with the workpiece 2 placed on the sample table 3. It has become.

  The appearance inspection apparatus 1 includes a dome illumination device 4 serving as illumination means, a CCD camera (imaging means) 5 attached to the top of the dome illumination device 4 so that the optical axis is coaxial with the dome illumination device 4, and An image processing device (image processing means) 6 and a control device 7 are provided. The CCD camera 5 and the dome illumination device 4 are arranged above the sample table 3.

  The dome illumination device 4 is configured by arranging LEDs uniformly in a dome shape. In the present embodiment, the dome illumination device 4 in which 312 LEDs are arranged is used. In this embodiment, these LEDs are divided into 52 blocks (× 6 LEDs), and a lighting / extinguishing circuit is provided in each block, so that illumination from 52 directions can be switched.

  As shown in FIG. 1, the CCD camera 5 is provided so as to be integrated with the dome illumination device 4, and is installed at the center of the dome of the dome illumination device 4. The CCD camera 5 images the work while irradiating the work with the dome illumination device 4.

  The image picked up by the CCD camera 5 is a two-dimensional image with the field of view of the camera as the image pickup area. This imaging region is a range in which the entire inspection target region (tip portion of the workpiece) in the negative land portion of the workpiece 2 is accommodated. The CCD camera 5 captures an image so that the normal part of the negative land part shines. This two-dimensional image is sent to the image processing device 6.

  The image captured by the CCD camera 5 is moved to the work 2 for each predetermined irradiation area by moving the irradiation area little by little along the ridge line at the tip of the cutting edge of the work 2 using the dome illumination device 4. Take an image while irradiating light. As shown in (a) to (e) of FIG. 2, each captured image is captured in a state in which a bright portion appears in a chopped state while being in the same imaging region. In this embodiment, the directivity of illumination is improved by determining an irradiation area and illuminating from one direction. As a result, useless light does not hit and reflect the defect, and the defect appears clearly as a dark part in each captured image.

  The image processing device 6 is configured by a computer and includes a monitor (not shown). The image processing apparatus 6 receives image data captured by the CCD camera 5 and performs image processing on the input image.

  The image processing device 6 includes a storage unit that stores data of an image captured by the CCD camera 5, an image processing unit that performs binarization processing on the captured image, and binarization processing by the image processing unit. A determination unit that compares the captured image data with reference data to obtain a difference, and determines the presence or absence of a defect based on the magnitude of the difference.

  Further, the image processing unit superimposes a plurality of captured images captured by the CCD camera 5 with different irradiation areas so that a bright portion which is a normal portion of the negative land portion appears continuously and combines them into one image. To create a composite image. That is, the captured images shown in FIGS. 2A to 2E are combined to create a combined image shown in FIG. A composite image is created by performing an OR operation on a plurality of images.

  Then, the image processing unit binarizes this composite image. By the binarization process, a normal part of the negative land part is represented by a bright part (for example, a white part), and the other part is represented by a dark part (a black part). Further, the image data of the workpiece 2 having no defect is stored in advance in the storage unit as reference data, and the reference data is binarized. The bright portion in the reference data is a normal negative land portion.

  In the present embodiment, the determination unit determines whether the workpiece 2 has a defect by comparing the reference data with the image data of the composite image. The determination unit compares the lighted area of the binarized composite image with the reference bright part area of the reference data to obtain a difference, and if this difference (dark part) is greater than a predetermined value, a defect is detected. It is determined that there is a defect, and it is determined that there is no defect when it is equal to or less than a predetermined value.

  The control device 7 is configured by a computer, and performs imaging timing control of the CCD camera 5 and illumination drive control for each irradiation region of the dome illumination device 4.

  Next, a method for inspecting the workpiece 2 for defects will be described. First, the workpiece 2 is set on the sample stage 3 and the ridge line portion at the tip of the workpiece 2 is imaged by the CCD camera 5. As shown in FIGS. 2A to 2E, each image picked up by the CCD camera 5 is in a state where a part of the negative land portion is illuminated. In each captured image of FIG. 2, the negative land portion is imaged in a chopped state by irradiating light from the dome illumination device 4 for each predetermined region along the negative land portion. In each captured image, when there is a defect within the range of each illuminated part, as shown in FIGS. 2D and 2E, a part that does not shine clearly appears.

  Then, these images are stored in the storage unit of the image processing device 6, and the image processing unit combines these captured images to create a composite image as shown in FIG. In the composite image shown in FIG. 3, a non-lighted portion appears on the right side of the negative land portion. Next, the composite image is binarized, and the binarized composite image is stored in the storage unit.

