Inspection method and inspection device

Abstract

The present invention provides an inspection method and an inspection device. The inspection method comprises: a first acquisition step of acquiring information obtained by assigning color difference information relative to a reference color to each of a plurality of first segmented areas obtained by segmenting a reference image; a second acquisition step of acquiring information obtained by assigning color difference information relative to the reference color to each of a plurality of second segmented areas obtained by segmenting a captured image; a first comparison step of comparing the color difference information of each first segmented area with the color difference information of each corresponding second segmented area; and a second comparison step of comparing the color difference information of each first segmented area with the color difference information of each second segmented area in a combination different from the combination compared in the first comparison step, and determining whether the reference image data and the captured image data are consistent based on the first comparison result obtained in the first comparison step and the second comparison result obtained in the second comparison step.

Description

Technical Field

[0001] The present invention relates to an inspection method and an inspection device. Background Art

[0002] For example, recognition devices are known that determine whether a reference image, serving as a basis for authenticity determination, matches a comparison image, serving as a comparison target, in printed matter. For example, the printed matter image recognition device described in Patent Document 1 sequentially performs a global integration process, a block integration process, a block differentiation process, and a determination phase.

[0003] Global integration is the process of calculating the global integral value by summing the pixel values ​​of the entire image being compared, for each color component. Block integration is the process of dividing the entire image into multiple blocks and, for each block, summing the pixel values ​​of each pixel within the block, for each color component, to calculate the block integral value. Block differential processing is the process of calculating the difference between adjacent pixels within each block and averaging these differences to calculate the block differential value. The judgment stage is the process of comparing the global integral value, block integral value, and block differential value of the reference image and the image under test to determine whether the reference image and the comparison image are consistent.

[0004] Patent Document 1: Japanese Patent Application Laid-Open No. 2010-183471

[0005] However, the recognition device described in Patent Document 1 assumes that the position of the measurement object is fixed when capturing the comparison image. Therefore, if the orientation of the measurement object differs from that in the reference image, a mismatch may be detected when the image should be identical. Summary of the Invention

[0006] The inspection method of the present invention is characterized in that it checks whether the reference image data of the reference image is consistent with the captured image data of the captured image, and the inspection method has: a first acquisition step, acquiring information obtained by assigning color difference information relative to the reference color to each of the multiple first segmented areas obtained by segmenting the reference image; a second acquisition step, acquiring information obtained by assigning color difference information relative to the reference color to each of the multiple second segmented areas obtained by segmenting the captured image; a first comparison step, comparing the color difference information of each first segmented area with the color difference information of the corresponding second segmented area; and a second comparison step, comparing the color difference information of each first segmented area with the color difference information of each second segmented area in a combination different from the combination compared in the first comparison step. In the inspection method, based on the first comparison result obtained in the first comparison step and the second comparison result obtained in the second comparison step, it is determined whether the reference image data is consistent with the captured image data.

[0007] The inspection device of the present invention is characterized in that it is provided with a control unit for checking whether the reference image data of the reference image is consistent with the captured image data of the captured image, and the control unit performs: a first acquisition step of acquiring information obtained by assigning color difference information relative to the reference color to each of the multiple first segmented areas obtained by segmenting the reference image; a second acquisition step of acquiring information obtained by assigning color difference information relative to the reference color to each of the multiple second segmented areas obtained by segmenting the captured image; a first comparison step of comparing the color difference information of each first segmented area with the color difference information of the corresponding second segmented area; and a second comparison step of comparing the color difference information of each first segmented area with the color difference information of each second segmented area in a combination different from the combination compared in the first comparison step, and the control unit determines whether the reference image data is consistent with the captured image data based on the first comparison result obtained in the first comparison step and the second comparison result obtained in the second comparison step. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] Figure 1 This is a functional block diagram of the first embodiment of the inspection device of the present invention.

[0009] Figure 2 yes Figure 1 A cross-sectional view of the spectrometer is shown.

[0010] Figure 3 This is a flowchart for explaining an example of the first embodiment of the inspection method of the present invention.

[0011] Figure 4 This is a flowchart for explaining an example of the first embodiment of the inspection method of the present invention.

[0012] Figure 5 FIG. 1 is a diagram showing a state where the first divided region is set in the reference image.

[0013] Figure 6 This is a diagram showing a state where each first divided area is compared with a reference color.

[0014] Figure 7 3 is a graph showing waveforms indicating color differences in each first divided area.

[0015] Figure 8 FIG. 1 is a diagram showing a state where the second divided region is set in the captured image.

[0016] Figure 9 3 is a diagram showing a state where each second divided area is compared with a reference color.

[0017] Figure 10 : is a graph showing a waveform indicating the color difference of each second divided area.

[0018] Figure 11 FIG. 1 is a diagram showing a state in which the second divided region is set in the captured image in the rotated state.

[0019] Figure 12 3 is a diagram showing a state where each second divided area is compared with a reference color.

[0020] Figure 13 : is a graph showing a waveform indicating the color difference of each second divided area.

[0021] Figure 14 This is a graph showing waveforms of color differences of respective first divided regions with each first divided region as a reference in the second embodiment of the inspection method of the present invention.

[0022] Description of Reference Numerals

[0023] 1. Inspection device; 10. Spectrometer; 15. Display; 16. Input; 17. Storage; 21. Image sensor; 31. Light source; 41. Spectrometer; 45. Electrostatic actuator; 60. Control unit; 81. Spectrometer-side optical system; 83. Image sensor-side optical system; 410. Fixed substrate; 411. Fixed reflective film; 412. Fixed electrode; 413. Groove; 414. Bonding film; 415. Reflective film setting unit; 420. Movable substrate 421, movable reflective film; 422, movable electrode; 423, groove; 425, reflective film setting unit; 601, light source control unit; 602, spectroscopic control unit; 603, image generation unit; 605, display control unit; 610, determination unit; 611, segmentation unit; 612, reference value determination unit; 613, spectrum generation unit; 614, color value calculation unit; color difference calculation unit; 616, determination unit; 811, incident lens; 812, projection lens; 831 , incident / exit lens; Cs, reference color; DPs, reference image data; DPx, captured image data; DPx', captured image data; OA, optical axis; Ps, reference image; Ps1, first divided area; Ps2, first divided area; Ps3, first divided area; Ps4, first divided area; Ps5, first divided area; Ps6, first divided area; Ps7, first divided area; Ps8, first divided area; Px, captured image; Px', captured image; Px1, second divided area; Px2, second divided area; Px3, second divided area; Px4, second divided area; Px5, second divided area; Px6, second divided area; Px7, second divided area; Px8, second divided area; X, captured object; ΔE1, waveform; ΔE2, waveform; ΔE3, waveform; ΔE4, waveform; ΔE5, waveform; ΔE6, waveform; ΔE7, waveform; ΔE8, waveform. DETAILED DESCRIPTION

