Visual inspection device

Abstract

To provide a technique capable of accurately specifying the size of a sag.SOLUTION: A visual inspection device comprising: a first light source that irradiates light toward a placement position where an object is placed; a second light source that irradiates light toward the placement position from the side opposite the first light source; an imaging unit that acquires a first image showing the brightness values of the object in each surrounding position as viewed from the first light source when light is being irradiated from the first light source and a second image showing the brightness values of the object in each surrounding position as viewed from the first light source when light is being irradiated from the second light source; and a specifying unit that uses the second image to identify a foreground area in which the object is captured and a background area in which the object is not captured in the first image, and then identifies the start and end points of a sag on the surface of the object on the side irradiated with light by the first light source, and the specifying unit specifies the distance between the start and end points as the size of the sag.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] The present invention relates to an appearance inspection apparatus.

Background Art

[0002] Conventionally, a technique for inspecting the appearance of an object by imaging reflected light from the object irradiated with light has been known. For example, Patent Document 1 discloses an inspection system including an inspection illumination device and an imaging device in which a first light shielding mask, a second light shielding mask, a lens, and a half mirror are arranged along the direction in which light irradiated from a surface light source travels.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In shearing using a press machine, the material is sheared by tools (punch and die) arranged to have an appropriate clearance. However, if the clearance between the tools increases due to wear on the cutting edge or side surface of the tools during continuous use, it is known that the sag occurring on the material surface becomes larger. If such a state where the clearance between the tools is enlarged is left unattended, it will lead to a decrease in yield. Therefore, a technique capable of accurately specifying the magnitude of the sag so that the tools used for shearing can be appropriately maintained has been desired. Note that Patent Document 1 does not consider at all the specification of the magnitude of the sag.

[0005] The present invention has been made to solve at least a part of the above-described problems, and an object thereof is to provide a technique capable of accurately specifying the magnitude of the sag.

Means for Solving the Problems

[0006] The present invention has been made to solve at least a part of the above-described problems and can be realized in the following forms.

[0007] (1) According to one aspect of the present invention, there is provided an appearance inspection apparatus for inspecting the appearance of an object. The appearance inspection apparatus is an appearance inspection apparatus for inspecting the appearance of an object, and includes a first light source that irradiates light toward an arrangement position where the object is arranged, a second light source that faces the first light source and irradiates light from a side opposite to the first light source toward the arrangement position, an imaging unit that acquires a first image showing luminance values at each position of the object and its surroundings as viewed from the side of the first light source in a state where light is being irradiated from the first light source, and a second image showing luminance values at each position of the object and its surroundings as viewed from the side of the first light source in a state where light is being irradiated from the second light source, and a specifying unit that specifies a foreground region in which the object appears and a background region in which the object does not appear in the first image by using the second image, and then specifies a start point and an end point of sag on the surface of the object on the side irradiated with light by the first light source. The specifying unit searches for the luminance values of the constituent pixels that make up the first image in order from the side of the background region toward the side of the foreground region, specifies the position of the constituent pixel that first shows a luminance value equal to or higher than the start point reference value as the start point, searches for the luminance values of the constituent pixels in order from the side of the foreground region toward the side of the background region, specifies the position of the constituent pixel that first shows a luminance value equal to or lower than the end point reference value as the end point, and then specifies the distance between the start point and the end point as the magnitude of the sag.

[0008] According to this configuration, by using the second image showing the contour of the object, the foreground area (the area where the object is imaged) and the background area (the area where the object is not imaged) in the first image are specified, so that the foreground area and the background area can be accurately specified. Then, based on the foreground area and the background area accurately specified in this way, by comparing the luminance values of the constituent pixels of the first image searched in order from one area side to the other area side with each of the start point reference value and the end point reference value, since the start point and the end point of the sag are specified, the size of the sag can be accurately specified.

[0009] (2) In the appearance inspection apparatus of the above aspect, the first light source can irradiate light toward the arrangement position with different illumination outer diameters, and the first image used by the specifying unit when specifying the start point and the end point is obtained by using a plurality of the first images acquired by the imaging unit when light is irradiated from the first light source with different illumination outer diameters, calculating luminance integration values by integrating the luminance values of each pixel in each of the first images for each same position, and then creating a luminance integration image by arranging each of the luminance integration values corresponding to each position. The luminance integration value may be a value calculated by normalizing the luminance values of each pixel in each of the images and then integrating the normalized luminance values for each same position. When the object is covered with processing oil, due to the decrease in the intensity of the light reflected from the object, the luminance values of the constituent pixels constituting each position of the object also tend to decrease in the image of the object. According to this configuration, the first image used by the specifying unit when specifying the start point and the end point of the sag is a luminance integration image. Also, since the luminance values of the constituent pixels constituting each position of the object in the luminance integration image are corrected by normalization, even if the object is covered with processing oil or the processing oil is partially adhered to the object, after reducing the influence of such processing oil, the size of the sag can be accurately specified.

