Color information estimation method and color information estimation device

Abstract

To provide a technique that enables estimation of a color that is visually equivalent to a target color on a surface of a target object.SOLUTION: A color information estimation method is provided, comprising a first acquisition step (S10) of acquiring a first image showing surface texture of a target object, a second acquisition step (S14) of acquiring color information of a target first color, and an estimation step (S16) of estimating color information of a second color visually equivalent to the first color on a surface of the target object according to the first image and the color information of the first color.SELECTED DRAWING: Figure 5

Description

[Technical Field]

[0001] The present invention relates to a color information estimation method and a color information estimation device. [Background technology]

[0002] Patent Document 1 discloses a method for producing paints based on computer-based color matching using an apparatus that includes a database in which compounding data and corresponding color data for compositions containing one or more colorants are registered, and a computer that runs color matching calculation logic using the data registered in the database. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent Publication No. 2021-188046 Summary of the Invention [Problem to be solved by the invention]

[0004] Due to the influence of minute irregularities on the surface of a material, the color that is visually perceived when a paint or the like is applied to the material may differ from the color of the applied paint or the like. Therefore, it is desirable to estimate what color paint or the like should be applied to the material so that the desired color is visually perceived.

[0005] An object of the present invention is to provide a technique capable of estimating a color that is visually perceived as being equivalent to a target color on the surface of an object. [Means for solving the problem]

[0006] In order to solve the above problem, a color information estimation method of one embodiment of the present invention is a color information estimation method executed by a computer, and includes a first acquisition step of acquiring a first image representing the surface texture of an object, a second acquisition step of acquiring color information of a first color of the target, and an estimation step of estimating color information of a second color that appears to be equivalent to the first color on the surface of the object based on the first image and the color information of the first color. The color information of the first color and the color information of the second color are each Lab values. In the estimating step, the Lab values ​​of the second color are derived so that a statistical value of the Lab values ​​of each of multiple pixels of a first combined image obtained by combining the Lab values ​​of the second color with the first image is equivalent to the Lab values ​​of the first color. In the first obtaining step, a second image representing the surface texture of the reference object and Lab values ​​of a third color are further obtained. In the second obtaining step, the Lab values ​​of a color that is visible when the third color is overlaid on the surface of the reference object are estimated based on the second image and the Lab values ​​of the third color, and the estimated Lab values ​​are obtained as the Lab values ​​of the first color.

[0009] In the second acquisition step, the Lab value of the first color may be estimated based on the second image and the Lab value of the third color using a machine-learned trained model.

[0010] The first image and the second image may each be a grayscale image. The second acquisition step may include a first derivation step of deriving a second composite image by combining the second image with the Lab values ​​of the third color, and a second derivation step of deriving statistics of the Lab values ​​of each pixel of the second composite image and acquiring the statistics as the Lab values ​​of the first color. In the first derivation step, for each pixel of the second image, a value obtained by multiplying a coefficient corresponding to the pixel value of the pixel by the L value of the third color may be set as the L value of the corresponding pixel of the second composite image, and the a-values ​​and b-values ​​of the third color may be set as the a-values ​​and b-values ​​of each pixel of the second composite image. In the estimation step, for each pixel of the first image, a value obtained by multiplying a coefficient corresponding to the pixel value of the pixel by the L value of the second color may be set as the L value of the corresponding pixel of the first composite image, and the a-values ​​and b-values ​​of the second color may be set as the a-values ​​and b-values ​​of each pixel of the first composite image.

