Methods for determining color matching and equipment for determining color matching.

Abstract

The method for determining color combinations, according to a scheme revealed in the description, may include the following steps: obtaining target color information corresponding to the target color; generating color combination information corresponding to at least one color combination consisting of at least one specific candidate color from among the first to the nth candidate color; estimating at least one reflectance predicting the color combination by referencing the color combination information; comparing the target color measurement reflectance corresponding to the target color information with the color combination prediction reflectance; and determining and making the optimal color combination information, the specific color combination information corresponding to the specific color combination prediction reflectance that satisfies the threshold reflectance condition established on the basis of the target color measurement reflectance from among the color combination prediction reflectances.

Description

Color combination determination method and color combination determination device

[0001] Cross-citation with related applications

[0002] This invention claims the benefit of priority from Korean Patent Application No. 10-2023-0132752, filed on October 5, 2023, and all contents of the document in that Korean Patent Application are incorporated herein by reference.

[0003] Technology field

[0004] The embodiments disclosed in this document relate to a color combination determination method and a color combination determination device.

[0005] In the past, in determining the optimal color combination (e.g., the combination of base and colorant), an initial color combination corresponding to a target color was determined, a specimen was created according to the initial color combination, and the initial color combination was modified based on the result of comparing the colorimetric results of the specimen with the target color. This process was repeated to derive the optimal color combination.

[0006] The average color scheme designer will typically go through three or more iterations of the process to arrive at the optimal color scheme.

[0007] The time required to determine the initial color combination or modified color combination and to mix paints accordingly to create a specimen is approximately 30 minutes to 1 hour, and there is a problem that it takes approximately 2 to 3 hours to derive the optimal color combination according to the conventional method.

[0008] Therefore, attempts are being made to quickly derive the optimal color combination corresponding to the target color in order to meet the consumer's demand for various target colors.

[0009] The embodiments disclosed in this document are intended to provide a color combination determination method and a color combination determination device using the same.

[0010] The embodiments disclosed in this document are intended to provide a color combination determination method and a color combination determination device using the same for quickly and accurately deriving optimal color combination information corresponding to a target color.

[0011] The embodiments disclosed in this document are intended to provide a color combination determination method and a color combination determination device using the same for reducing the number of color combination information modifications in deriving optimal color combination information.

[0012] The embodiments disclosed in this document are intended to provide a color combination determination method corresponding to a user's color combination design environment and a color combination determination device using the same.

[0013] A method for determining a color combination according to an embodiment disclosed in the present document comprises the steps of: obtaining target color information corresponding to a target color; generating color combination information corresponding to at least one color combination including at least one specific candidate color among a first candidate color to an n-th candidate color; estimating at least one color combination prediction reflectance with reference to the color combination information; comparing a target color measurement reflectance corresponding to the target color information with the color combination prediction reflectance; estimating at least one corrected color combination prediction reflectance with reference to corrected concentration information and characteristic information of each of the specific candidate colors when the color combination prediction reflectance does not satisfy a threshold reflectance condition set based on the target color measurement reflectance; comparing the target color measurement reflectance with the corrected color combination prediction reflectance; And, among the above-mentioned modified color combination prediction reflectances, a step of determining specific modified color combination information corresponding to a specific modified color combination prediction reflectance that satisfies the threshold reflectance condition set based on the target color measurement reflectance as the optimal color combination information may be included.

[0014] As an example, in the step of estimating the color combination prediction reflectance, the color combination prediction reflectance can be estimated by referring to the set concentration information and characteristic information of each of the specific candidate colors included in the color combination information.

[0015] As an example, the characteristic information includes first characteristic information to m-th characteristic information corresponding to a first wavelength to an m-th wavelength, the target color measurement reflectance includes first target color measurement reflectance to m-th target color measurement reflectance corresponding to the first wavelength to the m-th wavelength, and in the step of estimating the color combination prediction reflectance, the first color combination prediction reflectance to m-th color combination prediction reflectance is estimated as the color combination prediction reflectance with reference to the set concentration information of each of the specific candidate colors and the first characteristic information to the m-th characteristic information, and in the step of determining the optimal color combination information, among the color combination prediction reflectances, specific color combination information corresponding to a specific color combination prediction reflectance that satisfies a first threshold reflectance condition to an m-th threshold reflectance condition set based on the first target color measurement reflectance to the m-th target color measurement reflectance can be determined as the optimal color combination information.

