Method and device for evaluating the color rendering properties of a painting illumination based on the spectrum of the light source

Abstract

The disclosure provides an evaluation method and device for painting illumination color rendering based on light source spectrum, which can be applied to the fields of cultural relic illumination and artificial intelligence technology. The method comprises the following steps: obtaining initial evaluation information corresponding to a plurality of paintings respectively obtained through evaluation experiments in a preset illumination environment; determining initial evaluation information meeting a first evaluation condition from the initial evaluation information; determining target evaluation information meeting a second evaluation condition from the initial evaluation information, wherein the target evaluation information represents the radiation power distribution information of the light source spectrum at different wavelengths in the preset illumination environment, and the second evaluation condition comprises at least one of a feature evaluation condition and a contribution degree evaluation condition; inputting the target evaluation information into an evaluation model to obtain an evaluation result corresponding to the light source color rendering. Through the method, the objectivity of the evaluation information and the data quality can be evaluated, and the applicability and accuracy of the light source color rendering evaluation method are improved.

Description

Technical Field

[0001] This disclosure relates to the fields of cultural relic lighting and artificial intelligence technology, specifically to a method and apparatus for evaluating the colorimetric properties of painting illumination based on the light source spectrum. Background Technology

[0002] Light source is a key factor in determining the display effect of traditional paintings. Among related technologies, the methods for evaluating the color rendering performance of light sources mainly include the Color Rendering Index, the Color Quality Scale, and the IES™-30 color rendering standard.

[0003] However, the evaluation of color rendering properties of painting light sources, using the color rendering index (CRI) and color quality index (CGI) methods, which are based on the CIE 1964 UVW and CIE LAB color spaces respectively, lacks consideration of the influence of the observation environment on human color perception. This results in a significant discrepancy between the perceived color of objects and the observer's subjective experience. While the IES TM-30 method, based on the CAM02 UCS uniform color space, does consider the influence of color vision psychology on color recognition, its applicability to traditional Chinese paintings (such as those in high-contrast lighting environments like exhibition halls or those with low overall color saturation) remains problematic, leading to a larger error in the evaluation results. Summary of the Invention

[0004] In view of the above problems, this disclosure provides a method, apparatus, device, medium and program product for evaluating the colorimetric properties of painting photography based on the light source spectrum.

[0005] According to a first aspect of this disclosure, a method for evaluating the color rendering properties of paintings based on the light source spectrum is provided, comprising: acquiring initial evaluation information corresponding to multiple paintings obtained through evaluation experiments in a preset lighting environment, wherein the initial evaluation information characterizes the evaluation results of multiple objects on multiple paintings; determining initial evaluation information that satisfies a first evaluation condition from the initial evaluation information, wherein the first evaluation condition includes at least one of a reliability evaluation condition and a correlation evaluation condition; determining target evaluation information that satisfies a second evaluation condition from the initial evaluation information, wherein the target evaluation information characterizes the radiant power distribution information of the light source spectrum at different wavelengths in the preset lighting environment, and the second evaluation condition includes at least one of a feature evaluation condition and a contribution evaluation condition; and inputting the target evaluation information into an evaluation model to obtain an evaluation result corresponding to the color rendering properties of the light source.

[0006] The second aspect of this disclosure provides an evaluation device for the color rendering properties of paintings based on the light source spectrum, comprising: an acquisition module for acquiring initial evaluation information corresponding to multiple paintings obtained through evaluation experiments in a preset lighting environment, wherein the initial evaluation information represents the evaluation results of multiple objects on multiple paintings; a determination module for determining initial evaluation information that meets a first evaluation condition from the initial evaluation information, wherein the first evaluation condition includes at least one of a reliability evaluation condition and a correlation evaluation condition; an information determination module for determining target evaluation information that meets a second evaluation condition from the initial evaluation information, wherein the target evaluation information represents the radiant power distribution information of the light source spectrum at different wavelengths in the preset lighting environment, and the second evaluation condition includes at least one of a feature evaluation condition and a contribution evaluation condition; and an input module for inputting the target evaluation information into an evaluation model to obtain an evaluation result corresponding to the color rendering properties of the light source.

[0007] A third aspect of this disclosure provides an electronic device comprising: one or more processors; and a memory for storing one or more computer programs, wherein the one or more processors execute the one or more computer programs to implement the steps of the method described above.

[0008] A fourth aspect of this disclosure also provides a computer-readable storage medium having a computer program or instructions stored thereon, which, when executed by a processor, implement the steps of the above-described method.