[0010] (3) In the appearance inspection apparatus of the above-described embodiment, in addition to the size of the sag, the presence or absence of a shape defect of the object and the size of the shape defect may be specified using the second image. According to this configuration, by using the second image, the specifying unit can specify, in addition to the size of the sag, the presence or absence of a shape defect of the object and the size of such a shape defect. Therefore, it is possible to provide an appearance inspection apparatus capable of simultaneously detecting the size of the sag and the shape defect of the object.

[0011] Note that the present invention can be realized in various forms, for example, in the form of an appearance inspection apparatus, an appearance inspection system, an appearance inspection method, a method for controlling an appearance inspection operation, a computer program for executing these apparatuses and methods, a server apparatus for distributing this computer program, a non-temporary storage medium storing the computer program, and the like.

Brief Description of the Drawings

[0012]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Mode for Carrying Out the Invention

[0013] <First Embodiment> FIG. 1 is an explanatory diagram illustrating the configuration of an appearance inspection apparatus 1 as a first embodiment of the present invention. In FIG. 1, XYZ axes orthogonal to each other are illustrated. The X axis corresponds to the direction in which the light irradiated from a first light source 5 described later travels, and the Y axis and the Z axis correspond to directions orthogonal to the X axis. This XYZ axis is common to each of the figures after FIG. 1. The appearance inspection apparatus 1 is an apparatus for inspecting the appearance of an object OB. Specifically, the appearance inspection apparatus 1 is an apparatus capable of specifying the size of sag on the surface of the object OB on the side irradiated with light by the first light source 5. Details of the sag will be described with reference to FIG. 5 described later. The appearance inspection apparatus 1 includes a first light source 5, a plano-convex lens 40, a half mirror 50, a second light source 60, a camera 70, and a control unit 80. In FIG. 1, the optical axis AX indicates the optical axis of the first light source 5 and the optical axis of the second light source 60.

[0014] FIG. 2(A) shows a cross section of the first light source 5 along the line F2A-F2A in FIG. 1. FIG. 2(B) shows a cross section of the first light source 5 along the line F2B-F2B in FIG. 2(A). As shown in FIG. 1, the first light source 5 irradiates light toward the arrangement position PL where the object OB is arranged. In FIG. 1, a state where the object OB is arranged at the arrangement position PL is shown. The first light source 5 is a unit in which a plate-like member 10, a wall member 20, and a diffusion member 30 are laminated in the X-axis direction. As shown in FIG. 2(B), light sources 11 to 15 that irradiate light on the object OB are arranged on the surface of the plate-like member 10 facing the +X-axis direction side. Specifically, as shown in FIG. 2(A), when viewed from the +X-axis direction side, one light source 11 is arranged at the center, and a plurality of light sources 12 are arranged in a circular shape so as to surround the light source 11. Further, a plurality of light sources 13 are arranged in a circular shape so as to surround the plurality of light sources 12. Similarly, a plurality of light sources 14 are arranged in a circular shape so as to surround the plurality of light sources 13, and a plurality of light sources 15 are arranged in a circular shape so as to surround the plurality of light sources 14. That is, the light sources 12 to 15 are arranged concentrically on the surface of the plate-like member 10 facing the +X-axis direction side. The light sources 11 to 15 are LEDs. The first light source 5 can irradiate light toward the arrangement position PL with different illumination outer diameters by adjusting which of the light sources 11 to 15 irradiates light. As an example of different illumination outer diameters, FIG. 2(A) shows an illumination outer diameter Da when light is irradiated from the light sources 11 to 13 and an illumination outer diameter Db when light is irradiated from the light sources 11 to 15.

