JP2018146365A - Image inspection device - Google Patents

Abstract

PROBLEM TO BE SOLVED: To obtain an image inspection device with which it is possible to perform abnormality inspection based on luminance and abnormality inspection based on height, for example, with greater convenience.SOLUTION: The image inspection device in an embodiment comprises, for example: a first captured image acquisition unit for acquiring a first two-dimensional captured image of a surface under inspection at each of a plurality of positions along a first direction of the surface under inspection; a second captured image acquisition unit for acquiring a second two-dimensional captured image of the surface under inspection that includes an image of bright line radiated upon the surface under inspection at each of the plurality of positions along the first direction of the surface under inspection; an inspection area determination unit for determining a unidimensional inspection area in the first captured image that corresponds to the second captured image on the basis of the position of bright line in each of the second captured images; and a first inspection image generation unit for generating a first two-dimensional inspection image derived by concatenating images of inspection area in each of the plurality of first captured images.SELECTED DRAWING: Figure 3

Description

  The present disclosure relates to an image inspection apparatus.

  2. Description of the Related Art Conventionally, there is known an image inspection apparatus that achieves both inspection using slit light and inspection using area light (for example, Patent Document 1).

JP 2003-214824 A

  In this type of image inspection apparatus, in order to achieve both inspection with slit light and inspection with area light, for example, a two-dimensional image to be inspected with area light includes a bright line based on slit light, making it difficult to inspect, etc. There were cases where problems occurred.

  Thus, one of the problems of the present disclosure is to obtain an image inspection apparatus capable of more conveniently combining, for example, an abnormality inspection based on luminance and an abnormality inspection based on height.

  In the image inspection apparatus according to the embodiment, for example, a first captured image acquisition unit that acquires a two-dimensional first captured image of the inspection target surface at each of a plurality of positions along the first direction of the inspection target surface; A second captured image acquisition unit that acquires a two-dimensional second captured image of the inspection target surface including images of bright lines irradiated on the inspection target surface at each of a plurality of positions along the first direction of the inspection target surface And an inspection area determining unit that determines a one-dimensional inspection area in the first captured image corresponding to the second captured image based on the position of the bright line in each of the second captured images, and each of the plurality of first captured images A first inspection image generation unit that generates a two-dimensional first inspection image obtained by joining the images in the inspection area.

FIG. 1 is an exemplary and schematic side view illustrating a schematic configuration of an inspection system according to an embodiment. FIG. 2 is an exemplary schematic diagram illustrating a captured image, a first captured image, and a second captured image acquired by the inspection system of the embodiment. FIG. 3 is an exemplary schematic block diagram illustrating a schematic configuration of the image inspection apparatus according to the embodiment. FIG. 4 is an exemplary and schematic explanatory view showing a second captured image obtained in the image inspection apparatus of the embodiment. FIG. 5 is an exemplary schematic illustration of a line pseudo image generated from the second photographed image of FIG. FIG. 6 is an exemplary schematic diagram illustrating a first captured image obtained in the image inspection apparatus according to the embodiment. FIG. 7 is an exemplary schematic illustration of a line luminance image generated from the first captured image of FIG. FIG. 8 is an exemplary schematic illustration showing the angle between the light sheet or virtual light sheet and the photographing direction at each position of the inspection system of the embodiment. FIG. 9 is an exemplary schematic diagram illustrating the height and the deviation from the reference position in the layout of FIG. 1 of the inspection system of the embodiment.

  Hereinafter, exemplary embodiments and modifications of the present invention will be disclosed. The configurations and controls of the embodiments and modifications shown below, and the operations and results (effects) brought about by the configurations and controls are examples. The present invention can also be realized by other than the configurations and controls disclosed in the following embodiments and modifications. Further, the present invention can obtain various effects including derivative effects obtained by basic configuration and control.

  FIG. 1 is a configuration diagram of the inspection system 1. In the figure, direction X is the main scanning direction, direction Y is the sub-scanning direction, direction Z is the height direction, and direction M is the moving direction (conveying direction).

  As shown in FIG. 1, the inspection system 1 includes an area light source 10, a sheet light source 20, and an area sensor 30. The inspection system 1 performs an appearance inspection of the surface 2a of the inspection object 2 based on the image captured by the area sensor 30. The surface 2a can also be referred to as an inspection target surface. The captured image can also be referred to as a camera image, a sensor image, a base image, or the like.

