WO2021131686A1 - Inspection method, program, and inspection system - Google Patents

Abstract

Provided are an inspection method, program, and inspection system that make it possible to enhance the accuracy of inspection of the state of the surface of a subject. This inspection method comprises an acquisition step (S11) and an inspection step (S12). The acquisition step (S11) is a step for acquiring a subject image relating to the surface of a subject. In the inspection step (S12), the state of the surface of the subject is inspected on the basis of subject information that has been obtained from the subject image and includes shape information representing the shape of the frequency distribution of a pixel-value-based parameter.

Description

Inspection method, program, and inspection system

This disclosure relates to inspection methods, programs, and inspection systems. In particular, the present disclosure relates to inspection methods, programs, and inspection systems for inspecting the surface condition of an object with images.

Patent Document 1 discloses a coloring inspection apparatus. The color inspection apparatus disclosed in Patent Document 1 includes a camera having three spectral sensitivities linearly converted equivalent to the CIEXYZ color matching function, and three images having three spectral sensitivities acquired by the camera in the CIEXYZ color system. It includes an arithmetic processing device that acquires and calculates coloring data converted into stimulus values, and an illumination unit that illuminates an automobile, which is an example of a measurement object. The color inspection apparatus inspects colors by calculating a color distribution matching index indicating the overlapping ratio of two xyz chromaticity histogram distributions of an inspection object and a reference object.

Japanese Unexamined Patent Publication No. 2015-155892

The appearance of the color of the inspection object (measurement object, object) can be affected by the shape of the surface of the inspection object. Therefore, even if the color distribution matching index, which indicates the overlapping ratio of the two xyz chromaticity histogram distributions of the inspection object and the reference object, which is obtained in Patent Document 1, is high, the visual sensation felt by a person may be different.

An object of the present disclosure is to provide an inspection method, a program, and an inspection system capable of improving the accuracy of inspection of the surface condition of an object.

The inspection method of one aspect of the present disclosure includes an acquisition step and an inspection step. The acquisition step is a step of acquiring an object image relating to the surface of the object. The inspection step is a step of inspecting the state of the surface of the object based on the target information including the shape information representing the shape of the frequency distribution of the parameter based on the pixel value obtained from the target image.

Another aspect of the program of the present disclosure is a program for causing one or more processors to execute the inspection method of the present disclosure.

Another aspect of the inspection system of the present disclosure is a target information including an acquisition unit that acquires a target image on the surface of an object and shape information that represents the shape of a frequency distribution of parameters based on pixel values obtained from the target image. It is provided with an inspection unit that inspects the surface condition of the object based on the above.

According to the aspect of the present disclosure, it is possible to improve the accuracy of the inspection of the surface condition of the object.

FIG. 1 is a flowchart of an inspection method of one embodiment. FIG. 2 is a block diagram of an inspection system that implements the above inspection method. FIG. 3 is an explanatory diagram of a method for generating shape information used in the above inspection method. FIG. 4 is an explanatory diagram of an example of shape information obtained by the inspection system. FIG. 5 is an explanatory diagram of another example of the shape information obtained by the inspection system. FIG. 6 is an explanatory diagram of another example of the shape information obtained by the inspection system. FIG. 7 is an explanatory diagram of an example of the target information and the reference information obtained by the inspection system. FIG. 8 is an explanatory diagram of another example of the target information and the reference information obtained by the inspection system. FIG. 9 is an explanatory diagram of another example of the target information and the reference information obtained by the inspection system. FIG. 10 is a graph showing the matching rate of a plurality of samples prepared as an object with the reference object. FIG. 11 is a graph showing the results of visual evaluation of a plurality of samples prepared as objects. FIG. 12 is a graph showing the relationship between the concordance rate and the result of visual evaluation of a plurality of samples prepared as objects. FIG. 13 is an explanatory diagram of a method of generating shape information in one modification. FIG. 14 is an explanatory diagram of a method of generating shape information in one modification. FIG. 15 is an explanatory diagram of a method of acquiring a target image in an inspection method of a modified example. FIG. 16 is an explanatory diagram of an example of the target image. FIG. 17 is an explanatory diagram of an example of the target image. FIG. 18 is an explanatory diagram of an example of a histogram obtained from the target image. FIG. 19 is an explanatory diagram of an example of a histogram obtained from the target image. FIG. 20 is an explanatory diagram of an example of an image of the surface of an object. FIG. 21 is an explanatory diagram of a method of acquiring a target image in an inspection method of a modified example. FIG. 22 is an explanatory diagram of a method of generating shape information of one modification. FIG. 23 is an explanatory diagram of a method of acquiring a target image in the inspection method of one modified example. FIG. 24 is a diagram showing an example of inspection results presented by the inspection system. FIG. 25 is a diagram showing another example of the inspection result presented by the inspection system. FIG. 26 is a diagram showing another example of the inspection result presented by the inspection system. FIG. 27 is a diagram showing another example of the inspection result presented by the inspection system. FIG. 28 is a diagram showing another example of the inspection result presented by the inspection system.

(1) Embodiment (1.1) Outline The inspection method of one embodiment can be used for inspecting the surface condition of the object 100 as shown in FIG. The surface condition of the object 100 may include the color, shape, texture, glossiness, gradation, and coating condition of the surface of the object 100. In the present embodiment, the gradation may include not only the gradation generated depending on the incident angle and the reflection angle when the surface is a curved surface, but also the flip-flop property, the color travel effect, the brilliance feeling, and the graininess feeling. In the present embodiment, the object 100 is assumed to be an automobile. In particular, the surface of the object 100 is a part of the outer surface of the vehicle body of the automobile. The object 100 is not limited to an automobile. For example, the object 100 may or may not be a moving body other than an automobile. Examples of mobiles include motorcycles, trains, drones, aircraft, construction machinery, and ships. Further, the object 100 may be an electric device, tableware, a container, furniture, clothing, a building material, or the like. In short, the object 100 may be an object having a surface.

FIG. 1 shows a flowchart of the inspection method of the present embodiment. The inspection method of the present embodiment includes acquisition step S11 and inspection step S12. The acquisition step S11 is a step of acquiring an object image relating to the surface of the object 100. The inspection step S12 inspects the state of the surface of the object 100 based on the object information including the shape information representing the shape of the frequency distribution of the parameter based on the pixel value obtained from the object image.

In the inspection method of the present embodiment, the state of the surface of the object 100 is inspected by using the shape information representing the shape of the frequency distribution of the parameters based on the pixel values obtained from the object image on the surface of the object 100. To do. That is, in the inspection method of this embodiment, the shape of the frequency distribution itself is used. As a result, according to the inspection method of the present embodiment, the accuracy of inspection of the surface condition of the object 100 can be improved.

(1.2) Details Hereinafter, the inspection method of the present embodiment will be described in more detail with reference to FIGS. 1 to 12. The inspection method of this embodiment can be executed by the inspection system 1 shown in FIG. The inspection system 1 is a system for inspecting the surface of the object 100. The inspection system 1 has a function as a coloring inspection device. The inspection system 1 can also paint the object 100. The inspection system 1 can paint the object 100 according to the result of the inspection, whereby the object 100 with the desired coating can be obtained.