[0015] As shown in Fig. 2(A), the wall member 20 includes wall portions 21 to 25 that concentrically surround each of the light sources 11 to 15 when viewed from the +X-axis direction side. Each of the wall portions 21 to 25 is formed so as to surround the light sources 11 to 15 when viewed from the +X-axis direction side and extends along the X-axis direction (see Fig. 2(B)). Specifically, each of the wall portions 21 to 24 is formed in a circular shape when viewed from the +X-axis direction side and is arranged so as to surround the light sources 11 to 14. The wall portion 25 is formed in a rectangular parallelepiped shape having a cylindrical through-hole (the space where the light sources 11 to 15 and the wall portions 21 to 24 are arranged) in the central portion when viewed from the +X-axis direction side and is arranged so as to surround the light source 15. The diffusion member 30 diffuses the light emitted from the light sources 11 to 15. In Figs. 2(A) and 2(B), since the wall portions 21 to 24 are cross-sections, they should originally be shown with hatching, but the hatching is omitted for the sake of illustration.

[0016] Returning to the description of Fig. 1, as shown in Fig. 1, the plano-convex lens 40 is arranged between the first light source 5 and a half mirror 50 described later in the X-axis direction. The plano-convex lens 40 condenses the light emitted from the light sources 11 to 15 through the diffusion member 30. The half mirror 50 is arranged between the first light source 5 and the arrangement position PL. Specifically, the half mirror 50 is arranged on the +X-axis direction side of the plano-convex lens 40 among the space between the first light source 5 and the arrangement position PL. The half mirror 50 transmits a part of the light emitted from the light sources 11 to 15 (the first light source 5) through the diffusion member 30 toward the object OB and reflects a part of the light reflected from the object OB toward a camera 70 described later. Also, the half mirror 50 reflects a part of the light emitted from a second light source 60 described later toward the camera 70.

[0017] The second light source 60 faces the first light source 5 and irradiates light from the side opposite to the first light source 5 toward the arrangement position PL. The second light source 60 is an LED. The light emitted from the second light source 60 is converted into collimated light through a telecentric lens 62 attached to the second light source 60 and then irradiated toward the arrangement position PL.

[0018] The camera 70 is an imaging unit that images light incident inside via the half mirror 50. The telecentric lens 72 attached to the camera 70 allows only light parallel to the optical axis of the telecentric lens 72 to be incident on the camera 70. The camera 70 is capable of imaging the light incident on the camera 70 via the half mirror 50 when the object OB arranged at the arrangement position PL is irradiated with light from the first light source 5, and imaging the light incident on the camera 70 via the half mirror 50 when the object OB arranged at the arrangement position PL is irradiated with light from the second light source 60. The control unit 80 is a computer including a ROM, a RAM, and a CPU, and performs various controls of the appearance inspection device 1.

[0019] The control unit 80 changes the irradiation angle θ of the light irradiated on the object OB by controlling the illumination outer diameter (exemplified as illumination outer diameters Da and Db in FIG. 2(A)) defined by the light irradiated from each of the light sources 11 to 15 (see FIG. 1). For example, the illumination outer diameter is larger in a state where light is irradiated from the light sources 11 to 13 than in a state where light is irradiated only from the light source 11. Similarly, the illumination outer diameter is larger in a state where light is irradiated from the light sources 11 to 15 than in a state where light is irradiated from the light sources 11 to 13. The larger the illumination outer diameter, the larger the irradiation angle θ. The control unit 80 also controls the execution of imaging by the camera 70.

[0020] FIG. 3 is an explanatory diagram showing an example of the first image G1. In the appearance inspection device 1, the camera 70 can acquire the first image G1. The first image G1 is an image showing the luminance values at each position of the object OB and the periphery SR viewed from the side of the first light source 5 in a state where the object OB is irradiated with light from the first light source 5. The periphery SR refers to the periphery of the object OB that enters the angle of view when imaging the object OB. The plane SF shown in FIG. 3 is the plane of the object OB facing the -X axis direction side.

[0021] FIG. 4 is an explanatory diagram showing an example of the second image G2. In addition to the first image G1, the camera 70 can acquire the second image G2. The second image G2 is an image showing the luminance values at the respective positions of the object OB and the periphery SR as viewed from the side of the first light source 5 in a state where light is irradiated from the second light source 60. In other words, the second image G2 is an image obtained by imaging the light incident on the camera 70 through the half mirror 50 when light is irradiated from the second light source 60 toward the object OB disposed at the arrangement position PL. That is, in the second image G2, since the periphery SR exhibits a higher luminance than the object OB, it can be said that the second image G2 is an image showing the contour of the object OB. The hatching in the object OB shown in FIG. 4 indicates that the luminance value inside the object OB in the second image G2 is lower than the luminance value of the periphery SR.

