Inspection device

Abstract

To provide an inspection device capable of performing various inspections of an object to be measured quickly and accurately.SOLUTION: An inspection device comprises: a camera unit including illumination for illuminating an object to be measured and a spectral scanning type spectroscopic camera for imaging the object to be measured; a movable mechanism that changes a positional relationship between the object to be measured and the camera unit; and an inspection unit that performs inspection of the object to be measured on the basis of an image captured and acquired by the camera unit. The inspection device has a single-wavelength imaging mode for imaging the object to be measured at a single wavelength and a multi-wavelength imaging mode for imaging the object to be measured at multiple wavelengths. While switching between the single-wavelength imaging mode and the multi-wavelength imaging mode and changing the positional relationship between the object to be measured and the camera unit by means of the movable mechanism, the camera unit images a predetermined portion of the object to be measured.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to an inspection device. [Background technology]

[0002] Automating the final visual inspection of products with housings larger than a certain size is being considered. When inspecting for scratches and color, it is difficult to judge the entire product from a single image.

[0003] As an inspection device for inspecting an object to be measured, Patent Document 1 discloses an imaging system for inspection that has a monochrome camera and a robot arm or automatic stage that changes the positional relationship between the camera and the object to be measured. This imaging system takes multiple images of the object to be measured with the camera while changing the positional relationship between the camera and the object to be measured, and then performs image processing on the captured images to inspect the appearance of the entire object to be measured.

[0004] Furthermore, as an inspection device, Patent Document 2 discloses an image inspection device having a robot arm and a line-scan multispectral camera attached to the tip of the robot arm. In this image inspection device, the multispectral camera is attached to the tip of the robot arm, so that color inspection and spectroscopic inspection of the object to be measured can be performed with high accuracy over a wide range. [Prior art documents] [Patent documents]

[0005] [Patent Document 1] Japanese Patent Application Publication No. 2023-44764 [Patent Document 2] WO2020 / 152866 Summary of the Invention [Problem to be solved by the invention]

[0006] In the imaging system described in Patent Document 1, an image is acquired by photographing an object to be measured using a camera at a single wavelength, so it is not possible to inspect the color of the object to be measured or calibrate the components with high accuracy.

[0007] Furthermore, the image inspection device described in Patent Document 2 uses a multispectral camera to capture images of the object to be measured at multiple wavelengths, which means that it takes a long time to capture the image of the object to be measured and the amount of image data to be captured is enormous, which means that inspection takes a long time. [Means for solving the problem]

[0008] The inspection device of the present invention includes a camera unit having an illumination device for illuminating an object to be measured and a spectral scanning type spectroscopic camera for photographing the object to be measured; a movable mechanism for changing the positional relationship between the object to be measured and the camera unit; an inspection unit that inspects the object to be measured based on an image captured by the camera unit, a single wavelength imaging mode in which the object to be measured is imaged at a single wavelength; a multiple wavelength imaging mode for imaging the object to be measured at multiple wavelengths, The present invention is characterized in that a predetermined portion of the object to be measured is photographed by the camera unit while switching between the single wavelength photographing mode and the multiple wavelength photographing mode and changing the positional relationship between the object to be measured and the camera unit by the movable mechanism. [Brief explanation of the drawings]

[0009] [Figure 1] 1 is a perspective view showing an embodiment of an inspection device of the present invention, and includes a block diagram in part. [Figure 2] FIG. 2 is a block diagram of the inspection device shown in FIG. [Figure 3] 2 is a flowchart for explaining the operation of the inspection device shown in FIG. [Figure 4] 2 is a flowchart for explaining the operation of the inspection device shown in FIG. [Figure 5]FIG. 10 is a block diagram of an inspection device according to a second embodiment. [Figure 6] 6 is a flowchart for explaining the operation of the inspection device shown in FIG. 5. [Figure 7] FIG. 10 is a block diagram of an inspection device according to a third embodiment. [Figure 8] 8 is a flowchart for explaining the operation of the inspection device shown in FIG. 7. [Figure 9] FIG. 10 is a block diagram of an inspection device according to a fourth embodiment. [Figure 10] 10 is a flowchart for explaining the operation of the inspection device shown in FIG. [Figure 11] FIG. 10 is a block diagram of an inspection device according to a fifth embodiment. [Figure 12] 12 is a flowchart for explaining the operation of the inspection device shown in FIG. [Figure 13] FIG. 10 is a block diagram of an inspection device according to a sixth embodiment. [Figure 14] 14 is a flowchart for explaining the operation of the inspection device shown in FIG. [Figure 15] FIG. 13 is a block diagram of an inspection device according to a seventh embodiment. [Figure 16] 16 is a flowchart for explaining the operation of the inspection device shown in FIG. DETAILED DESCRIPTION OF THE INVENTION

[0010] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS An inspection device according to the present invention will be described in detail below with reference to the embodiments shown in the accompanying drawings. First Embodiment Fig. 1 is a perspective view showing an embodiment of an inspection device of the present invention, and part of the view includes a block diagram. Fig. 2 is a block diagram of the inspection device shown in Fig. 1. Figs. 3 and 4 are flow charts for explaining the operation of the inspection device shown in Fig. 1.

[0011] As shown in Figure 1, the X-axis, Y-axis, and Z-axis are shown as three mutually orthogonal axes. The tip end of the arrow indicating each axis is designated as "+: positive" and the base end is designated as "-: negative."

[0012] The inspection device 1 shown in Fig. 1 is a device that inspects a measured object W, which is an object to be inspected, and in particular inspects the appearance of the measured object W. Note that the inspection device 1 also includes devices that inspect things other than the appearance of the measured object W. The measured object W is not particularly limited, and examples include various products and various parts, and Fig. 1 shows a printer as an example.

[0013] As shown in Figures 1 and 2, the inspection device 1 has a camera unit 2 that photographs the object to be measured W, a movable mechanism 3 that changes the positional relationship between the object to be measured W and the camera unit 2, and an inspection device main body 10 that inspects the object to be measured W.

[0014] Furthermore, the inspection device main body 10 is communicatively connected to the camera unit 2 and the movable mechanism 3. The inspection device main body 10, the camera unit 2, and the movable mechanism 3 may be communicatively connected in a wired manner using a cable or the like, for example, or may be communicatively connected in a wireless manner.

[0015] The inspection device main body 10 also has an inspection unit 4 that inspects the object to be measured W, an image processing unit 5 that performs image processing on the image, a control unit 6 that controls the driving of the inspection device 1, a memory unit 7 that stores various information and various programs, a display unit 12 that displays various information, and an operation unit 13 that is an input unit for various instructions and various inputs. Note that the concept of photographing also includes capturing images.

