Painting evaluation device and painting evaluation method

Abstract

In this coating evaluation device and coating evaluation method, emission light having a first intensity distribution is emitted onto a coating surface, and a second intensity distribution of the light reflected from the coating surface is acquired. Further, a third intensity distribution corresponding to the second intensity distribution is acquired on the basis of the curvature of the coating surface, and an evaluation value corresponding to the third intensity distribution is estimated using an evaluation model that outputs an evaluation value for the image clearness of a coating surface in response to input including a third intensity distribution.

Description

Technical Field

[0001] The present invention relates to a painting evaluation apparatus and a painting evaluation method.

Background Art

[0002] There is known an invention in which a light and dark pattern light, which is a repeating pattern of light and dark, is projected onto a painted surface, the light and dark pattern formed on the painted surface is photographed, the luminance distribution in the repeating direction of light and dark is calculated, the luminance distribution is Fourier-transformed, the wavelength distribution, which is the distribution of amplitudes with respect to wavelength, is calculated, the integral value of the section corresponding to a predetermined wavelength range of the wavelength distribution is calculated, and the painted surface is evaluated based on the integral value (Patent Document 1).

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] According to the invention described in Patent Document 1, when the painted surface is a curved surface, the boundary between light and dark in the formed light and dark pattern may become blurred, and there is a problem that the accuracy in evaluating the distinctness of image of the painted surface may decrease.

[0005] The present invention has been made in view of the above problems, and an object thereof is to provide a painting evaluation apparatus and a painting evaluation method capable of accurately evaluating the distinctness of image of a painted surface even when the painted surface is a curved surface.

Means for Solving the Problems

[0006] A paint evaluation apparatus and a paint evaluation method according to an aspect of the present invention irradiate a painted surface with incident light having a first intensity distribution, and acquire a second intensity distribution of the reflected light from the painted surface. Further, based on the curved shape of the painted surface, a third intensity distribution associated with the second intensity distribution is calculated, and an evaluation value of the distinctness of image of the painted surface is output for an input including the third intensity distribution using an evaluation model, and an evaluation value corresponding to the third intensity distribution is estimated.

Effects of the Invention

[0007] According to the present invention, even when the painted surface is a curved surface, the distinctness of image of the painted surface can be accurately evaluated.

Brief Description of the Drawings

[0008]

Figure 1

Figure 2

Figure 3A

Figure 3B

Figure 4A

Figure 4B

Embodiments for Carrying Out the Invention

[0009] Hereinafter, embodiments of the present invention will be described with reference to the drawings. In the description of the drawings, the same parts are denoted by the same reference numerals and the description thereof is omitted.

[0010] [Configuration of Paint Evaluation Apparatus] Referring to FIG. 1, a configuration example of a painting evaluation apparatus according to the present embodiment will be described. As shown in FIG. 1, the painting evaluation apparatus includes a shape acquisition unit 11, a strength acquisition unit 15, a light source unit 19, and a controller 100. In addition, the painting evaluation apparatus may include a material acquisition unit 13 and an output unit 400. The shape acquisition unit 11, the material acquisition unit 13, the strength acquisition unit 15, the light source unit 19, and the output unit 400 are connected to the controller 100.

[0011] The shape acquisition unit 11 acquires shape information representing the curved shape of the painted surface to be evaluated for painting. More specifically, the shape acquisition unit 11 may acquire the design data of the painted surface as the shape information. For example, CAD (Computer-aided design) data may be mentioned as the design data. The design data is not limited thereto as long as it represents the degree (curvature) of the curvature of the painted surface.

[0012] The shape acquisition unit 11 may acquire the stored design data of the painted surface from a database (not shown), or may acquire the design data of the painted surface from an external connection device (not shown) via a wired or wireless network. In addition, the shape acquisition unit 11 may acquire the design data based on the input of the user.