[0009] The fifth aspect of this disclosure also provides a computer program product, including a computer program or instructions that, when executed by a processor, implement the steps of the above-described method.

[0010] According to the methods, apparatus, devices, media, and program products for evaluating the color rendering properties of paintings based on light source spectra provided in this disclosure, targeted evaluation information that meets multi-level evaluation conditions is obtained by performing targeted evaluation processing on the information to be evaluated at different stages. Since the target information to be evaluated after evaluation processing is objective information on the radiant power distribution of the light source at different wavelengths in a preset lighting environment, it is compatible with the actual lighting environment of the painting and the overall color of the picture, avoiding the bias problems caused by traditional human eye color recognition, improving the objectivity and data quality of the target information to be evaluated, and further enhancing the applicability of the light source color rendering property evaluation method and the accuracy of the evaluation results. Attached Figure Description

[0011] The foregoing contents, as well as other objects, features, and advantages of this disclosure, will become clearer from the following description of embodiments with reference to the accompanying drawings, in which:

[0012] Figure 1The illustration schematically depicts an application scenario of a method, apparatus, device, medium, and program product for evaluating the colorimetric properties of painting illumination based on the light source spectrum according to embodiments of the present disclosure.

[0013] Figure 2 A flowchart illustrating a method for evaluating the colorimetric properties of painting illumination based on a light source spectrum according to an embodiment of the present disclosure is shown schematically.

[0014] Figure 3A The illustrations depict different color styles of paintings according to embodiments of the present disclosure.

[0015] Figure 3B This schematic diagram illustrates the relative spectral reflectance distribution at 11 locations on four paintings according to an embodiment of the present disclosure;

[0016] Figure 3C A schematic diagram of an evaluation experiment scenario according to an embodiment of the present disclosure is shown.

[0017] Figure 4 The schematic diagram illustrates the mean square error of the model parameters and a regression analysis diagram of the evaluation model according to an embodiment of the present disclosure;

[0018] Figure 5 This schematic diagram illustrates a structural block diagram of a painting illumination colorimetric evaluation apparatus based on a light source spectrum according to an embodiment of the present disclosure;

[0019] Figure 6 A block diagram schematically illustrates an electronic device suitable for implementing an evaluation method for the colorimetric properties of painting illumination based on a light source spectrum, according to an embodiment of the present disclosure. Detailed Implementation

[0020] The embodiments of the present disclosure will now be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the disclosure. In the following detailed description, numerous specific details are set forth to provide a thorough understanding of the embodiments of the present disclosure for ease of explanation. However, it will be apparent that one or more embodiments may be practiced without these specific details. Furthermore, descriptions of well-known structures and techniques are omitted in the following description to avoid unnecessarily obscuring the concepts of the present disclosure.

[0021] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit this disclosure. The terms “comprising,” “including,” etc., as used herein indicate the presence of the stated features, steps, operations, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, or components.

[0022] All terms used herein (including technical and scientific terms) have the meanings commonly understood by those skilled in the art, unless otherwise defined. It should be noted that the terms used herein are to be interpreted in a manner consistent with the context of this specification, and not in an idealized or overly rigid way.

[0023] When using expressions such as "at least one of A, B and C", they should generally be interpreted in accordance with the meaning that is commonly understood by those skilled in the art (e.g., "a system having at least one of A, B and C" should include, but is not limited to, a system having A alone, a system having B alone, a system having C alone, a system having A and B, a system having A and C, a system having B and C, and / or a system having A, B and C, etc.).

[0024] In the technical solution disclosed herein, the user information (including but not limited to user personal information, user image information, user device information, such as location information) and data (including but not limited to data used for analysis, stored data, and displayed data) involved are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, storage, use, processing, transmission, provision, disclosure, and application of related data all comply with relevant laws, regulations, and standards, necessary confidentiality measures have been taken, and they do not violate public order and good morals. Corresponding operation entry points are provided for users to choose to authorize or refuse.

[0025] In related technologies, the color rendering index (CRI) and color quality index (CGI) evaluation methods for assessing the color rendering properties of painting light sources are based on the CIE 1964 UVW and CIE LAB color spaces, respectively. These methods lack consideration for the influence of the observation environment on human eye color recognition, resulting in a significant discrepancy between the perceived color of objects and the observer's subjective experience. While the IESTM-30 method is based on the CAM02 UCS uniform color space and considers the influence of color vision psychological effects on color recognition, its applicability to traditional paintings (e.g., special lighting environments with high brightness contrast in exhibition halls and low overall color saturation) remains problematic, leading to a large error in the evaluation results.