[0024] First embodiment

[0025] Figure 1 This is a functional block diagram of the first embodiment of the inspection device of the present invention. Figure 2 yes Figure 1 A cross-sectional view of the spectrometer is shown. Figure 3 This is a flowchart for explaining an example of the first embodiment of the inspection method of the present invention. Figure 4 This is a flowchart for explaining an example of the first embodiment of the inspection method of the present invention. Figure 5 FIG. 1 is a diagram showing a state where the first divided region is set in the reference image. Figure 6 This is a diagram showing a state where each first divided area is compared with a reference color. Figure 7 3 is a graph showing waveforms indicating color differences in each first divided area. Figure 8FIG. 1 is a diagram showing a state where the second divided region is set in the captured image. Figure 9 3 is a diagram showing a state where each second divided area is compared with a reference color. Figure 10 : is a graph showing a waveform indicating the color difference of each second divided area. Figure 11 FIG. 1 is a diagram showing a state in which the second divided region is set in the captured image in the rotated state. Figure 12 3 is a diagram showing a state where each second divided area is compared with a reference color. Figure 13 : is a graph showing a waveform indicating the color difference of each second divided area.

[0026] Hereinafter, the inspection method and the inspection apparatus of the present invention will be described in detail based on preferred embodiments shown in the accompanying drawings.

[0027] 1. Inspection device

[0028] Figure 1 The inspection device 1 shown here is a device that performs the inspection method of the present invention. It inspects whether a captured image Px, representing an image of a captured object X, matches a reference image Ps. Specifically, the device spectrally analyzes reflected light from the captured object X, generates a spectral image based on multiple wavelengths of light, and generates a spectrum derived from the spectral image. The inspection is then performed based on this information. The captured object X is not particularly limited; examples include patterns printed on paper, patterned fabric, and ceramic tiles.

[0029] The inspection apparatus 1 includes a spectroscopic measurement unit 10, a control unit 60, a display unit 15, an input unit 16, and a storage unit 17. Each unit will be described below in sequence.

[0030] 1.1. Spectrophotometry Unit

[0031] The spectroscopic measurement unit 10 includes a light source 31 , an imaging element 21 , and a spectroscopic unit 41 .

[0032] The light source 31 is an element that irradiates light toward the object X. The light irradiated and reflected by the object X enters the imaging element 21 as reflected light via the spectroscopic unit 41 described later. The light source 31 may be provided separately from the inspection device 1 .

[0033] Examples of light source 31 include LED (Light Emitting Diode) elements, organic EL (Electro Luminescence) elements, xenon lamps, and halogen lamps. Furthermore, light source 31 preferably has light intensity across the entire wavelength range that can be dispersed by spectroscopic unit 41, described later. Specifically, it is preferred to use a light source that can emit white light with light intensity across the entire visible light range. Alternatively, light source 31 may be an element capable of emitting light in wavelengths other than white light, such as infrared light or other light other than visible light.

[0034] The imaging element 21 is an element that captures reflected light from the imaging object X. Examples of the imaging element 21 include a CCD (Charge Coupled Device) and a CMOS (Complementary Metal Oxide Semiconductor).

[0035] The spectroscopic unit 41 is an optical element having a function of selectively emitting (transmitting) light in a specific wavelength range from incident light. The light emitted from the spectroscopic unit 41 is incident on the imaging element 21 . Figure 2 The spectroscopic unit 41 shown is a variable wavelength interference filter capable of changing the wavelength range of emitted light, that is, a specific wavelength range.

[0036] As a wavelength-variable interference filter, for example, a wavelength-variable Fabry-Perot etalon filter, an acousto-optic tunable filter (AOTF), a linear variable filter (LVF), a liquid crystal tunable filter (LCTF), etc. can be cited. Among them, as a wavelength-variable interference filter, a wavelength-variable Fabry-Perot etalon filter is preferably used. In a wavelength-variable Fabry-Perot etalon filter, the size of the gap between the two filters (reflectors) can be adjusted by an electrostatic actuator 45 described later, etc. Thus, a specific wavelength region can be changed.

[0037] Furthermore, the Fabry-Perot etalon filter utilizes multiple interference formed by two filters to extract light in a specific wavelength range. Because each filter can be made thinner, the spectrometer 41 employing the Fabry-Perot etalon filter can be made sufficiently thin. Specifically, the thickness of the spectrometer 41 can be set to 2.0 mm or less. This allows for miniaturization of the spectrometer 41 and, consequently, the inspection device 1.

[0038] Figure 2 2 shows a spectroscopic section 41 in which a wavelength-variable Fabry-Perot etalon filter is used as a wavelength-variable interference filter.

[0039] Figure 2 The light splitting portion 41 shown is provided with Figure 2 The spectrometer 41 is a plate-shaped member extending in a direction intersecting the optical axis OA and extending vertically along the optical axis OA. The spectrometer 41 includes a fixed substrate 410, a movable substrate 420, a fixed reflective film 411, a movable reflective film 421, fixed electrodes 412 and 422, and a bonding film 414. The fixed substrate 410 and the movable substrate 420 are laminated and integrally bonded to each other via the bonding film 414.

[0040] When viewed from above from a position on the optical axis OA, the fixed substrate 410 has a reflective film installation portion 415 located in the center and a groove 413 surrounding the reflective film installation portion 415. The portion of the fixed substrate 410 corresponding to the reflective film installation portion 415 is thicker along the length of the optical axis OA, that is, thicker than the portion corresponding to the groove 413. A fixed reflective film 411 is provided on the surface of the reflective film installation portion 415 on the movable substrate 420 side. The fixed reflective film 411 functions as a fixed optical mirror, one of the optical elements of the Fabry-Perot etalon filter.

[0041] When viewed from above from a position on the optical axis OA, the movable substrate 420 has a reflective film installation portion 425 located in the center and a groove 423 surrounding the reflective film installation portion 425. The portion of the movable substrate 420 corresponding to the reflective film installation portion 425 is thicker along the length of the optical axis OA, that is, thicker than the portion corresponding to the groove 423. Therefore, a movable reflective film 421 is provided on the surface of the reflective film installation portion 425 on the fixed substrate 410 side. The movable reflective film 421 also functions as a movable optical mirror, one of the optical elements of the Fabry-Perot etalon filter.