[0013] Further, the shape acquisition unit 11 may acquire the measurement data obtained by measuring the painted surface as the shape information. For example, a 3D scanner may be mentioned as the shape acquisition unit 11.

[0014] In addition, the shape acquisition unit 11 may acquire the position information of the region irradiated with the incident light by the light source unit 19 described later on the painted surface, and acquire the shape information based on the position information. That is, based on the position of the region irradiated with the incident light, the design data of the painted surface or the measurement data obtained by measuring the painted surface may be acquired.

[0015] The material acquisition unit 13 acquires the material information of the painted surface. More specifically, the material acquisition unit 13 acquires information such as the type and color of the member as the material information of the painted surface. The material acquisition unit 13 may acquire the stored material information of the painted surface from a database (not shown), or may acquire the material information of the painted surface from an external connection device (not shown) via a wired or wireless network. Alternatively, the material acquisition unit 13 may acquire the material information based on the input of the user.

[0016] The light source unit 19 irradiates the painted surface with incident light having the set first intensity distribution. More specifically, the light source unit 19 has a plurality of light sources arranged in a plane, and the intensity of the light emitted by each light source is adjusted by a controller 100 described later, so as to irradiate the painted surface with incident light having the first intensity distribution.

[0017] Examples of the light source constituting the light source unit 19 include various types such as an LED lamp, an incandescent bulb, and a fluorescent lamp.

[0018] Here, the first intensity distribution of the incident light may have a periodic structure in the first direction. FIG. 3A shows an example of the first intensity distribution having a striped periodic structure in which bright and dark portions are continuously arranged along the R1 direction. Further, the first intensity distribution may have a periodic structure in a second direction different from the first direction. FIG. 3B shows an example of the first intensity distribution having a striped periodic structure in which bright and dark portions are continuously arranged along the R2 direction different from the R1 direction.

[0019] Note that the first intensity distribution of the incident light may have a periodic structure in the direction of the main direction vector at a predetermined position on the painted surface. Here, the main direction vector means a tangent vector when the curvature of a curve appearing in the common part of the plane including the tangent vector and the normal vector of the painted surface and the painted surface becomes the principal curvature of the painted surface at a predetermined position.

[0020] For example, based on the shape information acquired by the material acquisition unit 13, the controller 100 described later may calculate the main direction vector at a predetermined position on the painted surface, and the intensity distribution having a periodic structure in the direction of the main direction vector may be defined as the first intensity distribution. Further, the painted surface may be rotated with respect to the light source unit 19 about an axis parallel to the incident direction of the incident light so that the first direction in which the first intensity distribution has a periodic structure and the main direction vector at a predetermined position on the painted surface are in a coincident positional relationship.

[0021] In addition, at the boundary between the "bright part" and the "dark part" of the first intensity distribution, the intensity of the light may change intermittently. Therefore, for example, when the intensity of the incident light in the "bright part" (first region) is equal to or greater than the first threshold value, the intensity of the incident light in the "dark part" (second region) may be equal to or less than a second threshold value that is smaller than the first threshold value.

[0022] In addition, for alignment, the light source unit 19 may irradiate incident light including a first marking pattern. FIG. 4A shows an example of a rectangular first marking pattern that is set to surround the incident light of the first intensity distribution shown in FIG. 3A.

[0023] Note that since the painted surface can have various curved shapes, the intensity distribution of the reflected light from the painted surface can change according to the curved shape. FIG. 4B shows a second marking pattern that is curved from a rectangle according to the curved shape. By comparing the first marking pattern and the second marking pattern, the degree of curvature of the region irradiated with the first marking pattern can be calculated.

[0024] The intensity acquisition unit 15 acquires a second intensity distribution of the reflected light from the painted surface that has received the incident light. More specifically, the intensity acquisition unit 15 is a digital camera equipped with a solid-state imaging device such as a CCD or a CMOS, and images a region of the painted surface irradiated with the incident light to acquire a digital image. The second intensity distribution is represented by the intensity of the light at each pixel constituting the digital image.