[0026] In view of this, this disclosure obtains target evaluation information that meets multi-level evaluation conditions by performing targeted evaluation processing on the information to be evaluated at different stages. Since the target evaluation information after evaluation processing is objective information on the radiant power distribution of the light source at different wavelengths in the preset lighting environment, it is compatible with the actual lighting environment of the painting and the overall color of the picture, avoiding the deviation problem caused by traditional human eye color recognition, improving the objectivity and data quality of the target evaluation information, and further enhancing the applicability of the light source color rendering evaluation method and the accuracy of the evaluation results.

[0027] The embodiments of this disclosure provide a method for evaluating the color rendering properties of paintings based on the light source spectrum, comprising: acquiring initial evaluation information corresponding to multiple paintings obtained through evaluation experiments in a preset lighting environment, wherein the initial evaluation information represents the evaluation results of multiple objects on multiple paintings; determining initial evaluation information that meets a first evaluation condition from the initial evaluation information, wherein the first evaluation condition includes at least one of a reliability evaluation condition and a correlation evaluation condition; determining target evaluation information that meets a second evaluation condition from the initial evaluation information, wherein the target evaluation information represents the radiant power distribution information of the light source spectrum at different wavelengths in the preset lighting environment, and the second evaluation condition includes at least one of a feature evaluation condition and a contribution evaluation condition; and inputting the target evaluation information into an evaluation model to obtain an evaluation result corresponding to the color rendering properties of the light source.

[0028] Figure 1 The illustration schematically depicts an application scenario of a method, apparatus, device, medium, and program product for evaluating the colorimetric properties of painting illumination based on a light source spectrum, according to embodiments of the present disclosure.

[0029] like Figure 1 As shown, application scenario 100 according to this embodiment may include a first terminal device 101, a second terminal device 102, a third terminal device 103, a network 104, and a server 105. The network 104 serves as a medium for providing a communication link between the first terminal device 101, the second terminal device 102, the third terminal device 103, and the server 105. The network 104 may include various connection types, such as wired or wireless communication links, or fiber optic cables, etc.

[0030] Users can use the first terminal device 101, the second terminal device 102, and the third terminal device 103 to interact with the server 105 via the network 104 to receive or send messages, etc. Various communication client applications can be installed on the first terminal device 101, the second terminal device 102, and the third terminal device 103, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social media platform software, etc. (for example only).

[0031] The first terminal device 101, the second terminal device 102, and the third terminal device 103 can be various electronic devices with displays and support web browsing, including but not limited to smartphones, tablets, laptops, and desktop computers.

[0032] Server 105 can be a server that provides various services, such as a backend management server that supports websites browsed by users using the first terminal device 101, the second terminal device 102, and the third terminal device 103 (this is just an example). The backend management server can analyze and process data such as received user requests, and feed back the processing results (such as web pages, information, or data obtained or generated according to user requests) to the terminal devices.

[0033] It should be noted that the method for evaluating the colorimetric properties of painting based on light source spectrum provided in this embodiment can generally be executed by server 105. Correspondingly, the device for evaluating the colorimetric properties of painting based on light source spectrum provided in this embodiment can generally be located in server 105. The method for evaluating the colorimetric properties of painting based on light source spectrum provided in this embodiment can also be executed by a server or server cluster that is different from server 105 and capable of communicating with the first terminal device 101, the second terminal device 102, the third terminal device 103, and / or server 105. Correspondingly, the device for evaluating the colorimetric properties of painting based on light source spectrum provided in this embodiment can also be located in a server or server cluster that is different from server 105 and capable of communicating with the first terminal device 101, the second terminal device 102, the third terminal device 103, and / or server 105.

[0034] It should be understood that Figure 1 The number of terminal devices, networks, and servers shown is merely illustrative. Depending on implementation needs, any number of terminal devices, networks, and servers can be included.

[0035] The following will be based on Figure 1 The described scene, through Figures 2-4 The method for evaluating the colorimetric properties of painting illumination based on the light source spectrum of the disclosed embodiments is described in detail.

[0036] Figure 2 A flowchart illustrating a method for evaluating the colorimetric properties of a painting based on a light source spectrum, according to an embodiment of the present disclosure, is shown schematically.

