JP2024039507A - Inspection method and program - Google Patents

Abstract

[Problem] To improve a technique for detecting defects in an edge region of an object to be inspected. [Solution] The inspection method disclosed herein is executed by an inspection device, and includes calculating (S1) the size of an area that the object to be inspected occupies within a predetermined area that includes the edge of the object to be inspected, moving (S2) the predetermined area in a predetermined direction, and judging the presence or absence of a defect in the edge region of the object to be inspected based on the change in the size accompanying the movement of the predetermined area (S4). [Selected Figure] Figure 2

Description

The present disclosure relates to an inspection method and program.

Conventionally, the presence or absence of a defect in an object to be inspected has been determined by utilizing the contrast of an image of the object to be inspected. Patent Document 1 discloses an inspection system that utilizes the contrast between a region of interest in an image photographed by a photographing unit and a surrounding region of the region of interest.

Japanese Patent Application Publication No. 2017-111085

Conventional techniques leave room for improvement in detecting defects in edge regions of objects to be inspected.

An object of the present disclosure is to improve techniques for detecting defects in edge regions of an inspected object.

An inspection method according to the present disclosure is an inspection method executed by an inspection device, which includes calculating the size of an area occupied by the object to be inspected out of a predetermined area including an edge of the object to be inspected; and determining the presence or absence of a defect in the edge region of the object to be inspected based on the change in size accompanying the movement of the predetermined region.

A program according to the present disclosure causes a computer to calculate the size of an area occupied by the object to be inspected out of a predetermined area including an edge of the object to be inspected, and to move the predetermined area in a predetermined direction. , determining the presence or absence of a defect in an edge region of the object to be inspected based on the change in size as the predetermined region moves.

According to the present disclosure, it is possible to improve a technique for detecting defects in an edge region of an object to be inspected.

FIG. 1 is a diagram showing the configuration of an inspection device according to an embodiment of the present disclosure. It is a figure showing operation of an inspection device concerning one embodiment of this indication. FIG. 3 is a diagram illustrating feature amounts in an embodiment of the present disclosure. FIG. 3 is a diagram illustrating a change in a difference in feature amounts in an embodiment of the present disclosure. FIG. 7 is a diagram illustrating feature amounts in a modified example of the present disclosure.

With the conventional technology, as described above, it is difficult to detect defects in the edge region of the object to be inspected. This is because, in an image including the object to be inspected, an area where a defect exists among the edge regions of the object to be inspected is recognized as a non-inspection area (background). Therefore, the present inventors attempted to detect defects in the edge region by following the edge shape of the object to be inspected with a geometric shape such as a circular arc or a line segment. However, with this method, there is a limit to the ability to follow the geometric shape of an irregularly shaped inspected object where the shape of the product varies from product to product and it is difficult to find regularity in the variation. Furthermore, with this method, it is difficult to detect defects at the tip of the object to be inspected. Therefore, the inventors of the present invention have conducted extensive studies and found that by focusing on the size of the area occupied by the object to be inspected out of a predetermined area including the edges of the object to be inspected, the edge of the object to be inspected can be improved even when the object is irregularly shaped. It has been found that it is possible to detect defects in the area.

Hereinafter, one embodiment of the present disclosure will be described with reference to the drawings. In this embodiment, the irregular-shaped inspection object includes not only products whose shape or size varies by several millimeters or tens of millimeters, but also approximate figures circumscribing the product (for example, bounding boxes, etc.). The shape or size of the rectangle may vary from product to product by several millimeters or tens of millimeters. This variation largely occurs during setup changes in lot production, but is not limited to this, and may occur every time a product is manufactured. Examples of products include processed foods including frozen foods, confectionery, and breads, but if the product itself is soft or the raw materials are soft and some deformation is expected during the manufacturing process, It's not limited to processed foods. The edge region may be, for example, from the edge of the object to be inspected to the center or center of gravity of the object to be inspected, up to at least 5%, up to at least 10% of the distance from the center or center of gravity of the object to the edge. but not limited to, up to at least 15%, or up to at least 20%.

With reference to FIG. 1, the configuration of an inspection apparatus 10 according to this embodiment will be described.

The inspection device 10 includes a control section 11, a storage section 12, an imaging section 13, an input section 14, and an output section 15.