[0016] The movable mechanism 3 also includes a robot 31 and an automatic stage 32. In this embodiment, the robot 31 is a device that supports the camera unit 2 and displaces, i.e., moves, the camera unit 2. In this embodiment, the automatic stage 32 is a device that supports the object W to be measured and displaces, i.e., moves, the object W to be measured. When changing the positional relationship between the object W to be measured and the camera unit 2, either or both of the robot 31 and the automatic stage 32 are driven.

[0017] In this embodiment, the robot 31 is a single-arm, vertically articulated robot having a robot arm 312 that supports the object W to be measured and a control device 311 that controls the driving of the robot 31, including the robot arm 312. This robot 31 can move the camera unit 2 to a desired position and can also set the attitude of the camera unit 2 to a desired attitude.

[0018] The robot 31 is not limited to this, and examples thereof include a Cartesian coordinate type, a cylindrical coordinate type, a polar coordinate type, a parallel articulated type, and a parallel link type. The robot 31 may also be, for example, a legged walking robot with legs, or a robot with multiple arms such as a dual-arm robot.

[0019] In this embodiment, the automatic stage 32 is a device that has a support part 321 that supports the workpiece W, and moves the support part 321 in the X-axis direction, the Y-axis direction, and the Z-axis direction, and rotates it about the X-axis, the Y-axis, and the Z-axis. The automatic stage 32 can move the workpiece W to a desired position, and can also set the posture of the workpiece W to a desired posture.

[0020] The automatic stage 32 is not limited to this, but may be, for example, a stage that moves in at least one of the X-axis, Y-axis, and Z-axis directions, a stage that rotates around at least one of the X-axis, Y-axis, and Z-axis, a goniostage, or a stage that combines two or more of these.

[0021] Furthermore, in this embodiment, the movable mechanism 3 is configured to be able to move both the camera unit 2 and the object to be measured W, but the movable mechanism 3 is not limited to this, and for example, either the robot 31 or the automatic stage 32 may be omitted.

[0022] Furthermore, the device that moves the camera unit 2 is not limited to the robot 31, but may be another device such as an automatic stage. Furthermore, the device that moves the object to be measured W is not limited to the automatic stage 32, but may be another device such as a robot. Furthermore, the movable mechanism 3 may be a device having multiple robot arms, such as a dual-arm robot, in which case one robot arm supports the camera unit 2, and the other robot arm supports the object to be measured W.

[0023] The camera unit 2 also has an illumination 21 that illuminates the object W to be measured, and a spectral camera 22 that photographs the object W to be measured using a spectral scanning method.

[0024] Furthermore, the spectroscopic camera 22 can capture images of the object W at multiple wavelengths, i.e., multiple wavelengths. That is, spectroscopic measurement can be performed. In this case, the spectroscopic camera 22 first sets the wavelength to one predetermined wavelength and captures an image of the object W. Next, the spectroscopic camera 22 changes the wavelength to another wavelength and captures an image of the object W. This operation is performed for all of the multiple wavelengths captured by the spectroscopic camera 22.

[0025] Furthermore, the spectroscopic camera 22 can capture an image of the object W to be measured using a single wavelength, that is, one wavelength.

[0026] The lighting 21 is not particularly limited as long as it can irradiate the object W with illumination light, and examples thereof include ring lighting, dome lighting, coaxial epi-illumination, and bar lighting.

[0027] The light source for the illumination 21 is not particularly limited, but it is preferable to use a light source that has a wide emission wavelength band and a gentle emission intensity relative to the wavelength resolution of the spectroscopic camera 22. Specific examples of the light source include an LED light source such as a white LED light source, and a halogen light source such as a halogen lamp with a diffusion / light guide unit. The light source may be a single item, or a light source unit that combines multiple types of light.

[0028] Furthermore, in the case where it is possible to perform fluorescence measurement of the object W to be measured, it is preferable that the light source of the illumination 21 includes a light source with a high emission intensity of excitation light, i.e., a light source with a high output of the excitation wavelength, for example, in order to capture and acquire the fluorescence using the spectroscopic camera 22 so as to have a high S / N ratio.

[0029] The inspection device 1 also has a single wavelength imaging mode for imaging the object W to be measured at a single wavelength, and a multiple wavelength imaging mode for imaging the object W to be measured at multiple wavelengths, as imaging modes for imaging the object W to be measured, i.e., modes for imaging the object W to be measured and acquiring an image. The inspection device 1 sets an appropriate imaging mode from the single wavelength imaging mode or the multiple wavelength imaging mode for each imaging session using the camera unit 2.

[0030] In the single wavelength imaging mode, one wavelength is selected from among a plurality of wavelengths that can be captured by the spectroscopic camera 22, and an image of the object to be measured W is acquired at the single wavelength. This image acquisition means acquiring image data. The wavelength selected may be changed for each image capture, or may not be changed, i.e., may be constant.

[0031] In this single wavelength imaging mode, inspections that can be processed using brightness information and two-dimensional image processing are performed, such as determining whether there are scratches, foreign matter, or a part of the object to be measured W. Note that inspections other than these may also be performed.

[0032] In the multiple wavelength imaging mode, two or more wavelengths are selected from among the multiple wavelengths that can be captured by the spectroscopic camera 22, and the object W to be measured is captured at the multiple wavelengths to obtain an image. Obtaining this image means obtaining image data. The wavelengths selected may be changed for each capture, or may not be changed, i.e., may be constant.

[0033] Specifically, in the multiple wavelength imaging mode, spectral images corresponding to multiple spectral wavelengths input from the spectroscopic camera 22 are acquired as captured images. In this case, the multiple spectral images included in the captured image are captured under the same imaging conditions for the same object to be measured W, which is the same imaging target, and each pixel of each spectral image has information for the same position, i.e., the same part, on the object to be measured W, which is the imaging target.

[0034] In this multi-wavelength imaging mode, for example, inspections are performed that utilize wavelength information for each pixel on an image for analysis, such as colorimetry, calibration, material identification, etc. Note that inspections other than these may also be performed.

[0035] The control unit 6 is configured to include an arithmetic circuit such as a CPU (Central Processing Unit) and can be realized as one or more processors, and reads and executes various programs stored in the storage unit 7. This allows the control of the operation of the inspection device 1 and various processes such as various calculations and various judgments to be performed.

[0036] The storage unit 7 also stores various programs that can be executed by the control unit 6. The storage unit 7 is also capable of storing various data input from the outside. The storage unit 7 is configured to include, for example, a volatile memory such as a RAM (Random Access Memory) and a non-volatile memory such as a ROM (Read Only Memory). The storage unit 7 is not limited to being non-detachable, and may be configured to include a detachable external storage device.