[0042] A fixed electrode 412 is provided on the surface of the movable substrate 420 that is located within the groove 413 of the fixed substrate 410. Furthermore, a movable electrode 422 is provided on the surface of the movable substrate 420 that is located within the groove 423 of the fixed substrate 410. Electrostatic attraction is generated by applying a voltage between the fixed electrode 412 and the movable electrode 422, thereby adjusting the size of the gap between the fixed reflective film 411 and the movable reflective film 421. Thus, the fixed electrode 412 and the movable electrode 422 constitute the electrostatic actuator 45. Furthermore, since the movable electrode 422 is provided at a position corresponding to the groove 423, the displacement of the movable reflective film 421 when electrostatic attraction is generated can be increased.

[0043] It should be noted that the thickness of the fixed substrate 410 and the movable substrate 420 is preferably between approximately 0.1 mm and 1.0 mm. With such thicknesses, the overall thickness of the spectrometer 41 can be kept below 2.0 mm. This allows for miniaturization of the spectrometer 10.

[0044] Here, the fixed reflective film 411 and the movable reflective film 421 are arranged opposite each other with a gap between them. Furthermore, the fixed electrode 412 and the movable electrode 422 are also arranged opposite each other with a gap between them. As described above, the fixed electrode 412 and the movable electrode 422 constitute the electrostatic actuator 45 that adjusts the size of the gap between the fixed reflective film 411 and the movable reflective film 421. Specifically, when a voltage is applied between the fixed electrode 412 and the movable electrode 422, an electrostatic attraction is generated, causing the movable substrate 420 to bend. As a result, the size of the gap, or the distance, between the fixed reflective film 411 and the movable reflective film 421 can be varied. By appropriately setting the size of this gap, the wavelength range of light transmitted through the spectrometer 41 along the optical axis OA can be selected. In other words, the specific wavelength range can be changed. Furthermore, by varying the configuration of the fixed reflective film 411 and the movable reflective film 421, the half-value width of the transmitted light, or the resolution of the Fabry-Perot etalon filter, can be controlled.

[0045] Examples of the constituent materials of the fixed substrate 410 and the movable substrate 420 include various glasses such as soda glass, crystalline glass, quartz glass, lead glass, potassium glass, borosilicate glass, and alkali-free glass, and quartz.

[0046] The bonding film 414 bonds the fixed substrate 410 and the movable substrate 420. The bonding film 414 is not particularly limited, and an example thereof is a plasma polymerized film containing siloxane as a main material.

[0047] Examples of the fixed reflective film 411 and the movable reflective film 421 include metal films such as Ag and Ag alloys, and dielectric multilayer films including a high refractive index layer and a low refractive index layer.

[0048] As constituent materials of the fixed electrode 412 and the movable electrode 422 , for example, various conductive materials can be cited.

[0049] Figure 1 The spectroscopic measurement unit 10 shown further includes a spectroscopic unit-side optical system 81 and an imaging element-side optical system 83 .

[0050] The spectroscopic unit-side optical system 81 is arranged between the imaging subject X and the spectroscopic unit 41 . Figure 1 The spectroscopic unit side optical system 81 shown includes an incident lens 811 as an incident optical system and a projection lens 812. The spectroscopic unit side optical system 81 guides the reflected light reflected by the imaging object X to the spectroscopic unit 41.

[0051] The imaging element side optical system 83 is arranged between the spectroscopic unit 41 and the imaging element 21 . Figure 1The imaging element side optical system 83 shown includes an incident / exit lens 831. Such an imaging element side optical system 83 guides the outgoing light emitted from the spectroscopic unit 41 to the imaging element 21.

[0052] By providing at least one of the spectrometer-side optical system 81 and the image sensor-side optical system 83 in the spectroscopic measurement unit 10 , the focusing efficiency of the image sensor 21 for light reflected from the object X can be improved.

[0053] Note that at least one of the spectrometer-side optical system 81 and the image sensor-side optical system 83 may be omitted depending on the light-gathering efficiency of the image sensor 21 .

[0054] In addition, the spectroscopic side optical system 81 Figure 1 In addition to the positions shown, the optical fiber may be arranged between the spectroscopic unit 41 and the image sensor side optical system 83 .

[0055] The spectrometer 10 has been described above, but the position of the spectrometer 41 is not limited to Figure 1 Specifically, Figure 1 In the illustrated spectroscopic measurement unit 10 , the spectroscopic unit 41 is disposed between the imaging object X and the imaging element 21 . However, the spectroscopic unit 41 may be disposed between the imaging object X and the light source 31 .

[0056] 1.2. Display

[0057] The display unit 15 displays an image obtained by visualizing the spectroscopic image captured by the imaging element 21 and other arbitrary information. As the display unit 15, for example, a liquid crystal display element, an organic EL display element, or the like is used.

[0058] 1.3. Input

[0059] The input unit 16 receives input of data necessary for the operation of the control unit 60 from the user of the inspection apparatus 1 .

[0060] As the input unit 16 , for example, a touch panel, a slider, a keyboard, a mouse, etc. The input unit 16 may be combined with the display unit 15 and integrated with the display unit 15 .

[0061] 1.4. Storage

[0062] The storage unit 17 stores various information such as programs and data required for the operation of each functional unit of the control unit 60 , data acquired by the spectroscopic measurement unit 10 , data required for display on the display unit 15 , and data input by the input unit 16 .

[0063] The storage unit 17 uses a memory such as a RAM (Random Access Memory) or a ROM (Read Only Memory).

[0064] 1.5. Control Department

[0065] Figure 1 The control unit 60 shown includes a light source control unit 601, a spectroscopic control unit 602, an image generation unit 603, a display control unit 605, and a determination unit 610. The operation of each of these functional units is achieved through a combination of hardware such as a processor (CPU), memory, and external interfaces. For example, the control unit 60 reads and executes a program stored in the storage unit 17 to operate each functional unit and achieve its functions.

[0066] The light source control unit 601 controls the lighting and extinguishing of the light source 31 and the wavelength and intensity of the emitted light based on information input to the input unit 16 and information stored in the storage unit 17 .

[0067] The spectroscopic control unit 602 obtains a driving voltage corresponding to a specific wavelength range of light emitted from the spectroscopic unit 41 based on the information stored in the storage unit 17. The spectroscopic control unit 602 then outputs a control signal for applying the obtained driving voltage to the electrostatic actuator 45 of the spectroscopic unit 41. In this way, the spectroscopic control unit 602 can control the operation of the spectroscopic unit 41 and the specific wavelength range of light emitted from the spectroscopic unit 41.

[0068] The image generation unit 603 controls the operation of the spectroscopic measurement unit 10 so as to capture light incident on the imaging element 21 via the spectroscopic unit 41. A spectroscopic image is then generated based on the captured data obtained from the imaging element 21. The generated spectroscopic image is stored in the storage unit 17. Multiple wavelengths are selected from the reflected light from the imaging object X, and the spectroscopic image includes images captured at each wavelength. It should be noted that when the image generation unit 603 stores the spectroscopic image in the storage unit 17, it also stores the specific wavelength region used to generate the spectroscopic image.