[0011] Another aspect of the present invention is a color information estimation device that includes a first acquisition unit that acquires a first image representing the surface texture of an object, a second acquisition unit that acquires color information of a first color of a target, and an estimation unit that estimates color information of a second color that appears to be equivalent to the first color on the surface of the object based on the first image and the color information of the first color. The color information of the first color and the color information of the second color are each Lab values. The estimation unit derives the Lab values ​​of the second color so that a statistical value of the Lab values ​​of each of multiple pixels of a first combined image obtained by combining the Lab values ​​of the second color with the first image is equivalent to the Lab values ​​of the first color. The first acquisition unit further acquires a second image representing the surface texture of the reference object and the Lab values ​​of a third color. The second acquisition unit estimates the Lab values ​​of a color that is visible when the third color is overlaid on the surface of the reference object based on the second image and the Lab values ​​of the third color, and acquires the estimated Lab values ​​as the Lab values ​​of the first color. [Effects of the Invention]

[0012] According to the present invention, it is possible to estimate a color that is visually perceived as being equivalent to the target color on the surface of an object. [Brief explanation of the drawings]

[0013] [Figure 1] FIG. 10 is a diagram showing an example of a surface image of a material. [Figure 2] FIG. 2 shows an example of a simulated image of the material of FIG. 1 with a painted surface. [Figure 3] 2 shows another example of a simulated image of the material of FIG. 1 with a painted surface. [Figure 4] 1 is a diagram illustrating a configuration of a color information estimation device according to an embodiment. [Figure 5] 5 is a flowchart showing the process of the color information estimation device of FIG. 4. DETAILED DESCRIPTION OF THE INVENTION

[0014] For example, when considering the color of paint or the like to be used to paint various parts of an object such as a vehicle, the color information estimation device of the embodiment simulates the color that will be perceived when the paint or the like is applied to a material, and estimates the color of the paint or the like that will be perceived as the desired color.

[0015] When the same color paint is applied to two materials with different surface textures, the appearance of the color, such as brightness and saturation, may differ depending on the surface texture. For example, a color will appear relatively dark on a material with many uneven surfaces, while a color will appear relatively light on a material with many flat surfaces. Therefore, for example, it is desirable to paint a reference object and a target object with different surface textures, and obtain the color to be painted on the target object in a situation where you want to match the appearance of the color painted on the reference object.

[0016] Therefore, a color information estimation device according to an embodiment uses a color that is visually perceived when a reference color is applied to a reference object as a target color, and estimates color information for a color that will be visually perceived as equivalent to the target color when applied to the object, based on an image representing the surface texture of the object and color information about the target color. The following describes an example in which the color information is Lab values. Lab values ​​represent lightness L*, chromaticity a*, and b* in the CIE L*a*b* color space. Hereinafter, lightness L* will be referred to as the L value or L, chromaticity a* as the a value or a, and chromaticity b* as the b value or b.

[0017] FIG. 1 shows an example of a surface image of a material. FIG. 1(a) shows a second image representing the surface texture of a reference object, and FIG. 1(b) shows a first image representing the surface texture of a target object. The first and second images are grayscale images of actual materials magnified using a microscope or the like. The magnification ratio can be determined appropriately for each material through experiments or simulations. The multiple pixel values ​​in the first and second images represent the surface irregularities of the material. For example, the closer a pixel color is to white, the larger the pixel value and the higher the height, and the closer it is to black, the smaller the pixel value and the lower the height. For example, in the irregularities of multiple samples of various materials, the maximum depth is set to the lowest pixel value, and the maximum height is set to the highest pixel value. As shown in the figure, the reference object and the target object have different surface textures. The reference object and the target object may be, for example, resin or metal.

[0018] Figure 2 shows an example of a simulated image of the material of Figure 1 with a painted surface. Figure 2(a) shows a second composite image 100a obtained by combining the second image of Figure 1(a) with a reference third color. Figure 2(b) shows a first composite image 102a obtained by combining the first image of Figure 1(b) with a reference third color.

[0019] These composite images are color images that simulate the colors actually seen. The compositing method is described below. Even though the same third color is used, the overall brightness of the first composite image 102a is different from the overall brightness of the second composite image 100a, and the overall color of the first composite image 102a is perceived differently from the overall color of the second composite image 100a.

[0020] The color information estimation device acquires the average value of the Lab values ​​of each pixel in the second composite image 100a in Fig. 2(a) as color information of the target first color. The color information estimation device estimates color information of a second color that appears to be equivalent to the first color on the surface of the object, based on the first image in Fig. 1(b) and the color information of the first color.