  The inspection object 2 is transported in the direction M by a transport mechanism (not shown) so that the imaging position of the surface 2a by the area sensor 30 changes with time. The area sensor 30 acquires captured images at different positions on the surface 2a at a plurality of times at intervals.

  In this embodiment, the inspection object 2 moves, but the inspection system 1 (the area light source 10, the sheet light source 20, and the area sensor 30) may move, or the inspection object 2 and the inspection system 1 Both may move. The relative movement direction (direction M) between the inspection system 1 and the inspection object 2 (surface 2a) is not limited to a direction along a straight line, and may be a direction along a curve.

  In the inspection system 1, the position of the inspection object 2 or the transport mechanism, the speed, the photographing time of the area sensor 30, and the like are controlled so that the predetermined position of the surface 2 a is photographed by the area sensor 30.

  Area light emitted from the area light source 10 is applied to a predetermined range (position P1) of the surface 2a of the inspection object 2. The light from the area light source 10 may be directly irradiated on the surface 2a or may be irradiated through an optical system component.

  Further, the light sheet LS (for example, a laser light sheet) based on the light emitted from the sheet light source 20 is in a range (position P2) different from the range irradiated with the light from the area light source 10 on the surface 2a. , Irradiated. The light sheet LS is literally sheet-like light, and spreads along the direction X and the direction Z (XZ plane) in the example of FIG. The position P2 is away from the position P1 in the direction M. The light sheet LS may be irradiated directly from the sheet light source 20 to the surface 2a, or may be irradiated through another optical system component.

  The area sensor 30 includes, for example, a CMOS or a CCD, and acquires a two-dimensional captured image of the surface 2a. The two-dimensional captured image includes an image of the light irradiation range from the area light source 10 and an image of the light irradiation range from the sheet light source 20.

  FIG. 2 is an explanatory diagram illustrating the captured image Imc, the first captured image Ima, and the second captured image Imb acquired by the inspection system 1. In the figure, the direction n is the number of times of shooting, and the direction t is time (time). The direction X is the main scanning direction, and the direction Y is the sub-scanning direction. The direction X and the direction Y are directions of the real coordinate system in the inspection system 1 and are not directions in the image.

  As shown in FIG. 2, the area sensor 30 acquires a plurality of captured images Imc at different times. The area sensor 30 acquires the captured image Imc1 at the number n = 1 (time t = δt × 1, δt is a time interval), and thereafter the number n = i (time t = δt × i, i is an integer). ), A captured image Imci (i = 1, 2,...) Is acquired. Note that the shooting time interval need not be constant.

  Of the photographed image Imc, the first photographed image Ima for luminance inspection is included behind the direction Y (in front of the direction M). The first captured image Ima is included in the light irradiation range from the area light source 10.

  Further, in the captured image Imc, the second captured image Imb for light section inspection is included in front of the direction Y (backward in the direction M). The second captured image Imb includes an irradiation range of light from the sheet light source 20.

  Specifically, the photographed image Imc1 includes an area of the first photographed image Ima1 having the position y = 1 in the direction Y as a reference position, and an area of the second photographed image Imb301 having the position y = 301 in the direction Y as the reference position. And are included. The reference position of the surface 2a is, for example, the center position in the direction Y of each image. Thereafter, the photographed image Imci acquired at the number n = i (time t = δt × i) includes a first photographed image Imai with the position in the direction Y = i as a reference position, and a position in the direction Y = i + 300 ( a second photographed image Imbj having j as an integer) as a reference position is included. As apparent from FIG. 2, the reference position of the first captured image Imai and the reference position of the second captured image Imbj are 300 × s apart in the direction Y. Here, s is a unit length in the direction Y, that is, a length per one y coordinate, for example, a length corresponding to one pixel. The reference position is an example of a reference line. The position y = i is an example of the first position, and the position y = j is an example of the second position.