Control unit 11 includes one or more processors, one or more programmable circuits, one or more dedicated circuits, or a combination thereof. The processor is a general-purpose processor such as a CPU (Central Processing Unit) or a GPU (Graphics Processing Unit), or a dedicated processor specialized for specific processing. The programmable circuit is, for example, an FPGA (Field-Programmable Gate Array). The dedicated circuit is, for example, an ASIC (Application Specific Integrated Circuit). The control unit 11 executes various processes related to the operation of the inspection apparatus 10 while controlling each part of the inspection apparatus 10.

Storage unit 12 includes one or more semiconductor memories, one or more magnetic memories, one or more optical memories, or a combination thereof. The semiconductor memory is, for example, RAM (Random Access Memory) or ROM (Read Only Memory). The storage unit 12 functions as, for example, a main storage device, an auxiliary storage device, or a cache memory. The storage unit 12 stores information used for the operation of the inspection apparatus 10 and information obtained by the operation of the inspection apparatus 10.

The imaging unit 13 includes any camera that generates an image of the object to be inspected within its field of view. The camera may be a camera capable of detecting wavelengths in the visible light region, or may be a camera capable of detecting wavelengths in the non-visible light region. The non-visible light region is, for example, an infrared region, an ultraviolet region, or an X-ray region. A camera includes, for example, an optical system such as a lens, and an image sensor such as a CCD (Charge-Coupled Device) image sensor or a CMOS (Complementary Metal Oxide Semiconductor) image sensor.

The input unit 14 includes one or more input interfaces. The input interface is, for example, a physical key, a capacitive key, a pointing device, or a touch screen integrated with the display. The input unit 14 accepts a user's operation to input information used for the operation of the inspection device 10. Instead of being included in the inspection device 10, the input unit 14 may be connected to a PC (Personal Computer), a tablet terminal, or the like using any method such as USB (Universal Serial Bus), HDMI (registered trademark), or Bluetooth (registered trademark). may be connected to the inspection device 10 as an external input device.

The output unit 15 includes one or more output interfaces. The output interface is, for example, a display. The display is, for example, an LCD (Liquid Crystal Display) or an organic EL (Electro Luminescence) display. The output unit 15 outputs information obtained by the operation of the inspection device 10. The output unit 15 is, for example, a USB (Universal
It may be connected to the inspection apparatus 10 as an external output device such as a PC (Personal Computer) or a tablet terminal by any method such as Serial Bus), HDMI (registered trademark), or Bluetooth (registered trademark).

The operation of the inspection apparatus 10 according to this embodiment will be described with reference to FIGS. 2 to 4. This operation corresponds to the inspection method according to this embodiment.

Step S1: The control unit 11 of the inspection apparatus 10 calculates the size of the area occupied by the inspection object W out of a predetermined area including the edge of the inspection object W.

Specifically, first, the control unit 11 of the inspection device 10 acquires an image of the object W to be inspected via the imaging unit 13. Then, the control unit 11 of the inspection device 10 identifies an approximate figure (for example, one bounding box) that circumscribes the main surface of the inspection object W in the acquired image by using any image recognition technique. . Here, when the entire area of the approximate figure circumscribing the main surface of the inspected object W is not included in the field of view of the imaging unit 13, the control unit 11 of the inspection device 10 controls the control unit 11 to control the control unit 11 so that if the entire area of the approximate figure circumscribing the main surface of the inspected object W is not included in the field of view of the imaging unit 13, the entire area of the approximate figure is It is possible to control the imaging unit 13 so that the imaging unit 13 is included in the field of view of the imaging unit 13 . Then, the control unit 11 of the inspection device 10 identifies the edge of the object W to be inspected based on the acquired image by using any image recognition technique. Then, the control unit 11 of the inspection device 10 calculates the size of the area occupied by the inspection object W in the predetermined area including the identified edge by using any image recognition technique. Note that the size and shape of the predetermined area can be appropriately set by the user via the input unit 14 of the inspection device 10. Further, the control unit 11 of the inspection device 10 uses a binary image generated by binarizing the image acquired by the imaging unit 13 to The size of the area occupied by the inspection object W may be calculated.