[0069] It should be noted that the image generating unit 603 may store the visualized image obtained by visualizing the spectral image together with the spectral image in the storage unit 17 , or may directly display the visualized image on the display unit 15 .

[0070] The display control unit 605 causes the display unit 15 to display the spectroscopic image, various information, and the like as visualized images.

[0071] The determination unit 610 includes a division unit 611 , a reference value determination unit 612 , a spectrum generation unit 613 , a color value calculation unit 614 , a color difference calculation unit 615 , and a determination unit 616 .

[0072] The segmentation unit 611 segments the reference image Ps to generate a plurality of first segmented regions, and segments the captured image Px, which is an image of the captured object X, to generate a plurality of second segmented regions, which will be described in detail later.

[0073] Such a dividing unit 611 executes step S102 and step S202 described later.

[0074] In a second embodiment described later, the reference value determination unit 612 determines a reference value for obtaining the color difference between the first divided area and the second divided area.

[0075] The spectrum generating unit 613 generates a spectral spectrum for each pixel based on the spectral image of the object X and the specific wavelength region stored in the storage unit 17. A spectral spectrum is the distribution of light intensity at each wavelength, and a spectral spectrum for each pixel can be generated based on the spectral image. Therefore, the spectrum generating unit 613 can also calculate an "overall spectrum," which is the average spectral spectrum of the entire measurement target region, and a "regional spectrum," which is the average spectral spectrum of each region generated by the segmentation unit 611.

[0076] In this embodiment, the spectral spectrum is a spectrum obtained by measuring light intensity in four or more wavelength bands. Furthermore, the spectral spectrum according to this embodiment is preferably a spectrum obtained by measuring light intensity in 16 or more wavelength bands.

[0077] Note that the spectrum generating unit 613 may be configured to generate spectral information based on information directly obtained from the image generating unit 603 without passing through the storage unit 17 . The generated spectral information is stored in the storage unit 17 .

[0078] Such a spectrum generating unit 613 executes step S103 and step S203 described later.

[0079] The color value calculation unit 614 calculates tristimulus values ​​for each region based on the spectroscopic spectrum, for example, and then calculates color values ​​based on the obtained tristimulus values. These color values ​​represent the color of the entire measurement target region and the color of each region. The obtained color values ​​are stored in the storage unit 17 along with information identifying the entire measurement target region and information identifying each region.

[0080] Such a color value calculation unit 614 executes step S104 and step S204 described later.

[0081] The color difference calculation unit 615 calculates the color difference from the reference value based on the color value of each region obtained by the color value calculation unit 614. The color difference calculation unit 615 executes step S105 and step S205 described later.

[0082] The determination unit 616 compares the color difference calculated by the color difference calculation unit 615 with a threshold value to determine whether the color difference is within an acceptable range. The determination result is stored in the storage unit 17 and displayed on the display unit 15 as needed. The determination unit 616 executes steps S106 and S206 to S212, which will be described later.

[0083] 2. Inspection method

[0084] Next, based on Figure 3 as well as Figure 4 The flowchart shown in FIG. 1 illustrates an example of the inspection method of the present invention.

[0085] The inspection method comprises: a first step S1, such as Figure 3 As shown, the reference image data DPs of the reference image Ps is obtained and various preparations are performed; and the second step S2, as shown Figure 4 Check as shown.

[0086] 2.1. First step S1

[0087] First, in step S101, reference image data DPs for a reference image Ps is acquired. This step may be performed by capturing an image of a reference object using the spectroscopic measurement unit 10, acquiring reference image data DPs for the reference image Ps from the input unit 16, or reading and acquiring reference image data DPs for the reference image Ps pre-stored in the storage unit 17.

[0088] Next, in step S102, the number of vertical and horizontal divisions is specified. That is, how to divide the reference image Ps is determined and the first divided image is set. Figure 5 As shown, a total of 8 first segmented areas are set, with 2 rows and 4 columns. It should be noted that in the following description, the 4 segmented areas in the upper section of the figure are referred to as the first segmented area Ps1, the first segmented area Ps2, the first segmented area Ps3, and the first segmented area Ps4, from the left side of the figure, and the 4 segmented areas in the lower section of the figure are referred to as the first segmented area Ps5, the first segmented area Ps6, the first segmented area Ps7, and the first segmented area Ps8, from the left side of the figure.

[0089] Next, in step S103, the spectral images of each of the first segmented area Ps1 to the first segmented area Ps8 are measured, that is, the spectral spectrum is obtained. The scanning (sweep) wavelength range of the spectral spectrum can be set to any wavelength region in the visible light region, for example, a wavelength region of 400 nm to 700 nm or a wavelength region of 380 nm to 780 nm. In addition, these wavelength regions can be a structure that can be set using the input unit 16, or they can be pre-set. In addition, the measurement interval is not particularly limited, for example, it can be set to 5 nm, 10 nm, or 20 nm. These measurement intervals can be a structure that can be set using the input unit 16, or they can be pre-set.

[0090] Next, in step S104, the color values ​​of the first segmented area Ps1 to the first segmented area Ps8 are calculated. The color value mentioned here refers to the average color value of each of the first segmented area Ps1 to the first segmented area Ps8. As a method for calculating the color value, a method of calculating from the overall XYZ value according to the provisions of a prescribed color space can be listed. As examples of prescribed color spaces, the L*a*b* colorimetric system, the LCH colorimetric system, the Munsell colorimetric system, the Yxy colorimetric system, etc. can be listed. When a non-luminous object such as a printed matter or a fabric is the inspection object, the color value is preferably obtained according to the provisions of the color space of the L*a*b* colorimetric system.

[0091] Next, in step S105, the color difference ΔE of the first segmented area Ps1 to the first segmented area Ps8 is calculated and the calculation results are stored. In this embodiment, the color difference ΔE refers to the difference in color value from the reference color Cs. That is, the color difference ΔE of the first segmented area Ps1 can be obtained by calculating the difference between the average color value of the first segmented area Ps1 and the color value of the reference color Cs. Similarly, the color difference ΔE of the first segmented area Ps2 can be obtained by calculating the difference between the average color value of the first segmented area Ps2 and the color value of the reference color Cs. Similarly, the color difference ΔE of the first segmented area Ps3 can be obtained by calculating the difference between the average color value of the first segmented area Ps3 and the color value of the reference color Cs. Similarly, the color difference ΔE of the first segmented area Ps4 can be obtained by calculating the difference between the average color value of the first segmented area Ps4 and the color value of the reference color Cs. Similarly, the color difference ΔE of the first segmented area Ps5 can be calculated by calculating the difference between the average color value of the first segmented area Ps5 and the color value of the reference color Cs. Similarly, the color difference ΔE of the first segmented area Ps6 can be calculated by calculating the difference between the average color value of the first segmented area Ps6 and the color value of the reference color Cs. Similarly, the color difference ΔE of the first segmented area Ps7 can be calculated by calculating the difference between the average color value of the first segmented area Ps7 and the color value of the reference color Cs. Similarly, the color difference ΔE of the first segmented area Ps8 can be calculated by calculating the difference between the average color value of the first segmented area Ps8 and the color value of the reference color Cs.