[0025] The intensity acquisition unit 15 images the area irradiated with incident light when the focal length, the angle of view of the lens, the vertical and horizontal angles of the camera, etc. are set.

[0026] Further, the intensity acquisition unit 15 may acquire the intensity distribution of the reflected light from the area irradiated with the first marking pattern as the second marking pattern among the painted surfaces.

[0027] Note that by comparing the first marking pattern and the second marking pattern, the degree of curvature of the area irradiated with the first marking pattern can be calculated. For example, the controller 100 described later may acquire the reference shape information of the area irradiated with the first marking pattern based on the difference between the first marking pattern and the second marking pattern.

[0028] Then, the position information of the area on the painted surface having the shape information that matches the reference shape information may be acquired. Thereby, alignment can be performed in accordance with the area irradiated with the incident light, and the shape information can be acquired.

[0029] The controller 100 is a general-purpose computer including a CPU (Central Processing Unit), a memory, a storage device, an input / output unit, and the like.

[0030] A computer program (painting evaluation program) for causing the controller 100 to function as a painting evaluation device is installed in the controller 100. By executing the computer program, the controller 100 functions as a plurality of information processing circuits included in the painting evaluation device.

[0031] Here, an example of realizing a plurality of information processing circuits included in the painting evaluation device by software is shown. Of course, it is also possible to prepare dedicated hardware for executing each of the following information processing to configure the information processing circuit. Further, the plurality of information processing circuits may be configured by individual hardware.

[0032] The controller 100 includes an intensity correction unit 110, an evaluation model setting unit 120, and an evaluation value estimation unit 130.

[0033] The intensity correction unit 110 calculates a third intensity distribution associated with the second intensity distribution based on the shape information. Specifically, the second intensity distribution includes a light scattering component caused by the deviation of the curved shape of the painted surface from the planar shape. Therefore, the intensity correction unit 110 calculates the third intensity distribution so as to cancel out the light scattering component on the painted surface due to the deviation included in the second intensity distribution.

[0034] The light scattering component caused by the deviation of the curved shape of the painted surface from the planar shape is calculated by using rendering techniques using computer graphics, simulation techniques such as shading, etc. By using these simulation techniques, the intensity correction unit 110 can calculate the third intensity distribution so as to cancel out the light scattering component on the painted surface due to the deviation included in the second intensity distribution.

[0035] For example, the smaller the deviation of the curved shape from the planar shape, the smaller the difference between the second intensity distribution and the third intensity distribution. Also, when the curved shape is a planar shape, the second intensity distribution and the third intensity distribution coincide.

[0036] The evaluation model setting unit 120 sets an evaluation model that outputs an evaluation value of the distinctness of image of the painted surface for an input including the third intensity distribution. Here, the evaluation model is a learning model generated by machine learning based on teacher data that is a set of the intensity distribution of the reflected light obtained by irradiating incident light on an evaluated painted surface having a planar shape and the evaluation value of the distinctness of image of the evaluated painted surface.

[0037] Here, the evaluation value of the distinctness of image is an index determined by at least one of, for example, the smoothness of the painted surface, the ratio of diffuse reflection in the reflected light on the painted surface, and the resolution of the image reflected on the painted surface. The evaluation value of the distinctness of image of the evaluated painted surface is a numerical value previously given to the evaluated painted surface by another distinctness of image evaluation method.

[0038] Note that the evaluation model setting unit 120 may set an evaluation model that outputs an evaluation value of the distinctness of image of the painted surface for an input including material information and the third strength distribution. In this case, the evaluation model is a learning model generated by machine learning based on teacher data that is a set of material information of an evaluated painted surface having a planar shape, the intensity distribution of reflected light obtained by irradiating the evaluated painted surface with incident light, and the evaluation value of the distinctness of image of the evaluated painted surface.