As shown in FIG. 2, the inspection system 1 includes a determination system 10, a lighting system 20, an imaging system 30, and a painting system 40.

The lighting system 20 is a system for irradiating the surface of the object 100 with light. The lighting system 20 includes one or more lamps that illuminate the object 100 with light. The lamp is, for example, an LED (Light Emitting Diode) lamp. The lamp also emits white light. In the lighting system 20, the number of lamps is not particularly limited, and the type of lamp may be a light source other than the LED. Further, the emission color of the lamp is not limited to white. The emission color of the lamp can be appropriately set in consideration of the color of the object 100 and the color detectable by the imaging system 30. Further, the wavelength of the light emitted by the lighting system 20 may be changeable.

The imaging system 30 is a system for generating an image (digital image) of the surface of the object 100. In the present embodiment, the imaging system 30 images the surface of the object 100 illuminated by the lighting system 20 to generate an image of the surface of the object 100. The imaging system 30 includes one or more cameras. The camera comprises one or more image sensors. The camera may include one or more line sensors.

The painting system 40 is a system for painting the surface of the object 100. The painting system 40 includes one or more painting parts (painting robots). Since the painting robot may have a conventionally known configuration, detailed description thereof will be omitted.

As shown in FIG. 2, the determination system 10 includes an input / output unit 11, a storage unit 12, and a processing unit 13. The determination system 10 can be realized by a computer system. A computer system may include one or more processors, one or more connectors, one or more communication devices, one or more memories, and the like.

The input / output unit 11 inputs / outputs information between the lighting system 20, the imaging system 30, and the painting system 40. In the present embodiment, the input / output unit 11 is communicably connected to the lighting system 20, the imaging system 30, and the painting system 40. The input / output unit 11 includes one or more input / output devices and uses one or more input / output interfaces.

The storage unit 12 is used to store the information used by the processing unit 13. The storage unit 12 includes one or more storage devices. The storage device is, for example, a RAM (RandomAccessMemory) or an EEPROM (ElectricallyErasableProgrammableReadOnlyMemory).

The processing unit 13 can be realized by, for example, one or more processors (microprocessors). That is, one or more processors execute one or more programs (computer programs) stored in one or more memories, thereby functioning as the processing unit 13. The one or more programs may be recorded in advance in one or more memories, may be recorded through a telecommunication line such as the Internet, or may be recorded and provided on a non-temporary recording medium such as a memory card.

As shown in FIG. 2, the processing unit 13 has an acquisition unit F11, an inspection unit F12, a presentation unit F13, and a control unit 14. The acquisition unit F11, the inspection unit F12, the presentation unit F13, and the control unit F14 do not show a substantive configuration, but show a function realized by the processing unit 13.

The acquisition unit F11 executes acquisition step S11 (see FIG. 1) to acquire an object image relating to the surface of the object 100. In the present embodiment, the target image is an image obtained by capturing the surface of the object 100 illuminated by the lighting system 20 with the imaging system 30. Here, the imaging system 30 images a part of the surface of the object 100, not the entire surface. Therefore, from the object 100, a plurality of target images having different surface portions of the captured object 100 are acquired. That is, the inspection is performed for each part of the surface of the object 100. In the present embodiment, the acquisition unit F11 acquires an image of the surface of the object 100 from the imaging system 30. That is, the acquisition unit F11 receives an image from the image pickup system 30 via the input / output unit 11. The image acquired by the acquisition unit F11 from the imaging system 30 is determined by the imaging conditions of the imaging system 30. The imaging condition may include a relative positional relationship between the object 100, the lighting system 20, and the imaging system 30 (that is, information on the positional relationship between the object to be photographed, the lighting, and the camera). In the present embodiment, the pixel value of the target image may include the values of three colors. The values of the three colors can be an R value corresponding to red, a G value corresponding to green, and a B value corresponding to blue. As described above, in the present embodiment, the pixel value is represented by the RGB color system.

The inspection unit F12 executes the inspection step S12 (see FIG. 1) for inspecting the surface condition of the object 100. For inspection of the surface condition of the object 100, the inspection unit F12 generates target information from the target image (S12a, S12b in FIG. 1). The target information includes shape information representing the shape of the frequency distribution of the parameter based on the pixel value. In this embodiment, the parameter is a color parameter. In particular, as the parameters, the lightness (L), the saturation (C), and the hue (h), which are the parameters of the LCh color system, are used. Therefore, the inspection unit F12 converts the pixel value of the target image from the RGB color system to the LCh color system. Then, the inspection unit F12 obtains the frequency distribution of the parameters (brightness, saturation, hue) based on the pixel value. Therefore, in the present embodiment, the target information includes shape information regarding each of the plurality of parameters (three of lightness, saturation, and hue).

In the present embodiment, the shape information includes a feature amount representing the feature of the shape of the frequency distribution. For example, FIG. 3 shows a histogram H10 representing a frequency distribution of lightness. In FIG. 3, the horizontal axis represents the parameter brightness, and the vertical axis represents the frequency. In the present embodiment, the shape of the frequency distribution is the shape of a histogram representing the frequency distribution. The feature quantity includes a plurality of evaluation values and representative values.

The plurality of evaluation values are values representing the shape of the histogram representing the frequency distribution. In this embodiment, the plurality of evaluation values are treated as vectors. Hereinafter, a plurality of evaluation values may be referred to as evaluation vectors. The evaluation vector is calculated based on the area of each of the plurality of divisions of the shape parameter of the frequency distribution. For example, as shown in FIG. 3, the inspection unit F12 obtains the area Si (S1 to S7) of each of the plurality of divisions Di (D1 to D7) of the shape parameter (brightness) of the histogram H10. Here, i is an integer of 1 or more. In the present embodiment, the plurality of divisions Di have the same width (difference between the upper limit and the lower limit of the division). Further, the inspection unit F12 obtains the total area S (= ΣSi) of the shape of the histogram H10. The inspection unit F12 uses a value obtained by dividing the area Si of the category by the total area S as the evaluation value of the category. That is, the evaluation value corresponds to the ratio of each category to the entire histogram H10. Here, if the evaluation value of the division Di is wi, then wi = Si / S is established. Then, in the example of FIG. 3, since there are seven categories D1 to D7, the evaluation vector of the histogram H10 is (w1, w2, w3, w4, w5, w6, w7).

The representative value is the representative value of the frequency distribution. In the present embodiment, the representative value corresponds to the value (center value) of the parameter (brightness in FIG. 3) that is the center of the frequency distribution. The representative value is a value obtained from the ratio (evaluation vector) of each of the plurality of divisions of the parameter of the shape of the frequency distribution to the entire shape of the shape of the frequency distribution and the value of the parameter corresponding to the plurality of divisions. For example, in FIG. 3, the value of the parameter corresponding to the division Di (D1 to D7) is Li (L1 to L7). Here, the value Li of the parameter corresponding to the division Di is a representative value of the range of the parameters corresponding to the division Di, and may be any of an average value, a mode value, a median value, a maximum value, and a minimum value. .. In this case, if the representative value of the frequency distribution is C, then C = ΣLi * wi holds. Here, "*" of Li * wi represents multiplication.