  The determination unit of the image processing apparatus 6 reads the reference data set in advance from the storage unit and the composite image data, and the binarized reference data and image so that the position of the bright part serving as the negative land part matches. The difference is obtained by overlaying and comparing the data.

  When this difference is larger than a predetermined value, it is determined that there is a dark part that becomes a defect, and when the difference is equal to or smaller than a predetermined value, it is determined that there is no defect, and the defect inspection ends. In the composite image shown in FIG. 3, since the dark portion exists on the right side of the negative land portion (bright portion), the determination unit determines that the work 2 has a defect.

  In addition, the appearance inspection apparatus 1 according to the present embodiment does not synthesize a plurality of images as in the above embodiment, but after capturing a plurality of captured images in the same manner as in the above embodiment, Thus, according to the imaging order, a change in the position of the bright part in the preceding and following captured images can be obtained, and the presence or absence of a defect can be inspected in the state of this change.

  In this case, the calculation of the position change of the bright part is performed by the image processing device 6. The image processing unit of the image processing device 6 performs processing for recognizing the position of the bright portion in each captured image, and the determination unit changes the position of the bright portion different from the reference position change according to the imaging order. It is determined as a defect when

More specifically, the dome illumination device 4 is used to capture an image while moving the irradiation area little by little along the ridgeline at the tip of the blade edge of the workpiece 2. The shining portion (predetermined area of the negative land portion) moves little by little like each image shown in FIG. The positions of the shining parts (centers of gravity P ₁ , P ₂₁ , P ₂₂ , P ₃ ) are recognized by the image processing unit as shown in FIGS. When there is no chip in the negative land portion, the position of the shining portion moves regularly.

However, if there is a chip in the negative land portion, as shown in FIG. 4, the illumination region of the negative land portion not only shines when illuminated at an arbitrary angle, but is also outside the range of the negative land irradiation region. The chipped portion in FIG. 5 also shines brightly (state shown in FIG. 5B). Since the normal part and the missing part are thus lit, the position of the missing part (center of gravity position P ₂₂ ) is also recognized by image processing. If there is a chip, the change of the position of the shining portion becomes irregular, and at this time, it is determined that there is a chip.

  Hereinafter, a method for detecting a defect by image processing by shining a chipped portion will be described with reference to the vector diagram of FIG. 5 and the flowchart of FIG.

  The dome lighting device 4 divides a large number of LEDs arranged in a dome shape into N blocks. At this time, the first block, the second block, the second block, the third block,..., The (N−1) th block and the Nth block are adjacent blocks.

  First, the work 2 is irradiated with illumination from a certain direction by turning on the LED of the first block (i = 1) (step S1). The image is picked up by the CCD camera 5 (step S2), and the image processing unit of the image processing device 6 binarizes with a threshold value (th) to extract a bright part (white part on the image processing). (Step S3).

Next, the barycentric coordinates of the bright part are calculated by image processing (step S4). Thereby, it is possible to recognize the position P ₁ (X ₁ , Y ₁ ) of the bright part.

Next, the process proceeds from the first block to the next second block (i = 2) (step S5). It is determined whether or not this block is an N + 1 block (step S6). If it is not an N + 1 block, the process returns to step S1, the first block is turned off, the second block is turned on, and the same as the first block. Is performed (steps S2 to S4), and the bright portion position P ₂ (X ₂ , Y ₂ ) is recognized.

When there are a plurality of bright portions in one image data, a plurality of positions such as P ₂₁ (X ₂₁ , Y ₂₁ ) and P ₂₂ (X ₂₂ , Y ₂₂ ) are recognized. In this way, each position from P ₁ (X ₁ , Y ₁ ) to P _N (X _N , Y _N ) is obtained while switching the illumination from one block to the last N blocks.

When imaging and position recognition have been completed up to the last N blocks, a vector of each position is calculated (step S7). The vectors are calculated by calculating a vector L ₂ from P ₁ to P ₂ , a vector L ₃ from P ₂ to P ₃ ,..., A vector L _N from P _{N −1} to P _N. In Figure 5, to calculate the vector L ₃₂ from the vector L _31, P ₂₂ from the vector L _22, P ₂₁ from the vector L _{21, P 1} from _{P 1} to P ₂₁ to P ₂₂ to P ₃ to P ₃ ing.