In the example shown in FIG. 3, the control unit 11 of the inspection device 10 calculates a length Ln along the short axis direction of the test object W, which is a flat processed food, out of a region Rn corresponding to a predetermined region. do. Here, "n" indicates the number of times the processes of steps S1 to S3 are repeated. Then, the control unit 11 of the inspection device 10 stores the calculated length Ln in the storage unit 12. Here, the width of the region Rn along the long axis direction of the object to be inspected W (hereinafter referred to as "width of the region Rn") is, for example, 1 pixel, but is not limited to this. Also, the length of the region Rn along the short axis direction of the object W to be inspected (hereinafter referred to as the "length of the region Rn") is set to be longer than the short side of the rectangle circumscribing the main surface of the object W to be inspected, for example. or may match the length of the short side of the rectangle, but is not limited thereto. The shape of the region Rn, including the width and length of the region Rn, can be appropriately set by the user via the input unit 14 of the inspection device 10. Further, instead of the length Ln, the area of the region occupied by the inspected object W in the region Rn may be used. Note that the short axis direction of the object W to be inspected is, for example, a direction along the short side of a rectangle circumscribing the object W to be inspected, but is not limited thereto. The short axis direction of the object W to be inspected may be, for example, the direction of the short axis of an ellipse when the shape of the main surface of the object W to be inspected is approximated by an ellipse.

Step S2: The control unit 11 of the inspection device 10 moves the predetermined area in step S1.

In the example shown in FIG. 3, the control unit 11 of the inspection apparatus 10 displays the size of the area Rn on the image acquired in step S1 at a position different from the position of the area Rn used for the calculation in step S1. The region Rn is moved by a predetermined movement width along the long axis direction of the object W to be inspected while maintaining the shape. That is, the region Rn moves relative to the inspected object W, and the destination of the region Rn becomes region Rn+1. The movement width is, for example, 8 pixels when the size of the defect that the user wants to detect is 5 mm or more, but is not limited to this. The moving direction and moving width of the region Rn can be set by the user as appropriate via the input unit 14 of the inspection apparatus 10, taking into account the size of the defect that the user wants to detect. Note that the long axis direction of the object W to be inspected is, for example, a direction along the long side of a rectangle circumscribing the main surface of the object W to be inspected, but is not limited thereto. The long axis direction of the object W to be inspected may be, for example, the direction of the long axis of an ellipse when the shape of the main surface of the object W to be inspected is approximated by an ellipse.

Step S3: The control unit 11 of the inspection device 10 determines whether to continue the calculation in step S1. If it is determined to continue the calculation, the process returns to step S1. If it is not determined that the calculation should be continued, the process proceeds to step S4.

In the example shown in FIG. 3, when the process returns to step S1, the control unit 11 of the inspection device 10 controls the inspection target W of the area Rn+1 corresponding to the predetermined area after movement in the same manner as the method described above. A length Ln+1 along the minor axis direction is calculated. In addition, the control unit 11 of the inspection device 10, if the scanning (movement) from one end of the image acquired in step S1 (the upper end of the paper in FIG. 3) to the other end (the lower end of the paper in FIG. 3) is not completed, It may be determined that the calculation is to be continued.

Step S4: The control unit 11 of the inspection device 10 determines the presence or absence of a defect in the edge region of the object W to be inspected, based on the change in size in step S2 due to movement of the predetermined region.

Specifically, the control unit 11 of the inspection device 10 selects the size calculated in step S1 corresponding to, for example, one region of interest selected from a predetermined region, and the size corresponding to a predetermined direction with respect to the region of interest. A first difference between the size and the size calculated in step S1 corresponding to the area located in the opposite direction to the movement direction is calculated. The control unit 11 of the inspection device 10 also determines the size calculated in step S1 corresponding to the region of interest and the region located in the forward direction of the movement direction corresponding to the predetermined direction with respect to the region of interest. A second difference between the size calculated in step S1 and the size calculated in step S1 is calculated. Then, the control unit 11 of the inspection device 10 determines, based on the first difference and the second difference, whether or not the change due to the movement of the size calculated in step S1 is accompanied by an extreme value. Calculate the amount. Then, the control unit 11 of the inspection device 10 determines that the change is accompanied by an extreme value based on the feature amount, and when the feature amount is equal to or greater than a predetermined threshold, the control unit 11 determines that the defect in the edge region of the inspected object W is detected. Determine that it exists. Then, the control unit 11 of the inspection device 10 presents the determination result to the user via the output unit 15. The difference is used in this way because, for an irregularly shaped inspected object W, the size deviation calculated in step S1 from some standard such as the radius of the inspected object W is used as a criterion for determining the presence or absence of a defect. This is because it is difficult to do so. In addition, even if there is an extreme value in the feature amount, the predetermined threshold value is used not for the extreme value caused by a defect, but for the variation in the edge shape of the object W to be inspected (in this case, for each individual object). This is to remove extreme values caused by variations in the edge shape of the inspection object W. According to this embodiment, as in the example shown in FIG. 4, the rise and fall of the difference related to defects can be easily recognized.