[0037] like Figure 2 As shown, the method for evaluating the colorimetric properties of painting illumination based on the light source spectrum in this embodiment includes operations S210 to S240.

[0038] In operation S210, initial evaluation information corresponding to multiple paintings is obtained through evaluation experiments in a preset lighting environment. The initial evaluation information represents the evaluation results of multiple objects on multiple paintings.

[0039] In the embodiments of this disclosure, the preset lighting environment can be the lighting environment for the evaluation experiment determined according to actual conditions, and is determined through illuminance information, correlated color temperature information, fidelity information, and color gamut information of the painting surface. The evaluation experiment can be an experiment in which multiple subjects (observers) subjectively evaluate the color rendering of multiple Chinese paintings under the preset lighting environment, and obtain the evaluation results of multiple observers on multiple paintings. The multiple observers can be divided into multiple observation groups to evaluate multiple paintings in different lighting environments separately.

[0040] In operation S220, initial information to be evaluated that meets the first evaluation condition is determined from the initial evaluation information, wherein the first evaluation condition includes at least one of the reliability evaluation condition and the correlation evaluation condition.

[0041] In embodiments of this disclosure, the initial information to be evaluated can characterize the information obtained from the first evaluation process of the evaluation results between different observation groups and between different observers, satisfying the reliability evaluation criteria and the correlation evaluation criteria. The reliability evaluation criteria can be used to assess the consistency between the evaluation information between different observation groups and between the evaluation information between different observers. The correlation evaluation criteria can be used to determine whether there is a linear correlation between different paintings and the degree of correlation.

[0042] In operation S230, target information to be evaluated that meets the second evaluation condition is determined from the initial information to be evaluated. The target information to be evaluated characterizes the radiant power distribution information of the light source spectrum at different wavelengths in the preset lighting environment. The second evaluation condition includes at least one of the feature evaluation condition and the contribution evaluation condition.

[0043] In embodiments of this disclosure, feature evaluation conditions can be used to determine important features from multiple features for evaluating the color rendering of a light source, thereby obtaining feature evaluation results. Contribution evaluation conditions can be used to determine the radiant power distribution values ​​of the obtained important features at different wavelengths, which can also be referred to as contribution values.

[0044] For example, after obtaining the initial information to be evaluated, the initial information to be evaluated can be further evaluated using feature evaluation conditions and contribution evaluation conditions to obtain the feature evaluation results and contribution values ​​corresponding to the initial information to be evaluated. Thus, if the feature evaluation results and contribution values ​​are greater than or equal to the corresponding preset thresholds, the target information to be evaluated that meets the second evaluation conditions can be obtained.

[0045] In operation S240, the target information to be evaluated is input into the evaluation model to obtain the evaluation results corresponding to the color rendering properties of the light source.

[0046] In embodiments of this disclosure, the evaluation model can be a pre-trained model that meets a preset evaluation accuracy. The evaluation result can characterize the result obtained by using the evaluation model to evaluate the color rendering properties of different paintings under different light sources.

[0047] According to embodiments of this disclosure, by performing targeted evaluation processing on the information to be evaluated at different stages, target information to be evaluated that meets multi-level evaluation conditions is obtained. Since the target information to be evaluated after evaluation processing is objective information on the radiant power distribution of a light source at different wavelengths in a preset lighting environment, it is compatible with the actual lighting environment of the painting and the overall color of the picture, avoiding the bias problems caused by traditional human eye color recognition. This improves the objectivity and data quality of the target information to be evaluated, further enhancing the applicability of the light source color rendering evaluation method and the accuracy of the evaluation results.

[0048] According to the disclosed embodiments, the preset lighting environment is determined based on the light intensity information corresponding to the painting and the color information of the light source; the evaluation experiment includes: building the preset lighting environment based on the light intensity information and color information; multiple objects evaluate the color rendering of the painting under multiple working conditions through a random strategy to obtain initial evaluation information, wherein the multiple paintings have different color styles and the light source colors corresponding to the multiple working conditions are different.

[0049] In the embodiments of this disclosure, the light intensity information may include illuminance information of the experimental conditions in the evaluation experiment, and the color information may include correlated color temperature information, fidelity information, and color gamut information. The operating condition information may include a first operating condition corresponding to the first light source and a second operating condition corresponding to the second light source. The second light source may change according to the needs of different time periods of the experiment, while the first light source remains fixed throughout the entire experiment.