[0016] As an example, in the step of estimating the color combination prediction reflectance, the color combination information including the set concentration information of each of the specific candidate colors may be input into a reflectance estimation model so that the reflectance estimation model estimates the color combination prediction reflectance corresponding to the color combination information.

[0017] As an example, before the step of estimating the color combination prediction reflectance, the method may further include the steps of: (1) inputting learning color combination information into the reflectance estimation model to cause the reflectance estimation model to estimate the learning color combination prediction reflectance, (2) generating a color combination reflectance loss based on the learning color combination prediction reflectance and the corresponding color combination GT (ground truth) reflectance, and (3) updating at least some of the parameters of the reflectance estimation model by backpropagating the color combination reflectance loss.

[0018] As an example, the correction concentration information can be generated by applying a concentration gradient matrix, which is calculated by referencing a target L value, a target a value, a target b value, an L value change amount, an a value change amount, and a b value change amount on a Lab color space corresponding to at least one specific candidate color, to the set concentration information.

[0019] A color combination determination device according to an embodiment disclosed in the present document comprises: a target color information acquisition unit for acquiring target color information corresponding to a target color; a color combination information generation unit for generating color combination information corresponding to at least one color combination including at least one specific candidate color among a first candidate color to an n-th candidate color; a reflectance estimation unit for estimating at least one color combination prediction reflectance by referring to the color combination information; a reflectance comparison unit for comparing a target color measurement reflectance corresponding to the target color information and the color combination prediction reflectance; And, when the color combination prediction reflectance does not satisfy the threshold reflectance condition set based on the target color measurement reflectance, the color combination prediction reflectance may include an optimal color combination information determining unit that estimates at least one corrected color combination prediction reflectance by referring to the correction concentration information and the characteristic information of each of the specific candidate colors, compares the target color measurement reflectance and the corrected color combination prediction reflectance, and determines, as the optimal color combination information, specific corrected color combination information corresponding to a specific corrected color combination prediction reflectance that satisfies the threshold reflectance condition set based on the target color measurement reflectance among the corrected color combination prediction reflectances.

[0020] As an example, the reflectance estimation unit can estimate the color combination prediction reflectance by referring to the set concentration information and characteristic information of each of the specific candidate colors included in the color combination information.

[0021] As an example, the characteristic information includes first characteristic information to m-th characteristic information corresponding to a first wavelength to an m-th wavelength, the target color measurement reflectance includes first target color measurement reflectance to m-th target color measurement reflectance corresponding to the first wavelength to the m-th wavelength, the reflectance estimation unit estimates the first color combination prediction reflectance to m-th color combination prediction reflectance as the color combination prediction reflectance by referring to the set concentration information of each of the specific candidate colors and the first characteristic information to the m-th characteristic information, and the optimal color combination information determination unit can determine specific color combination information corresponding to a specific color combination prediction reflectance that satisfies a first threshold reflectance condition to an m-th threshold reflectance condition set based on the first target color measurement reflectance to m-th target color measurement reflectance, as the optimal color combination information.

[0022] As an example, the reflectance estimation unit may input the color combination information including the set concentration information of each of the specific candidate colors into a reflectance estimation model, thereby causing the reflectance estimation model to estimate the color combination prediction reflectance corresponding to the color combination information.

[0023] As an example, the reflectance estimation model may be in a state in which (1) a process of inputting learning color combination information into the reflectance estimation model to cause the reflectance estimation model to estimate learning color combination prediction reflectance, (2) a process of generating a color combination reflectance loss based on the learning color combination prediction reflectance and the corresponding color combination GT (ground truth) reflectance, and (3) a process of updating at least some of the parameters of the reflectance estimation model by backpropagating the color combination reflectance loss may be performed.

[0024] As an example, the correction concentration information can be generated by applying a concentration gradient matrix, which is calculated by referencing a target L value, a target a value, a target b value, an L value change amount, an a value change amount, and a b value change amount on a Lab color space corresponding to at least one specific candidate color, to the set concentration information.

[0025] The embodiments disclosed in this document can provide a color combination determination method and a color combination determination device using the same.

[0026] The embodiments disclosed in this document can provide a color combination determination method and a color combination determination device using the same for quickly and accurately deriving optimal color combination information corresponding to a target color.

[0027] The embodiments disclosed in this document can provide a color combination determination method and a color combination determination device using the same for reducing the number of color combination information modifications in deriving optimal color combination information.