The inspection unit F12 generates shape information for each parameter based on the pixel value. In the present embodiment, the inspection unit F12 generates shape information for each of lightness, saturation, and hue with respect to the target image. In each of the lightness, saturation, and hue shape information, the feature amount includes an evaluation vector and a representative value. For example, FIGS. 4, 5 and 6 are explanatory views of examples of shape information of lightness, saturation and hue, respectively. In FIG. 4, regarding the brightness, HT1 shows a histogram, wT1 shows an evaluation vector, and CT1 shows a representative value. Further, in FIG. 5, regarding the saturation, HT2 shows a histogram, wT2 shows an evaluation vector, and CT2 shows a representative value. Further, FIG. 6 shows a histogram in HT3, an evaluation vector in wT3, and a representative value in CT3 with respect to hue. As described above, it can be said that the feature amount of the shape information is a simplified representation of the frequency distribution so that the shape and position are not impaired.

The inspection unit F12 compares the target information generated in this way with the reference information (S12c in FIG. 1). The reference information can be stored in advance in the storage unit 12. The reference information includes shape information obtained from a reference image regarding the surface of the reference object that is the reference of the object 100. The reference information is generated by the same method as the target information. In the reference information, the lightness (L), the saturation (C), and the hue (h), which are the parameters of the LCh color system, are used as in the target information. Therefore, the inspection unit F12 converts the pixel value of the reference image from the RGB color system to the LCh color system as necessary, and obtains the frequency distribution of the parameters (brightness, saturation, hue) based on the pixel value. .. Therefore, in the present embodiment, the reference information includes shape information relating to each of the plurality of parameters (three of lightness, saturation, and hue) as well as the target information. Then, as with the target information, the feature amount includes the evaluation vector and the representative value in each of the lightness, saturation, and hue shape information. For example, FIGS. 7, 8 and 9 are explanatory views of examples of target information and reference information regarding lightness, saturation and hue, respectively. In FIG. 7, wR1 shows an evaluation vector based on the shape of the frequency distribution from the reference image, and CR1 shows a representative value of the frequency distribution from the reference image. Further, in FIG. 8, wR2 shows an evaluation vector based on the shape of the frequency distribution from the reference image, and CR2 shows a representative value of the frequency distribution from the reference image. In FIG. 9, wR3 shows an evaluation vector based on the shape of the frequency distribution from the reference image, and CR3 shows a representative value of the frequency distribution from the reference image.

The inspection unit F12 obtains the difference in the feature amount of the shape information for each parameter in the comparison between the target information and the reference information. The difference in the feature amount includes the difference in the evaluation vector and the difference in the representative value. In the example shown in FIG. 7, the difference Dw1 of the evaluation vector is wT1-wR1, and the difference Dc1 of the representative value is CT1-CR1. Table 1 below shows an example of the difference Dw1 of the evaluation vector, and Table 2 below shows an example of the difference Dc1 of the representative value.

In the example shown in FIG. 8, the difference Dw2 of the evaluation vector is wT2-wR2, and the difference Dc2 of the representative value is CT2-CR2. Table 3 below shows an example of the difference Dw2 of the evaluation vector, and Table 4 below shows an example of the difference Dc2 of the representative value.

In the example shown in FIG. 9, the difference Dw3 of the evaluation vector is wT3-wR3, and the difference Dc3 of the representative value is CT3-CR3. Table 5 below shows an example of the difference Dw3 of the evaluation vector, and Table 6 below shows an example of the difference Dc3 of the representative value.

Then, the inspection unit F12 obtains a determination value (first determination value) of the evaluation vector and a determination value (second determination value) of the representative value from the difference in the feature amount of the shape information for each parameter. Assuming that the first determination value is E1, E1 = (Dw1 ² + Dw2 ² + Dw3 ² ) ^1/2 . When the second judgment value and ^E2, E2 ⁼ a ^{(Dc1 2 + Dc2 2 + Dc3} 2) 1/2.

Then, the inspection unit F12 determines whether the surface condition of the object 100 passes or fails based on the result of comparison between the target information and the reference information (S12d in FIG. 1). In the present embodiment, when the first determination value E1 is less than the first specified value and the second determination value E2 is less than the second specified value, the inspection unit F12 passes the surface condition of the object 100. Suppose there is. On the other hand, the inspection unit F12 fails the surface condition of the object 100 when the first determination value E1 is equal to or greater than the first specified value or the second determination value E2 is equal to or greater than the second specified value. And.

As an example, the specified values (first specified value and second specified value) may be determined by using visual evaluation. A brief explanation will be given on how to determine the specified value using visual evaluation. For example, a plurality of samples d1 to dn with different coating conditions are prepared as the object 100. Note that n is an arbitrary integer of 2 or more. As an example, the coating conditions may be set so that the colors become lighter in the order of samples d1 to dn.

Each of the plurality of samples d1 to dn is compared with the reference material, and the matching rate is obtained based on the first judgment value and the second judgment value. FIG. 10 shows the relationship between the samples d1 to dn and the concordance rate. In FIG. 10, the matching rate is the highest in the sample dk. Then, each of the samples d1 to dn is visually evaluated (visually evaluated) by a plurality of people (30 people as an example) to obtain the correct answer rate. In the visual evaluation, one of the samples d1 to dn is compared with the sample dk. The correct answer rate is the ratio of the number of people who selected the sample dk to the number of people who performed the visual evaluation. FIG. 11 shows the result of visual evaluation. A sample with a correct answer rate of 1.0 may be clearly rejected. For a sample with a correct answer rate of 0.5, the correct answer rate is the same as random, so it may be passed. Then, for the samples d2 to dk-2 and dk + 2 to dn-1 whose accuracy rate is between 0.5 and 1.0, it is further determined which sample is within the permissible range. Note that k is an integer.

For example, as shown in FIG. 12, for the samples dk + 2 to dn-1, the sample dm (k-2 ≦ m ≦ n-1) having a large gradient (slope) of the matching rate among the samples dk + 2 to dn-1 is passed. Visual evaluation is performed with the sample dk + 2. Here, if the correct answer rate is 1.0, the sample dm is rejected. Then, the sample dm-1 and the sample dm, which have the second highest matching rate after the sample dm, are visually evaluated. Then, if the correct answer rate is 1.0, the sample dm-1 is rejected. Then, the sample dm-2 and the sample dm-1, which have the second highest matching rate after the sample dm-1, are visually evaluated. If the accuracy rate is 0.5, the sample dm-1 is set as the sample within the permissible range. In this way, the visual evaluation is repeated until the correct answer rate becomes 0.5, and the sample when the correct answer rate becomes 0.5 is taken as the sample within the permissible range. However, if the sample dk + 2 is reached before the accuracy rate reaches 0.5, the visual evaluation ends with the sample dk + 2 as the sample within the permissible range. Note that m is an integer.