Next, the vector _{L 2} and _L angle theta ₃ of _{3, L 3} and the angle theta ₄ of _{L 4,} · · _·, obtains the _{L N-1} and _{L N} angle theta _N in (step S8). In Figure 5 we are seeking the angle theta ₃₂ vector _{L 21} and the angle theta ₃₁ of _{L 31, L 22} and _{L 32.}

Then, with respect to the angle theta ₃ theta _N, the angle determines whether more than 90 degrees (step S9). If there is even one exceeding 90 degrees, it is determined that there is a chip (step S10), and if there is no object exceeding 90 degrees, it is determined that there is no defect (step S11), and the inspection is terminated. In FIG. 5, since the angle θ ₃₂ formed by L ₂₂ and L ₃₂ exceeds 90 degrees, it is determined that there is a defect.

  The reason for determining whether the angle exceeds 90 degrees is that the first block to the Nth block composed of the LEDs of the dome lighting device 4 are arranged adjacent to each other sequentially. When the workpiece 2 has a normal flat surface or curved surface (eg, negative land), the part that shines with the illumination of the first block (bright part) to the part that shines with the N block (bright part) has an arc shape. They are arranged in order in a connected state. Therefore, the direction of the vector (the angle formed inside the arc) that connects the center of gravity of the bright part changes by more than 90 degrees means that the bright parts are not arranged in order. This is because 2 has an abnormality (deficiency). When there are a plurality of shining portions, the vector and the angle formed by the vectors are calculated and determined.

  As described above, by recognizing the position of the bright part while switching the irradiation area of the dome lighting device 4, it is possible to detect the chipping by repeating N times.

  Depending on the shape of the object to be inspected, it can be determined that there is a defect when a plurality of positions (center of gravity positions) are detected in one captured image. However, the defect can be more accurately determined by the vector angle as in the present embodiment.

  The appearance inspection apparatus of the present invention is suitable for inspecting defects that occur in the vicinity of a ridge formed by the surfaces of an object to be inspected, such as a throw-away tip of a cutting tool.

It is a schematic structure figure showing the whole appearance inspection device of the present invention. It is the some picked-up image imaged with the CCD camera of the external appearance inspection apparatus of this invention. It is a synthesized image obtained by synthesizing a plurality of captured images captured by a CCD camera. It is explanatory drawing which shows a negative land part and the part which a chip | tip shines, when illumination is irradiated to a workpiece | work front-end | tip part for every irradiation area | region. It is explanatory drawing which shows the vector which connected the gravity center position and gravity center position of the some captured image imaged with the CCD camera of the external appearance inspection apparatus of this invention. It is a flowchart which shows the operation procedure at the time of performing the method of recognizing the position of a bright part and detecting a defect.

Explanation of symbols

1 Visual inspection device
2 Workpiece 3 Sample stage
4 Dome lighting device (lighting means)
5 CCD camera (imaging means)
6 Image processing device
7 Control unit

Claims (4)

Illuminating means for irradiating light on a predetermined area with respect to the entire inspection target area of the curved surface on a portion formed by a curved surface on the surface of the object to be inspected,
An imaging unit that receives light reflected by the surface of the object to be inspected and has an imaging region in which the entire curved region to be inspected fits;
Image processing means for performing image processing on a plurality of picked-up images with different irradiation areas picked up by the image pick-up means, determining the presence / absence of a defect generated on the surface of the inspection object based on the plurality of picked-up images, and detecting defects An appearance inspection apparatus comprising: The imaging means images so that the normal part of the curved surface appears as a bright part,
The image processing unit superimposes a plurality of captured images captured by the imaging unit so that a bright part continuously appears and combines them into a single image, and an image processing unit that creates a composite image. The determination part which compares the area | region of a bright part with the reference | standard bright part area | region set beforehand, and determines the presence or absence of the defect which generate | occur | produced on the surface of to-be-inspected object is provided. Appearance inspection device. The illumination means sequentially irradiates light for each predetermined area along the curved surface,
The imaging means images so that the normal part of the curved surface appears as a bright part,
An image processing unit performs image processing on the captured image captured by the imaging unit to recognize the position of the bright part, and changes in the position of the bright part differ from the reference position change according to the imaging order. The appearance inspection apparatus according to claim 1, further comprising a determination unit that determines that the defect is defective.   The illuminating means includes a plurality of light emitting diodes (LEDs) so as to emit three-dimensional planar light, and the LEDs can be lit for each predetermined region. An appearance inspection apparatus according to any one of the above.

Images