[0028] The embodiments disclosed in this document can provide a color combination determination method corresponding to a user's color combination design environment and a color combination determination device using the same.

[0029] In addition, various effects may be provided, either directly or indirectly, through this document.

[0030] FIG. 1 is a drawing illustrating a color combination determination device according to one embodiment disclosed in this document.

[0031] FIG. 2 is a flowchart illustrating a method for determining a color combination according to one embodiment disclosed in this document.

[0032] FIGS. 3A to 3C are schematic diagrams illustrating a UI screen of a program to which a color combination determination method according to one embodiment disclosed in this document is applied.

[0033] Figures 4a and 4b are drawings comparing the reflectance of color combinations according to a conventional method and the present invention.

[0034] In connection with the description of the drawings, the same or similar reference numerals may be used for identical or similar components.

[0035] Hereinafter, various embodiments of the present invention will be described with reference to the attached drawings. However, this is not intended to limit the present invention to specific embodiments, and it should be understood that the present invention encompasses various modifications, equivalents, and / or alternatives of the embodiments.

[0036] In this document, the singular form of a noun corresponding to an item may include one or more of said items, unless the context clearly indicates otherwise. In this document, phrases such as "A or B," "at least one of A and B," "at least one of A or B," "A, B, or C," "at least one of A, B, and C," and "at least one of A, B, or C" may each include any one of the items listed together in that phrase, or all possible combinations thereof. Terms such as "first," "second," or "first" or "second" may be used merely to distinguish the corresponding element from other corresponding elements, and do not limit the corresponding elements in any other respect (e.g., importance or order). When a component (e.g., a first component) is referred to as being “coupled” or “connected” to another component (e.g., a second component), with or without the terms “functionally” or “communicatively,” it means that the component can be connected to the other component directly (e.g., wired), wirelessly, or through a third component.

[0037] Each component (e.g., a module or a program) described in this document may include one or more entities. According to various embodiments, one or more components or operations of the components may be omitted, or one or more other components or operations may be added. Alternatively or additionally, a plurality of components (e.g., a module or a program) may be integrated into a single component. In such a case, the integrated component may perform one or more functions of each of the plurality of components identically or similarly to those performed by the corresponding component among the plurality of components prior to integration. According to various embodiments, the operations performed by a module, program, or other component may be executed sequentially, in parallel, iteratively, or heuristically, or one or more of the operations may be executed in a different order, omitted, or one or more other operations may be added.

[0038] The term "module" or "part" used in this document may include a unit implemented in hardware, software, or firmware, and may be used interchangeably with terms such as logic, logic block, component, or circuit. A module may be an integral component, or a minimum unit or part of such a component that performs one or more functions. For example, according to one embodiment, a module may be implemented in the form of an application-specific integrated circuit (ASIC).

[0039] Various embodiments of the present document may be implemented as software (e.g., a program or an application) including one or more instructions stored in a machine-readable storage medium (e.g., memory). For example, a processor of the device may call at least one instruction among the one or more instructions stored from the storage medium and execute it. This enables the device to operate to perform at least one function according to the at least one instruction called. The one or more instructions may include code generated by a compiler or code executable by an interpreter. The machine-readable storage medium may be provided in the form of a non-transitory storage medium. Here, "non-transitory" only means that the storage medium is a tangible device and does not contain a signal (e.g., electromagnetic waves), and this term does not distinguish between cases where data is stored semi-permanently and cases where it is stored temporarily in the storage medium.

[0040] FIG. 1 is a drawing to help understand a color combination determination device according to one embodiment disclosed in this document, and schematically illustrates the color combination determination device.

[0041] Referring to FIG. 1, a color combination determination device (100) may include a target color information acquisition unit (110), a color combination information generation unit (120), a reflectance estimation unit (130), a reflectance comparison unit (140), and an optimal color combination information determination unit (150).

[0042] First, the target color information acquisition unit (110) can acquire target color information corresponding to the target color. For example, the target color information can be acquired by measuring the target color using colorimetric equipment.

[0043] And, the color combination information generation unit (120) can generate at least one color combination information corresponding to at least one color combination including at least one specific candidate color among the first candidate color to the n-th candidate color.

[0044] For example, the color combination information generation unit (120) can generate color combination information as a combination of some colors among the first candidate color to the nth candidate color.

[0045] For reference, the color combination information generated by the color combination information generation unit (120) may be one, but is not limited thereto, and multiple color combination information may be generated as candidates for optimal color combination information.