[0022] FIG. 5 is an explanatory diagram regarding the size of the sag inspected by the appearance inspection apparatus 1. FIG. 5 shows a cross section of the object OB cut along the XZ plane. The sag is a rounded surface formed by stretching the surface of the material when the material is sheared by tools (punch and die). FIG. 5 shows the sag SG of the object OB. In addition, when the material is sheared, in addition to the sag SG, a shear surface SH, a fracture surface FR, and a burr BR are formed. The burr BR is a shape defect such as a protrusion or a return formed at the edge of the material subjected to processing such as cutting or shearing.

[0023] For example, in the object OB, the size of the sag SG can be defined as follows. That is, in the object OB, when the starting point SP is the position where the portion along the Z-axis direction in the surface SF on the -X-axis direction side starts to incline toward the +X-axis direction side, and the end point EP is the position corresponding to the boundary between the surface SF and the shear surface SH, the size of the sag SG can be defined as the distance between the starting point SP and the end point EP.

[0024] The inclination of the surface SF with respect to the Z-axis direction increases as it goes from the starting point SP to the ending point EP. For example, when the cross-section SH is along the X-axis direction, the inclination of the surface SF with respect to the Z-axis direction continuously changes from 0 degrees to 90 degrees. However, even when imaging the object OB using a light source (e.g., the first light source 5 mentioned above) capable of irradiating light with different illumination outer diameters (from the -X-axis direction side), it is impossible to image the portion of the surface SF that is greatly inclined with respect to the Z-axis direction. For this reason, even if the starting point SP can be identified from the captured image, it is difficult to identify the ending point EP, and thus it is also difficult to identify the magnitude of the sag SG. In this regard, since the appearance inspection apparatus 1 can identify the starting point SP and the ending point EP, the magnitude of the sag SG can also be identified. In FIGS. 6 to 9 below, the method for identifying the starting point SP and the ending point EP by the appearance inspection apparatus 1 will be described.

[0025] FIG. 6 is a flowchart showing the procedure of the appearance inspection process executed by the control unit 80 in the appearance inspection apparatus 1. The appearance inspection process is a process for inspecting the appearance of the object OB arranged at the arrangement position PL. More specifically, the appearance inspection process is a process for identifying the magnitude of the sag SG by identifying the starting point SP and the ending point EP of the sag SG on the surface of the object OB (exemplified as the surface SF in FIG. 5) on the side irradiated with light by the first light source 5.

[0026] When the appearance inspection process is started, the control unit 80 acquires a first image G1 (step S11). In the present embodiment, the first image G1 used by the control unit 80 to identify the starting point SP and the ending point EP is a luminance integrated image. The luminance integrated image is an image created by using a plurality of first images G1 acquired by the camera 70 when the first light source 5 irradiates light with different illumination outer diameters, calculating the luminance integrated value by integrating the luminance values of each pixel in each of the first images G1 for each same position, and then arranging each of the luminance integrated values corresponding to each position.

[0027] The plurality of first images G1 described above are a plurality of images captured each time the illumination outer diameter of the light irradiated from the first light source 5 is changed to a different size. For example, when the camera 70 captures images for each state of a state where light is irradiated only from the light source 11, a state where light is irradiated from the light sources 11 to 13, and a state where light is irradiated from the light sources 11 to 15, three images correspond to the plurality of images described above. Further, calculating the luminance integration value by integrating the luminance values of each pixel in each of the first images G1 for each same position means that, for example, when the plurality of images described above are three images, there are three pixels constituting the same position in each image, and the luminance integration value is calculated by integrating the three pieces of data for each same position. Arranging each of the luminance integration values corresponding to each position means that, for example, assuming that the luminance integration value integrated for the coordinates (Xi, Yj) corresponds to the coordinates (Xi, Yj), the luminance integration value is arranged at the position indicated by the coordinates (Xi, Yj). That is, the luminance value of each pixel constituting the luminance integration image is the luminance integration value calculated based on the plurality of first images G1.