[0021] 2(c) shows a first composite image 102b obtained by combining the first image of FIG. 1(b) with the estimated second color. The overall brightness of the first composite image 102c is equivalent to the overall brightness of the second composite image 100a, and the overall color of the first composite image 102c is perceived as being equivalent to the overall color of the second composite image 100a. Therefore, a user can easily grasp in a short time that painting the surface of an object with paint of the estimated second color can be perceived as being equivalent to the color of a reference object painted with paint of a third color, without conducting experiments in which various colors of paint are applied to the object.

[0022] Figure 3 shows another example of a simulated image of the material of Figure 1 with a color applied to the surface. Figure 3(a) shows a second composite image 100b obtained by combining a reference third color with the second image of the reference object of Figure 1(a). Figure 3(b) shows a first composite image 102c obtained by combining a reference third color with the first image of the target object of Figure 1(b). The third color in Figure 3 is different from the third color in Figure 2.

[0023] The overall brightness of the first composite image 102c is perceived differently from the overall brightness of the second composite image 100b, and the overall color of the first composite image 102c is perceived differently from the overall color of the second composite image 100b.

[0024] The color information estimation device acquires the average value of the Lab values ​​of each pixel of the second composite image 100b in Fig. 3(a) as the color information of the target first color. The color information estimation device estimates the color information of the second color based on the first image in Fig. 1(b) and the color information of the first color.

[0025] Fig. 3(c) shows a first composite image 102d obtained by combining the first image of Fig. 1(b) with the estimated second color. The overall brightness of the first composite image 102d is equivalent to the overall brightness of the second composite image 100b, and the overall color of the first composite image 102d is visually equivalent to the overall color of the second composite image 100b.

[0026] In this way, color information of the second color that is visually recognized as a color equivalent to the target first color on the surface of the object can be estimated according to the surface texture of the object.

[0027] FIG. 4 shows the configuration of a color information estimation device 1 according to an embodiment. The color information estimation device 1 includes a first acquisition unit 10, a second acquisition unit 12, a first estimation unit 14, and an output unit 16. The second acquisition unit 12 includes a second estimation unit 20. The configuration of the color information estimation device 1 can be realized in hardware terms using the CPU, memory, and other LSIs of any computer, and in software terms using programs loaded into memory, but the diagram illustrates functional blocks realized by the cooperation of these. Therefore, those skilled in the art will understand that these functional blocks can be realized in various ways using only hardware, only software, or a combination of both.

[0028] The first acquisition unit 10 acquires, in accordance with a user's instructions, a second image representing the surface texture of the reference object, a first image representing the surface texture of the target object, and the Lab values ​​of the reference third color, for example, via a network. The first acquisition unit 10 supplies the second image and the Lab values ​​of the third color to the second acquisition unit 12, and supplies the first image to the first estimating unit 14.

[0029] In the example shown in Figures 2(a) and 2(b), the Lab values ​​of the third color are L=87.6, a=-1.6, and b=6.4. In the example shown in Figures 3(a) and 3(b), the Lab values ​​of the third color are L=54.51, a=12.5, and b=22.4.

[0030] The second acquisition unit 12 acquires the Lab values ​​of the target first color and supplies the acquired Lab values ​​of the first color to the first estimation unit 14. Specifically, the second estimation unit 20 estimates the Lab values ​​of the color that is visible when the third color is superimposed on the surface of the reference object, based on the second image acquired by the first acquisition unit 10 and the Lab values ​​of the third color, and the second acquisition unit 12 acquires the estimated Lab values ​​as the Lab values ​​of the first color.

[0031] More specifically, the second estimation unit 20 combines the Lab values ​​of the third color with the second image to derive the second combined image. For each pixel in the second image, the second estimation unit 20 multiplies a coefficient corresponding to the pixel value of the pixel by the L value of the third color, and sets the resulting value as the L value of the corresponding pixel in the second combined image. This coefficient is, for example, a real number between 0 and 1, and increases as the pixel value increases. For example, the coefficient corresponding to the minimum pixel value is 0, and the coefficient corresponding to the maximum pixel value is 1.