[0046] And, the reflectance estimation unit (130) can estimate at least one color combination prediction reflectance by referring to color combination information.

[0047] For example, the reflectance estimation unit (130) can estimate the color combination prediction reflectance by referring to the set concentration information and characteristic information of each specific candidate color included in the color combination information.

[0048] For example, when the first to fifth colors are included in the color combination as specific candidate colors, the reflectance estimation unit (130) can estimate the color combination prediction reflectance by referring to the set concentration information (the first set concentration information to the fifth set concentration information) and the characteristic information (the first characteristic information to the fifth characteristic information) of the first to fifth colors.

[0049] For example, the color characteristic information may include at least some of the color absorption coefficient (K) and reflection coefficient (scattering coefficient; S).

[0050] At this time, the color characteristic information may have values ​​corresponding to each wavelength of light. For example, the characteristic information may include first characteristic information to m-th characteristic information corresponding to the first to m-th wavelengths of light, respectively.

[0051] Additionally, the target colorimetric reflectance may include first to m-th target colorimetric reflectances corresponding to the first to m-th wavelengths of light, respectively.

[0052] For example, when the first to fifth colors are included in the color combination as specific candidate colors, the reflectance estimation unit (130) can estimate the first color combination prediction reflectance by referring to (i) the set concentration information of the first to fifth colors and (ii) the first characteristic information corresponding to the first wavelength of the first to fifth colors. Similarly, the reflectance estimation unit (130) can estimate the second to m-th color combination prediction reflectance for the second to m-th wavelengths.

[0053] For example, the reflectance estimation unit (130) can estimate the color combination prediction reflectance using Equations 1 and 2 below, which represent the relationship between reflectance and color (colorant) concentration, modeled based on the Kubelka-Munk theory.

[0054] [Formula 1]

[0055]

[0056] In relation to Equation 1, K represents the absorption coefficient, S represents the reflection coefficient (scattering coefficient), and R represents the reflectance.

[0057]

[0058] [Formula 2]

[0059]

[0060] Regarding Equation 2, K M is the average absorption coefficient of the color combination, S Mis the average reflection coefficient of the color combination, C P is the concentration of the base, K PW is the absorption coefficient of the base, S PW is the reflection coefficient of the base, C1 to C n is the concentration of the first to nth color, K 1W Inland K nW is the absorption coefficient of the first to nth colors, S 1W Inland S nW represents the reflection coefficient of the first to nth colors.

[0061] For reference, C1 to C n and C p has a value greater than or equal to 0, and is C1 to C n and C p The sum of can be 1.

[0062] For reference, reflectance may refer to, but is not limited to, the reflectance R itself derived based on the absorption coefficient and the reflection coefficient. For example, reflectance may be a value corresponding to the ratio of the absorption coefficient and the reflection coefficient.

[0063] As another example, the reflectance estimation unit (130) may input color combination information including set concentration information of each specific candidate color into the reflectance estimation model, thereby causing the reflectance estimation model to estimate a color combination prediction reflectance corresponding to the color combination information.

[0064] At this time, the reflectance estimation model may be a model that estimates the color combination prediction reflectance based on machine learning.

[0065] For example, the reflectivity estimation model may be a machine learning-based model trained through the following learning process. For example, the reflectivity estimation model may be a multi-layer perceptron model, but is not limited thereto. For example, the reflectivity estimation model may be a decision tree model or a regression model.

[0066] First, learning color combination information can be input into a reflectance estimation model to allow the reflectance estimation model to estimate the predicted reflectance of the learning color combination. At this time, the learning color combination information can include at least some of the concentration information of the base and colorant, and information on the absorption coefficient and reflection coefficient.

[0067] For reference, the learned reflectance estimation model can estimate the first to mth color combination prediction reflectance corresponding to the first to mth wavelengths of light, respectively (i.e., a vector representing the reflectance for each of the first to mth wavelengths).

[0068] For example, in order to learn a reflectance estimation model, 2300 training color combination information, as shown in Table 1 below, can be input into the reflectance estimation model.

[0069] For reference, using the 'Forest Ace Exterior' product, we generated approximately 2,300 learning color combinations based on four types of bases, and trained a reflectance estimation model using these.

[0070] For reference, the number of learning color combination information (2300), concentration (88.47, etc.), and type of color (WW1, etc.) listed in Table 1 are merely examples to help understanding, and those skilled in the art will easily understand that various learning color combination information (e.g., different types of bases, etc.) can be used to learn the reflectance estimation model.