[0028] In the present embodiment, the luminance integration value is a value calculated by normalizing the luminance value of each pixel in each of the first images G1 and then integrating the normalized luminance values for each same position. Normalization is a process of dividing the difference between the luminance value of each pixel constituting the same position in each of the first images G1 and the minimum luminance value of the pixels constituting the same position by the difference between the maximum luminance value and the minimum luminance value of the pixels constituting the same position. Through this normalization, the luminance value of each pixel constituting the same position is converted into a value within the range of 0 to 1. When the object OB is covered with machining oil, the intensity of the light reflected from the object OB decreases, and thus the luminance value of the pixels constituting each position of the object OB also tends to decrease in the image of the object OB captured. On the other hand, by normalizing the luminance value, the influence of the machining oil can be reduced.

[0029] Next, the control unit 80 acquires the second image G2 (step S12). Specifically, the control unit 80 acquires the second image G2 by causing the camera 70 to capture an image in a state where light is being irradiated from the second light source 60 toward the object OB disposed at the arrangement position PL.

[0030] Next, the control unit 80 functions as a specifying unit that specifies, using the second image G2, the foreground region in which the object OB appears and the background region in which the object OB does not appear in the first image G1 (luminance integrated image in the present embodiment) (step S13). Specifically, the control unit 80 specifies the foreground region and the background region in the first image G1 in the following order. First, the control unit 80 applies Otsu's binarization, which is a method of determining a binarization threshold such that the separation degree regarding the frequency distribution of luminance values = (between-class variance) / (within-class variance) is maximized, to the second image G2, thereby specifying the foreground region and the background region in the second image G2. Next, the control unit 80 specifies, as the foreground region and the background region in the first image G1, the regions in the first image G1 that correspond to the positions of the foreground region and the background region in the second image G2, respectively, at the same positions. At this time, it is assumed that the luminance values (luminance integrated values in the present embodiment) of the pixels constituting the region specified as the background region in the first image G1 are replaced with 0.

[0031] FIG. 7 is an explanatory diagram for explaining the creation of a luminance value profile. In FIG. 7, a part of the first image G1 after the foreground region FG and the background region BG are specified is shown enlarged. The foreground region FG shown in FIG. 7 is a region where the object OB (specifically, the surface SF of the object OB) is imaged. The hatching in the background region BG shown in FIG. 7 indicates a state in which the luminance values of the pixels constituting the background region BG have been replaced with 0 through step S13. After specifying the foreground region FG and the background region BG in the first image G1 (step S13), the control unit 80 creates a luminance value profile using the first image G1 (step S14). The luminance value profile is a graph of the luminance values of the constituent pixels constituting the first image G1 along a specific direction. In FIG. 7, a plurality of arrows AR are shown as an example of the specific direction. The starting point ST is the starting point of the arrow AR. As exemplified by the arrow AR, the specific direction used for creating the luminance value profile is a direction that crosses from one of the regions of the background region BG and the foreground region FG to the other region in the first image G1.

[0032] FIG. 8 is an explanatory diagram showing an example of the created luminance value profile. In FIG. 8, the horizontal axis represents the distance from the starting point ST explained in FIG. 7. The vertical axis represents the luminance value of the pixels at each distance from the starting point ST. FIG. 8 is a luminance value profile created along the central arrow AR among the seven arrows AR shown in FIG. 7. In the range of the luminance value profile shown in FIG. 8 from a distance of 0 mm to about 2.6 mm, since the luminance value is 0, it corresponds to the background region BG. In the range of the luminance value profile shown in FIG. 8 from a distance of about 2.6 mm to 5 mm, since the luminance value is greater than 0, it corresponds to the foreground region FG. In step S14, the control unit 80 creates a luminance value profile along the arrow AR for each position of the boundary BD (see FIG. 7) between the foreground region FG and the background region BG.

[0033] FIG. 9 is an explanatory diagram of a method for specifying the size of sag SG using a luminance value profile. After creating the luminance value profile (step S14), the control unit 80 specifies the start point SP and the end point EP of the sag SG on the surface of the object OB on the side irradiated with light by the first light source 5. In the present embodiment, after creating the luminance value profile (step S14), the control unit 80 first specifies the start point SP (step S15). Specifically, as indicated by the arrow AF in FIG. 9, the control unit 80 searches for the luminance values of the constituent pixels that make up the first image G1 in order from the background region BG side to the foreground region FG side in the luminance value profile, and first identifies the position of the constituent pixel that exhibits a luminance value equal to or higher than the start point reference value SV as the start point SP. The start point reference value SV is the difference between the baseline FL obtained by fitting each of the luminance values included within the set range of the foreground region FG (a range of 2 mm in the present embodiment) in the luminance value profile with a linear function, and the standard deviation σ F from that baseline FL (baseline FL - standard deviation σ F ). As shown in FIG. 9, the intersection of the start point reference value SV and the luminance value profile is identified as the start point SP.