[0092] The specific method for calculating color difference is not particularly limited, and a method using a known color difference formula can be used. Examples of such color difference formulas include the CIE76 color difference formula (ΔE76), the CIE94 color difference formula (ΔE94), the CMC color difference formula (ΔEcmc), and the CIEDE2000 color difference formula (ΔE00).

[0093] Next, in step S106, the waveform information of the color difference ΔE of the first divided area Ps1 to the first divided area Ps8, that is, the ΔE waveform, is calculated and stored. Figure 7 As shown, the ΔE waveform can be represented by a graph in which the color differences ΔE of the first divided areas Ps1 to Ps8 are plotted.

[0094] Through the first step S1 described above, the preparation of the reference image data DPs for the reference image Ps is completed before inspection. Specifically, the first step S1 is a first acquisition step for acquiring information obtained by assigning color difference information relative to the reference color Cs to each of the plurality of first segmented areas Ps1 through Ps8 obtained by segmenting the reference image Ps.

[0095] 2.2. Second step S2

[0096] First, in step S201, captured image data DPx of captured image Px is acquired. In this step, the spectroscopic measurement unit 10 is used to capture the subject X and acquire the captured image data DPx of captured image Px. However, the present invention is not limited to this configuration; the captured image data DPx of captured image Px may be acquired by inputting the captured image data DPx from the input unit 16, or by reading and acquiring the captured image data DPx of captured image Px pre-stored in the storage unit 17.

[0097] In this step, if the position of the measuring object X in the captured image Px is offset from the position of the measuring object X in the reference image Ps, a process such as trimming may be performed to arrange them at the same position.

[0098] Next, in step S202, the number of vertical and horizontal divisions is specified. That is, it is determined how to divide the captured image Px to set the second divided image. In this step, the number of divisions is set to be the same as the number of divisions set in step S102 of the first step S1. Therefore, if Figure 8 As shown, a total of 8 second segmented areas are set, with 2 rows and 4 columns. It should be noted that in the following description, the 4 segmented areas in the upper section of the figure are referred to as the second segmented area Px1, the second segmented area Px2, the second segmented area Px3, and the second segmented area Px4, in order from the left side of the figure, and the 4 segmented areas in the lower section of the figure are referred to as the second segmented area Px5, the second segmented area Px6, the second segmented area Px7, and the second segmented area Px8, in order from the left side of the figure.

[0099] Next, in step S203 , the spectral images of each of the second divided regions Px1 to Px8 are measured, that is, the spectral spectrum is obtained. In this step, the spectral spectrum is obtained in the same manner as in step S103 of the first step S1 .

[0100] Next, in step S204, the color values ​​of the second segmented areas Px1 to Px8 are calculated. The color value here refers to the average color value of each of the second segmented areas Px1 to Px8. This calculation method is the same as step S103 of step S1.

[0101] Next, in step S205, the color difference ΔE of the second segmented area Px1 to the second segmented area Px8 is calculated and the calculation result is stored. Figure 9As shown, the color difference ΔE of the second segmented area Px1 can be calculated by calculating the difference between the average color value of the second segmented area Px1 and the color value of the reference color Cs. Similarly, the color difference ΔE of the second segmented area Px2 can be calculated by calculating the difference between the average color value of the second segmented area Px2 and the color value of the reference color Cs. Similarly, the color difference ΔE of the second segmented area Px3 can be calculated by calculating the difference between the average color value of the second segmented area Px3 and the color value of the reference color Cs. Similarly, the color difference ΔE of the second segmented area Px4 can be calculated by calculating the difference between the average color value of the second segmented area Px4 and the color value of the reference color Cs. Similarly, the color difference ΔE of the second segmented area Px5 can be calculated by calculating the difference between the average color value of the second segmented area Px5 and the color value of the reference color Cs. Similarly, the color difference ΔE of the second segmented area Px6 can be calculated by calculating the difference between the average color value of the second segmented area Px6 and the color value of the reference color Cs. Similarly, the color difference ΔE of the second segmented area Px7 can be calculated by calculating the difference between the average color value of the second segmented area Px7 and the color value of the reference color Cs. Similarly, the color difference ΔE of the second segmented area Px8 can be calculated by calculating the difference between the average color value of the second segmented area Px8 and the color value of the reference color Cs.

[0102] The specific method of calculating the color difference is as described in the description of step S105 .

[0103] Next, in step S206, the waveform information of the color difference ΔE of the second divided area Px1 to the second divided area Px8, that is, the ΔE waveform, is calculated and stored. Figure 10 As shown in FIG. 1 , the ΔE waveform can be represented by a graph in which the color differences ΔE of the second divided areas Px1 to Px8 are plotted.

[0104] In addition, in this step, Figure 11 As shown, captured image data DPx' is created for captured image Px' obtained by rotating captured image Px by 180°. Specifically, the four segmented areas in the upper section of the figure are, from the left in the figure, the second segmented area Px8, the second segmented area Px2, the second segmented area Px6, and the second segmented area Px5, and the four segmented areas in the lower section of the figure are, from the left in the figure, the second segmented area Px4, the second segmented area Px3, the second segmented area Px2, and the second segmented area Px1.

[0105] Then, if Figure 12 As shown, the color difference ΔE of the second divided area Px1 to the second divided area Px8 is calculated, and the ΔE waveform is calculated and stored. Figure 13 As shown, the ΔE waveform can be represented by a graph in which the color differences ΔE of the second divided area Px8 to the second divided area Px1 are plotted sequentially from the left.

[0106] Such steps S201 to S205 are second acquisition steps for acquiring information by assigning information on color differences with respect to the reference color Cs to each of the plurality of second divided regions Px1 to Px8 obtained by dividing the captured image Px.

[0107] Next, in step S207, Figure 7 The ΔE waveform shown and the ΔE calculated in step S206 Figure 10 The ΔE waveforms shown are compared to determine whether they match. This determination is made using, for example, the Mahalanobis distance, based on a pre-set threshold. Specifically, the color differences ΔE between the first segmented areas Ps1 to Ps8 and the color differences ΔE between the second segmented areas Px1 to Px8 are compared using the specified combinations to determine whether the deviation is below a specified value.