[0050] In the embodiments of this disclosure, based on the light protection requirement that the surface illuminance of a traditional painting needs to be less than or equal to 50 lux (lx), the surface illuminance of a traditional painting can be determined to be 50 lx in the evaluation experiment. Based on the recommended range of correlated color temperature in relevant lighting standards (such as CIE157:2004 and ANSI / IES RP-30-20), four gradients of 2650K, 3150K, 3650K, and 4150K can be selected as the correlated color temperature experimental variables. According to the Rf-Rg spatial distribution of TM-30-20, the target fidelity index Rf is selected as 65, 75, 85, and 95, and the target color gamut index Rg is selected as 80, 90, 100, 110, and 120. The 12 achievable combinations (Rf|Rg) are (65 | 80, 90, 100, 110, 120), (75 | 90, 100, 110), (85 | 90, 100, 110), and (95 | 100), forming a total of 48 experimental conditions.

[0051] For the four correlated color temperatures mentioned above, a light source whose chromaticity coordinates are as close as possible to the blackbody radiation trajectory can be selected as the experimental standard light source based on the chromaticity coordinate table of the blackbody locus isotherms. The above experimental conditions are then simulated using a channel-spectrum adjustable simulation light box that meets the relevant standard requirements. It is understood that the type and size of the simulation light box, as well as the illumination parameters of the experimental standard light source, can be determined based on actual conditions and are not limited here.

[0052] Figure 3A The illustrations depict different color styles of paintings according to embodiments of the present disclosure.

[0053] like Figure 3A As shown, different types of paintings can be categorized as follows: Qilian Mountain foothills paintings dominated by warm colors ( Figure 3A-1 Landscape paintings dominated by cool colors ( Figure 3A-2 ), Peony painting with mixed warm and cool colors ( Figure 3A -3) and the "Dream Brush Blossoms" painting, which is mainly in ink ( Figure 3A-4 ).

[0054] Based on the color style of traditional paintings, this disclosure selects four paintings as experimental samples, as shown in Table 1A below. Each high-definition inkjet-printed simulated painting is placed in the first display device corresponding to the first working condition and the second display device corresponding to the second working condition. Table 1A schematically illustrates painting-related information according to embodiments of this disclosure.

[0055] Table 1A

[0056]

[0057] Figure 3B The diagram illustrates the relative spectral reflectance distribution at 11 locations on four paintings according to an embodiment of the present disclosure.

[0058] like Figure 3B As shown, the spectral reflectance function of the main colors in each painting can be measured using a spectral color luminance meter under the International Commission on Illumination Standard A light source. By comparing the spectral reflectance function of the color points with the spectral reflectance function of the Standard A light source, the spectral reflectance of 11 color points can be obtained.

[0059] In the embodiments disclosed herein, based on the relevant standards for museum exhibition halls and artifact display rooms, a painting exhibition hall reflecting the characteristics of a real museum lighting environment is constructed at a 1:1 scale in an optical laboratory that meets the preset standard requirements. This serves as the preset lighting environment for the experiment. The experimental space dimensions are 7.2m x 4.65m x 3.6m (length x width x height), with a reflectivity of 0.8 for the interior walls, 0.2 for the floor, and 0.2 for the ceiling. Six display devices can be arranged in the optical laboratory. Display devices 1 and 2 are used for evaluation experiments and are arranged side by side. The lighting device (lightbox) is positioned directly above the painting display case, and the light from the experimental light source is perpendicular to the painting surface. A black blackout cloth is laid in between to prevent the influence of the other light source. Display devices 3 to 6 are used for background creation. The surface illuminance of the painting can be set to 50 lx, the correlated color temperature to 3300 K, and the average illuminance of the laboratory floor to 10 lx. The above lighting parameters remain constant during the experiment.

[0060] Figure 3C A schematic diagram of an evaluation experiment scenario according to an embodiment of the present disclosure is shown.

[0061] like Figure 3C As shown, the observer can observe from a fixed station location to maintain a fixed perspective. Two identical painting samples are placed flat in the display device, and the light source is not visible to the observer during the experiment. The evaluation experiment can use a continuous scale to assess the color rendering of four traditional paintings under different conditions. Continuous scales have advantages in studies with individual differences, helping to improve the accuracy and generalization ability of experimental results. The observer's age, gender, visual acuity, and experimental time can be determined according to experimental needs. In the embodiments of this disclosure, color rendering can represent the degree of similarity between the overall color of the painting under the target light source and the overall color of the painting under the reference light source.