[0034] After specifying the start point SP (step S15), the control unit 80 specifies the end point EP (step S16). Specifically, as indicated by the arrow AB in FIG. 9, the control unit 80 searches for the luminance values of the constituent pixels that make up the first image G1 in order from the foreground region FG side to the background region BG side in the luminance value profile, and first identifies the position of the constituent pixel that exhibits a luminance value equal to or lower than the end point reference value EV as the end point EP. The end point reference value EV is the sum of the baseline BL obtained by fitting each of the luminance values included within the set range of the background region BG (a range of 2 mm in the present embodiment) in the luminance value profile with a linear function, and the standard deviation σ B from that baseline BL (baseline BL + standard deviation σ B) That is. As shown in FIG. 9, the intersection point of the end point reference value EV and the luminance value profile is specified as the end point EP. Note that since the luminance values of the pixels constituting the background region BG have been replaced with 0 through step S13, the baseline BL and the standard deviation σ B are both 0.

[0035] After specifying the end point EP (step S16), the control unit 80 specifies the magnitude of the sag SG as the distance between the start point SP and the end point EP (see FIG. 5) (step S17). Thereafter, the control unit 80 ends the appearance inspection process.

[0036] Next, as a comparative example, a method for specifying the magnitude of the sag Sg using the height profile will be described. Sag Sg is used when referring to the sag when specified using the height profile of the comparative example. FIG. 10 is an explanatory diagram showing a height profile created using a three-dimensional shape measuring machine. FIG. 11 shows a part of the object OB and the periphery SR that are the objects for creating the height profile. FIG. 10 is a height profile created when using the VR-6000 manufactured by Keyence Corporation as a three-dimensional shape measuring machine. Specifically, the height profile shown in FIG. 10 is a graph of the heights of the object OB and the periphery SR along a specific direction (illustrated as arrow Ar in FIG. 11) in the same manner as when creating the luminance value profile described in FIG. 7. Note that the height profile is created by obtaining, in order along a specific direction (arrow Ar), the numerical values indicating the heights at each position on the surface of the object OB and the periphery SR for the actual object OB instead of the first image G1. The specific direction used for creating the height profile is the direction that crosses from one of the object OB and the periphery SR to the other. The height profile is created along arrow Ar for each position of the boundary BD (see FIG. 11) between the object OB and the periphery SR.

[0037] In FIG. 10, the horizontal axis indicates the distance from the starting point St (see FIG. 11) of the arrow Ar. The vertical axis indicates the height of the object OB or the periphery SR at each distance from the starting point St. The height of 0 mm on the vertical axis corresponds to the portion along the Z-axis direction of the surface SF of the object OB (see FIG. 5). When specifying the magnitude of the sag Sg using the height profile, for example, the specification is performed by the following method. That is, after specifying the region Fg (see FIG. 10) where the object OB exists and the region Bg (see FIG. 10) where the object OB does not exist, based on the position P (see FIG. 10) where the height value starts to increase, as shown by the arrow Af in FIG. 10, the height values indicated by the height profile are searched in order from the side of the region Bg toward the side of the region Fg, and the position that first shows a height equal to or higher than the starting point reference height Sv is specified as the starting point Sp. Also, similar to step S16, as shown by the arrow Ab in FIG. 10, the height values indicated by the height profile are searched in order from the side of the region Fg toward the side of the region Bg, and the position that first shows a height equal to or lower than the end point reference height Ev is specified as the end point Ep. Here, the starting point reference height Sv, similar to the starting point reference value SV, is the difference between the baseline fL obtained by fitting each of the height values within the set range (for example, a range of 2 mm) of the region Fg in the height profile with a linear function and the standard deviation σ f from this baseline fL (baseline fL - standard deviation σ f ). Since the height values within the set range of the region Fg are almost substantially constant, the standard deviation σ f is extremely small. Therefore, in FIG. 10, the baseline fL = starting point reference height Sv is shown. On the other hand, the end point reference height Ev, similar to the end point reference value EV, is the sum of the baseline bL obtained by fitting each of the height values within the set range (for example, a range of 2 mm) of the region Bg in the height profile with a linear function and the standard deviation σ b from this baseline bL (baseline bL + standard deviation σ b ). Since the height values within the set range of the region Bg are almost substantially constant, the standard deviation σ bis infinitely small. Therefore, in FIG. 10, the baseline bL is shown as the end point reference height Ev.