On the other hand, in the visual evaluation of the sample dm and the passing sample dk + 2, if the correct answer rate is 0.5, the sample dm is passed. Then, the sample dm + 1 and the sample dm, which have the second lowest matching rate after the sample dm, are visually evaluated. Then, if the correct answer rate is 0.5, the sample dm + 1 is passed. Then, the sample dm + 2 and the sample dm + 1, which have the second lowest matching rate after the sample dm + 1, are visually evaluated. If the accuracy rate is 1.0, the sample dm + 1 is set as the sample within the allowable range. In this way, the visual evaluation is repeated until the correct answer rate becomes 1.0, and the sample when the correct answer rate becomes 1.0 is set as the sample within the allowable range. However, if the sample dn-1 is reached before the accuracy rate reaches 1.0, the visual evaluation is completed with the sample dn-2 immediately before the sample dn-1 as the sample within the allowable range.

Then, in the same manner for samples d2 to dk-2, a sample with an allowable range limit may be determined. Then, based on the matching rate of the sample of the limit of the allowable range selected from the samples d2 to dk-2 and the matching rate of the sample of the limit of the allowable range selected from the samples dk + 2 to dn-1, the specified value ( The first specified value and the second specified value) are determined. For example, then, the larger of the matching rate of the upper limit sample selected from the samples d2 to dk-2 and the matching rate of the upper limit sample selected from the samples dk + 2 to dn-1. The specified values (first specified value and second specified value) may be set based on the smaller one or the average value.

The presentation unit F13 executes the presentation step S13 (see FIG. 1) for presenting based on the inspection result (inspection result in the inspection step) in the inspection unit F12. That is, the presentation unit F13 makes a presentation based on the result of the inspection by the inspection unit F12. The presentation based on the inspection result may also include the presentation of the judgment result in the inspection unit F12 using the result of comparison between the target information and the reference information. Therefore, the presentation unit F13 may present the result of the determination by the inspection unit F12. In the present embodiment, the presentation unit F13 outputs the result of the determination by the inspection unit F12 to the external device through the input / output unit 11. The external device may present the result of the determination by the inspection unit F12, that is, the result of the inspection by the inspection system 1.

The control unit F14 executes a control step S14 (see FIG. 1) that outputs control information based on the inspection result in the inspection step S12 to the coating system 40 that paints the surface of the object 100. In the present embodiment, when the inspection unit F12 determines that the surface condition of the object 100 is unacceptable, the control unit F14 outputs control information to the coating system 40 to repaint the object 100. Let me. As an example, the control information may include data in the format shown in Table 7 below. The control information includes a plurality of items. The plurality of items are "model", "camera", "part", "result", "E1", "E2", "color space", and "number of bins". Here, "model" indicates information for identifying the inspection system 1. “Camera” indicates the number of the camera of the imaging system 30 used to generate the target image. “Part” indicates information for identifying a part of the object 100 shown in the target image. Here, "part" indicates a number assigned to the part. “Result” indicates the result of the inspection by the inspection unit F12. Here, the "result" is "NG", indicating that the test result is unsuccessful. “E1” indicates a first determination value corresponding to the target image. “E2” indicates a second determination value corresponding to the target image. The "color space" indicates information regarding the color system of the frequency distribution of the target image. Table 7 shows that the "color space" is the LCh color system. "Number of bins" indicates the number of elements of the evaluation vector of each color system. Table 7 shows that the number of elements of the evaluation vector for each of lightness, saturation, and hue is 64. By giving such control information, it is possible to convey to the painting system 40 which part of the object 100 should be repainted and how.

In repainting, the control unit F14 controls the painting system 40 based on the result of comparison between the target information obtained from the control information and the reference information (difference in the feature amount of the shape information for each parameter). That is, the control unit F14 controls the coating system 40 that paints the surface of the object 100 based on the result of the inspection by the inspection unit F12. As a result, the state of the surface of the object 100 can be brought closer to the target state. When the inspection unit F12 determines that the surface condition of the object 100 is acceptable, the control unit F14 may output control information to the coating system 40 to finish the coating of the object 100.

(1.3) Operation Next, the inspection method performed by the inspection system 1 described above will be briefly described with reference to the flowchart of FIG. In the inspection system 1, the acquisition unit F11 acquires an object image relating to the surface of the object 100 from the imaging system 30 (S11). Next, the inspection unit F12 inspects the surface condition of the object 100 (S12). Here, the inspection unit F12 obtains the frequency distribution for each parameter based on the pixel value from the target image (S12a). In the present embodiment, since there are three parameters, lightness, saturation, and hue, a frequency distribution of lightness, a frequency distribution of saturation, and a frequency distribution of hue can be obtained. Next, the inspection unit F12 generates target information based on the frequency distribution (S12b). The target information includes shape information regarding lightness, saturation, and hue. The shape information includes a feature amount representing the feature of the shape of the frequency distribution, and includes an evaluation vector (plural evaluation values) and a representative value. Next, the inspection unit F12 compares the target information with the reference information (S12c). In the comparison between the target information and the reference information, the inspection unit F12 obtains the difference in the feature amount of the shape information for each parameter (here, brightness, saturation, hue). The difference in the feature amount includes the difference in the evaluation vector and the difference in the representative value. Then, the determination value (first determination value) of the evaluation vector and the determination value (second determination value) of the representative value are obtained from the difference in the feature amount of the shape information. The inspection unit F12 determines whether the surface condition of the object 100 passes or fails based on the result of comparison between the target information and the reference information (S12d). In the present embodiment, when the first determination value E1 is less than the first specified value and the second determination value E2 is less than the second specified value, the inspection unit F12 passes the surface condition of the object 100. Suppose there is. On the other hand, the inspection unit F12 fails the surface condition of the object 100 when the first determination value E1 is equal to or greater than the first specified value or the second determination value E2 is equal to or greater than the second specified value. And. Then, in the inspection system 1, the presentation unit F13 outputs the result of the inspection by the inspection unit F12 to the external device through the input / output unit 11 (S13). Further, in the inspection system 1, the control unit F14 outputs control information based on the inspection result to the painting system 40 (S14).

(1.4) Summary The inspection system 1 described above includes an acquisition unit F11 and an inspection unit F12. The acquisition unit F11 is a step of acquiring an object image relating to the surface of the object 100. The inspection unit F12 inspects the state of the surface of the object 100 based on the target information including the shape information representing the shape of the frequency distribution of the parameter based on the pixel value obtained from the target image. According to this inspection system 1, the accuracy of inspection of the surface condition of the object 100 can be improved.