[0062] As we understand it, the above text has already evaluated different paintings through an evaluation experiment to obtain initial evaluation information. The following will explain how to process the initial evaluation information to obtain the initial information to be evaluated.

[0063] According to the disclosed embodiments, the initial evaluation information includes internal evaluation information and inter-observer evaluation information based on the different objects; determining the initial evaluation information that meets the first evaluation condition from the initial evaluation information includes: evaluating the internal evaluation information using a reliability evaluation strategy to obtain a first evaluation result, and evaluating the inter-observer evaluation information using a reliability evaluation strategy to obtain a second evaluation result; if the first evaluation result and the second evaluation result are greater than or equal to a preset evaluation threshold, the initial evaluation information is obtained.

[0064] In the embodiments of this disclosure, the preset evaluation threshold is, for example, 0.7 to 0.9. It is understood that the preset evaluation threshold can be determined according to actual needs and is not specifically limited. After obtaining the initial evaluation information, the initial evaluation information can be classified based on different observers, including evaluation information between different observers (internal evaluation information) and evaluation information between different observation groups (inter-observer evaluation information). A reliability evaluation strategy is then used to evaluate the internal evaluation information and the inter-observer evaluation information respectively, obtaining their respective evaluation results. When both the internal evaluation information and the inter-observer evaluation information are greater than or equal to the preset evaluation threshold, the initial information to be evaluated is obtained.

[0065] For example, the process of evaluating observer internal evaluation information using a reliability assessment strategy may include: determining the sum of all observers' evaluation information for the i-th painting and the variance of the sum, and obtaining the average of all observers' total scores; thereby obtaining the variance of the total score for each painting based on the number of observers, the average total score, and the sum of evaluation information for the i-th painting; after obtaining the variances of the total scores for multiple paintings, calculating the covariance between each painting and other paintings, and based on this, obtaining the first evaluation result based on the variance of each painting and the variance of the total score.

[0066] Understandably, the second evaluation result can also be obtained through the same or similar methods described above. After obtaining the first and second evaluation results, the first and second evaluation results can be plotted between 0.7 and 0.9 to determine the initial information to be evaluated that meets the information consistency requirement. For example, by using a reliability assessment strategy to evaluate the data consistency within the observer group and between different observation groups, if the average reliability coefficient α is greater than 0.95, it can be concluded that the initial evaluation information is reliable and can be used for subsequent analysis and evaluation.

[0067] According to embodiments of this disclosure, by performing reliability assessment on the initial evaluation information, multiple paintings with high internal correlation and consistency can be obtained, thereby improving the accuracy and reliability of the information to be evaluated and providing reasonable data support for the subsequent evaluation results of the color rendering properties of the light source.

[0068] As we have already explained above how to determine the initial information to be evaluated, we will now explain that further below.

[0069] According to the disclosed embodiments, determining the initial evaluation information that meets the first evaluation condition from the initial evaluation information further includes: evaluating the average value of the initial evaluation information using a correlation evaluation strategy to obtain multiple correlation values ​​between multiple paintings; and obtaining the initial evaluation information when the multiple correlation values ​​are greater than or equal to a preset correlation threshold.

[0070] In the embodiments of this disclosure, the correlation evaluation strategy can be used to determine whether there is a linear correlation between multiple paintings and the correlation value between the multiple paintings. The preset correlation threshold can be determined according to the actual situation, and is not limited here.

[0071] For example, the process of evaluating initial evaluation information using a correlation assessment strategy may include: randomly identifying paintings with various color characteristics from the initial evaluation information; determining the mean, standard deviation, and covariance of multiple paintings with different color characteristics; and then calculating the correlation values ​​between different variables of the paintings based on the covariance. The evaluation reveals that the average correlation coefficient of the ratings for multiple painting types is 0.94, indicating a significant positive correlation. The statistical significance of the correlation coefficient can be denoted as p, where p < 0.01, indicating a low degree of inconsistency between the observed data and the null hypothesis (i.e., no correlation). Specifically, Table 1B schematically illustrates the correlation values ​​between different types of paintings.

[0072] Table 1B

[0073]

[0074] It is understandable that by calculating the correlation values ​​between different types of paintings, it can be determined that the different color characteristics of the paintings used in this embodiment have little impact on the color rendering evaluation. Therefore, for ease of analysis, the arithmetic mean of the evaluation values ​​of the above four painting types under the same experimental conditions can be used to represent the color rendering evaluation values ​​of different paintings.