[0071] Mixture Number BASE WW1 WK2 WG2 WR2 2 WR3 3 WY2 2 WV 1 88.4 7 7.68--1.84--2.01 290.26 0.78---0.84-8.13 .......................... 2299 89.41 1.74--1.93--6.93 2300 88.93 3.33 2.60 0.94--4.20-

[0072]

[0073] Additionally, examples of predicted reflectances for learning color combinations output in response to specific learning color combination information input to the reflectance estimation model are shown in Table 2 below.

[0074] Wavelength (nm) 400 410 420 430 440 450 460 470 480 490 Reflectance 46.8 967 1175 93 77 29 77 16 76 94 77 55 78 67 9.8 18 0.92 Wavelength (nm) 500 510 520 530 540 550 560 570 580 590 Reflectance 81.61 81.4181.6181.9382.0281.8681.5681.4581.8882.63Wavelength(nm)610620630640650660670680690700Reflectance82.6282.4382.2782.181.9481.6980.9580.9181.2181.51

[0075] In addition, a color combination reflectance loss can be generated based on the predicted reflectance of the learning color combination and the corresponding color combination GT (ground truth) reflectance. For reference, the color combination GT reflectance can be a reflectance obtained by colorimetrically measuring a specimen to which the corresponding color combination is actually applied.

[0076] Additionally, the color mixing reflectance loss can be backpropagated to update at least some of the parameters of the reflectance estimation model.

[0077] In addition, the accuracy of the reflectivity estimation model can be increased by repeatedly performing the above learning process.

[0078] Meanwhile, the reflectance comparison unit (140) can compare the target color measurement reflectance and the color combination prediction reflectance corresponding to the target color information.

[0079] And, the optimal color combination information determining unit (150) can determine specific color combination information corresponding to a specific color combination prediction reflectance that satisfies a threshold reflectance condition set based on a target color measurement reflectance among the color combination prediction reflectances as optimal color combination information.

[0080] For example, the optimal color combination information determining unit (150) can determine, as optimal color combination information, specific color combination information corresponding to a specific color combination prediction reflectance that has the smallest difference from the target color measurement reflectance among the color combination prediction reflectances.

[0081] At this time, the optimal color combination information determining unit (150) can determine the optimal color combination information based on the reflectance of each of the first wavelength to the mth wavelength.

[0082] For example, the optimal color combination information determining unit (150) can determine specific color combination information corresponding to a specific color combination prediction reflectance that satisfies a first threshold reflectance condition to an m-th threshold reflectance condition set based on a first target color measurement reflectance to an m-th target color measurement reflectance among color combination prediction reflectances as optimal color combination information.

[0083] For example, the optimal color combination information determining unit (150) determines whether each of the first to m-th color combination predicted reflectances corresponding to the first to m-th wavelengths of a specific color combination satisfies the first to m-th critical reflectance conditions, and if it is determined that at least some of the first to m-th critical reflectance conditions are satisfied, the specific color combination information corresponding to the specific color combination can be determined as optimal color combination information.

[0084] At this time, the critical reflectance condition may be a condition indicating that the color mixing prediction reflectance is within the critical reflectance range set based on the target color measurement reflectance, but is not limited thereto, and various modified examples may exist.

[0085] For example, the critical reflectance condition may be a condition indicating that the ratio of the color combination prediction reflectance and the target color measurement reflectance is within a critical range.

[0086] Meanwhile, when the color combination prediction reflectance does not satisfy the critical reflectance condition, the optimal color combination information determining unit (150) compares the predicted reflectance of the modified color combination information in which the concentration of at least some of the colors of the color combination is adjusted with the target color measurement reflectance, thereby determining the optimal color combination information.

[0087] For example, when the color combination prediction reflectance from the reflectance estimation model does not satisfy the threshold reflectance condition set based on the target color measurement reflectance, the optimal color combination information determining unit (150) estimates at least one corrected color combination prediction reflectance by referring to the correction concentration information and the characteristic information of each specific candidate color, compares the target color measurement reflectance and the corrected color combination prediction reflectance, and determines specific corrected color combination information corresponding to a specific corrected color combination prediction reflectance that satisfies the threshold reflectance condition set based on the target color measurement reflectance among the corrected color combination prediction reflectances as the optimal color combination information.