  As is clear from FIG. 2, the first captured image Ima301 at the position y = 301 is included in the captured image Imc301, while the second captured image Imb301 at the position y = 301 is included in the captured image Imc1. Similarly, the first captured image Ima302 at the position y = 302 is included in the captured image Imc302, while the second captured image Imb302 at the position y = 302 is included in the captured image Imc2 and the first captured image at the position y = 303. The image Ima303 is included in the captured image Imc303, while the second captured image Imb303 at the position y = 303 is included in the captured image Imc3. As described above, the first captured image Ima and the second captured image Imb captured at the same position on the surface 2a are included in the captured image Imc acquired at different times t (time steps). The specifications such as the number of pixels of the captured image Imc, the first captured image Ima, the second captured image Imb, and the length (number of pixels) between the reference positions of the first captured image Ima and the second captured image Imb are as follows. However, the present invention is not limited to this example.

  FIG. 3 is a block diagram illustrating a schematic configuration of the image inspection apparatus 100. The image inspection apparatus 100 performs the luminance inspection of the surface 2a based on the first captured image Ima acquired from the captured image Imc, and also uses the light cutting method to detect the surface 2a based on the second captured image Imb acquired from the captured image Imc. Perform height inspection (unevenness inspection).

  As shown in FIG. 3, the image inspection apparatus 100 includes an arithmetic processing unit 110, a main storage unit 120, a data storage unit 130, and the like. The arithmetic processing unit 110 is, for example, a central processing unit (CPU) or a controller, and the main storage unit 120 is, for example, a read only memory (ROM), a random access memory (RAM), or the like. Is, for example, a hard disk drive (HDD), a solid state drive (SSD), a flash memory, or the like. The data storage unit 130 is an example of an auxiliary storage device. The data storage unit 130 is an example of a database.

  The arithmetic processing and control by the arithmetic processing unit 110 may be executed by software, or may be executed by hardware. The arithmetic processing and control by the arithmetic processing unit 110 may include arithmetic processing and control by software and arithmetic processing and control by hardware. In the case of processing by software, the arithmetic processing unit 110 reads and executes a program (application) stored in a ROM, HDD, SSD, flash memory, or the like. The arithmetic processing unit 110 operates in accordance with the program, so that each unit included in the arithmetic processing unit 110, that is, the image data acquisition unit 111, the position data acquisition unit 112, the luminance inspection unit 113, the light section inspection unit 114, the image It functions as the output control unit 115 or the like. In this case, the program includes modules corresponding to the above-described units.

  The program can be provided by being recorded in a computer-readable recording medium such as a CD-ROM, an FD, a CD-R, a DVD, or a USB memory as a file in an installable or executable format. The program can be introduced by being stored in a storage unit of a computer connected to a communication network and downloaded via the network. Further, the program may be incorporated in advance in a ROM or the like.

  Further, when all or part of the arithmetic processing unit 110 is configured by hardware, the arithmetic processing unit 110 may include, for example, an FPGA, an ASIC, or the like.

  The image data acquisition unit 111 acquires a two-dimensional captured image Imc acquired at each time from the area sensor 30.

  The position data acquisition unit 112 acquires the position in the direction Y of each captured image Imc. The position is, for example, a detection result by an encoder provided in the transport mechanism, information obtained by image processing from the captured image Imc, or the like, but is not limited thereto.

  Note that the plurality of captured images Imc acquired at different shooting times acquired by the image data acquisition unit 111 may be stored in the data storage unit 130 in a state in which the association with the position acquired by the position data acquisition unit 112 is known. Good.

  The light section inspection unit 114 performs the height inspection (unevenness inspection) of the surface 2a by the light section method based on the second photographed image Imb. The light section inspection unit 114 includes a second image acquisition unit 114a, a line pseudo image generation unit 114b, a two-dimensional pseudo image generation unit 114c, a height abnormality detection unit 114d, and the like.

  The second image acquisition unit 114a acquires the second captured image Imb from the captured image Imc. In addition, the line pseudo image generation unit 114b generates a line pseudo image based on the second captured image Imb. The second image acquisition unit 114a is an example of a second captured image acquisition unit.