[0038] The average value of the measured values obtained by measuring the magnitude of the sag Sg at each position of the boundary BD using the height profile (see FIG. 10) and the average value of the measured values obtained by measuring the magnitude of the sag SG at each position of the boundary BD using the luminance value profile (see FIG. 9) tend to show close values. However, when creating a height profile using a three-dimensional shape measuring machine, the length range of the boundary BD that can be measured at one time is as small as about several millimeters to several tens of millimeters. Therefore, depending on the size of the object OB, a complex scanning mechanism is required. As a result, there is a risk of increasing the cost of the three-dimensional shape measuring machine and lengthening the time required to specify the magnitude of the sag Sg. On the other hand, in the appearance inspection apparatus 1 of the present embodiment, by adjusting so that the entire length of the boundary BD enters the first image G1 and the second image G2, the magnitude of the sag SG can be measured over the entire length of the boundary BD (see FIG. 7) at one time.

[0039] As described above, according to the appearance inspection apparatus 1 of the first embodiment, by using the second image G2 showing the contour of the object OB, the foreground region FG (the region where the object is imaged) and the background region BG (the region where the object is not imaged) in the first image G1 are specified (see FIG. 7). Therefore, the foreground region FG and the background region BG can be accurately specified. Then, based on the foreground region FG and the background region BG accurately specified in this way, by comparing the luminance values of the constituent pixels of the first image G1 searched in order from one region side to the other region side with the start point reference value SV and the end point reference value EV respectively, the start point SP and the end point EP of the sag SG are specified. Therefore, the magnitude of the sag SG can be accurately specified.

[0040] When the object OB is covered with machining oil, the intensity of the light reflected from the object OB decreases, and thus the luminance values of the constituent pixels constituting each position of the object OB also tend to decrease in the image of the object OB. In this regard, in the appearance inspection apparatus 1 of the first embodiment, the first image G1 used by the control unit 80 to specify the start point SP and the end point EP is a luminance integrated image. Further, since the luminance values of the constituent pixels constituting each position of the object OB in the luminance integrated image are corrected by normalization, even if the object OB is covered with machining oil or machining oil is partially adhered to the object OB, after reducing the influence of such machining oil, the magnitude of the sag SG can be accurately specified.

[0041] <Modification Example of the Present Embodiment> The present invention is not limited to the above-described embodiments, and can be implemented in various modes without departing from the gist thereof. For example, the following modifications are possible.

[0042] In the above-described embodiment, the light sources 11 to 15 included in the first light source 5 are LEDs, but the present invention is not limited thereto. The light sources 11 to 15 included in the first light source 5 may be another point light source different from the LED (for example, a halogen lamp or the like). Further, in the above-described embodiment, the size of the illumination outer diameter is changed by adjusting which of the light sources 11 to 15 irradiates light as the first light source 5, but the present invention is not limited thereto. For example, as the first light source 5, a liquid crystal display capable of emitting light from all or part of the screen may be used, and in the liquid crystal display, the size of the illumination outer diameter may be changed by designating the light-emitting region.

[0043] In the above-described embodiment, the first image G1 used by the control unit 80 to identify the start point SP and the end point EP was an integrated luminance image, but it is not limited thereto. For example, the first image G1 used by the control unit 80 to identify the start point SP and the end point EP may be an image showing the luminance values at the respective positions of the object OB and the periphery SR as viewed from the side of the first light source 5 in a state where light is irradiated from the first light source 5 with an illumination outer diameter of a certain size. That is, the first image G1 is not an integrated luminance image, but is an image captured in a state where light is irradiated from the first light source 5 with an illumination outer diameter of a certain size, and may be an image that has not been processed using the data of other images.

[0044] In the above-described embodiment, the start point reference value SV is the difference between the baseline FL and the standard deviation σ F and the end point reference value EV is the sum of the baseline BL and the standard deviation σ B but it is not limited thereto. The start point reference value SV may be the baseline FL, or the end point reference value EV may be the baseline BL. Also, the start point reference value SV may be the average value of the luminance values of the constituent pixels that make up the surface SF (see FIG. 5) of the object OB shown in the first image G1, or the end point reference value EV may be a luminance value of 0.