[0108] It should be noted that the comparison in this step can be said to be performed based on the following combination 1.

[0109] Combination 1:

[0110] (Information on the Color Difference of the First Division Region Ps1 and the Color Difference of the Second Division Region Px1)

[0111] (Information on the Color Difference of the First Segmented Area Ps2 and the Color Difference of the Second Segmented Area Px2)

[0112] (Information on the Color Difference of the First Segmented Area Ps3 and the Color Difference of the Second Segmented Area Px3)

[0113] (Information on the Color Difference of the First Division Region Ps4 and Information on the Color Difference of the Second Division Region Px4)

[0114] (Information on the Color Difference of the First Division Region Ps5 and Information on the Color Difference of the Second Division Region Px5)

[0115] (Information on the Color Difference of the First Division Region Ps6 and Information on the Color Difference of the Second Division Region Px6)

[0116] (Information on the Color Difference of the First Segmented Area Ps7 and Information on the Color Difference of the Second Segmented Area Px7)

[0117] (Information on the Color Difference of the First Division Region Ps8 and Information on the Color Difference of the Second Division Region Px8)

[0118] Step S207 is a first comparison step of comparing the color difference information of the first divided areas Ps1 to Ps8 with the color difference information of the corresponding second divided areas Px1 to Px8. The comparison result in this step is the first comparison result.

[0119] If it is determined that they are consistent in step S207, the process proceeds to step S209. On the other hand, if it is determined that they are inconsistent in step S207, the process proceeds to step S208. Figure 7 The ΔE waveform shown and the ΔE calculated in step S206 Figure 13 The ΔE waveforms shown are compared to determine whether they match. The determination in this step is performed in the same manner as in step S207. That is, the color differences ΔE of the first segmented areas Ps1 to Ps8 are compared with the color differences ΔE of the second segmented areas Px1 to Px8 using the determined combinations to determine whether the deviation is below a specified value.

[0120] It should be noted that the comparison in this step can be said to be performed based on the following combination 2.

[0121] Combination 2:

[0122] (Information on the Color Difference of the First Division Region Ps1 and Information on the Color Difference of the Second Division Region Px8)

[0123] (Information on the color difference of the first divided area Ps2 and information on the color difference of the second divided area Px7)

[0124] (Information on the Color Difference of the First Division Region Ps3 and Information on the Color Difference of the Second Division Region Px6)

[0125] (Information on the Color Difference of the First Division Region Ps4 and Information on the Color Difference of the Second Division Region Px5)

[0126] (Information on the Color Difference of the First Division Region Ps5 and Information on the Color Difference of the Second Division Region Px4)

[0127] (Information on the Color Difference of the First Division Region Ps6 and Information on the Color Difference of the Second Division Region Px3)

[0128] (Information on the Color Difference of the First Segmented Area Ps7 and Information on the Color Difference of the Second Segmented Area Px2)

[0129] (Information on the Color Difference of the First Segmented Area Ps8 and Information on the Color Difference of the Second Segmented Area Px1)

[0130] Step S208 is a second comparison step that compares the color difference information of the first segmented areas Ps1 to Ps8 with the color difference information of the second segmented areas Px1 to Px8 using a different combination than the combination compared in step S207, the first comparison step. The comparison result in this step is a second comparison result.

[0131] If the determination in step S208 is that they do not match, in step S212, the reference image data DPs and the captured image data DPx are deemed to be inconsistent. Note that this determination result may be displayed on the display unit 15 as needed. On the other hand, if the determination in step S208 is that they do match, the process proceeds to step S209.

[0132] By going through steps S207 and S208, the following advantages can be achieved. For example, when capturing a captured image Px rotated 180° and comparing it with the reference image Ps, the images may be judged inconsistent despite being consistent. This is a drawback of conventional methods that perform only one comparison, assuming that the captured image Px and the reference image Ps are oriented in the same direction. In contrast, the present invention, based on the comparison results of the first and second comparison steps, can prevent the conventional misjudgment of whether the reference image data DPs and the captured image data DPx are consistent, enabling more accurate inspection.

[0133] Next, in step S209, a color check is performed. Specifically, the color values ​​of the reference image Ps and the captured image Px are compared to determine whether the degree of deviation is within an allowable range.

[0134] This step may, for example, determine whether the difference between the average color value of the entire reference image Ps and the color value of the entire captured image Px is below a threshold. Alternatively, the color values ​​of each of the first segmented areas Ps1 to Ps8 and the color values ​​of each of the second segmented areas Px1 to Px8 may be compared using combination 1 or combination 2 to determine whether the difference in color value between the areas is below a threshold. In the latter case, the comparison is performed using the combination 1 or combination 2 that is determined to be consistent in step S207 or step S208.

[0135] If the difference between the color values ​​of the reference image Ps and the captured image Px is determined to be less than the threshold value in step S209, the reference image data DPs and the captured image data DPx are deemed to be consistent in step S211. The determination result may be displayed on the display unit 15 as needed.

[0136] If it is determined in step S209 that the difference between the color value of the reference image Ps and the color value of the captured image Px exceeds the threshold, it is determined in step S212 that the reference image data DPs and the captured image data DPx do not coincide with each other.

[0137] Note that steps S209 and S210 may be omitted. Furthermore, even if the difference between the color values ​​of the reference image Ps and the captured image Px exceeds a threshold in step S209, the process may proceed to step S211 and determine that they are consistent. However, in this case, it is preferable to store the information that the reference image data DPs and the captured image data DPx are consistent but differ in hue (color tone).

[0138] By going through such step S209 , even the matching of color values ​​can be regarded as matching, and a more accurate inspection can be performed.

[0139] As described above, the inspection method of the present invention is an inspection method for inspecting whether the reference image data DPs of the reference image Ps is consistent with the captured image data DPx of the captured image Px. The inspection method comprises: a first acquisition step of acquiring information obtained by assigning information of color differences relative to the reference color Cs to each of the plurality of first segmented areas Ps1 to first segmented areas Ps8 obtained by segmenting the reference image Ps; a second acquisition step of acquiring information obtained by assigning information of color differences relative to the reference color Cs to each of the plurality of second segmented areas Px1 to second segmented areas Px8 obtained by segmenting the captured image; a first comparison step of acquiring information obtained by assigning information of color differences relative to the reference color Cs to each of the plurality of first segmented areas Ps1 to first segmented areas Ps8 obtained by segmenting the captured image; In this inspection method, the color difference information of the first segmented areas Ps1 to Ps8 is compared with the color difference information of the corresponding second segmented areas Px1 to Px8; and in a second comparison step, the color difference information of the first segmented areas Ps1 to Ps8 is compared with the color difference information of the second segmented areas Px1 to Px8 using a combination different from the combination compared in the first comparison step. Based on the first comparison result obtained in the first comparison step and the second comparison result obtained in the second comparison step, a determination is made as to whether the reference image data DPs and the captured image data DPx are consistent. This present invention offers the following advantages. For example, when a captured image Px is obtained in a 180° rotated state and compared with the reference image Ps, a determination of inconsistency may occur even though the comparison should be consistent. This is a disadvantage of performing only one comparison, i.e., assuming that the captured image Px and the reference image Ps are in the same orientation, as in the conventional method. In contrast, in the present invention, whether the reference image data DPs and the captured image data DPx are consistent is determined based on the comparison results in the first and second comparison steps, thereby preventing conventional erroneous determinations and enabling more accurate inspections.