  FIG. 4 is an explanatory diagram showing the second photographed image Imb. As shown in FIG. 4, the second captured image Imb includes an image of the bright line BL based on the light emitted from the sheet light source 20. In the light cutting method, as shown in FIG. 1, there is an angle difference between the imaging angle of the surface 2a by the area sensor 30 and the irradiation angle to the surface 2a of the light sheet LS based on the light emitted from the sheet light source 20. Since it is set, the position in the direction Y of the bright line BL changes according to the height (unevenness) of the surface 2a. In addition, in the example of FIG. 1, although the light sheet LS is irradiated at substantially right angle with respect to the surface 2a, it is not limited to this example. In addition, the bright line BL may spread over a plurality of pixels in the direction Y in some cases. In such a case, the position of the bright line BL can be calculated by, for example, a weighted average of a plurality of luminance values in the width direction of the bright line BL. Further, the number of pixels in the direction X and the direction Y of the second photographed image Imb is not limited to the example of FIG.

  FIG. 4 shows an example of the second captured image Imb 301 at a position y = 301 in the direction Y. In this case, the position y = 301 is the reference position (reference line), and at each position of x = 1 to 20 in the direction X, the bright line BL is at the position y = at the position where the height of the surface 2a is the reference height. 301. Further, at a position where the height of the surface 2a is higher than the reference height, the bright line BL is further away from the position y = 301 toward the rear in the direction Y (upward in FIG. 4), and the height of the surface 2a is the reference. At a position lower than the height, the bright line BL moves away from the position y = 301 in the direction Y (downward in FIG. 4) as the height is lower.

  Specifically, in the section A1 of the position x = 1 to 3 and 17 to 20 in the direction X, since the bright line BL is located at the position y = 301 (reference position), the height of the surface 2a is the reference height. is there. In the section A2 of the position x = 4, 5, 15, 16 in the direction X, since the bright line BL is located at the position y = 300, the height of the surface 2a is higher than the height (reference height) in the section A1. Is also expensive. In the section A3 of the position x = 6 to 8, 13, 14 in the direction X, the bright line BL is located at the position y = 299, and therefore the height of the surface 2a is higher than the height in the section A2. In the section A4 with the position x = 9 to 12 in the direction X, the bright line BL is located at the position y = 298, and therefore the height of the surface 2a is higher than the height in the section A3. That is, in the example of FIG. 4, the surface 2a has a shape in which the central portion in the direction X protrudes gently.

  The line pseudo image generation unit 114b generates a one-dimensional pseudo image at the reference position in the direction Y (y = 301 in the example of FIG. 4). The line pseudo image Imbl is a linear one-dimensional image corresponding to the reference position in the direction Y of the second captured image Imb. The pixel at each position in the direction X of the line pseudo image Imbl has a luminance value corresponding to the height at each position. The luminance value of each pixel is set higher as the height of the surface 2a is higher, and is set lower as the height of the surface 2a is lower. As described above, the height of the surface 2a at each position corresponds to the deviation from the reference position (reference line) in the direction Y of the bright line BL in the second photographed image Imb. Therefore, the line pseudo image generation unit 114b generates the line pseudo image Imbl by giving each pixel a luminance value corresponding to the deviation of the bright line BL from the reference position at each position. The line pseudo image Imbl is an example of a pseudo image, and the line pseudo image generation unit 114b is an example of a pseudo image generation unit. The line pseudo image Imbl can also be referred to as a one-dimensional pseudo image.

  FIG. 5 is an explanatory diagram of a line pseudo image Imbl generated from the second captured image Imb of FIG. As shown in FIG. 5, in the line pseudo image Imbl301 corresponding to the bright line BL in FIG. 4, a higher luminance value is given as the height of the surface 2 a is higher at each position x = 1 to 20 in the direction X. That is, the brightness value at each position (pixel, x = 9 to 12) in the section A4 is the highest, and the brightness value at each position (x = 6 to 8, 13, 14) in the section A3 is higher than the brightness value in the section A4. The brightness value at each position (x = 4, 5, 15, 16) in the section A2 is lower than the brightness value in the section A3, and the brightness value at each position (x = 1-3, 17-20) in the section A1. Is set lower than the luminance value of the section A2. Thereby, as shown in FIG. 5, a line pseudo image Imbl having a higher luminance value at a higher height is obtained.

  The two-dimensional pseudo image generation unit 114c combines a plurality of one-dimensional line pseudo images Imbl along the direction X acquired for each position (reference position) in the direction Y to generate a two-dimensional pseudo image. Is generated. The two-dimensional pseudo image is an example of a second inspection image, and the two-dimensional pseudo image generation unit 114c is an example of a second inspection image generation unit. The two-dimensional pseudo image can also be referred to as a height image, a three-dimensional image, an uneven image, or the like.