[0088] For reference, the above description describes that the optimal color combination information determination unit (150) estimates the predicted reflectance of the modified color combination and compares the predicted reflectance of the modified color combination with the target color measurement reflectance, but is not limited thereto, and the color combination information generation unit (120) described above may generate the corrected color combination information, the reflectance estimation unit (130) may estimate the predicted reflectance of the modified color combination, and the reflectance comparison unit (140) may compare the predicted reflectance of the modified color combination with the target color measurement reflectance.

[0089] At this time, the correction concentration information of a specific candidate color of the correction color combination can be generated by applying a concentration gradient matrix (∇w) calculated by referencing the target L value, target a value, target b value, L value change amount, a value change amount, and b value change amount in the Lab color space corresponding to at least one specific candidate color to the set concentration information.

[0090] For example, the concentration gradient matrix (∇w) can be produced through the following process.

[0091] First, a virtual tinting table based on the Kubelka-Munk theory can be created, as shown in Table 3. Note that L represents brightness information, a represents red-green information, and b represents yellow-blue information.

[0092] JH0008, 1% Tinting Table Illuminant Color Difference 1 Color Difference 2 Color Difference 3 Color Difference...N Color Difference D65△L * -5.47-3.43-0.27...△L * N △a * -2.504.29-0.18△a * N △b * -2.502.074.10△b * N F2△L * -5.73-3.15-0.03...△L * N △a * -1.893.28-0.29△a * N △b * -2.992.514.71△b * N A10△L * -5.93-2.81-0.03...△L * N △a * -2.984.580.46△a * N △b * -3.233.214.26△b * N

[0093] And, based on the virtual tinting table, the concentration gradient matrix (∇w) can be calculated according to Equations 3 and 4 below.

[0094] C0= [1, ..., 1] T

[0095] m, v = [0, ..., 0]T

[0096] C0, m, v ∈ R N

[0097] β1=0.9

[0098] β2=0.999

[0099] ε=1e -8

[0100] f=w T w

[0101]

[0102] [Formula 3]

[0103]

[0104]

[0105] [Formula 4]

[0106]

[0107]

[0108] [Formula 5]

[0109] for i in range(n iter )

[0110]

[0111]

[0112] m^ t =m t / (1-β1 niter+1 )

[0113] v^ t =v t / (1-β2 niter+1 )

[0114] C t =C t-1 -(α*m^ t ) / (sqrt(v^ t )* )

[0115]

[0116] And, by applying the concentration gradient matrix produced as above to the existing color combination information, the modified color combination information with modified concentration can be produced.

[0117] FIG. 2 is a flowchart schematically illustrating a method for determining color combinations according to one embodiment disclosed in this document.

[0118] Referring to FIG. 2, in step 101, target color information corresponding to the target color can be obtained.

[0119] And, in step 103, color combination information corresponding to a color combination including at least one specific candidate color among the first candidate color to the n-th candidate color can be generated.

[0120] And, in step 105, the color combination prediction reflectance can be estimated by referring to the color combination information.

[0121] And, in step 107, the target color measurement reflectance and the color combination prediction reflectance corresponding to the target color information can be compared.

[0122] And, in step 109, specific color combination information corresponding to a specific color combination prediction reflectance that satisfies a critical reflectance condition among the color combination prediction reflectances or specific modified color combination information corresponding to a specific modified color combination prediction reflectance among the modified color combination prediction reflectances can be determined as optimal color combination information.

[0123] FIGS. 3A to 3C schematically illustrate a UI screen of a program implementing a color mixing method according to one embodiment disclosed in this document.

[0124] First, referring to FIG. 3a, which illustrates an initial mixing UI screen, a user can create color mixing information corresponding to at least one color mixing including at least one specific candidate color among the first candidate color to the nth candidate color through the initial mixing UI.

[0125] And, referring to FIG. 3b and FIG. 3c showing the color mixing UI screen, if there is a significant difference between the reflectance of the color mixing generated through the initial mixing UI and the target reflectance, the user can determine optimal color mixing information by modifying the concentration of each specific candidate color through the modification mixing UI.

[0126] Table 4 shows the results of comparing a conventional color mixing method and a color mixing method according to an embodiment disclosed in this document.

[0127] Conventional color matching method (X-rite i-Match) Color matching method disclosed in this document Average initial color difference (DE) * )A Base1.810.74B Base2.031.2C Base2.471.28Total average2.201.07Average number of modificationsA Base1.2 times0.6 timesB Base2.1 times0.9 timesC Base2.6 times1.1Rotational average2.2 times0.8 times

[0128]

[0129] Referring to Table 4, it can be seen that, compared to conventional color mixing methods, the color difference in the initial color mixing is significantly reduced when using the color mixing method according to one embodiment disclosed in this document. Accordingly, the number of times the initial color mixing method needs to be modified is also reduced by less than half compared to conventional color mixing methods.