In other words, it can be said that the inspection system 1 executes the following method (inspection method). The inspection method includes acquisition step S11 and inspection step S12. The acquisition step S11 acquires an object image relating to the surface of the object 100. The inspection step S12 inspects the state of the surface of the object 100 based on the object information including the shape information representing the shape of the frequency distribution of the parameter based on the pixel value obtained from the object image. According to this inspection method, the accuracy of inspection of the surface condition of the object 100 can be improved as in the inspection system 1.

The inspection method is realized by executing a program (computer program) by one or more processors. This program is a program for causing one or more processors to execute the above-mentioned inspection method. According to such a program, the accuracy of the inspection of the surface condition of the object 100 can be improved as in the inspection method. The program may then be provided by a storage medium. This storage medium is a non-temporary storage medium that can be read by a computer and stores the above program. According to such a storage medium, the accuracy of the inspection of the surface condition of the object 100 can be improved as in the inspection method.

(2) Modified Example The embodiment of the present disclosure is not limited to the above embodiment. The above-described embodiment can be changed in various ways depending on the design and the like as long as the object of the present disclosure can be achieved. Examples of modifications of the above embodiment are listed below.

In one modification, the target information includes shape information corresponding to each of a plurality of parameters, but the target information may include shape information corresponding to a single parameter instead of a plurality of parameters. Further, the feature amount included in the shape information may include at least one of a plurality of evaluation values (evaluation vectors) and representative values.

In one modification, the pixel value of the target image is not limited to the RGB color system. Examples of the color system include CIE color systems such as XYZ color system, xyY color system, L ^* u ^* v ^* color system, L ^* a ^* b ^* color system, and Lch color system. Be done. As an example, the imaging system 30 may generate an image in which the pixel value is represented by the XYZ color system instead of an image in which the pixel value is represented by the RGB color system. Alternatively, the color system may be converted by arithmetic processing. For example, an image in which the pixel value is represented by the RGB color system may be converted into an image in which the pixel value is represented by the XYZ color system. A model expression, a look-up table, or the like can be used for the arithmetic processing in this case. Thereby, it is possible to convert the pixel value of the target image into a parameter of a desired color system.

In one modification, the inspection unit F12 does not need to use all of the shape information of a plurality of parameters obtained from the pixel values of the target image for inspection. For example, suppose the parameters are lightness, saturation, and hue. At this time, if the surface saturation of the object 100 is low and it is considered to be achromatic, the hue can change significantly with a slight difference in color. In such a case, the use of hue in the inspection may reduce the accuracy of the inspection. Therefore, when the surface of the object 100 is achromatic, it is better not to use the shape information regarding the hue. Thus, under certain conditions, certain parameters of the plurality of parameters may not be valid for inspection. In short, when a plurality of parameters include the first parameter and the second parameter, the inspection unit F12 does not use the shape information regarding the second parameter for the inspection when the first parameter satisfies a predetermined condition. May be good. For example, the first parameter is saturation and the second parameter is hue. The predetermined condition is that the saturation is equal to or less than the threshold value. Here, the threshold value can be determined based on whether or not the surface of the object 100 can be determined to be achromatic if the saturation is equal to or less than the threshold value. The combination of the first parameter and the second parameter is not limited to saturation and hue, and may be other parameters.

In one modification, weighted values may be set individually for a plurality of parameters. That is, the inspection unit F12 may weight a plurality of parameters. For example, when the surface saturation of the object 100 is low and it is considered to be achromatic, the hue can change significantly with a slight difference in color. In such a case, the use of hue in the inspection may reduce the accuracy of the inspection. In this case, it is conceivable that the closer the surface of the object 100 is to an achromatic color, the smaller the weighting value for the hue (lightening the weighting), thereby reducing the influence of the hue on the inspection result. For example, as shown in FIG. 13, the inspection unit F12 sets a weighted value in the evaluation vector w11 to generate an evaluation vector w12 in which the influence on the inspection is suppressed, and the inspection is performed based on the evaluation vector w12. You may go. In this way, the inspection unit F12 may individually change the weight value for a plurality of parameters according to the surface of the object 100.

In one modification, weighted values may be set individually for a plurality of evaluation values. That is, the inspection unit F12 may weight each element of the evaluation vector corresponding to each parameter. For example, in the state of the surface of the object 100, there is a case where it is desired to perform an inspection paying attention to a feeling of brilliance. At this time, if the area of the high-brightness region in the target image is small, the desired inspection accuracy may not be obtained with respect to the brilliance. In such a case, the inspection unit F12 may set a weighted value that increases as the brightness increases. For example, as shown in FIG. 14, the inspection unit F12 sets a weighted value for each element of the evaluation vector w11 to generate an evaluation vector w13 in which a region having a large brightness is emphasized, and based on this evaluation vector w13. , May be inspected. In this way, the inspection unit F12 may individually change the weight value for the plurality of evaluation values according to the surface of the object 100. Further, regarding the feeling of brilliance, although the result of the inspection by the inspection unit F12 is passed, the result of the inspection may not be passed when visually observed by a person. That is, the result of the inspection by the inspection unit F12 may not match the way a person feels. In such a case, it is conceivable to adopt a psychophysical quantity that reflects the psychological quantity according to the way a person feels as a weighted value. This makes it possible to reflect the psychological amount of a person in the inspection by the inspection unit F12.

In one modification, the target information may be obtained from a deviation image obtained from the target image. The deviation image is an image having a value obtained by subtracting a reference value of the pixel value of the target image from the pixel value of the target image as a pixel value. The reference value can be selected from the average value, the mode value, the median value, and the representative value of the frequency distribution obtained from the target image. Such a deviation image is effective for inspecting the texture of the surface of the object 100. That is, when inspecting the texture of the surface of the object 100 as the state of the surface of the object 100, the inspection unit F12 generates a deviation image from the target image, and the target is based on the deviation image. Generate information. In this case, a deviation image is generated by the same method for the reference object to be compared with the object 100. By generating the target information using the deviation image in this way, it is possible to improve the accuracy of the inspection of the texture of the surface of the object 100.

In one modification, the acquisition unit F11 may acquire a plurality of target images obtained by imaging the surface of the object 100 under different imaging conditions. That is, the acquisition step S11 may be a step of acquiring a plurality of target images obtained by imaging the surface of the object 100 under different imaging conditions. Examples of imaging conditions include imaging range, imaging direction, resolution, and the like. For example, in order to make the imaging conditions different, the imaging system 30 may use a plurality of cameras 31 and 32 having different imaging ranges and resolutions, as shown in FIG. FIG. 15 is an explanatory diagram of a method of acquiring a target image in an inspection method of a modified example. In FIG. 15, the camera 31 can capture a wider range than the camera 32, but the camera 32 has a higher resolution than the camera 31. Then, the camera 32 is arranged closer to the surface of the object 100 than the camera 31. As shown in FIG. 15, the camera 31 outputs an image of the first imaging range 111 of the surface 110 of the object 100 as the target image P11 (see FIG. 16). The camera 32 outputs an image of the second imaging range 112 of the surface 110 of the object 100 as the object image P12 (see FIG. 17). Here, the second imaging range 112 is narrower than the first imaging range 111. The second imaging range 112 may not be included in the first imaging range 111. The camera 31 is a macro camera suitable for inspection (for example, inspection related to gradation) of the surface 110 of the object 100 from a larger viewpoint than the camera 32. The camera 32 is a micro camera suitable for inspection of the surface 110 of the object 100 from a smaller viewpoint (for example, inspection of graininess) than the camera 31. For example, FIG. 18 shows a histogram H11 corresponding to the target image P11, and FIG. 19 shows a histogram H12 corresponding to the target image P12. As described above, if the imaging conditions are different, the obtained histogram is naturally different. The inspection unit F12 obtains the target information for each of the target image P11 and the target image P12, and compares the target information with the corresponding reference information. Thereby, the accuracy of the inspection of the state of the surface 110 of the object 100 can be improved.