More specifically, in the example shown in FIG. 3, by repeating the processes of steps S1 to S3, the length L1 corresponding to the region R1 and the length L1 corresponding to the region R2 are stored in the storage unit 12 of the inspection device 10. Length L2, . . . , length LN corresponding to region RN will be stored. Here, among the regions R1 to RN, the region of interest is Rj (where j is a natural number from 2 to (N-1)). Further, with respect to the region of interest Rj, an area located in the opposite direction to the moving direction in step S2 is defined as Ri (where i is a natural number that is 1 or more and (N-2) or less and less than j). Further, with respect to the region of interest Rj, an area located in the forward direction of the movement direction in step S2 is defined as Rk (where k is a natural number that is 3 or more and N or less and greater than j). The control unit 11 of the inspection device 10 calculates a first difference Δji (for example, Δji=Lj−Li) between the length Lj corresponding to the region of interest Rj and the length Li corresponding to the region Ri. Further, the control unit 11 of the inspection device 10 calculates a second difference Δjk (for example, Δjk=Lj−Lk) between the length Lj corresponding to the region of interest Rj and the length Lk corresponding to the region Rk. Then, the control unit 11 of the inspection device 10 calculates a feature amount Δ (for example, Δ=Δji×Δjk) for determining the presence or absence of an extreme value based on the first difference Δji and the second difference Δjk. Then, when the feature amount Δ is greater than or equal to 0, the control unit 11 of the inspection device 10 determines that the change accompanying the movement of the length Ln is accompanied by an extreme value. Therefore, when i, j, and k are continuous natural numbers, for example, there are no extreme values for L1 = 100 (pix), L2 = 120 (pix), and L3 = 140 (pix), whereas Extreme values exist for L4=140 (pix), L5=100 (pix), and L6=120 (pix). Then, the control unit 11 of the inspection device 10 determines that a defect exists in the edge region of the inspected object W when the change due to the movement of the length Ln is accompanied by an extreme value and the feature amount Δ is greater than or equal to a predetermined threshold. judge. However, the present disclosure is not limited to these. Note that i, j, and k do not necessarily have to be continuous natural numbers; The user can set it as appropriate. Further, the predetermined threshold value can be appropriately set by the user via the input unit 14 of the inspection apparatus 10, depending on the size of the defect that the user wants to detect.

As described above, the inspection method according to the present embodiment includes a direction that includes an edge of the inspected object W and intersects with a direction along the long axis of the inspected object W (a direction along the short axis) that corresponds to a predetermined direction. calculating the size of the area occupied by the object W to be inspected out of a predetermined area extending in the area (step S1); It includes moving (step S2) and determining the presence or absence of a defect in the edge area of the inspection object W based on the change in size accompanying the movement of a predetermined area (step S4). Note that "intersection" may be orthogonal, but does not necessarily have to be orthogonal as long as the extending directions of the predetermined regions are parallel or approximately parallel before and after movement (that is, substantially parallel). Good too.

According to this embodiment, the size of the area occupied by the inspected object W in a predetermined area including the edge of the inspected object W is used as the feature amount. Therefore, even if there is a limit to following the edge shape of the object W to be inspected with a geometric shape, it is possible to detect defects in the edge region of the object W to be inspected. Further, by appropriately setting the movement direction of the predetermined area, it is possible to detect defects in the tip portion of the object W to be inspected. Therefore, the technique for detecting defects in the edge region of the inspected object W can be improved. Note that the inspection method according to the present embodiment may be performed after it is determined that there are no defects in areas other than the edge areas of the object W to be inspected by utilizing contrast as in the conventional technique.

Although the present disclosure has been described above based on the drawings and examples, it should be noted that those skilled in the art may make various changes and modifications based on the present disclosure. It should therefore be noted that these variations and modifications are included within the scope of this disclosure. For example, the functions included in each component or each step can be rearranged to avoid logical contradictions, and multiple components or steps can be combined into one or divided. It is possible.