  The height abnormality detection unit 114d detects an abnormality in the height of the surface 2a based on the two-dimensional pseudo image. The height abnormality detection unit 114d, for example, if the area where the luminance value of the pseudo image is not within a predetermined range, that is, the area where the height of the surface 2a is not within the predetermined range is greater than or equal to a threshold value, An area is detected as a height abnormality (unevenness abnormality). The height abnormality detection unit 114d can also be referred to as a first abnormality detection unit.

  The luminance inspection unit 113 performs a luminance inspection of the surface 2a based on the first captured image Ima. The luminance inspection unit 113 includes a first image acquisition unit 113a, an inspection region determination unit 113b, a two-dimensional luminance image generation unit 113c, a luminance abnormality detection unit 113d, and the like.

  The first image acquisition unit 113a acquires the first captured image Ima from the captured image Imc. Further, the inspection area determination unit 113b determines the inspection area in the first captured image Ima based on the bright line BL included in the second captured image Imb at the same reference position. The first image acquisition unit 113a is an example of a first captured image acquisition unit.

  FIG. 6 is an explanatory diagram illustrating the first captured image Ima, and FIG. 7 is an explanatory diagram illustrating generation of the line luminance image Imal based on the first captured image Ima. FIG. 6 shows an example of the first captured image Ima301 at the position y = 301. Although not shown in FIG. 6, each pixel of the first captured image Ima301 has a luminance value. Further, the number of pixels in the direction X and the direction Y of the first captured image Ima is not limited to the example of FIG.

  As shown in FIG. 6, the examination region determination unit 113b is included in the first captured image Ima301 at the position y = 301 (reference position) and in the second captured image Imb301 at the same position y = 301 (reference position). Apply the bright line BL. Then, as illustrated in FIG. 7, the inspection region determination unit 113b extracts pixels at positions overlapping with the bright line BL, and arranges them in a line to generate a line luminance image Imal. As is apparent from FIG. 7, the inspection area determination unit 113b has a position (y = 298) different from the position y = 301 in the direction Y on the bright line BL according to the shape of the bright line BL in the second captured image Imb301. ˜300) is treated as the pixel at position y = 301. As can be seen from FIGS. 1 and 4, the position of the bright line BL in the first photographed image Ima301 and the second photographed image Imb301 indicates the position where the light sheet LS hits on the surface 2a. The position of the bright line BL in the first photographed image Ima301 in FIG. 6 is an example of a one-dimensional inspection region.

  The two-dimensional luminance image generation unit 113c combines a plurality of one-dimensional line luminance images Imal along the direction X acquired for each position (reference position) in the direction Y into the two-dimensional luminance image. Is generated. The two-dimensional luminance image is an example of a first inspection image, and the two-dimensional luminance image generation unit 113c is an example of a first inspection image generation unit. The line luminance image Imal can also be referred to as a one-dimensional luminance image.

  The luminance abnormality detection unit 113d detects abnormality of the surface 2a based on the two-dimensional luminance image. The luminance abnormality detection unit 113d, for example, detects the region as a luminance abnormality when the size of the region where the luminance value of the luminance image is not within a predetermined range is equal to or greater than a threshold value.

  As described above, in the present embodiment, the inspection region determination unit 113b determines the pixel (position) of the first captured image Ima to be subjected to the luminance inspection based on the position of the bright line BL. As described above, the position of the bright line BL in the first photographed image Ima301 and the second photographed image Imb301 indicates the position where the light sheet LS hits on the surface 2a. According to such a configuration, for example, since a luminance image when the area sensor 30 is virtually installed in the irradiation direction of the light sheet LS can be obtained, the area light source 10 in the inspection system 1, the sheet light source 20, There is an advantage that the degree of freedom of layout of the area sensor 30 and the like is increased.

  Further, in the present embodiment, the image inspection apparatus 100 includes a two-dimensional luminance image generation unit 113c (first inspection image generation unit) that generates a two-dimensional luminance image based on the bright line BL, and two images based on the bright line BL. A two-dimensional pseudo image generation unit 114c (second inspection image generation unit) that generates a two-dimensional pseudo image is provided. Therefore, according to the present embodiment, both the luminance inspection by the luminance inspection unit 113 and the light cutting inspection by the light cutting inspection unit 114 can be performed.