[0037] The inspection unit 4 is configured to include an arithmetic circuit such as a CPU (Central Processing Unit) and can be realized as one or more processors, and reads and executes various programs stored in the storage unit 7. The inspection unit 4 also inspects the object to be measured W based on images captured by the camera unit 2, as will be described later.

[0038] The image processing unit 5 is configured to include an arithmetic circuit such as a CPU (Central Processing Unit), and can be realized as one or more processors, and reads and executes various programs stored in the storage unit 7. The image processing unit 5 also performs various types of image processing on the image, as will be described later.

[0039] The processors that realize the control unit 6, the inspection unit 4, and the image processing unit 5 may be provided separately, or all or part of them may be shared.

[0040] Similarly, in other embodiments described later, the processors that realize the control unit 6, the inspection unit 4, the image processing unit 5, the feature image generation unit 8, the single-wavelength image selection unit 9, and the specific area extraction unit 11 may each be provided separately, or all or part of them may be shared.

[0041] The display unit 12 has a function of displaying various types of information, for example. The display unit 12 is not particularly limited, and examples thereof include direct-view display devices such as liquid crystal display devices and organic EL display devices, and projection display devices such as projectors.

[0042] The operation unit 13 is not particularly limited, and examples thereof include a mouse, a keyboard, an operation button, an operation switch, an operation dial, etc. By operating the operation unit 13, the operator can issue various instructions and input various information to the inspection device 1, for example.

[0043] Furthermore, instead of the display unit 12 and the operation unit 13, a display input unit having the functions of both the display unit 12 and the operation unit 13 may be used. As the display input unit, for example, a touch panel or the like may be used.

[0044] Next, the operation and control of the inspection device 1 will be described. <<Explanation of operation and control of inspection device 1>> When inspecting the object W, the inspection device 1 switches between a single wavelength imaging mode and a multiple wavelength imaging mode, and changes the positional relationship between the object W and the camera unit 2 using the movable mechanism 3, while capturing images of predetermined portions of the object W using the camera unit 2 to obtain multiple images. The inspection unit 4 inspects the object W based on the obtained images. The display unit 12 then displays the results of the inspection. The display unit 12 is an example of a notification unit that notifies the user of the results of the inspection.

[0045] Here, the number of times the positional relationship between the object to be measured W and the camera unit 2 is changed is one or more times, and may be multiple times, but in this embodiment, a case where it is changed only once will be described as a representative example.

[0046] In an example configuration in this embodiment, a predetermined portion of the object W is photographed in single-wavelength photography mode to obtain an image. Next, the movable mechanism 3 is used to change the positional relationship between the object W and the camera unit 2, and the predetermined portion of the object W is photographed in multiple-wavelength photography mode to obtain an image. In this case, the portion of the object W photographed in the single-wavelength photography mode and the portion of the object W photographed in the multiple-wavelength photography mode may be the same, may partially overlap, or may be different. Note that the predetermined portion of the object W may first be photographed in multiple-wavelength photography mode to obtain an image, and then the movable mechanism 3 is used to change the positional relationship between the object W and the camera unit 2, and the predetermined portion of the object W is photographed in the single-wavelength photography mode to obtain an image.

[0047] In another configuration example of this embodiment, a predetermined portion of the object W is photographed in single wavelength photographing mode to obtain an image, and then a predetermined portion of the object W is photographed in multiple wavelength photographing mode to obtain an image without changing the positional relationship between the object W and the camera unit 2 by the movable mechanism 3. In this case, the portion of the object W photographed in the single wavelength photographing mode and the portion of the object W photographed in the multiple wavelength photographing mode may be the same, may partially overlap, or may be different. Also, either the single wavelength photographing mode or the multiple wavelength photographing mode may be omitted.

[0048] Next, the positional relationship between the object to be measured W and the camera unit 2 is changed by the movable mechanism 3, and a predetermined portion of the object to be measured W is photographed in the single wavelength photographing mode to obtain an image, and a predetermined portion of the object to be measured W is photographed in the multiple wavelength photographing mode to obtain an image. In this case, the portion of the object to be measured W photographed in the single wavelength photographing mode and the portion of the object to be measured W photographed in the multiple wavelength photographing mode may be the same, may partially overlap, or may be different. Also, either the single wavelength photographing mode or the multiple wavelength photographing mode may be omitted.

[0049] According to such an inspection device 1, since it has a single wavelength imaging mode and a multiple wavelength imaging mode, various inspections of the object to be measured W can be carried out quickly and accurately.

[0050] Furthermore, since the inspection can be performed automatically instead of manually, the inspection can be performed easily and accurately.

[0051] Next, the operation and control of the inspection device 1 in the single wavelength imaging mode and the multiple wavelength imaging mode will be described.

[0052] <<Single wavelength photography mode>> The operation and control of the inspection device 1 in the single wavelength imaging mode will be described.

[0053] (Step S101) As shown in FIG. 3, in the inspection device 1, the imaging mode is set to the single wavelength imaging mode.

[0054] In the single wavelength imaging mode, one wavelength is selected from among a plurality of wavelengths that can be captured by the spectroscopic camera 22, and the wavelength in the single wavelength imaging mode is set, for example, according to at least one of the color of the object W to be measured and the content of the inspection. This allows the object W to be appropriately imaged at a single wavelength.

[0055] The content of the inspection is not particularly limited, and examples include inspection for defect modes, inspection for the presence or absence of foreign matter, inspection for printing, inspection for the presence or absence of parts, etc. If the color of dirt adhering to the surface of the workpiece W is known in advance and the dirt is to be detected, a single wavelength suitable for identifying the color of the dirt is set. Examples of defect modes include scratches, dents, color unevenness, etc. In this embodiment, as will be described later, inspection for scratches, inspection for the presence or absence of parts, etc. are performed.

[0056] The reason for performing the scratch inspection in single wavelength photography mode is that it is easier to identify scratches in images captured using a single wavelength than in images captured using multiple wavelengths.

[0057] Furthermore, if the inspection is for flaws, it is preferable to select blue wavelengths. For example, scratches on a white casing are easier to see with blue wavelengths. Also, if the casing is blue and there are green parts, it is preferable to select wavelengths that make it easier to see the parts to be inspected.

[0058] (Step S102) The camera unit 2 captures an image by photographing a predetermined portion of the object W to be measured. In this case, the illumination 21 irradiates the object W with illumination light, and the spectroscopic camera 22 captures an image at a single wavelength to obtain one image at the single wavelength. The image is stored in the storage unit 7 and is read out as needed. Furthermore, parameters related to the illumination 21, such as the brightness of the illumination 21, may be constant or may be changed for each image capture.

[0059] Note that the operations after step S102, i.e., the operations from step S103 onwards described below, may be performed before acquiring an image in the next shot, for example, immediately after step S102, or may be performed after acquiring an image in the next shot.