As a modified example, the predetermined direction may be a direction along the short axis of the object W to be inspected, and the predetermined region may extend in a direction intersecting the direction along the short axis of the object W to be inspected. . That is, in this modification, a predetermined area that includes an edge of the object W to be inspected and extends in a direction (direction along the long axis) that intersects a direction along the short axis of the object W to be inspected, which corresponds to a predetermined direction. Among these, calculating the size of the area occupied by the inspected object W (step S1), and moving a predetermined area in a direction along the short axis of the inspected object W corresponding to a predetermined direction (step S2). and determining the presence or absence of a defect in the edge region of the object to be inspected W based on the change in size accompanying movement of a predetermined region (step S4). Moreover, from the viewpoint of improving the accuracy of detecting defects in the tip portion of the object W to be inspected, this modification may be implemented in combination with the embodiment described above. Note that other than the direction in which the predetermined region extends and the direction in which it moves, it is the same as in the embodiment described above, and therefore the description thereof will be omitted.

In addition, as a modified example, as in the example shown in FIG. It may extend toward the edge of the object W to be inspected. That is, in this modification, the size of the area occupied by the object to be inspected W is calculated out of a predetermined area that includes the edge of the object to be inspected and extends from the point O of the object to be inspected W toward the edge. (Step S1), moving a predetermined area in a rotational direction centering on point O of the object W to be inspected corresponding to a predetermined direction (Step S2), and changing the size of the predetermined area due to movement of the predetermined area. (Step S4). In addition, although the rotation direction is clockwise in the example shown in FIG. 5, it is not limited to this, and may be counterclockwise. Moreover, since it is the same as that of the embodiment mentioned above other than the extending direction and moving direction of the predetermined area, the explanation will be omitted. This modification is particularly effective when the roundness, which can be calculated using any mathematical method from an approximate figure circumscribing the main surface of the object W to be inspected, is greater than or equal to a predetermined threshold. Therefore, when the roundness of the inspected object W is less than a predetermined threshold value, the inspection method according to the embodiment described above with reference to FIG. In this case, the inspection method according to this modification may be implemented. Note that the point O may be a center of gravity that can be calculated using any image recognition technique from the area of the area occupied by the inspected object W in the image captured in step S1 in the above-described embodiment. , but not limited to this.

Further, as a modified example, the predetermined direction is a direction that intersects the normal direction of each point on the edge of the object W to be inspected, and the predetermined area is a direction that intersects the normal direction of each point on the edge of the object W to be inspected. It may also extend along the normal direction. That is, in this modification, the area occupied by the inspected object W out of a predetermined area that includes the edge of the inspected object W and extends along the normal direction of each point on the edge of the inspected object W. calculating the size (step S1); moving a predetermined area in a direction intersecting the normal direction of each point on the edge of the object W corresponding to a predetermined direction (step S2); The process also includes determining whether there is a defect in the edge area of the object W to be inspected based on the change in size as the area moves (step S4). Note that other than the direction in which the predetermined region extends and the direction in which it moves, it is the same as in the embodiment described above, and therefore the description thereof will be omitted.

Moreover, as a modified example, it is also possible to adopt an embodiment in which, for example, a general-purpose computer functions as all or a part (for example, the control unit 11) of the inspection apparatus 10 according to the above-described embodiment. Specifically, a program that describes the processing content for realizing all or part of the functions of the inspection device 10 according to the embodiment described above is stored in the memory of a general-purpose computer, and the program is read and executed by a processor. . Therefore, the present disclosure can also be implemented as a program executable by a processor or a non-transitory computer-readable medium storing the program. Note that the computer that executes the program is, for example, a PC (Personal Computer), a tablet terminal, or a smartphone, but is not limited to these examples.