[0039] As a method for generating a learning model by machine learning, for example, a method using one or a combination of two or more of neural network, support vector machine, Random Forest, XGBoost, LightGBM, PLS regression, Ridge regression, and Lasso regression can be mentioned. The method for generating a learning model by machine learning is not limited to the examples listed here.

[0040] The evaluation model setting unit 120 may perform machine learning based on teacher data acquired from a database (not shown) to set an evaluation model. Also, an evaluation model may be stored in advance in a database (not shown), and the evaluation model setting unit 120 may set the evaluation model acquired from the database.

[0041] The evaluation value estimation unit 130 estimates an evaluation value corresponding to the third strength distribution using the set evaluation model. More specifically, when the set evaluation model is an evaluation model that outputs an evaluation value of the distinctness of image of the painted surface for an input including the third strength distribution, the evaluation value estimation unit 130 inputs the third strength distribution to the evaluation model. Then, the evaluation value estimation unit 130 uses the value output from the evaluation model as the evaluation value corresponding to the third strength distribution. The evaluation value corresponding to the third strength distribution is an estimated evaluation value regarding the distinctness of image of the painted surface.

[0042] When the set evaluation model is an evaluation model that outputs an evaluation value of the distinctness of image of the painted surface for an input including material information and the third strength distribution, the evaluation value estimation unit 130 inputs the material information and the third strength distribution into the evaluation model. Then, the evaluation value estimation unit 130 uses the value output from the evaluation model as the evaluation value corresponding to the combination of the material information and the third strength distribution. The evaluation value corresponding to the third strength distribution is the estimated evaluation value regarding the distinctness of image of the painted surface.

[0043] The output unit 400 outputs the estimated evaluation value regarding the distinctness of image of the painted surface.

[0044] [Processing Procedure of Painting Evaluation Apparatus] Next, the processing procedure of the painting evaluation apparatus according to the present embodiment will be described with reference to the flowchart of FIG. 2. It is assumed that the evaluation model has already been set by the evaluation model setting unit 120 before the processing shown in the flowchart of FIG. 2 is started.

[0045] In step S101, the shape acquisition unit 11 acquires shape information. Also, the material acquisition unit 13 acquires material information.

[0046] In step S105, the controller 100 sets the first strength distribution of the incident light.

[0047] In step S107, the strength acquisition unit 15 acquires the second strength distribution of the reflected light.

[0048] In step S109, the strength correction unit 110 calculates the third strength distribution associated with the second strength distribution based on the shape information.

[0049] In step S111, the evaluation value estimation unit 130 estimates the evaluation value corresponding to the third strength distribution using the set evaluation model.

[0050] In step S113, the output unit 400 outputs the evaluation value estimated by the evaluation value estimation unit 130.

[0051] [Effects of Embodiment] As described in detail above, the painting evaluation apparatus, painting evaluation method, and painting evaluation program according to the present embodiment irradiate the painted surface with incident light having a first intensity distribution, and acquire a second intensity distribution of the reflected light from the painted surface. Further, based on the curved shape of the painted surface, a third intensity distribution associated with the second intensity distribution is calculated, and an evaluation value corresponding to the third intensity distribution is estimated using an evaluation model that outputs an evaluation value of the distinctness of image of the painted surface for an input including the third intensity distribution.

[0052] Thereby, even when the painted surface is a curved surface, the distinctness of image of the painted surface can be accurately evaluated. Further, since the evaluation value is estimated by the evaluation model, dedicated equipment or skilled personnel for evaluating the distinctness of image of the painted surface are not required, and the cost for evaluating the distinctness of image of the painted surface can be reduced.

[0053] Further, in the painting evaluation apparatus, painting evaluation method, and painting evaluation program according to the present embodiment, the smaller the deviation of the curved shape from the planar shape is, the smaller the difference between the second intensity distribution and the third intensity distribution may be. Further, when the curved shape is a planar shape, the second intensity distribution and the third intensity distribution may coincide with each other. Thereby, the light scattering component on the painted surface due to the deviation of the curved shape from the planar shape can be removed from the second intensity distribution. That is, the third intensity distribution is calculated so as to cancel the light scattering component on the painted surface due to the deviation included in the second intensity distribution.