[0060] (Step S103) The image processing unit 5 performs image processing, including binarization and morphology processing, which are two-dimensional image processing, on the image captured in the single wavelength imaging mode. This increases the contrast of the image, making it easier to see the defect mode to be determined, or in this embodiment, scratches in the scratch inspection, and allowing for proper inspection.

[0061] Note that the image processing is not limited to the above-mentioned processing. Specifically, for example, the following image processing can be mentioned.

[0062] Examples of image correction include contrast conversion and brightness correction. Examples of image conversion include monochrome image conversion. Examples of image processing include noise removal, edge emphasis, enlargement / reduction, etc. Examples of image feature extraction include center of gravity measurement, area measurement, circularity measurement, angle measurement, etc. Examples of image recognition include object identification, etc.

[0063] (Step S104) The inspection unit 4 performs at least one of a scratch inspection and an inspection for the presence or absence of components during the inspection, thereby making it possible to determine whether the workpiece W has scratches or whether the workpiece W actually has scratches, or both.

[0064] The contents of the inspection are not limited to the above-mentioned inspections, and may include, for example, inspections for other defect modes, inspections for the presence or absence of foreign matter, inspections of printing, etc. Furthermore, other inspections may include, for example, identifying the position of the object W to be measured, the position of a predetermined portion of the object W to be measured, etc., and the results of such inspections may be used in the multiple wavelength imaging mode. The test results are stored in the storage unit 7 and are read out as needed.

[0065] (Step S105) The test results are displayed on the display unit 12. This allows the test results to be ascertained. Note that step S105 may be omitted. Also, in step S105, the test results may be notified by another notification unit that notifies by voice or the like instead of the display unit 12, or the display of the test results by the display unit 12 and the notification of the test results by another notification unit may be used in combination.

[0066] <<Multi-wavelength imaging mode>> The operation and control of the inspection device 1 in the multiple wavelength imaging mode will be described.

[0067] (Step S201) As shown in FIG. 4, in the inspection device 1, the imaging mode is set to a multiple wavelength imaging mode.

[0068] In the multiple wavelength imaging mode, two or more wavelengths are selected from among the multiple wavelengths that can be captured by the spectroscopic camera 22. The two or more wavelengths in the multiple wavelength imaging mode are set according to, for example, the content of the inspection, etc. This allows the object W to be properly imaged at multiple wavelengths.

[0069] (Step S202) The camera unit 2 captures an image by photographing a predetermined portion of the object W. In this case, the illumination 21 irradiates the object W with illumination light, and the spectroscopic camera 22 captures images at multiple wavelengths to obtain multiple images for each wavelength. Each image is stored in the storage unit 7 and read out as needed. Furthermore, parameters related to the illumination 21, such as the brightness of the illumination 21, may be constant or may be changed for each image capture.

[0070] Note that the operations after step S202, i.e., the operations from step S203 onwards described below, may be performed before acquiring an image in the next shot, for example, immediately after step S202, or may be performed after acquiring an image in the next shot.

[0071] (Step S203) During the inspection, the inspection unit 4 performs spectroscopic analysis on each image captured in the multi-wavelength imaging mode, and performs at least one of color inspection, material identification, classification, and calibration. Note that during the inspection, various processes are performed, such as comparing each acquired image with a reference image or threshold value stored in advance in the storage unit 7 for each wavelength.

[0072] This makes it possible to ascertain one or more of the color of the object W, the constituent material of the object W, the class / grade of the object W, and the calibration value of the object W. In addition, by performing spectroscopic analysis on the image, it is possible to identify features that cannot be identified in images captured using a single wavelength or RGB wavelengths.

[0073] The test results are stored in the storage unit 7 and are read out as needed. The contents of the inspection are not limited to those described above. Specific examples of the processing in the inspection are given below.

[0074] The inspection involves pre-processing, analysis, comparison, and judgment, in the order of pre-processing, analysis, and comparison / judgment. The processes performed in the pre-processing, analysis, and comparison / judgment are as follows:

[0075] Examples of preprocessing include spectral smoothing, noise removal, filtering using a filter such as a differential filter, image calculation, etc. Examples of analysis include substance identification by peak detection, calibration, feature analysis by multivariate analysis, color calculation, clustering (grading), etc. Examples of comparison and judgment include color comparison, substance identification, class discrimination (grading), calibration value judgment, etc.

[0076] Here, when the object W to be measured is configured by combining multiple parts, it is preferable to perform inspection at multiple locations on the object W to be measured, i.e., multiple regions on the object W, in the multiple wavelength imaging mode. This allows inspection to be performed on each part.

[0077] Furthermore, if the object to be measured W is constructed by combining multiple parts of the same color, inspection can be performed by checking for color differences, such as when the colors of two specified parts do not match when compared.

[0078] Also, even if the object to be measured W is composed of one part, there is a possibility that discoloration may occur at any point on the object to be measured W, so inspection may be performed at multiple points on the object to be measured W.

[0079] Furthermore, when the object W to be measured is made up of one part, in the multiple wavelength photographing mode, for example, spectral analysis for color inspection or the like is performed on an image acquired in a single photographing. On the other hand, in the single wavelength photographing mode, the positional relationship between the object W to be measured and the camera unit 2 may be changed, and for example, a scratch inspection or the like may be performed at multiple locations on the object W to be measured.

[0080] Furthermore, if the object W is made of resin and a camera capable of capturing images at near-infrared wavelengths is used, the mechanical strength of the object W can be measured.

[0081] Furthermore, when the workpiece W is made of resin, examples of the inspection of the workpiece W include inspection of sink marks, weld lines, and the like.

[0082] (Step S204) The test results are displayed on the display unit 12. This allows the test results to be ascertained. Note that step S204 may be omitted. Also, in step S204, the test results may be notified by another notification unit that notifies by voice or the like instead of the display unit 12, or the display of the test results by the display unit 12 and the notification of the test results by another notification unit may be used in combination.

[0083] As described above, the inspection device 1 can perform various inspections of the object to be measured W quickly and accurately.

[0084] Furthermore, since the inspection can be performed automatically instead of manually, the inspection can be performed easily and accurately.

[0085] Second Embodiment Fig. 5 is a block diagram of an inspection device according to the second embodiment, and Fig. 6 is a flowchart for explaining the operation of the inspection device shown in Fig. 5.

[0086] The second embodiment will be described below, focusing on the differences from the previous embodiment, and omitting a description of the same points.

[0087] The second embodiment is similar to the first embodiment except for the configuration of the inspection device main body 10 and the operation and control in the multiple wavelength imaging mode.