[0032] The second estimation unit 20 sets the a-values ​​and b-values ​​of the third color as the a-values ​​and b-values ​​of each pixel of the second composite image. That is, the a-values ​​and b-values ​​of each pixel of the second composite image are the a-values ​​and b-values ​​of the third color.

[0033] The second estimation unit 20 derives a statistical value of the Lab values ​​of each pixel in the second composite image and acquires the statistical value as the Lab value of the first color. The statistical value is, for example, an average value. The average Lab values ​​of each pixel in the second composite image represent a set of the average L values ​​of multiple pixels, the average a values ​​of multiple pixels, and the average b values ​​of multiple pixels. This process allows the Lab value of the first color to be acquired with a relatively small computational load.

[0034] In the example of Fig. 2(a), the average Lab values ​​of each pixel of the second composite image 100a, i.e., the Lab values ​​of the first color, are L = 29.4, a = -1.6, and b = 6.4. In the example of Fig. 3(a), the average Lab values ​​of each pixel of the second composite image 100b, i.e., the Lab values ​​of the first color, are L = 18.2, a = 12.5, and b = 22.4.

[0035] The first estimation unit 14 estimates the Lab value of a second color that appears to be equivalent to the first color on the surface of the object based on the first image acquired by the first acquisition unit 10 and the Lab value of the first color acquired by the second acquisition unit 12.

[0036] Specifically, the first estimation unit 14 derives the Lab values ​​of the second color so that the statistical value of the Lab values ​​of each of the pixels of the first composite image obtained by combining the Lab values ​​of the second color with the first image is equivalent to the Lab values ​​of the first color. As described above, the statistical value is, for example, an average value.

[0037] For each pixel in the first image, the first estimation unit 14 multiplies the L value of the second color by a coefficient corresponding to the pixel value of that pixel and sets the resulting value as the L value of the corresponding pixel in the first composite image. The first estimation unit 14 sets the a value and b value of the second color as the a value and b value of each pixel in the first composite image. This process makes it possible to obtain the Lab value of the second color with a relatively small computational load.

[0038] The first estimation unit 14 supplies the derived Lab values ​​of the second color and the first composite image obtained using the Lab values ​​of the second color to the output unit 16.

[0039] In the example of FIG. 2(c), the Lab values ​​of the second color are L=46.27, a=-1.6, and b=6.4. The average Lab values ​​of each pixel of the first composite image 102b are L=29.3, a=-1.6, and b=6.4. Since the average Lab values ​​of each pixel of the first composite image 102b are equivalent to the average Lab values ​​of each pixel of the second composite image 100a in FIG. 2(a), as described above, the overall color of the first composite image 102b is perceived as being equivalent to the overall color of the second composite image 100a.

[0040] 2(b), the average values ​​of the Lab values ​​of each pixel of the first composite image 102a using the third color are L=55.5, a=-1.6, and b=6.4, which is significantly different from the average value of the Lab values ​​of each pixel of the second composite image 100a. The first estimation unit 14 derives the Lab values ​​of the second color so that the difference in the average values ​​of the Lab values ​​between the second composite image 100a and the first composite image 102b is small.

[0041] In the example of Fig. 3(c), the Lab values ​​of the second color are L = 29.02, a = 12.5, and b = 22.4. The average Lab values ​​of each pixel of the first composite image 102d are L = 18.3, a = 12.5, and b = 22.4. Since the average Lab values ​​of each pixel of the first composite image 102d are equivalent to the average Lab values ​​of each pixel of the second composite image 100b in Fig. 3(a), as described above, the overall color of the first composite image 102d is perceived as being equivalent to the overall color of the second composite image 100b.

[0042] 3(b), the average values ​​of the Lab values ​​of each pixel of the first composite image 102c using the third color are L=34.5, a=12.5, and b=22.4, which is significantly different from the average value of the Lab values ​​of each pixel of the second composite image 100b. The first estimation unit 14 derives the Lab values ​​of the second color so that the difference in the average values ​​of the Lab values ​​between the second composite image 100b and the first composite image 102d is small.