[0054] Furthermore, in the painting evaluation apparatus, painting evaluation method, and painting evaluation program according to the present embodiment, the evaluation model may be a learning model generated by machine learning based on teacher data that is a set of the intensity distribution of the reflected light obtained by irradiating an evaluated painted surface having a planar shape with incident light and the evaluation value of the distinctness of image of the evaluated painted surface. Thereby, the distinctness of image of a painted surface that is a curved surface can be accurately evaluated by the evaluation model generated from the teacher data regarding the evaluated painted surface having a planar shape.

[0055] In addition, in the painting evaluation apparatus, painting evaluation method, and painting evaluation program according to the present embodiment, the evaluation value of the distinctness of image of the painted surface may be an index determined by at least one of the smoothness of the painted surface, the ratio of diffuse reflection in the reflected light on the painted surface, and the resolution of the image reflected on the painted surface. In this way, the criteria for evaluating the distinctness of image of the painted surface are clarified.

[0056] Furthermore, the painting evaluation apparatus, painting evaluation method, and painting evaluation program according to the present embodiment may acquire the design data of the painted surface as shape information, or may acquire the measurement data obtained by measuring the painted surface as shape information. Thereby, it is possible to suppress the influence of the curved shape of the painted surface and accurately evaluate the distinctness of image of the painted surface.

[0057] In addition, in the painting evaluation apparatus, painting evaluation method, and painting evaluation program according to the present embodiment, the first intensity distribution may have a periodic structure in the first direction. For example, the first intensity distribution may have a striped periodic structure. Thereby, it is possible to evaluate the painted surface based on the luminance distribution along the direction having the periodic structure and accurately evaluate the distinctness of image of the painted surface.

[0058] Furthermore, in the painting evaluation apparatus, painting evaluation method, and painting evaluation program according to the present embodiment, the first intensity distribution may have a periodic structure in a second direction different from the first direction. Thereby, it is possible to evaluate the painted surface based on the luminance distribution along the direction having the periodic structure and accurately evaluate the distinctness of image of the painted surface. Furthermore, it is possible to reduce the influence caused by the direction of the periodic structure and evaluate the painted surface.

[0059] In addition, the painting evaluation apparatus, painting evaluation method, and painting evaluation program according to the present embodiment may calculate a main direction vector at a predetermined position on the painted surface based on the shape information, and set an intensity distribution having a periodic structure in the direction of the main direction vector as the first intensity distribution. Thereby, it is possible to suppress the influence of the curved shape of the painted surface and accurately evaluate the distinctness of image of the painted surface.

[0060] Furthermore, in the painting evaluation apparatus, painting evaluation method, and painting evaluation program according to the present embodiment, the first intensity distribution may have a first region where the intensity of the incident light is equal to or greater than a first threshold value and a second region where the intensity of the incident light is less than the first threshold value and equal to or less than a second threshold value. Thereby, at the boundary between the "bright part" and the "dark part" of the first intensity distribution, the intensity of the light changes intermittently, and the distinctness of image of the painted surface can be accurately evaluated.

[0061] Also, the painting evaluation apparatus, painting evaluation method, and painting evaluation program according to the present embodiment may acquire position information of a region of the painted surface irradiated with incident light and acquire shape information based on the position information. Thereby, alignment between the painted surface to be evaluated and the curved shape represented by the shape information can be performed.

[0062] Furthermore, the painting evaluation apparatus, painting evaluation method, and painting evaluation program according to the present embodiment may irradiate the painted surface with incident light including a first marking pattern, and acquire, as a second marking pattern, the intensity distribution of the reflected light from the region of the painted surface irradiated with the first marking pattern. Then, based on the difference between the first marking pattern and the second marking pattern, reference shape information of the region of the painted surface irradiated with the first marking pattern may be acquired, and position information of a region on the painted surface having shape information that matches the reference shape information may be acquired. Thereby, alignment between the painted surface to be evaluated and the curved shape represented by the shape information can be performed.