In one modification, the inspection unit F12 may inspect the uneven state of the surface of the object 100 as the state of the surface of the object 100. FIG. 20 is an explanatory diagram of an example of an image of the surface of the object 100 in this modified example. Here, it is considered that the characteristic of the unevenness on the surface of the object 100 often appears in the specular reflection portion 130 on the surface of the object 100 in the object image P20 shown in FIG. Therefore, the acquisition unit F11 acquires a plurality of target images obtained by imaging the surface of the object 100 under different imaging conditions. Examples of imaging conditions include imaging range, imaging direction, resolution, and the like. For example, in order to make the imaging conditions different, the imaging system 30 may use a plurality of cameras 33, 34 having different imaging directions, as shown in FIG. In FIG. 21, the surface 110 of the object 100 is illuminated by the lighting system 20. A part of the light 21 from the lighting system 20 becomes the light 22 mirror-reflected on the surface 110, and the rest of the light 21 from the lighting system 20 is diffuse-reflected. The camera 33 is arranged at a position where the light diffusely reflected by the surface 110 of the object 100 is received. The object image generated by the camera 33 reflects the diffuse reflection component on the surface 110 of the object 100. The camera 34 is arranged at a position where it receives the light reflected by the mirror surface on the surface 110 of the object 100. The specular reflection component on the surface 110 of the object 100 is well reflected in the object image generated by the camera 34. The shape of the surface 110 of the object 100 is more reflected in the specular reflection component than the diffuse reflection component, and the color itself of the surface 110 of the object 100 is more reflected in the diffuse reflection component than the mirror reflection component. It is well reflected. As a result, the state of the surface 110 of the object 100 can be inspected by taking into account not only the color of the surface of the object 100 itself but also the shape of the surface of the object 100. As a result, according to the inspection system 1, the accuracy of inspection of the surface condition of the object 100 can be improved. When the imaging directions are different, the surface 110 of the object 100 may be imaged from different positions with the same camera. Further, in order to better inspect the uneven state of the surface of the object 100, the specular reflection portion 130 may be imaged by a macro camera and a micro camera to obtain an object image. Further, the target image obtained by using high dynamic range imaging may be used. Since the target image obtained by high dynamic range composition can handle a wider dynamic range than usual, a component with a relatively small amount of light such as a diffuse reflection component has a relatively large amount of light such as a specular reflection component. Even the components can be captured in a single image.

In one modification, the division Di when obtaining a plurality of evaluation values does not necessarily have to be the same width. For example, in the above embodiment, as shown in FIG. 3, the plurality of divisions D1 to D7 have the same width. On the other hand, the plurality of divisions Di may have different widths. As the width of the division Di is narrowed, the resolution of the evaluation vector is improved, and the accuracy of the inspection can be improved. In particular, it is preferable that the width of the division Di closer to the peak of the histogram be smaller. For example, FIG. 22 shows a histogram H20 obtained from a target image containing a large amount of specular reflection components. The peak of the histogram H20 is biased toward the bright side (right side). In FIG. 22, a plurality of divisions Di (D21 to D30) are set for the histogram H20. Here, the widths of the plurality of divisions D21 to D30 are narrowed in this order. By setting the widths of the divisions D21 to D30 in this way, the shape of the histogram H20 is better reflected in the evaluation vectors obtained from these divisions D21 to D30. Therefore, it is possible to improve the accuracy of the inspection of the surface condition of the object 100. In particular, in the range where the change in frequency is large in the histogram H20, it is possible to better reflect the shape of the histogram H20 in the evaluation vector by reducing the width of the division. Conversely, in the range where the change in frequency is small in the histogram H20, the width of the division may be increased, whereby the amount of data of the evaluation vector can be reduced.

In one modification, the inspection unit F12 may inspect the surface mapping property of the object 100 as the state of the surface of the object 100. The mapability is an index of the sharpness of an image (reflection image) of an object reflected on the surface of the object 100. When the reproducibility is poor, the reflected image becomes unclear, and when the reproducibility is good, the reflected image becomes clear. The mapability is affected by the surface roughness and shape of the object 100. In the mapability inspection, as shown in FIG. 23, the inspection image 200 is used. For the inspection image 200, a chart to which a predetermined test pattern is applied is used. Light 23 is applied to the inspection image 200 from the lighting system 20 so that the reflection image 210 of the inspection image 200 is projected on the surface 110 of the object 100. Then, the imaging system 30 is arranged at a position where the light 24 from the reflected image 210 is received. As a result, the imaging system 30 captures an image of the reflection image 210 reflected on the surface 110 of the object 100 and outputs it as the target image. That is, in the mapability inspection, the target image is an image of a reflection image of the inspection image 200 by the surface 110 of the object 100. The inspection unit F12 may generate target information from such a target image, compare the target information with the corresponding reference information, and inspect the state (mapping property) of the surface 110 of the target object 100. Instead of the chart, a self-luminous display displaying a predetermined test pattern may be used. In this case, it is not necessary to use the lighting system 20 to project the test pattern on the surface of the object 100.