[0045] In the above-described embodiment, after normalization, the luminance values of the respective pixels constituting the same position of the object OB in a plurality of images are converted to values within the range of 0 to 1, but it is not limited thereto. A numerical value different from 1 may be reassigned to the maximum value of the range of the luminance values after normalization, or a numerical value different from 0 may be reassigned to the minimum value. For example, after normalization, 100 may be reassigned to the maximum value and -100 may be reassigned to the minimum value. Also, the minimum value may be left at 0 and only 255 may be reassigned to the maximum value. That is, as long as the distribution of the luminance values of the respective pixels included in the range from the minimum value to the maximum value does not change compared to before normalization, any value may be reassigned to the maximum value and the minimum value.

[0046] In the above-described embodiment, the control unit 80 that functions as a specifying unit specified the magnitude of the sag SG, but the present invention is not limited to this. The control unit 80 that functions as a specifying unit may specify the presence or absence of a shape defect of the object OB and the magnitude of such a shape defect using the second image G2 in addition to the magnitude of the sag SG. For example, the control unit 80 refers to the second image G2 showing the contour of the object OB and a reference image showing the contour of the object OB without a shape defect in appearance, and compares the contour of the object OB shown in the second image G2 with the contour of the object OB shown in the reference image, whereby the presence or absence and the magnitude of the shape defect in the object OB shown in the second image G2 can be specified. When the control unit 80 functions in this way, it is possible to provide an appearance inspection apparatus that can simultaneously detect the magnitude of the sag SG and the shape defect of the object OB. Note that examples of the shape defect include, in addition to the burr BR, formation of a hole, dimensional differences between parts of the object OB, displacement of the relative positions of the respective parts of the object OB, and the like.

[0047] As described above, the present aspect has been described based on the embodiments and the modified examples. However, the embodiments of the above-described aspect are for facilitating the understanding of the present aspect and do not limit the present aspect. The present aspect can be changed and improved without departing from the spirit and scope of the claims, and equivalents thereof are included in the present aspect. Also, if the technical features are not described as essential in this specification, they can be deleted as appropriate.

Explanation of Reference Numerals

[0048] 1…Appearance inspection apparatus 5…First light source 10…Plate-like member 11~15…Light sources 20…Wall member 21~25…Wall parts 30…Diffusion member 40…Plano-convex lens 50…Half mirror 60…Second light source 62…Telecentric lens 70…Camera 72…Telecentric lens 80…Control Unit

Claims

1. An appearance inspection device for inspecting the appearance of an object, comprising: a first light source that irradiates light toward an arrangement position where the object is arranged; a second light source that faces the first light source and irradiates light from the side opposite to the first light source toward the arrangement position; an imaging unit that acquires a first image showing luminance values at each position of the object and its surroundings as viewed from the side of the first light source in a state where light is irradiated from the first light source, and a second image showing luminance values at each position of the object and its surroundings as viewed from the side of the first light source in a state where light is irradiated from the second light source; a specifying unit that specifies a foreground region in which the object appears and a background region in which the object does not appear in the first image using the second image, and then specifies a start point and an end point of sag on the surface of the object on the side irradiated with light by the first light source; The specifying unit searches for the luminance values of the constituent pixels that make up the first image in order from the side of the background region toward the side of the foreground region, specifies the position of the constituent pixel that first shows a luminance value equal to or greater than the start point reference value as the start point, searches for the luminance values of the constituent pixels in order from the side of the foreground region toward the side of the background region, specifies the position of the constituent pixel that first shows a luminance value equal to or less than the end point reference value as the end point, and then specifies the distance between the start point and the end point as the size of the sag. Appearance inspection device.

2. The appearance inspection device according to claim 1, The first light source can irradiate light toward the arrangement position with different illumination outer diameters, The first image used by the specifying unit when specifying the start point and the end point is created by using a plurality of the first images acquired by the imaging unit when light is irradiated from the first light source with different illumination outer diameters, calculating luminance integration values by integrating the luminance values of each pixel in each of the first images for each same position, and then arranging each of the luminance integration values corresponding to each position. It is a luminance integration image, The luminance integration value is a value calculated by normalizing the luminance values of each pixel in each of the images and then integrating the normalized luminance values for each same position. Appearance inspection device.

3. The appearance inspection device according to claim 1 or claim 2, The specifying unit specifies the presence or absence of a shape defect of the object and the size of the shape defect using the second image in addition to the size of the sag. Appearance inspection device.

Images