[0063] Also, the painting evaluation apparatus, painting evaluation method, and painting evaluation program according to the present embodiment may acquire material information of the painted surface, and estimate an evaluation value corresponding to a combination of the material information and a third intensity distribution using an evaluation model that outputs an evaluation value of the distinctness of image of the painted surface for an input including the material information and the third intensity distribution. By using, in addition to the intensity distribution of the reflected light, the material information of the painted surface for the evaluation of the distinctness of image of the painted surface, the distinctness of image of the painted surface can be accurately evaluated.

[0064] Furthermore, in the painting evaluation apparatus, painting evaluation method, and painting evaluation program according to the present embodiment, the evaluation model may be a learning model generated by machine learning based on teacher data including the material information of the evaluated painted surface having a planar shape, the intensity distribution of the reflected light obtained by irradiating the evaluated painted surface with incident light, and the evaluation value of the distinctness of image of the evaluated painted surface. Thereby, the distinctness of image of a curved painted surface can be accurately evaluated by the evaluation model generated from the teacher data regarding the evaluated painted surface having a planar shape.

[0065] Each function shown in the above-described embodiment can be implemented by one or a plurality of processing circuits. The processing circuit includes a programmed processor, an electric circuit, etc., and further includes a device such as an application-specific integrated circuit (ASIC) and circuit components arranged to execute the described functions.

[0066] As described above, the content of the present invention has been described in accordance with the embodiment. However, it is obvious to those skilled in the art that the present invention is not limited to these descriptions, and various modifications and improvements are possible. It should not be understood that the discussion and drawings forming part of this disclosure limit the present invention. Various alternative embodiments, examples, and operation techniques will be apparent to those skilled in the art from this disclosure.

[0067] Needless to say, the present invention includes various embodiments and the like not described herein. Therefore, the technical scope of the present invention is defined only by the invention-specific matters according to the legitimate claims based on the above description.

Explanation of Reference Numerals

[0068] 11 Shape acquisition unit 13 Material acquisition unit 15 Intensity acquisition unit 19 Light source unit 100 Controller 110 Intensity correction unit 120 Evaluation model setting unit 130 Evaluation value estimation unit 400 Output unit

Claims

1. A shape acquisition unit that measures a painted surface or acquires shape information representing the curved shape of the painted surface based on design data of the painted surface; A light source unit that irradiates the painted surface with incident light having a first intensity distribution; An intensity acquisition unit that acquires a second intensity distribution of reflected light from the painted surface; A painting evaluation device comprising a controller, wherein the controller calculates a third intensity distribution so as to cancel out a light scattering component on the painted surface due to a deviation from the planar shape of the curved shape, which is included in the second intensity distribution, based on the shape information; estimates an evaluation value corresponding to the third intensity distribution using an evaluation model that outputs an evaluation value of the distinctness of image of the painted surface for an input including the third intensity distribution A painting evaluation device characterized by the above.

2. The painting evaluation device according to claim 1, wherein the smaller the deviation, the smaller the difference between the second intensity distribution and the third intensity distribution, and when the curved shape is a planar shape, the second intensity distribution and the third intensity distribution coincide A painting evaluation device characterized by the above.

3. The painting evaluation device according to claim 1 or 2, wherein the evaluation model is a learning model generated by machine learning based on teacher data that is a set of the intensity distribution of reflected light obtained by irradiating an evaluated painted surface having a planar shape with the incident light and the evaluation value of the distinctness of image of the evaluated painted surface A painting evaluation device characterized by the above.