[0043] The output unit 16 outputs the Lab values ​​of the second color, the first composite image, and the second composite image to, for example, a display device (not shown). The display device displays the Lab values ​​of the second color, the first composite image, and the second composite image. From the information displayed on the display device, the user can determine which color to apply to the object, and by checking the first and second composite images, which are simulation images, the user can determine what color will appear.

[0044] 5 is a flowchart showing the processing of the color information estimation device 1 in FIG. 4. The color information estimation device 1 acquires a second image of a reference object, a first image of a target object, and Lab values ​​of a third color of the reference object (first acquisition step: S10). The color information estimation device 1 combines the Lab values ​​of the third color with the second image to derive a second combined image (first derivation step of the second acquisition step: S12), derives the average value of the Lab values ​​of each pixel of the second combined image, and acquires it as the Lab value of the target first color (second derivation step of the second acquisition step: S14). The color information estimation device 1 estimates the Lab value of the second color based on the first image and the Lab value of the first color (estimation step: S16), and ends the processing.

[0045] According to the embodiment, when a reference object and a reference third color are given, it is possible to estimate the first color that is perceived when the third color is superimposed on the surface of the reference object, and it is possible to estimate the Lab value of the second color that is perceived as a color equivalent to the first color when superimposed on the surface of the target object.

[0046] The present invention has been described above based on the embodiments. However, the embodiments are merely examples, and it will be understood by those skilled in the art that various modifications are possible in the combination of each component and each treatment process, and that such modifications are also within the scope of the present invention.

[0047] For example, in the embodiment, the second acquisition unit 12 acquires the Lab value of the first color based on the second image of the reference object and the Lab value of the reference third color, but if the Lab value of the target first color is specified in advance, the second acquisition unit 12 may acquire the Lab value of the first color input by the user to the input unit, for example. This modification simplifies the processing.

[0048] In the embodiment, an example has been described in which the color information is Lab values, but color values ​​in other color systems that use lightness may also be used, and the color information may be, for example, LCh values ​​in the L*C*h color space. This modification can improve the degree of freedom in the configuration of the color information estimation device 1.

[0049] In the embodiment, the a-values ​​and b-values ​​of each pixel in the second composite image are the a-values ​​and b-values ​​of the third color. However, they may be values ​​that reflect the pixel values ​​of each pixel in the second image. In this case, the second estimation unit 20 may, for each pixel in the second image, set the value obtained by substituting the pixel value of the pixel and the a-value of the third color into a predetermined first mathematical formula as the a-value of the corresponding pixel in the second composite image. The second estimation unit 20 may, for each pixel in the second image, set the value obtained by substituting the pixel value of the pixel and the b-value of the third color into a predetermined second mathematical formula as the b-value of the corresponding pixel in the second composite image. The first mathematical formula and the second mathematical formula may be determined as appropriate through experiments or simulations. Similarly, the first estimation unit 14 may, for each pixel in the first image, set the value obtained by substituting the pixel value of the pixel and the a-value of the second color into a predetermined first mathematical formula as the a-value of the corresponding pixel in the first composite image. For each pixel in the first image, the first estimation unit 14 may substitute the pixel value of the pixel and the b value of the second color into a predetermined second formula to obtain a value, which may be set as the b value of the corresponding pixel in the first composite image. This modification may enable the acquisition of a first composite image and a second composite image with higher accuracy.

[0050] In the embodiment, the second acquisition unit 12 acquires the average Lab value of each pixel in the second composite image as the Lab value of the target first color. However, instead of this process, the Lab value of the first color may be estimated using a trained model. In this variant, a learning device (not shown) pre-machines a model for estimating the Lab value of the first color. The learning device may be provided in the color information estimation device 1 or may be a device separate from the color information estimation device 1. The learning device derives image features from a second image of the reference object. Examples of features that can be used include the kurtosis of the distribution of surface irregularities, the arithmetic mean roughness of the surface, the luminance gradient, and periodicity in the image. The learning device receives as input the features of the second image of the reference object and the Lab value of the reference third color. The learning device learns a model using the Lab value measured with a colorimeter of the color of a sample of the reference object actually painted with the third color as the correct label. The learning device repeatedly trains the model.