[0130] In addition, referring to FIGS. 4a and 4b, it is possible to confirm the difference between the reflectance and the target color reflectance according to the conventional color mixing method and the color mixing method according to one embodiment disclosed in the present document.

[0131] First, referring to Fig. 4a regarding the conventional color mixing method, it can be confirmed that there is a large error between the reflectance of the color mixing according to the conventional color mixing method (red graph) and the reflectance of the target color (blue graph).

[0132] On the other hand, referring to FIG. 4b regarding a color mixing method according to an embodiment disclosed in the present document, it can be confirmed that there is almost no error between the reflectance of the color mixing according to the color mixing method according to an embodiment disclosed in the present document (red graph) and the reflectance of the target color (blue graph).

[0133] Although all components constituting the embodiments disclosed in this document have been described as being combined or operating in combination as one, the embodiments disclosed in this document are not necessarily limited to such embodiments. That is, within the scope of the purpose of the embodiments disclosed in this document, all of the components may be selectively combined and operated one or more times.

[0134] In addition, terms such as "include," "comprise," or "have" described above, unless specifically stated otherwise, mean that the corresponding component can be included, and therefore should be interpreted to include other components rather than excluding other components. All terms, including technical or scientific terms, have the same meaning as commonly understood by a person of ordinary skill in the art to which the embodiments disclosed in this document belong, unless otherwise defined. Commonly used terms, such as terms defined in a dictionary, should be interpreted to be consistent with the contextual meaning of the relevant technology, and shall not be interpreted in an idealized or overly formal sense, unless explicitly defined in this document.

[0135] The above description is merely an example of the technical idea disclosed in this document, and those skilled in the art to which the embodiments disclosed in this document pertain may make various modifications and variations without departing from the essential characteristics of the embodiments disclosed in this document. Therefore, the embodiments disclosed in this document are not intended to limit the technical idea of ​​the embodiments disclosed in this document, but to explain it, and the scope of the technical idea disclosed in this document is not limited by these embodiments. The scope of protection of the technical idea disclosed in this document should be interpreted by the claims below, and all technical ideas within a scope equivalent thereto should be interpreted as being included in the scope of rights of this document.

Claims

1. A step of obtaining target color information corresponding to a target color; A step of generating color combination information corresponding to at least one color combination including at least one specific candidate color among the first candidate color to the n-th candidate color; A step of estimating at least one color combination prediction reflectance by referring to the above color combination information; A step of comparing the target color measurement reflectance corresponding to the target color information and the color combination prediction reflectance; A step of estimating at least one corrected color combination prediction reflectance by referring to the corrected concentration information and characteristic information of each of the specific candidate colors, when the color combination prediction reflectance does not satisfy the threshold reflectance condition set based on the target color measurement reflectance; A step of comparing the target color measurement reflectance and the corrected color combination prediction reflectance; and A step of determining, as the optimal color combination information, specific modified color combination information corresponding to a specific modified color combination prediction reflectance that satisfies the threshold reflectance condition set based on the target color measurement reflectance among the modified color combination prediction reflectances; A method for determining a color combination including:

2. In paragraph 1, In the step of estimating the color combination prediction reflectance, A color combination determination method characterized in that the color combination prediction reflectance is estimated by referring to the set concentration information and characteristic information of each of the specific candidate colors included in the color combination information.

3. In paragraph 2, The above characteristic information includes first characteristic information to m-th characteristic information corresponding to the first wavelength to m-th wavelength, The above target color measurement reflectance includes the first target color measurement reflectance to the m-th target color measurement reflectance corresponding to the first wavelength to the m-th wavelength, In the step of estimating the color combination prediction reflectance, By referring to the set concentration information of each of the above specific candidate colors and the first characteristic information to the m-th characteristic information, the first color combination prediction reflectance to the m-th color combination prediction reflectance are estimated as the color combination prediction reflectance, In the step of determining the above optimal color combination information, A color combination determination method characterized in that, among the color combination prediction reflectances, specific color combination information corresponding to a specific color combination prediction reflectance that satisfies a first threshold reflectance condition to an m-th threshold reflectance condition set based on the first target color measurement reflectance to the m-th target color measurement reflectance is determined as optimal color combination information.