Although some or all of the embodiments described above may be described as in the following additional notes, the present disclosure is not limited thereto.
[Additional note 1]
An inspection method performed by an inspection device, comprising:
Calculating the size of an area occupied by the object to be inspected out of a predetermined area including an edge of the object to be inspected;
moving the predetermined area in a predetermined direction;
An inspection method comprising: determining the presence or absence of a defect in an edge region of the object to be inspected based on the change in size as the predetermined region moves.
[Additional note 2]
The test method described in Appendix 1,
In the inspection method, the predetermined direction is a direction along a long axis and/or a short axis of the object to be inspected, and the predetermined region extends in a direction intersecting the predetermined direction.
[Additional note 3]
The test method described in Supplementary note 1 or 2,
In the inspection method, the predetermined direction is a rotation direction about a point set on the object to be inspected, and the predetermined region extends from the point toward the edge.
[Additional note 4]
The inspection method described in any one of Supplementary Notes 1 to 3,
calculating a first difference between the size corresponding to a region of interest selected from the predetermined region and the size corresponding to a region located in a direction opposite to the predetermined direction with respect to the region of interest; ,
Calculating a second difference between the size corresponding to the attention area and the size corresponding to an area located forward in the predetermined direction with respect to the attention area;
Calculating a feature amount for determining whether the change involves an extreme value based on the first difference and the second difference;
The inspection method further comprises determining that the defect exists if it is determined that the change is accompanied by an extreme value based on the feature amount, and the feature amount is equal to or greater than a predetermined threshold value.
[Additional note 5]
The test method described in any one of Supplementary Notes 1 to 4,
In the inspection method, the shape of the object to be inspected is irregular.
[Additional note 6]
to the computer,
Calculating the size of an area occupied by the object to be inspected out of a predetermined area including an edge of the object to be inspected;
moving the predetermined area in a predetermined direction;
A program for determining the presence or absence of a defect in an edge region of the object to be inspected based on a change in the size as the predetermined region moves.
[Additional note 7]
The program described in Appendix 6,
The program, wherein the predetermined direction is a direction along a long axis and/or a short axis of the object to be inspected, and the predetermined region extends in a direction intersecting the predetermined direction.
[Additional note 8]
The program described in appendix 6 or 7,
The predetermined direction is a rotation direction centered on a point set on the object to be inspected, and the predetermined area extends from the point toward the edge.
[Additional note 9]
The program described in any one of appendices 6 to 8,
to the computer;
calculating a first difference between the size corresponding to a region of interest selected from the predetermined region and the size corresponding to a region located in a direction opposite to the predetermined direction with respect to the region of interest; ,
Calculating a second difference between the size corresponding to the attention area and the size corresponding to an area located forward in the predetermined direction with respect to the attention area;
Calculating a feature amount for determining whether the change involves an extreme value based on the first difference and the second difference;
The program further causes determining that the defect exists when it is determined that the change is accompanied by an extreme value based on the feature amount, and the feature amount is equal to or greater than a predetermined threshold value.
[Additional note 10]
The program described in any one of Supplementary Notes 6 to 9,
A program in which the shape of the object to be inspected is amorphous.

10 Inspection device 11 Control section 12 Storage section 13 Imaging section 14 Input section 15 Output section

Claims (6)

An inspection method performed by an inspection device, comprising:
Calculating the size of an area occupied by the object to be inspected out of a predetermined area including an edge of the object to be inspected;
moving the predetermined area in a predetermined direction;
An inspection method comprising: determining the presence or absence of a defect in an edge region of the object to be inspected based on the change in size as the predetermined region moves. The testing method according to claim 1,
In the inspection method, the predetermined direction is a direction along a long axis and/or a short axis of the object to be inspected, and the predetermined region extends in a direction intersecting the predetermined direction. The inspection method according to claim 1,
In the inspection method, the predetermined direction is a direction of rotation about a point set on the object to be inspected, and the predetermined region extends from the point toward the edge. The inspection method according to any one of claims 1 to 3,
calculating a first difference between the size corresponding to a region of interest selected from the predetermined region and the size corresponding to a region located in a direction opposite to the predetermined direction with respect to the region of interest; ,
Calculating a second difference between the size corresponding to the attention area and the size corresponding to an area located forward in the predetermined direction with respect to the attention area;
Calculating a feature quantity for determining whether the change involves an extreme value based on the first difference and the second difference;
The inspection method further comprises determining that the defect exists if it is determined that the change is accompanied by an extreme value based on the feature amount, and the feature amount is equal to or greater than a predetermined threshold value. The inspection method according to any one of claims 1 to 3,
In the inspection method, the shape of the object to be inspected is irregular. to the computer,
Calculating the size of an area occupied by the object to be inspected out of a predetermined area including an edge of the object to be inspected;
moving the predetermined area in a predetermined direction;
A program for determining the presence or absence of a defect in an edge region of the object to be inspected based on a change in the size as the predetermined region moves.

Images