  In this case, according to the present embodiment, the position of the surface 2a in the direction Y in which the luminance inspection is performed by the luminance inspection unit 113 and the position of the surface 2a in the direction Y in which the height inspection is performed by the light cutting inspection unit 114 are more Positioning can be performed with high accuracy. Therefore, according to the present embodiment, for example, when performing abnormality determination based on two abnormality detection results based on luminance and height, there is an advantage that the positional accuracy is improved and abnormality can be determined with higher accuracy.

(Modification)
When the inspection area determination unit 113b determines the inspection area in the first photographed image Ima for a predetermined position on the surface 2a, for example, the position y = 301, it is obtained in the layout of the optical system and the second photographed image Imb. Based on the bright line BL, when a virtual light sheet VLS (FIG. 1) parallel to the light sheet LS is irradiated to the imaging position (position P1) of the first captured image Ima, a virtual generated in the first captured image Ima. Bright lines (not shown) may be estimated. The layout of the optical system includes, for example, the position of the area sensor 30, the shooting direction by the area sensor 30, the irradiation direction of the light sheet LS on the surface 2a, and the shooting position of the first shot image Ima (position P1, first shooting position). ), The shooting position (position P2, second shooting position) of the second shot image Imb, and the like.

  The inspection area is preferably a position where the virtual light sheet VLS parallel to the light sheet LS hits in the first captured image Ima, but if the distance between the position P1 and the position P2 becomes too large, the second imaging is performed. There is a possibility that the difference between the position of the bright line BL generated by the light sheet LS in the image Imb and the position of the virtual bright line (not shown) generated by the virtual light sheet VLS in the first captured image Ima may increase. In such a case, the inspection area determination unit 113b estimates the virtual bright line based on the geometric layout of the optical system, and determines the inspection area in the first captured image Ima based on the virtual bright line. can do.

  8 is an explanatory diagram showing an angle θ1 between the virtual light sheet VLS and the photographing direction at the position P1 of the inspection system 1 and an angle θ2 between the light sheet LS and the photographing direction at the position P2 in the layout of FIG. . FIG. 9 is an explanatory diagram showing heights Hb1 and Hb2 and deviations Db1 and Db2 from the reference positions (reference lines LP1 and LP2) in the layout of FIG. 1 (FIG. 8).

For example, as shown in FIG. 9, the deviation Db2 from the reference position (reference line) LP2 at the position P2 of the bright line BL in the second photographed image Imb at the position P2 of the inspection system 1 and the position pd of the surface 2a. The relationship with the height Hb2 along the irradiation direction of the light sheet LS is expressed by the following formula (1) by a known light cutting method.
Hb2 = F2 (Db2) (1)
Here, F2 (Db2) is an angle θ2 (for example, on the surface 2a) between the irradiation direction to the surface 2a of the light sheet LS and the photographing direction by the area sensor 30 when viewed from the main scanning direction at the position P2. It is a function determined according to (angle). Equation (1) means that the height Hb2 is a function of the deviation Db2. In this case, the height Hb2 increases as the deviation Db2 increases.

Similarly, the deviation Db1 from the reference position (reference line) LP1 of the position P2 of the virtual bright line in the first photographed image Ima at the position P1 of the inspection system and the irradiation direction of the virtual light sheet VLS at the position pd of the surface 2a. The relationship with the height Hb1 is expressed by the following formula (2) by a known light cutting method.
Hb1 = F1 (Db1) (2)
Here, F1 (Db1) is an angle θ1 (for example, on the surface 2a) between the irradiation direction to the surface 2a of the virtual light sheet VLS and the photographing direction by the area sensor 30 when viewed from the main scanning direction at the position P1. It is a function that is determined according to the angle. Equation (2) means that the height Hb1 is a function of the deviation Db1. In this case, the greater the deviation Db1, the greater the height Hb1.

Expression (2) can be rewritten as the following expression (3).
Db1 = Fi1 (Hb1) (3)
Here, Fi1 (Hb1) is an inverse function of F1 (Db1).