[0140] In addition, the inspection apparatus of the present invention includes a control unit 60 for inspecting whether the reference image data DPs of the reference image Ps is consistent with the captured image data DPx of the captured image Px. The control unit 60 executes: a first acquisition step for acquiring information obtained by assigning information of color differences relative to the reference color Cs to each of the plurality of first segmented areas Ps1 to first segmented areas Ps8 obtained by segmenting the reference image Ps; a second acquisition step for acquiring information obtained by assigning information of color differences relative to the reference color Cs to each of the plurality of second segmented areas Px1 to second segmented areas Px8 obtained by segmenting the captured image; a first comparison step for acquiring information obtained by assigning information of color differences relative to the reference color Cs to each of the plurality of first segmented areas Ps1 to first segmented areas Ps8 obtained by segmenting the captured image; The color difference information of the first segmented area Ps1 to Ps8 is compared with the color difference information of the corresponding second segmented areas Px1 to Px8; and in a second comparison step, the color difference information of the first segmented area Ps1 to Ps8 is compared with the color difference information of the second segmented areas Px1 to Px8 using a combination different from the combination compared in the first comparison step. The control unit 60 determines whether the reference image data DPs and the captured image data DPx are consistent based on the first comparison result obtained in the first comparison step and the second comparison result obtained in the second comparison step. According to the present invention, as described above, it is possible to prevent conventional erroneous judgments and enable more accurate inspection.

[0141] Furthermore, in the inspection method of the present invention, if the degree of deviation between the color difference information of each of the first segmented areas Ps1 to Ps8 and the color difference information of each of the second segmented areas Px1 to Px8 in either the first comparison result or the second comparison result is less than a threshold value, the reference image data DPs is determined to be consistent with the captured image data DPx. If the degree of deviation between the color difference information of each of the first segmented areas Ps1 to Ps8 and the color difference information of each of the second segmented areas Px1 to Px8 in both the first comparison result and the second comparison result exceeds the threshold value, the reference image data DPs is determined to be inconsistent with the captured image data DPx. This makes it possible to more effectively prevent conventional misjudgments and enable more accurate inspections.

[0142] Furthermore, in the second comparison step, when the reference image Ps and the captured image Px are superimposed after being relatively rotated, the color difference information between the superimposed first and second segmented regions is compared. This effectively prevents conventional misjudgments even when the captured image Px is rotated 180°.

[0143] In addition, if Figure 7 、 Figure 10 as well as Figure 13As shown, the color difference information for comparison is waveform information showing the relationship between the color difference and the positions of the first segmented areas Ps1 to Ps8 and the second segmented areas Px1 to Px8. Thus, the first and second comparison steps can be performed by a simple method of comparing waveform information.

[0144] In the present embodiment, the reference color Cs is a predetermined color. Thus, the color difference information of the first divided areas Ps1 to Ps8 and the second divided areas Px1 to Px8 can be calculated by simple control.

[0145] Furthermore, as described in steps S209 and S210, the color values ​​of the first segmented areas Ps1 to Ps8 and the second segmented areas Px1 to Px8 are considered when determining whether the reference image data DPs and the captured image data DPx are consistent. This allows for more accurate inspection by further considering the color values ​​of the first segmented areas Ps1 to Ps8 and the second segmented areas Px1 to Px8 to be considered consistent.

[0146] Second embodiment

[0147] Figure 14 This is a graph for explaining a method of determining a reference color in the second embodiment of the inspection method of the present invention.

[0148] Hereinafter, the second embodiment will be described. However, in the following description, the differences from the first embodiment will be mainly described, and descriptions of the same matters will be omitted.

[0149] In this embodiment, the method of determining the reference color Cs when calculating the color difference in step S105 is different from that in the first embodiment. Therefore, only the method of determining the reference color Cs will be described.

[0150] First, the average color value of the first segmented area Ps1 is set as a temporary reference color, and the color difference between the first segmented area Ps1 to the first segmented area Ps8 is calculated. The color difference calculation method is as described in the first embodiment. Then, by plotting the color difference ΔE of the first segmented area Ps1 to the first segmented area Ps8, as shown in FIG. Figure 14 As shown, a waveform ΔE1 can be obtained.

[0151] Next, the average color value of the second segmented area Px3 is set as a temporary reference color, and the color difference with the first segmented area Ps1 to the first segmented area Ps8 is calculated. Then, by plotting the color difference ΔE of the first segmented area Ps1 to the first segmented area Ps8, as shown in FIG. Figure 14 As shown, a waveform ΔE3 can be obtained.

[0152] Next, the average color value of the second segmented area Px4 is set as a temporary reference color, and the color difference with the first segmented area Ps1 to the first segmented area Ps8 is calculated. Then, by plotting the color difference ΔE of the first segmented area Ps1 to the first segmented area Ps8, as shown in FIG. Figure 14 As shown, a waveform ΔE4 can be obtained.

[0153] Next, the average color value of the second segmented area Px5 is set as a temporary reference color, and the color difference with the first segmented area Ps1 to the first segmented area Ps8 is calculated. Then, by plotting the color difference ΔE of the first segmented area Ps1 to the first segmented area Ps8, as shown in FIG. Figure 14 As shown, a waveform ΔE5 can be obtained.

[0154] Next, the average color value of the second segmented area Px6 is set as a temporary reference color, and the color difference with the first segmented area Ps1 to the first segmented area Ps8 is calculated. Then, by plotting the color difference ΔE of the first segmented area Ps1 to the first segmented area Ps8, as shown in FIG. Figure 14 As shown, a waveform ΔE6 can be obtained.

[0155] Next, the average color value of the second segmented area Px7 is set as a temporary reference color, and the color difference with the first segmented area Ps1 to the first segmented area Ps8 is calculated. Then, by plotting the color difference ΔE of the first segmented area Ps1 to the first segmented area Ps8, as shown in FIG. Figure 14 As shown, a waveform ΔE7 can be obtained.