[0088] As shown in Figure 5, the inspection device main body 10 of the inspection device 1 of the second embodiment has an inspection unit 4, an image processing unit 5, a control unit 6, a memory unit 7, a display unit 12, an operation unit 13, and also a feature image generation unit 8 that generates feature images.

[0089] The feature image generating unit 8 is configured to include an arithmetic circuit such as a CPU (Central Processing Unit) and can be realized as one or more processors, and reads and executes various programs stored in the storage unit 7. As will be described later, the feature image generating unit 8 performs image calculations on multiple images of two or more wavelengths to generate feature images.

[0090] Next, the operation and control of the inspection device 1 in the multiple wavelength imaging mode will be described. (Step S301) As shown in FIG. 6, in the inspection device 1, the imaging mode is set to a multiple wavelength imaging mode.

[0091] (Step S302) A predetermined portion of the object W to be measured is photographed by the camera unit 2 to obtain an image.

[0092] (Step S303) The feature image generating unit 8 performs image calculations on images of two or more wavelengths captured in the multi-wavelength imaging mode to generate one feature image. In this case, the feature image may be generated using all images captured in the multi-wavelength imaging mode, or may be generated using fewer images than those captured in the multi-wavelength imaging mode. The feature image is stored in the storage unit 7 and read out as needed.

[0093] By generating the characteristic image in this manner, it is possible to perform image processing while excluding structures that are not the subject of analysis and fall within the field of view of the spectroscopic camera 22.

[0094] (Step S304) The image processing unit 5 performs image processing, including binarization and morphology processing, which are two-dimensional image processing, on the feature image generated in step S303. This increases the contrast of the image, making it easier to see the defect mode to be determined, or in this embodiment, scratches in the scratch inspection, and allowing for proper inspection. Furthermore, by binarizing the feature image, the binarization can be easily performed.

[0095] (Step S305) The inspection unit 4 performs at least one of a scratch inspection and an inspection for the presence or absence of components during the inspection, thereby making it possible to determine whether the workpiece W has scratches or whether the workpiece W actually has scratches, or both.

[0096] The test results are stored in the storage unit 7 and are read out as needed. The contents of the inspection are not limited to the above inspections.

[0097] (Step S306) The display unit 12 displays the test results.

[0098] The second embodiment as described above can also achieve the same effects as the previous embodiments.

[0099] <Third embodiment> Fig. 7 is a block diagram of an inspection device according to the third embodiment, and Fig. 8 is a flowchart for explaining the operation of the inspection device shown in Fig. 7.

[0100] The third embodiment will be described below, focusing on the differences from the previous embodiments, and omitting descriptions of similar points.

[0101] The third embodiment is similar to the first embodiment except for the configuration of the inspection device main body 10 and the operation and control in the multiple wavelength imaging mode.

[0102] As shown in Figure 7, the inspection device main body 10 of the inspection device 1 of the third embodiment has, in addition to the inspection unit 4, the image processing unit 5, the control unit 6, the memory unit 7, the display unit 12, and the operation unit 13, a single-wavelength image selection unit 9 that selects a single-wavelength image, and a specific area extraction unit 11 that extracts a specific area.

[0103] The single wavelength image selection unit 9 is configured to include an arithmetic circuit such as a CPU (Central Processing Unit) and can be realized as one or more processors, and reads and executes various programs stored in the storage unit 7. As will be described later, the single wavelength image selection unit 9 selects a predetermined single wavelength image from the selection candidates.

[0104] The specific area extraction unit 11 is configured to include an arithmetic circuit such as a CPU (Central Processing Unit) and can be realized as one or more processors, and reads and executes various programs stored in the storage unit 7. The specific area extraction unit 11 extracts a specific area, as will be described later.

[0105] Next, the operation and control of the inspection device 1 in the multiple wavelength imaging mode will be described. (Step S401) As shown in FIG. 8, in the inspection device 1, the imaging mode is set to a multiple wavelength imaging mode.

[0106] (Step S402) A predetermined portion of the object W to be measured is photographed by the camera unit 2 to obtain an image.

[0107] (Step S403) The single wavelength image selection unit 9 selects a single wavelength image from the images captured in the multi-wavelength imaging mode, thereby reducing the time required for imaging.

[0108] (Step S404) The specific region extraction unit 11 performs image processing on the single wavelength image selected in step S403 to identify the position of the single wavelength image, and extracts a specific region corresponding to the region of the single wavelength image.

[0109] (Step S405) In the inspection, the inspection unit 4 performs spectroscopic analysis on the specific region extracted in step S404, that is, the image of the specific region at multiple wavelengths, and performs at least one of color inspection, material identification, classification, and calibration, for example.

[0110] This makes it possible to ascertain one or more of the color of the object W, the constituent material of the object W, the class / grade of the object W, and the calibration value of the object W. In addition, by performing spectroscopic analysis on the image, it is possible to identify features that cannot be identified in images captured using a single wavelength or RGB wavelengths.

[0111] The test results are stored in the storage unit 7 and are read out as needed. The contents of the inspection are not limited to the above inspections.

[0112] (Step S406) The display unit 12 displays the test results.

[0113] The third embodiment as described above can also achieve the same effects as the previous embodiments.

[0114] <Fourth embodiment> Fig. 9 is a block diagram of an inspection device according to the fourth embodiment, and Fig. 10 is a flowchart for explaining the operation of the inspection device shown in Fig. 9.

[0115] The fourth embodiment will be described below, focusing on the differences from the previous embodiments, and omitting descriptions of similar points.

[0116] The fourth embodiment is similar to the first embodiment except for the configuration of the inspection device main body 10 and the operation and control in the multiple wavelength imaging mode.

[0117] As shown in Figure 9, the inspection device main body 10 of the inspection device 1 of the fourth embodiment has, in addition to the inspection unit 4, the image processing unit 5, the control unit 6, the memory unit 7, the display unit 12, and the operation unit 13, a feature image generation unit 8 that generates a feature image, and a specific area extraction unit 11 that extracts a specific area.

[0118] Next, the operation and control of the inspection device 1 in the multiple wavelength imaging mode will be described. (Step S501) As shown in FIG. 10, in the inspection device 1, the imaging mode is set to a multiple wavelength imaging mode.

[0119] (Step S502) A predetermined portion of the object W to be measured is photographed by the camera unit 2 to obtain an image.

[0120] (Step S503) The feature image generating unit 8 performs image calculations on images of two or more wavelengths captured in the multi-wavelength imaging mode to generate one feature image. In this case, the feature image may be generated using all images captured in the multi-wavelength imaging mode, or may be generated using fewer images than those captured in the multi-wavelength imaging mode. The feature image is stored in the storage unit 7 and read out as needed.

[0121] By generating the characteristic image in this manner, it is possible to perform image processing while excluding structures that are not the subject of analysis and fall within the field of view of the spectroscopic camera 22.