[0075] According to the disclosed embodiments, determining target information to be evaluated that meets the second evaluation condition from initial information to be evaluated includes: linearly combining the initial information to be evaluated to obtain intermediate information to be evaluated; determining feature evaluation information and contribution information corresponding to the intermediate information to be evaluated, wherein the feature evaluation information includes feature weights and feature vectors, and the contribution information represents the information contribution corresponding to the feature vectors; and determining the target information to be evaluated when the feature evaluation information meets the feature evaluation condition and when the contribution information meets the contribution evaluation condition.

[0076] In embodiments of this disclosure, the intermediate information to be evaluated can characterize the covariance matrix obtained after linearly combining the initial information to be evaluated, which is used to represent the linear relationship between different wavelengths. Feature weights can characterize the importance of features, and feature vectors can characterize the directional information of features.

[0077] In one feasible embodiment, the method for determining the target information to be evaluated may include: after calculating the covariance matrix of the initial information to be evaluated, performing eigenvalue decomposition on the covariance matrix to obtain feature weights and eigenvectors; then, according to the magnitude of the feature weights, selecting the feature weights greater than 1 as principal components in descending order of value; and then projecting the original light source spectral power distribution (SPD) values ​​onto the selected principal component directions to obtain the score of each principal component (representing the position of each light source in the principal component space), thus obtaining the target information to be evaluated.

[0078] It is understandable that this disclosure takes into account the shortcomings of traditional technologies, such as large data volume, excessive resource consumption, and low computational efficiency when performing calculations directly. By processing the initial information to be evaluated, target information to be evaluated that meets the second evaluation condition is obtained. By performing data dimensionality reduction, feature extraction, and data visualization on the initial information to be evaluated, the computational efficiency of the data can be improved, the interpretability of the data can be enhanced, a high-quality data foundation can be provided for subsequent data analysis and processing, and the data structure can be simplified while saving computational resources.

[0079] According to the disclosed embodiments, when the feature evaluation information meets the feature evaluation conditions and the contribution information meets the contribution evaluation conditions, the target information to be evaluated is determined, including: sorting the feature weights according to their numerical values ​​to obtain sorted feature weights; sorting the feature vectors based on the sorting information of the sorted feature weights to obtain sorted feature vectors; determining multiple feature vectors corresponding to sorted feature weights that are greater than or equal to a weight threshold from the sorted feature vectors as target feature vectors; and constructing a feature matrix when the sum of the information contributions of the target feature vectors is greater than or equal to the contribution threshold to obtain the target information to be evaluated.

[0080] In embodiments of this disclosure, the ranking feature weight can characterize the weight of different feature values ​​after being ranked based on their importance.

[0081] For example, the feature weights can be sorted in descending order, and the corresponding feature vectors can be arranged in the same order. The feature vectors corresponding to the k largest feature values ​​can be selected as the detoxification feature vectors. The selected k feature vectors can then be used to construct a feature matrix P with dimensions p*k. The feature matrix P can be used to project the original data onto a new feature space. The meaning of each principal component can then be determined by analyzing the coefficients of the feature vectors to determine the contribution of each principal component to the original features.

[0082] For example, using a step size of 5 nm, the SPD values ​​at different wavelengths within the 380 nm-780 nm range under different experimental conditions can be calculated, totaling 81 values. Principal component analysis can then be used to obtain the five principal components of the SPD with eigenvalues ​​greater than 1 (target information to be evaluated), which can be denoted as X. n (n=1~5), the contribution rates of these 5 principal component information to the variance of SPD information are 47.4%, 27.8%, 10.9%, 7.0% and 2.8% respectively, with a cumulative variance contribution rate of 95.9%. This indicates that these 5 principal component information can characterize 95.9% of the information of the light source.

[0083] Principal component X n It can be the sum of the products of the SPD's data matrix and its eigenvector matrix. Specifically, it is shown in formula (1):

[0084] (1);

[0085] In this matrix, each column represents a principal component, and each element in the column represents a contribution coefficient to the original variable. `anp` (n=1~5, p=1~81) represents the p-th contribution coefficient in the eigenvector matrix of the n-th principal component. There are a total of 5 principal components, and the eigenvector matrix of each principal component includes 81 contribution coefficients; λ 380~780 It can represent the SPD value of the light source at various wavelengths. Taking 5nm as a step size as an example, there are a total of 81 SPD values ​​at various wavelengths.