In one modification, the presentation unit F13 may present difference information that visually indicates the difference between the target information and the reference information based on the result of the inspection by the inspection unit F12. FIG. 24 shows an example of difference information. In FIG. 24, the difference between the representative values of the frequency distribution is emphasized and shown as the difference information. More specifically, as shown in FIG. 24, the difference information is a graph showing the evaluation vector wT1 and the representative value CT1 obtained from the target information and the evaluation vector wR1 and the representative value CR1 obtained from the reference information. Further, the difference information includes an upper limit value Th1 and a lower limit value Th2 in the allowable range of the representative value CT1 of the target information. The permissible range is set around the representative value CR1 obtained from the reference information. According to the difference information of FIG. 24, the user can visually determine whether or not the representative value CT1 of the target information is within the permissible range with respect to the representative value CR1 of the reference information. FIG. 25 shows another example of the difference information. In FIG. 25, as the difference information, the difference between the evaluation vectors of the target information and the reference information is emphasized. More specifically, the difference information is a graph showing the evaluation vector wT1 obtained from the target information and the evaluation vector wR1 obtained from the reference information in FIG. 25. Further, in FIG. 25, the regions R11 and R12 that are the differences between the evaluation vector wT1 of the target information and the evaluation vector wR1 of the reference information are emphasized and displayed. Therefore, according to the difference information of FIG. 25, the user can visually grasp the difference between the evaluation vector wT1 of the target information and the evaluation vector wR1 of the reference information. Therefore, the user can determine whether or not the evaluation vector wT1 of the target information is within the allowable range with respect to the evaluation vector wR1 of the reference information. FIG. 26 shows another example of the difference information. FIG. 26 shows the difference vector of the evaluation vector between the target information and the reference information as the difference information. More specifically, the difference information in FIG. 26 displays the regions R11 and R12 that are the differences between the evaluation vector wT1 of the target information and the evaluation vector wR1 of the reference information in FIG. 25. Therefore, according to the difference information of FIG. 26, the user can visually grasp the difference between the evaluation vector wT1 of the target information and the evaluation vector wR1 of the reference information. Therefore, the user can determine whether or not the evaluation vector wT1 of the target information is within the allowable range with respect to the evaluation vector wR1 of the reference information.

Further, the presentation unit F13 may present an image of the object 100 that reflects the difference between the target information and the reference information as a result of the inspection by the inspection unit F12 on the surface of the object 100. Further, the presentation unit F13 may make a presentation that clearly distinguishes the portion determined to be acceptable by the inspection unit F12 from the portion determined to be unacceptable. For example, in the image P30 of the object 100 shown in FIG. 27, the surface of the object 100 is classified into four regions R31, R32, R33, and R34. The four regions R31, R32, R33, and R34 indicate that the difference between the representative values of the target information and the reference information increases in this order. The region R34 is a portion of the surface of the object 100 that is determined to be unacceptable by the inspection unit F12. By presenting in such a presentation unit F13, it is possible to present a portion (a portion having an abnormality) determined to be rejected in the target image in an easy-to-understand manner. For example, in the image P40 of the object 100 shown in FIG. 28, the surface of the object 100 is classified into four regions R41, R42, R43, and R44. The four regions R41, R42, R43, and R44 indicate that the difference between the evaluation vectors of the target information and the reference information increases in this order. The region R44 is a portion of the surface of the object 100 that is determined to be unacceptable by the inspection unit F12. By presenting in such a presentation unit F13, it is possible to present a portion (a portion having an abnormality) determined to be rejected in the target image in an easy-to-understand manner.

In one modification, the input / output unit 11 may include an image display device. In this case, the presentation unit F13 may display the result of the inspection by the inspection unit F12 on the image display device of the input / output unit 11. Further, the input / output unit 11 may include an audio output device. In this case, the presentation unit F13 may output the result of the inspection by the inspection unit F12 from the audio output device of the input / output unit 11.

In one modification, the wavelength of the light emitted by the lighting system 20 may be changeable. This can be achieved by using light sources having different emission colors or color filters. Thus, in the inspection system 1, at least one of the wavelength of the light emitted by the lighting system 20 and the wavelength of the light detected by the imaging system 30 may be changeable.

In one modification, the inspection system 1 (judgment system 10) may be composed of a plurality of computers. For example, the functions of the inspection system 1 (determination system 10) (particularly, the acquisition unit F11, the inspection unit F12, the presentation unit F13, and the control unit F14) may be distributed to a plurality of devices. Further, at least a part of the functions of the inspection system 1 (determination system 10) may be realized by, for example, the cloud (cloud computing).

The execution subject of the inspection system 1 (judgment system 10) described above includes a computer system. A computer system has a processor and memory as hardware. When the processor executes the program recorded in the memory of the computer system, the function as the execution subject of the inspection system 1 (determination system 10) in the present disclosure is realized. The program may be pre-recorded in the memory of the computer system or may be provided through a telecommunication line. Further, the program may be provided by being recorded on a non-temporary recording medium such as a memory card, an optical disk, or a hard disk drive that can be read by a computer system. A processor in a computer system is composed of one or more electronic circuits including a semiconductor integrated circuit (IC) or a large scale integrated circuit (LSI). A field programmable gate array (FGPA), an ASIC (application specific integrated circuit), or a reconfigurable reconfigurable circuit partition inside the LSI that can be reconfigured after the LSI is manufactured. Logical devices can be used for the same purpose. A plurality of electronic circuits may be integrated on one chip, or may be distributed on a plurality of chips. The plurality of chips may be integrated in one device, or may be distributed in a plurality of devices.

(3) Aspects As is clear from the above embodiments and modifications, the present disclosure includes the following aspects. In the following, reference numerals are given in parentheses only to clearly indicate the correspondence with the embodiments.

The first aspect is an inspection method, which includes an acquisition step (S11) and an inspection step (S12). The acquisition step (S11) is a step of acquiring an object image relating to the surface of the object (100). The inspection step (S12) is a step of inspecting the surface condition of the object (100) based on the object information including the shape information representing the shape of the frequency distribution of the parameter based on the pixel value obtained from the object image. is there. According to this aspect, the accuracy of the inspection of the surface condition of the object (100) can be improved.

The second aspect is an inspection method based on the first aspect. In the second aspect, the shape information includes a feature quantity representing a feature of the shape of the frequency distribution. According to this aspect, the accuracy of the inspection of the surface condition of the object (100) can be improved.

The third aspect is an inspection method based on the second aspect. In the third aspect, the feature quantity includes a plurality of evaluation values based on the plurality of divisions (Di) of the parameters of the shape of the frequency distribution and the area (Si) of each. According to this aspect, the accuracy of the inspection of the surface condition of the object (100) can be improved.

The fourth aspect is an inspection method based on the third aspect. In the fourth aspect, in the inspection method, weighted values are individually set for a plurality of evaluation values. According to this aspect, the accuracy of the inspection of the surface condition of the object (100) can be improved.

The fifth aspect is an inspection method based on the second aspect. In the fifth aspect, the feature quantity includes a representative value of the frequency distribution. According to this aspect, the accuracy of the inspection of the surface condition of the object (100) can be improved.

The sixth aspect is an inspection method based on the fifth aspect. In the sixth aspect, the representative values are the ratio (wi) of each of the plurality of divisions (Di) of the parameters of the shape of the frequency distribution to the entire shape of the frequency distribution, and the values of the parameters corresponding to the plurality of divisions (Di). It is a value obtained from (Li). According to this aspect, the accuracy of the inspection of the surface condition of the object (100) can be improved.

The seventh aspect is an inspection method based on any one of the first to sixth aspects. In a seventh aspect, the parameter is a color parameter. According to this aspect, the accuracy of the color inspection can be improved as the surface condition of the object (100).

The eighth aspect is an inspection method based on any one of the first to seventh aspects. In the eighth aspect, the target information includes shape information for each of the plurality of parameters. According to this aspect, the accuracy of the inspection of the surface condition of the object (100) can be improved.