[0122] (Step S504) The specific region extraction unit 11 performs image processing on the characteristic image generated in step S503 to identify the position of the characteristic image, and extracts a specific region corresponding to the region of the characteristic image.

[0123] (Step S505) In the inspection, the inspection unit 4 performs spectroscopic analysis on the specific region extracted in step S504, i.e., the image of the specific region at multiple wavelengths, and performs at least one of color inspection, material identification, classification, and calibration. In this spectroscopic analysis, image processing is first performed on the feature image.

[0124] This makes it possible to ascertain one or more of the color of the object W, the constituent material of the object W, the class / grade of the object W, and the calibration value of the object W. In addition, by performing spectroscopic analysis on the image, it is possible to identify features that cannot be identified in images captured using a single wavelength or RGB wavelengths.

[0125] Furthermore, in the spectroscopic analysis, image processing is first performed on the characteristic image, so that structures that are not the subject of analysis and that fall within the field of view of the spectroscopic camera 22 can be excluded before image processing.

[0126] The test results are stored in the storage unit 7 and are read out as needed. The contents of the inspection are not limited to the above inspections.

[0127] (Step S506) The display unit 12 displays the test results.

[0128] The fourth embodiment as described above can also achieve the same effects as the previous embodiments.

[0129] Fifth Embodiment Fig. 11 is a block diagram of an inspection device according to the fifth embodiment, and Fig. 12 is a flowchart for explaining the operation of the inspection device shown in Fig. 11.

[0130] The fifth embodiment will be described below, focusing on the differences from the previous embodiments, and omitting descriptions of similar points.

[0131] The fifth embodiment is similar to the first embodiment except for the configuration of the inspection device main body 10 and the operation and control in the multiple wavelength imaging mode.

[0132] As shown in Figure 11, the inspection device main body 10 of the inspection device 1 of the fifth embodiment has, in addition to the inspection unit 4, the image processing unit 5, the control unit 6, the memory unit 7, the display unit 12, and the operation unit 13, a single-wavelength image selection unit 9 that selects a single-wavelength image, and a specific area extraction unit 11 that extracts a specific area.

[0133] Next, the operation and control of the inspection device 1 in the multiple wavelength imaging mode will be described. (Step S601) As shown in FIG. 12, in the inspection device 1, the imaging mode is set to a multiple wavelength imaging mode.

[0134] (Step S602) A predetermined portion of the object W to be measured is photographed by the camera unit 2 to obtain an image.

[0135] (Step S603) The specific region extraction unit 11 performs spectroscopic analysis on the image captured in the multi-wavelength imaging mode to extract a specific region that satisfies a specific condition, i.e., identifies the position of the specific region.

[0136] By performing spectroscopic analysis to identify the position in advance, it is possible to limit the target area and improve the accuracy of the image processing described below.

[0137] (Step S604) The single wavelength image selection unit 9 selects a single wavelength image from a specific region, that is, from images of multiple wavelengths of the specific region.

[0138] (Step S605) The image processing unit 5 performs image processing on the single wavelength image selected in step S604. As a specific example, when a plurality of objects made of various materials, i.e., different materials, are irregularly arranged and the position of a specific object among the plurality of objects is to be identified, the position of the specific object can be identified with high accuracy by performing image processing on the single wavelength image.

[0139] Although the description of the subsequent steps will be omitted, in the subsequent steps, for example, the various processes described in the other embodiments, such as inspection and display of inspection results, are performed.

[0140] The fifth embodiment as described above can also achieve the same effects as the previous embodiments.

[0141] Sixth Embodiment Fig. 13 is a block diagram of an inspection device according to the sixth embodiment, and Fig. 14 is a flowchart for explaining the operation of the inspection device shown in Fig. 13.

[0142] The sixth embodiment will be described below, focusing on the differences from the previous embodiments, and omitting descriptions of similar points.

[0143] The sixth embodiment is similar to the first and fifth embodiments except for the configuration of the inspection device main body 10 and the operation and control in the multiple wavelength imaging mode.

[0144] As shown in Figure 13, the inspection device main body 10 of the inspection device 1 of the sixth embodiment has, in addition to the inspection unit 4, the image processing unit 5, the control unit 6, the memory unit 7, the display unit 12, and the operation unit 13, a feature image generation unit 8 that generates a feature image, and a specific area extraction unit 11 that extracts a specific area.

[0145] Next, the operation and control of the inspection device 1 in the multiple wavelength imaging mode will be described. (Step S701) As shown in FIG. 14, in the inspection device 1, the imaging mode is set to a multiple wavelength imaging mode.

[0146] (Step S702) A predetermined portion of the object W to be measured is photographed by the camera unit 2 to obtain an image.

[0147] (Step S703) The specific region extraction unit 11 performs spectroscopic analysis on the image captured in the multi-wavelength imaging mode to extract a specific region that satisfies a specific condition, i.e., identifies the position of the specific region.

[0148] By performing spectroscopic analysis to identify the position in advance, it is possible to limit the target area and improve the accuracy of the image processing described below.

[0149] (Step S704) The feature image generating unit 8 performs image calculations on a specific region, that is, on images of two or more wavelengths among images of a plurality of wavelengths of the specific region, to generate one feature image.

[0150] (Step S705) The image processing unit 5 performs image processing on the feature image generated in step S704. As a specific example, when a plurality of objects made of various materials, i.e., different materials, are irregularly arranged and the position of a specific object among the plurality of objects is to be identified, the position of the specific object can be identified with high accuracy by performing image processing on the feature image.

[0151] Although the description of the subsequent steps will be omitted, in the subsequent steps, for example, the various processes described in the other embodiments, such as inspection and display of inspection results, are performed.

[0152] The sixth embodiment as described above can also achieve the same effects as the previous embodiments.

[0153] Seventh Embodiment Fig. 15 is a block diagram of an inspection device according to the seventh embodiment, and Fig. 16 is a flowchart for explaining the operation of the inspection device shown in Fig. 15.

[0154] The seventh embodiment will be described below, focusing on the differences from the previous embodiments, and omitting descriptions of similar points.

[0155] The seventh embodiment is similar to the first embodiment except for the configuration of the inspection device main body 10 and the operation and control in the multiple wavelength imaging mode.

[0156] As shown in Figure 15, the inspection device main body 10 of the inspection device 1 of the seventh embodiment has, in addition to the inspection unit 4, the image processing unit 5, the control unit 6, the memory unit 7, the display unit 12, and the operation unit 13, a feature image generation unit 8 that generates a feature image, a single-wavelength image selection unit 9 that selects a single-wavelength image, and a specific area extraction unit 11 that extracts a specific area.