4. In paragraph 1, In the step of estimating the color combination prediction reflectance, A color combination determination method characterized in that the color combination information including the set concentration information of each of the specific candidate colors is input into a reflectance estimation model, and the reflectance estimation model estimates the color combination prediction reflectance corresponding to the color combination information.

5. In paragraph 4, Before the step of estimating the color combination prediction reflectance, (1) A color combination determination method, characterized by further comprising the steps of: (1) a process of inputting learning color combination information into the reflectance estimation model to cause the reflectance estimation model to estimate learning color combination prediction reflectance; (2) a process of generating a color combination reflectance loss based on the learning color combination prediction reflectance and the corresponding color combination GT (ground truth) reflectance; and (3) a process of updating at least some of the parameters of the reflectance estimation model by backpropagating the color combination reflectance loss.

6. In paragraph 1, The above correction concentration information is, A color combination determination method characterized in that the concentration gradient matrix is ​​generated by applying the concentration gradient matrix, which is calculated by referencing the target L value, target a value, target b value, L value change amount, a value change amount, and b value change amount on the Lab color space corresponding to at least one specific candidate color, to the set concentration information.

7. A target color information acquisition unit that acquires target color information corresponding to a target color; A color combination information generation unit that generates color combination information corresponding to at least one color combination including at least one specific candidate color among the first candidate color to the nth candidate color; A reflectance estimation unit for estimating at least one color combination prediction reflectance by referring to the above color combination information; A reflectance comparison unit that compares the target color measurement reflectance corresponding to the target color information and the color combination prediction reflectance; and A color combination determination device comprising an optimal color combination information determination unit that estimates at least one corrected color combination prediction reflectance by referring to the correction concentration information and characteristic information of each of the specific candidate colors when the color combination prediction reflectance does not satisfy the threshold reflectance condition set based on the target color measurement reflectance, compares the target color measurement reflectance and the corrected color combination prediction reflectance, and determines, as the optimal color combination information, specific corrected color combination information corresponding to a specific corrected color combination prediction reflectance that satisfies the threshold reflectance condition set based on the target color measurement reflectance among the corrected color combination prediction reflectances.

8. In paragraph 7, The above reflectivity estimation unit, A color combination determination device characterized in that the color combination prediction reflectance is estimated by referring to the set concentration information and characteristic information of each of the specific candidate colors included in the color combination information.

9. In paragraph 8, The above characteristic information includes first characteristic information to m-th characteristic information corresponding to the first wavelength to m-th wavelength, The above target color measurement reflectance includes the first target color measurement reflectance to the m-th target color measurement reflectance corresponding to the first wavelength to the m-th wavelength, The above reflectivity estimation unit, By referring to the set concentration information of each of the above specific candidate colors and the first characteristic information to the m-th characteristic information, the first color combination prediction reflectance to the m-th color combination prediction reflectance are estimated as the color combination prediction reflectance, The above optimal color combination information determining unit is, A color combination determination device characterized in that, among the color combination prediction reflectances, specific color combination information corresponding to a specific color combination prediction reflectance that satisfies a first threshold reflectance condition to an m-th threshold reflectance condition set based on the first target color measurement reflectance to the m-th target color measurement reflectance is determined as optimal color combination information.

10. In paragraph 7, The above reflectivity estimation unit, A color combination determination device characterized in that the color combination information including the set concentration information of each of the specific candidate colors is input into a reflectance estimation model so that the reflectance estimation model estimates the color combination prediction reflectance corresponding to the color combination information.

11. In paragraph 10, The above reflectance estimation model is, (1) A color combination decision device characterized in that the following processes are performed: (1) a process of inputting learning color combination information into the reflectance estimation model to cause the reflectance estimation model to estimate learning color combination prediction reflectance, (2) a process of generating a color combination reflectance loss based on the learning color combination prediction reflectance and the corresponding color combination GT (ground truth) reflectance, and (3) a process of updating at least some of the parameters of the reflectance estimation model by backpropagating the color combination reflectance loss.

12. In paragraph 7, The above correction concentration information is, A color combination determination device characterized in that the color combination determination device is generated by applying a concentration gradient matrix calculated by referencing a target L value, a target a value, a target b value, a L value change amount, a a value change amount, and a b value change amount on a Lab color space corresponding to at least one specific candidate color to the set concentration information.

Images