The ninth aspect is an inspection method based on the eighth aspect. In the ninth aspect, weighted values are individually set for the plurality of parameters. According to this aspect, the accuracy of the inspection of the surface condition of the object (100) can be improved.

The tenth aspect is an inspection method based on the eighth or ninth aspect. In the tenth aspect, the plurality of parameters include a first parameter and a second parameter. In the inspection step (S12), when the first parameter satisfies a predetermined condition, the shape information regarding the second parameter is not used for the inspection. According to this aspect, the accuracy of the inspection of the surface condition of the object (100) can be improved.

The eleventh aspect is an inspection method based on the tenth aspect. In the eleventh aspect, the first parameter is saturation. The second parameter is hue. According to this aspect, the accuracy of the inspection of the surface condition of the object (100) can be improved.

The twelfth aspect is an inspection method based on any one of the first to eleventh aspects. In the twelfth aspect, the inspection step (S12) compares the target information with the reference information including the shape information obtained from the reference image regarding the surface of the reference object as the reference of the object (100). According to this aspect, the accuracy of the inspection of the surface condition of the object (100) can be improved.

The thirteenth aspect is an inspection method based on any one of the first to twelfth aspects. In the thirteenth aspect, the target information is obtained from a deviation image obtained from the target image. The deviation image is an image having a value obtained by subtracting a reference value of the pixel value of the target image from the pixel value of the target image as a pixel value. According to this aspect, it is possible to inspect the texture as the state of the surface of the object (100).

The 14th aspect is an inspection method based on any one of the 1st to 13th aspects. In the fourteenth aspect, the acquisition step (S11) acquires a plurality of target images obtained by imaging the surface of the object (100) under different imaging conditions. According to this aspect, the accuracy of the inspection of the surface condition of the object (100) can be improved.

The fifteenth aspect is an inspection method based on any one of the first to fourteenth aspects. In the fifteenth aspect, the target image is an image of a reflection image (210) of the inspection image (200) by the surface of the object (100). According to this aspect, the mapability can be inspected as the state of the surface of the object (100).

The sixteenth aspect is an inspection method based on any one of the first to fifteenth aspects. In the sixteenth aspect, the inspection method further includes a presentation step (S13) for making a presentation based on the result of the inspection in the inspection step (S12). According to this aspect, the result of the inspection of the object (100) can be presented.

The 17th aspect is an inspection method based on any one of the 1st to 16th aspects. In the seventeenth aspect, the inspection method is to provide a coating system (40) for painting the surface of the object (100) with a control step (S14) for outputting control information based on the inspection result in the inspection step (S12). Further included. According to this aspect, it is possible to improve the quality of coating on the surface of the object (100).

The eighteenth aspect is an inspection method based on any one of the first to seventeenth aspects. In the eighteenth aspect, the shape of the frequency distribution is the shape of a histogram. According to this aspect, the accuracy of the inspection of the surface condition of the object (100) can be improved.

The nineteenth aspect is a program for causing one or more processors to execute the inspection method of any one of the first to eighteenth aspects. According to this aspect, the accuracy of the inspection of the surface condition of the object (100) can be improved.

The twentieth aspect is an inspection system (1), which includes an acquisition unit (F11) and an inspection unit (F12). The acquisition unit (F11) acquires an object image on the surface of the object (100). The inspection unit (F12) inspects the surface condition of the object (100) based on the object information including the shape information representing the shape of the frequency distribution of the parameter based on the pixel value obtained from the object image. According to this aspect, the accuracy of the inspection of the surface condition of the object (100) can be improved.

The second to eighteenth aspects can be appropriately modified and applied to the nineteenth and twentieth aspects.

According to the inspection method, program, and inspection system of the present disclosure, the accuracy of inspection of the surface condition of the object can be improved. Therefore, the invention according to the present disclosure is industrially useful.

1 Inspection system F11 Acquisition unit F12 Inspection unit 100 Object 200 Inspection image 210 Reflection image S11 Acquisition step S12 Inspection step S13 Presentation step S14 Control step

Claims (20)

1. The acquisition step to acquire the target image about the surface of the object, and
   An inspection step of inspecting the surface condition of the object based on the object information including the shape information representing the shape of the frequency distribution of the parameter based on the pixel value obtained from the object image.
   including,
   Inspection method.
2. The shape information includes a feature amount representing a feature of the shape of the frequency distribution.
   The inspection method of claim 1.
3. The feature amount includes a plurality of evaluation values based on the area of each of the plurality of divisions of the parameter of the shape of the frequency distribution.
   The inspection method of claim 2.
4. Weighted values are individually set for the plurality of evaluation values.
   The inspection method of claim 3.
5. The feature amount includes a representative value of the frequency distribution.
   The inspection method of claim 2.
6. The representative value is a value obtained from the ratio of each of the plurality of divisions of the parameter of the shape of the frequency distribution to the entire shape of the shape of the frequency distribution and the value of the parameter corresponding to the plurality of divisions.
   The inspection method of claim 5.
7. The parameters are parameters relating to color.
   The inspection method according to any one of claims 1 to 6.
8. The target information includes shape information for each of the plurality of parameters.
   The inspection method according to any one of claims 1 to 7.
9. Weighted values are set individually for the plurality of parameters.
   The inspection method of claim 8.
10. The plurality of said parameters include a first parameter and a second parameter.
    In the inspection step, when the first parameter satisfies a predetermined condition, the shape information regarding the second parameter is not used for the inspection.
    The inspection method according to claim 8 or 9.
11. The first parameter is saturation.
    The second parameter is hue.
    The inspection method of claim 10.
12. The inspection step compares the target information with the reference information including the shape information obtained from the reference image regarding the surface of the reference object that serves as a reference for the object.
    The inspection method according to any one of claims 1 to 11.
13. The target information is obtained from a deviation image obtained from the target image.
    The deviation image is an image having a value obtained by subtracting a reference value of the pixel value of the target image from the pixel value of the target image as a pixel value.
    The inspection method according to any one of claims 1 to 12.
14. The acquisition step acquires a plurality of the target images obtained by imaging the surface of the object under different imaging conditions.
    The inspection method according to any one of claims 1 to 13.
15. The target image is an image of a reflection image of the inspection image by the surface of the target object.
    The inspection method according to any one of claims 1 to 14.
16. Further including a presentation step of making a presentation based on the result of the inspection in the inspection step.
    The inspection method according to any one of claims 1 to 15.
17. The coating system for painting the surface of the object further includes a control step that outputs control information based on the inspection result in the inspection step.
    The inspection method according to any one of claims 1 to 16.
18. The shape of the frequency distribution is the shape of a histogram.
    The inspection method according to any one of claims 1 to 17.
19. For causing one or more processors to perform any one of the inspection methods of claims 1-18.
    program.
20. An acquisition unit that acquires an object image on the surface of an object,
    An inspection unit that inspects the surface condition of the object based on the object information including the shape information that represents the shape of the frequency distribution of the parameter based on the pixel value obtained from the object image.
    To prepare
    Inspection system.

Images