[0157] Next, the operation and control of the inspection device 1 in the multiple wavelength imaging mode will be described. (Step S801) As shown in FIG. 16, in the inspection device 1, the imaging mode is set to a multiple wavelength imaging mode.

[0158] (Step S802) A predetermined portion of the object W to be measured is photographed by the camera unit 2 to obtain an image.

[0159] Here, the camera unit 2 captures images of a plurality of different locations on the object to be measured W, in this embodiment, two different locations on the object to be measured W. To achieve this, steps S802 to S804 are executed.

[0160] (Step S803) The control unit 6 determines whether the number of times of shooting is N. N is an integer equal to or greater than 2, and is set to a predetermined value in advance. In this embodiment, a representative case will be described where N is "2."

[0161] Therefore, in step S803, it is determined whether or not the number of times of photography is two, and if the number of times of photography is not two, that is, if it is one, the process proceeds to step S804.

[0162] (Step S804) The movable mechanism 3 changes the positional relationship between the object to be measured W and the camera unit 2. This makes it possible to capture an image of a wide range that does not fit within the angle of view of the spectroscopic camera 22.

[0163] After the positional relationship is changed, the process returns to step S802, and steps from step S802 onwards are executed again. Then, if it is determined in step S803 that the number of times of imaging is two, that is, if two different locations on the object W to be measured are imaged and two images of multiple wavelengths are acquired, the process proceeds to step S805.

[0164] (Step S805) The inspection unit 4 performs an inspection based on a plurality of images. In this inspection, the inspection unit 4 obtains feature amounts for a plurality of images acquired by photographing a plurality of different locations on the object to be measured W, and compares the feature amounts.

[0165] In this embodiment, since N=2, the inspection unit 4 obtains feature amounts for two images of multiple wavelengths acquired by photographing two different locations on the object to be measured W, and compares the two feature amounts.

[0166] In this embodiment, a case where the feature amount is color will be described as a representative example, and in this case, the inspection involves obtaining the colors of two different locations on the object W based on two images, comparing the two colors, and determining whether or not there is color unevenness. The inspection results are stored in the storage unit 7 and are read out as needed.

[0167] (Step S806) The display unit 12 displays the test results.

[0168] The seventh embodiment as described above can also achieve the same effects as the previous embodiments.

[0169] <Other configurations> The inspection device 1 may have the configuration described below, and this configuration may be applied to each of the above-described embodiments.

[0170] <<Configuration 1>> In the analysis methods of the single wavelength imaging mode and the multiple wavelength imaging mode, for example, in image processing and spectroscopic analysis, machine learning methods such as reinforcement learning, supervised learning, and deep learning may be used.

[0171] Furthermore, in calculating the feature image, a transformation matrix for conversion derived by machine learning may be used.

[0172] Also, a model for inspecting failure modes may be provided, and when predetermined data is input to the model, it may be possible to determine whether or not there is a failure.

[0173] <<Configuration 2>> A reference for the spectroscopic camera 22, that is, a white standard unit that serves as a white standard for acquiring reference data, may be provided somewhere in the inspection device 1.

[0174] A specific example of the white standard portion is a white standard for calibrating the spectroscopic camera 22.

[0175] Furthermore, when the wavelength band of the spectroscopic camera 22 is visible light, it is preferable that the standard portion be a white reference.

[0176] Furthermore, when the wavelength band of the spectroscopic camera 22 is near-infrared light, it is preferable that the standard portion has a high reflectance in the near-infrared region and has a flat shape.

[0177] <<Configuration 3>> The reference data obtained by photographing the white standard is stored in association with the photographing conditions. Furthermore, reference data is created and stored for each location to be photographed.

[0178] <<Configuration 4>> Reference data acquired by imaging under predetermined imaging conditions may be subjected to arithmetic processing to calculate reference data under different imaging conditions.

[0179] For example, in the case of a shooting condition in which the output of the light source of the illumination 21 is set to 80%, the reference data is calculated by multiplying the standard reference data, which is the original reference data, by 0.8.

[0180] Similarly, the exposure time can also be subjected to calculation processing to calculate reference data under different conditions.

[0181] <<Configuration 5>> In the multi-wavelength imaging mode, analysis may be performed in combination with image processing performed in the single-wavelength imaging mode. Examples of analysis include material identification by peak detection, calibration, feature analysis by multivariate analysis, color calculation, clustering, and classification. The combinations and processing details are as follows:

[0182] (Combination 1) Image processing is performed first, followed by spectroscopic analysis.

[0183] This combination 1 has already been explained in the third and fourth embodiments, so the explanation will be omitted.

[0184] (Combination 2) Spectroscopic analysis is carried out first, followed by image processing.

[0185] In the spectroscopic analysis, for example, at least one of color inspection, material identification, classification, and calibration is performed, and the spectroscopic analysis is also performed to extract a specific region that satisfies a specific condition. Next, in the image processing, image processing is performed on the specific region and inspection is performed.

[0186] As described above, the inspection device 1 includes the camera unit 2 having the illumination 21 that illuminates the object W and the spectral scanning camera 22 that images the object W, the movable mechanism 3 that changes the positional relationship between the object W and the camera unit 2, and the inspection unit 4 that inspects the object W based on images captured by the camera unit 2. The inspection device 1 also has a single-wavelength imaging mode that images the object W at a single wavelength, and a multiple-wavelength imaging mode that images the object W at multiple wavelengths. The inspection device 1 also images a predetermined portion of the object W using the camera unit 2 while switching between the single-wavelength imaging mode and the multiple-wavelength imaging mode and changing the positional relationship between the object W and the camera unit 2 using the movable mechanism 3.

[0187] According to such an inspection device 1, various inspections of the object to be measured W can be carried out quickly and accurately.

[0188] Furthermore, in the inspection device 1, the wavelength in the single wavelength imaging mode is set according to at least one of the color of the object W and the content of the inspection. This allows the object W to be appropriately imaged at a single wavelength.

[0189] The inspection device 1 also has an image processing unit 5 that performs image processing, including binarization and morphology processing, on images captured in single-wavelength imaging mode. The inspection unit 4 also performs at least one of a scratch inspection and an inspection for the presence or absence of components during the inspection. This increases the contrast of the image, making it easier to see the defect mode to be determined, in this case, scratches in the scratch inspection, and allows for proper inspection. This makes it possible to determine the presence or absence of scratches on the workpiece W, or the presence or absence of the workpiece W, or both.

[0190] Furthermore, in the inspection device 1, the inspection unit 4 performs spectroscopic analysis on the image captured in the multi-wavelength imaging mode during inspection, and performs at least one of color inspection, material identification, classification, and calibration. This makes it possible to ascertain one or more of the color of the object W, the constituent material of the object W, the class (grade) of the object W, and the calibration value of the object W. Furthermore, by performing spectroscopic analysis on the image, it is possible to identify features that cannot be identified in images captured at a single wavelength or RGB wavelengths.