[0156] Next, the average color value of the second segmented area Px8 is set as a temporary reference color, and the color difference with the first segmented area Ps1 to the first segmented area Ps8 is calculated. Then, by plotting the color difference ΔE of the first segmented area Ps1 to the first segmented area Ps8, as shown in FIG. Figure 14 As shown, a waveform ΔE8 can be obtained.

[0157] Next, the waveform with the largest difference between the maximum and minimum color differences among waveforms ΔE1 to ΔE8 is selected. In the illustrated configuration, waveform ΔE1 is selected because the difference between the color differences of first segmented area Ps1 and first segmented area Ps2 is the largest. The temporary reference color at this point, i.e., the average color value of first segmented area Ps1, is set as the reference color Cs, and waveform ΔE1 is used in subsequent steps.

[0158] According to such a method, when waveforms are compared with each other, the waveform that most clearly expresses the characteristics of the waveform is used, thereby enabling more accurate inspection.

[0159] Thus, in this embodiment, the reference color Cs is the average color, that is, the average color value, of one of the first divided areas Ps1 to Ps8 . This eliminates the need to set the reference color Cs separately in advance, simplifying control.

[0160] Furthermore, in this embodiment, first segmented areas Ps1 through Ps8 are sequentially selected, and the degree of deviation between the average color within each selected segmented area and the average color within first segmented areas other than the selected segmented area is calculated. In other words, the color difference is calculated sequentially, and the color of the first segmented area with the largest difference between the maximum and minimum color differences is set as the reference color Cs. This configuration allows the optimal reference color Cs to be set each time, thereby enabling more accurate inspections.

[0161] It should be noted that the reference color Cs can also be stored in advance, and the control in this embodiment can be performed. Figure 7 The waveform shown and Figure 14 Among the eight waveforms shown, the color with the largest difference between the maximum color difference and the minimum color difference is selected.

[0162] While the inspection method and apparatus of the present invention have been described above with reference to the illustrated embodiments, the present invention is not limited thereto. Furthermore, the various steps and components of the inspection method and apparatus can be replaced with any other steps or components that can achieve the same function. Furthermore, any additional steps or components may be added. Furthermore, the present invention may combine features from various embodiments.

[0163] In addition, the first comparison step and the second comparison step can be performed in the order described above, or in the reverse order, or simultaneously.

[0164] It should be noted that while the above embodiments describe a configuration for comparing color difference waveforms, the present invention is not limited thereto. For example, a configuration for comparing spectroscopic spectra may also be employed. In this case, the comparison can be performed using a correlation coefficient between the waveforms or the sum of squares of the errors between the waveforms.

[0165] In the above embodiments, the captured images are rotated for comparison, but the present invention is not limited thereto and the reference image may be rotated for comparison. In this case, it is preferable to generate reference image data by rotating the reference image in advance.

[0166] In the above embodiments, the reference image and the captured image are rectangular and the segmented regions are set by dividing the image into eight regions, each with two rows and four columns. However, the number of segments and the segmentation pattern are not limited to this in the present invention. Furthermore, if the reference image and the captured image are square and have the same vertical and horizontal segmentation ratios, such as two rows and two columns, it is preferable to generate four images, each rotated 90°, and compare them.

[0167] It should be noted that in the above embodiments, a structure for acquiring a captured image using a spectroscopic unit is described, but the present invention is not limited thereto. A structure for acquiring an image captured by a capturing unit without the spectroscopic unit may also be adopted.

Claims

1. An inspection method, characterized in that: Checking whether the reference image data of the reference image is consistent with the captured image data of the captured image, the checking method comprises: a first acquisition step of acquiring information obtained by assigning information of a color difference with respect to a reference color to each of a plurality of first segmented areas obtained by segmenting the reference image; a second acquisition step of acquiring information obtained by assigning information of color difference with respect to the reference color to each of a plurality of second divided areas obtained by dividing the captured image; a first comparison step of comparing the color difference information of each of the first segmented regions with the color difference information of the corresponding second segmented regions; as well as In a second comparison step, the color difference information of each of the first divided areas and the color difference information of each of the second divided areas are compared using a combination different from the combination compared in the first comparison step. In the inspection method, based on the first comparison result obtained in the first comparison step and the second comparison result obtained in the second comparison step, it is determined whether the reference image data and the captured image data are consistent. In the second comparison step, when the reference image and the captured image are relatively rotated and overlapped, information on color differences between the overlapped first divided area and the second divided area is compared.

2. The inspection method according to claim 1, characterized in that: When the degree of deviation between the color difference information of each of the first segmented areas and the color difference information of each of the second segmented areas in one of the first comparison result and the second comparison result is below a threshold value, it is determined that the reference image data is consistent with the captured image data. If the degree of deviation between the color difference information of each first divided area and the color difference information of each second divided area in both the first comparison result and the second comparison result exceeds a threshold, it is determined that the reference image data and the captured image data do not match.

3. The inspection method according to claim 1, characterized in that: The color difference information is waveform information indicating the relationship between the color difference and the positions of the first divided area and the second divided area.

4. The inspection method according to claim 1, characterized in that: The reference color is a predetermined color.

5. The inspection method according to claim 1, characterized in that: The reference color is an average color in one of the first divided areas.

6. The inspection method according to claim 5, characterized in that: Each of the first segmented areas is selected one by one in sequence, and the degree of deviation between the average color within the selected first segmented area and the average color within the first segmented area other than the selected first segmented area is calculated in sequence, and the color of the first segmented area with the largest difference between the maximum deviation and the minimum deviation is set as the reference color.

7. The inspection method according to claim 1, characterized in that: The determination is performed taking into account the color values ​​of the first segmented area and the second segmented area.

8. The inspection method according to claim 1, wherein: The captured image is a spectroscopic image captured by a spectroscopic camera.

9. An inspection device, characterized in that: A control unit is provided to check whether the reference image data of the reference image and the captured image data of the captured image are consistent, the control unit executing: a first acquisition step of acquiring information obtained by assigning information of a color difference with respect to a reference color to each of a plurality of first segmented areas obtained by segmenting the reference image; a second acquisition step of acquiring information obtained by assigning information of color difference with respect to the reference color to each of a plurality of second divided areas obtained by dividing the captured image; a first comparison step of comparing the color difference information of each of the first segmented regions with the color difference information of the corresponding second segmented regions; as well as In a second comparison step, the color difference information of each of the first divided areas and the color difference information of each of the second divided areas are compared using a combination different from the combination compared in the first comparison step. The control unit determines whether the reference image data and the captured image data are consistent based on a first comparison result obtained in the first comparison step and a second comparison result obtained in the second comparison step. In the second comparison step, when the reference image and the captured image are relatively rotated and overlapped, information on color differences between the overlapped first divided area and the second divided area is compared.

Images