[0051] The second estimation unit 20 of the second acquisition unit 12 estimates the Lab value of the first color based on the feature amount of the second image of the reference object and the Lab value of the third color using a trained model for first color estimation. The estimated Lab value of the first color corresponds to the Lab value of the color that is visually recognized when the third color is superimposed on the surface of the reference object. This modification improves the flexibility of the configuration of the color information estimation device 1.

[0052] The first estimation unit 14 may also estimate the Lab values ​​of the second color using a separate trained model for second color estimation. In this case, the learning device inputs the feature amounts of the first image of the object and the Lab values ​​of a sample of the object actually painted with the second color paint, measured with a colorimeter, and trains a model using the Lab values ​​of the second color as the correct label. The first estimation unit 14 uses the trained model for second color estimation to estimate the Lab values ​​of the second color based on the feature amounts of the first image of the object and the Lab values ​​of the target first color. [Explanation of symbols]

[0053] 1...Color information estimation device, 10...First acquisition section, 12...Second acquisition section, 14...First estimation section, 16...Output section, 20...Second estimation section.

Claims

1. 1. A computer-implemented method for estimating color information, comprising: a first acquisition step of acquiring a first image representing a surface texture of the object; a second acquisition step of acquiring color information of the first color of the target; an estimation step of estimating color information of a second color that is visually recognized as a color equivalent to the first color on the surface of the object based on the first image and color information of the first color; Equipped with the color information of the first color and the color information of the second color are each Lab values, In the estimation step, the Lab values ​​of the second color are derived so that a statistical value of the Lab values ​​of each of a plurality of pixels of a first composite image obtained by combining the Lab values ​​of the second color with the first image is equivalent to the Lab values ​​of the first color; In the first acquisition step, a second image representing a surface texture of the reference object and a Lab value of a third color are further acquired; In the second obtaining step, the Lab values ​​of a color that is visually recognized when the third color is superimposed on the surface of the reference object are estimated based on the second image and the Lab values ​​of the third color, and the estimated Lab values ​​are obtained as the Lab values ​​of the first color. A color information estimation method comprising:

2. the first image and the second image are each a grayscale image; The second acquisition step a first derivation step of deriving a second composite image by combining the Lab values ​​of the third color with the second image; a second derivation step of deriving a statistical value of the Lab values ​​of each pixel of the second composite image and acquiring the statistical value as the Lab value of the first color; and In the first derivation step, For each pixel of the second image, a value obtained by multiplying a coefficient according to the pixel value of the pixel by the L value of the third color is set as the L value of the corresponding pixel of the second composite image; setting the a-value and b-value of the third color as the a-value and b-value of each pixel of the second composite image; In the estimation step, for each pixel of the first image, a value obtained by multiplying a coefficient according to the pixel value of the pixel by the L value of the second color is set as the L value of the corresponding pixel of the first composite image; setting the a-value and b-value of the second color as the a-value and b-value of each pixel of the first composite image; 2. The color information estimation method according to claim 1.

3. a first acquisition unit that acquires a first image representing a surface texture of the object; a second acquisition unit that acquires color information of a first color of the target; an estimation unit that estimates color information of a second color that is visually recognized as a color equivalent to the first color on the surface of the object based on the first image and color information of the first color; Equipped with the color information of the first color and the color information of the second color are each Lab values, the estimation unit derives the Lab values ​​of the second color so that a statistical value of the Lab values ​​of each of a plurality of pixels of a first combined image obtained by combining the Lab values ​​of the second color with the first image is equivalent to the Lab values ​​of the first color; the first acquisition unit further acquires a second image representing a surface texture of the reference object and a Lab value of a third color; the second acquisition unit estimates Lab values ​​of a color that is visually recognized when the third color is superimposed on a surface of the reference object based on the second image and the Lab values ​​of the third color, and acquires the estimated Lab values ​​as the Lab values ​​of the first color. A color information estimation device characterized by:

Images