4. The painting evaluation device according to any one of claims 1 to 3, wherein the evaluation value of the distinctness of image of the painted surface is an index determined by at least one of the smoothness of the painted surface, the ratio of diffuse reflection in the reflected light on the painted surface, and the resolution of the image reflected on the painted surface A painting evaluation device characterized by the above.

5. The painting evaluation device according to any one of claims 1 to 4, wherein the first intensity distribution has a periodic structure in a first direction A painting evaluation device characterized by the above.

6. The painting evaluation device according to claim 5, wherein the first intensity distribution has a periodic structure in a second direction different from the first direction A painting evaluation device characterized by the above.

7. The painting evaluation device according to any one of claims 1 to 6, wherein the controller calculates a main direction vector at a predetermined position on the painted surface based on the shape information, and sets an intensity distribution having a periodic structure in the direction of the main direction vector as the first intensity distribution A painting evaluation device characterized by

8. The painting evaluation device according to any one of Claims 1 to 7, wherein the first intensity distribution includes a first region where the intensity of the incident light is equal to or greater than a first threshold value, and a second region where the intensity of the incident light is less than the first threshold value and equal to or less than a second threshold value, and having A painting evaluation device characterized by

9. The painting evaluation device according to any one of Claims 1 to 8, wherein the shape acquisition unit acquires position information of a region of the painted surface irradiated with the incident light, and acquires the shape information based on the position information A painting evaluation device characterized by

10. The painting evaluation device according to any one of Claims 1 to 9, wherein the light source unit irradiates the incident light including a first marking pattern, the intensity acquisition unit acquires, as a second marking pattern, an intensity distribution of reflected light from a region of the painted surface irradiated with the first marking pattern, the controller acquires reference shape information of a region irradiated with the first marking pattern based on a difference between the first marking pattern and the second marking pattern, and acquires position information of a region on the painted surface having the shape information that matches the reference shape information A painting evaluation device characterized by

11. The painting evaluation device according to any one of Claims 1 to 10, further comprising a material acquisition unit that acquires material information of the painted surface, the controller estimates an evaluation value corresponding to a combination of the material information and the third intensity distribution using the evaluation model that outputs an evaluation value of the distinctness of image of the painted surface with respect to an input including the material information and the third intensity distribution A painting evaluation device characterized by

12. The painting evaluation device according to Claim 11, wherein the evaluation model is a learning model generated by machine learning based on teacher data including the material information of an evaluated painted surface having a planar shape, the intensity distribution of reflected light obtained by irradiating the evaluated painted surface with the incident light, and the evaluation value of the distinctness of image of the evaluated painted surface A painting evaluation device characterized by

13. Measure the painted surface or acquire shape information representing the curved shape of the painted surface based on the design data of the painted surface, irradiate the painted surface with incident light having a first intensity distribution, acquire a second intensity distribution of the reflected light from the painted surface Based on the shape information, calculate a third intensity distribution so as to cancel out the light scattering component on the painted surface due to the deviation from the planar shape of the curved shape included in the second intensity distribution. Estimate the evaluation value corresponding to the third intensity distribution using an evaluation model that outputs the evaluation value of the distinctness of image of the painted surface for the input including the third intensity distribution. A painting evaluation method characterized by the above.

14. A shape acquisition unit that measures the painted surface or acquires shape information representing the curved shape of the painted surface based on the design data of the painted surface, A light source unit that irradiates the painted surface with incident light having a first intensity distribution, An intensity acquisition unit that acquires a second intensity distribution of the reflected light from the painted surface, In a computer for controlling, The step of acquiring the shape information using the shape acquisition unit, Based on the shape information, the step of calculating a third intensity distribution so as to cancel out the light scattering component on the painted surface due to the deviation from the planar shape of the curved shape included in the second intensity distribution, The step of estimating the evaluation value corresponding to the third intensity distribution using an evaluation model that outputs the evaluation value of the distinctness of image of the painted surface for the input including the third intensity distribution, A painting evaluation program for causing the above to be executed.

Images