[0191] The inspection device 1 also has a feature image generation unit 8 that performs image calculations on images of two or more wavelengths captured in the multi-wavelength imaging mode to generate a feature image, and an image processing unit 5 that performs image processing including binarization and morphology processing on the feature image.The inspection unit 4 also performs at least one of a scratch inspection and an inspection for the presence or absence of components during inspection.

[0192] By generating the feature image in this way, it is possible to perform image processing while excluding structures that are not the target of analysis and are included in the field of view of the spectroscopic camera. In addition, the feature image can be easily binarized by the image processing unit 5.

[0193] The inspection device 1 also has a single-wavelength image selection unit 9 that selects a single-wavelength image from images captured in the multi-wavelength imaging mode, and a specific area extraction unit 11 that performs image processing on the single-wavelength image to identify the position of the single-wavelength image and extract a specific area. The inspection unit 4 also performs spectroscopic analysis on the specific area during the inspection, which reduces the time required for imaging.

[0194] The inspection device 1 also has a feature image generation unit 8 that performs image calculations on images of two or more wavelengths captured in the multi-wavelength imaging mode to generate a feature image, and a specific region extraction unit 11 that performs image processing on the feature image to identify the position of the feature image and extract a specific region.The inspection unit 4 also performs spectroscopic analysis on the specific region during the inspection.

[0195] By generating a feature image in this manner, it is possible to perform image processing while excluding structures that are not the subject of analysis and fall within the field of view of the spectroscopic camera.

[0196] Furthermore, the inspection device 1 first processes the image of the feature image in the spectroscopic analysis, thereby enabling image processing to be performed while eliminating structures that are not the target of analysis and are within the field of view of the spectroscopic camera.

[0197] The inspection device 1 also has a specific area extraction unit 11 that performs spectroscopic analysis on images captured in the multiple wavelength shooting mode to extract specific areas, a single wavelength image selection unit 9 that selects a single wavelength image from the specific area, or a feature image generation unit 8 that performs image calculations on images of two or more wavelengths in the specific area to generate a feature image, and an image processing unit 5 that performs image processing on the single wavelength image or the feature image.

[0198] By performing spectroscopic analysis and identifying the location in advance, it is possible to limit the target area and improve the accuracy of image processing.

[0199] In the inspection device 1, the camera unit 2 captures images of a plurality of different locations on the object to be measured W. During the inspection, the inspection section 4 calculates feature amounts for a plurality of images acquired by capturing images of the plurality of locations, and compares the feature amounts. This allows inspection of a wide range that does not fit within the angle of view of the spectroscopic camera 22.

[0200] Although the inspection device of the present invention has been described above based on the illustrated embodiment, the present invention is not limited to this, and the configuration of each part can be replaced with any configuration having the same function. Also, any other configuration may be added.

[0201] Furthermore, the present invention may be a combination of any two or more of the configurations of the above-described embodiments.

[0202] The use of the inspection device is not particularly limited, and examples thereof include machine vision, injection molding, and factory automation. [Explanation of symbols]

[0203] REFERENCE SIGNS LIST 1...inspection device 2...camera unit 3...moving mechanism 4...inspection section 5...image processing section 6...control section 7...storage section 8...feature image generation section 9...single wavelength image selection section 10...inspection device main body 11...specific area extraction section 12 display section 13...operation section 21...lighting 22...spectroscopic camera 31...robot 32...automatic stage 311...control device 312...robot arm 321...support section W...object to be measured

Claims

1. a camera unit having an illumination for illuminating an object to be measured and a spectral scanning type spectroscopic camera for photographing the object to be measured; a movable mechanism for changing the positional relationship between the object to be measured and the camera unit; an inspection unit that inspects the object to be measured based on an image captured by the camera unit, a single wavelength imaging mode in which the object to be measured is imaged at a single wavelength; a multiple wavelength imaging mode for imaging the object to be measured at multiple wavelengths, an inspection device characterized in that the camera unit photographs a predetermined portion of the object to be measured while switching between the single wavelength photographing mode and the multiple wavelength photographing mode and changing the positional relationship between the object to be measured and the camera unit using the movable mechanism.

2. 2. The inspection device according to claim 1, wherein the wavelength in the single wavelength imaging mode is set in accordance with at least one of the color of the object to be measured and the content of the inspection.

3. an image processing unit that performs image processing including binarization and morphology processing on the image captured in the single wavelength imaging mode; The inspection device according to claim 1 , wherein the inspection unit performs at least one of a flaw inspection and an inspection for the presence or absence of a component in the inspection.

4. The inspection device according to claim 1 , wherein the inspection unit performs spectroscopic analysis on the image acquired by capturing in the multiple wavelength capturing mode during the inspection, and performs at least one of color inspection, material identification, classification, and calibration.

5. a feature image generating unit that performs image calculations on images of two or more wavelengths among images captured in the multiple wavelength imaging mode to generate a feature image; an image processing unit that performs image processing including binarization and morphology processing on the feature image, The inspection device according to claim 1 , wherein the inspection unit performs at least one of a flaw inspection and an inspection for the presence or absence of a component in the inspection.

6. a single wavelength image selection unit that selects a single wavelength image from the images captured in the multiple wavelength imaging mode; a specific region extraction unit that performs image processing on the single-wavelength image to identify a position of the single-wavelength image and extract a specific region, The inspection device according to claim 1 , wherein the inspection section performs spectroscopic analysis on the specific region during the inspection.

7. a feature image generating unit that performs image calculations on images of two or more wavelengths among images captured in the multiple wavelength imaging mode to generate a feature image; a specific region extraction unit that performs image processing on the feature image to identify a position of the feature image and extract a specific region, The inspection device according to claim 1 , wherein the inspection section performs spectroscopic analysis on the specific region during the inspection.

8. The inspection apparatus according to claim 7 , wherein the image that is first subjected to image processing in the spectroscopic analysis is the characteristic image.

9. a specific region extraction unit that performs spectroscopic analysis on the image captured in the multiple wavelength imaging mode to extract a specific region; a single wavelength image selection unit that selects a single wavelength image from the specific region, or a feature image generation unit that performs image calculations on images of two or more wavelengths in the specific region to generate a feature image; The inspection device according to claim 1 , further comprising an image processing unit that performs image processing on the single-wavelength image or the feature image.

10. the camera unit captures images of a plurality of different locations on the object to be measured, The inspection device according to claim 1 , wherein the inspection unit, in the inspection, obtains feature amounts for a plurality of images acquired by photographing the plurality of locations, and compares the feature amounts.

Images