Here, the virtual light sheet VLS is parallel to the light sheet LS. Therefore, as shown in FIG. 9, for the same position pd on the surface 2a, the height Hb1 along the virtual light sheet VLS and the height Hb2 along the light sheet LS are the same. Therefore, the deviation Db1 is obtained from the following equation (4) from the equations (1) and (3).
Db1 = Fi1 (F2 (Db2)) (4)
As an example, in the layout of FIG. 1 (FIG. 8), as shown in FIG. 9, the absolute value of the deviation Db1 is larger than the deviation Db2. In this case, in FIG. 6, a virtual bright line (not shown) is a line farther from the reference position than the bright line BL. Note that such estimation of the virtual bright line can be similarly applied to cases other than the layout as shown in FIG. In addition, it is possible to consider the difference in deviation in the main scanning direction between the position P1 and the position P2 by the function.

  According to this modification, for example, when performing abnormality determination based on two abnormality detection results based on luminance and height, there is an advantage that the position accuracy is further improved and abnormality can be determined with higher accuracy.

  As mentioned above, although embodiment of this invention was illustrated, the said embodiment is an example to the last. The embodiment can be implemented in various other forms, and various omissions, replacements, combinations, and changes can be made without departing from the scope of the invention. In addition, the configuration and shape of the embodiment can be partially replaced with other configurations and shapes. In addition, specifications (structure, type, direction, angle, shape, size, length, width, thickness, height, number, arrangement, position, material, etc.) of each configuration, shape, etc. are changed as appropriate. Can be implemented.

  For example, the light section inspection unit 114 does not generate the line pseudo image Imbl for the second captured image Imb once stored in the data storage unit 130, but the second captured image Imb obtained from the image data acquisition unit 111. The line pseudo image Imbl may be generated at any time. Further, in that case, every time the line pseudo image Imbl of the surface 2a is obtained, the luminance inspection unit 113 acquires the first captured image Ima for the position where the line pseudo image Imbl was obtained from the data storage unit 130, A line luminance image Imal may be generated.

  2a ... surface (surface to be inspected), 30 ... area sensor, 100 ... image inspection apparatus, 113a ... first image acquisition unit (first captured image acquisition unit), 113b ... inspection area determination unit, 113c ... two-dimensional luminance image generation Part (first inspection image generation part), 114a ... second image acquisition part (second photographed image acquisition part), 114b ... line pseudo image generation part (pseudo image generation part), 114c ... two-dimensional pseudo image generation part (first Two inspection image generation unit), BL ... bright line, Ima ... first captured image, Imb ... second captured image, Imbl ... line pseudo image (pseudo image), Imc ... captured image, P1 ... position (first captured position), P2 position (second photographing position).

Claims (4)

A first captured image acquisition unit that acquires a two-dimensional first captured image of the inspection target surface at each of a plurality of positions along the first direction of the inspection target surface;
A second captured image that acquires a two-dimensional second captured image of the inspection target surface including images of bright lines irradiated on the inspection target surface at each of a plurality of positions along the first direction of the inspection target surface. An acquisition unit;
An inspection region determination unit that determines a one-dimensional inspection region in the first captured image corresponding to the second captured image based on the position of the bright line in each of the second captured images;
A first inspection image generation unit that generates a two-dimensional first inspection image obtained by joining images in the inspection region in each of a plurality of first captured images;
An image inspection apparatus comprising: A pseudo image generation unit that generates a one-dimensional pseudo image that gives a luminance value according to a deviation from a reference line of the position of the bright line in each of the second captured images;
A second inspection image generation unit that generates a two-dimensional second inspection image obtained by joining the pseudo images;
The image inspection apparatus according to claim 1, comprising:   The first captured image at the first position of the inspection target surface and the second captured image at a second position different from the first position of the inspection target surface are among the captured images obtained by one area sensor. The image inspection apparatus according to claim 1, wherein the image is an image of two regions separated in the first direction. The first captured image at the first position of the inspection target surface is captured at the first imaging position by the one area sensor, and the second captured image at the first position of the inspection target surface is , Shot at a second shooting position different from the first shooting position,
The inspection area determination unit generates the bright line at the first photographing position from the bright line included in the second photographed image photographed at the second photographing position with respect to the first position of the inspection target surface. 4. A virtual bright line generated in the first captured image when virtual light parallel to the light is irradiated is estimated, and a one-dimensional inspection region in the first captured image is determined based on the virtual bright line. The image inspection apparatus according to 1.

Images