[0086] Based on the above formula (1), the principal component values ​​[X] for 48 experimental conditions can be calculated. 48 , where [X] 48 =[X1, X2, X3, X4, X5] 48 Each light source spectrum can be represented by 5 principal component information values, as shown in Table 2 below (including Table 2-1, Table 2-2 and Table 2-3). Table 2 schematically shows the principal component values ​​for 48 operating conditions.

[0087] Table 2-1

[0088]

[0089] Table 2-2

[0090]

[0091] Table 2-3

[0092]

[0093] As we have already explained above, the process of obtaining the target information to be evaluated will now be explained below.

[0094] According to the disclosed embodiments, the evaluation model is determined by the following operations: obtaining initial evaluation information of samples corresponding to multiple sample paintings obtained through evaluation experiments in a preset lighting environment, wherein the initial evaluation information of samples represents the evaluation results of multiple sample objects on multiple sample paintings; normalizing the initial evaluation information of samples to obtain sample evaluation information; constructing an initial evaluation model based on the sample evaluation information and initial parameters, wherein the initial parameters include multiple weight parameters and multiple update parameters; training the initial evaluation model using the training information and validation information in the sample evaluation information to obtain the evaluation model.

[0095] In the embodiments of this disclosure, the method for obtaining the initial evaluation information of the samples is the same as the method for obtaining the initial evaluation information, and will not be described in detail here. After obtaining the principal component information of 5 samples, the principal component information of the samples can be normalized by a normalization method (e.g., min-max normalization) to obtain the minimum and maximum values ​​of the principal component information of the samples. Then, the normalized values ​​are used to replace the original data to generate a new data table and obtain the sample evaluation information.

[0096] After normalizing the five principal component values ​​(denoted as X1, X2, X3, X4, X5) for 48 operating conditions, an initial evaluation model can be constructed. Taking a neural network model as an example, the initial evaluation model can include an input layer, a hidden layer, and an output layer.

[0097] For example, the data input in the input layer can be denoted as x. i (i=1~5), representing the 5 normalized principal component values; x can be... i (i=1~5) are processed through the hidden layer to obtain N. j (j=1~8), the first model parameter in the hidden layer may include: the first weight value parameter ω ij and the first update parameter b 1j The first weight parameter ω ij It can characterize the input parameter x i With hidden layer neurons N j Connection strength; first update parameter b 1j It can characterize the hidden layer neurons N j The bias; and then through the output layer and the second model parameters (the second weight value ω) j The output of the hidden layer is processed by the second update parameter b2) to obtain the color rendering prediction value, as shown in formula (2):

[0098] (2);

[0099] Among them, H j The output parameters of multiple hidden layers can be represented, where j represents the number of hidden layers, and w represents the number of hidden layers. j b1 can represent the second weight parameter of the output layer, and b2 can represent the second update parameter of the output layer, as shown in formula (3).

[0100] (3);

[0101] Where, x i The input can be represented by i, which represents the amount of input data, and w. ij The first weight parameter, b, can represent the hidden layer. 1j The first update parameter of the hidden layer can be used.

[0102] From formulas (2) and (3), it can be seen that the initial evaluation model for calculating color rendering properties can be as shown in formula (4):

[0103] (4);

[0104] When using formula (4) to calculate the color rendering score, the five principal component values ​​of the light source can first be normalized to x. i (i=1~5); thus x i Substituting into formula (4), we obtain y and its inverse normalized color rendering value. Therefore, to obtain the color rendering value of the light source x... i The color rendering index y under the influence can be calculated using ω in formula (4). ij b 1j ω j The model parameters for b2 are determined.

[0105] According to the disclosed embodiments, an initial evaluation model is trained using training information and validation information from the sample information to be evaluated, and an evaluation model is obtained. This includes: repeatedly using the training information to train the initial evaluation model to obtain an intermediate evaluation model; and determining the target parameters based on the intermediate evaluation results and validation information output by the intermediate evaluation model to obtain the evaluation model.

[0106] In the embodiments of this disclosure, an initial evaluation model can be trained using sample information to be evaluated, and the optimized and updated target parameters ω' can be obtained. ij b' 1j ,ω' j b'2. The sample information to be evaluated can be obtained from the input parameter matrix [X]. 48 and the output parameter matrix [y] 48 Composition, in which [X] 48=[ X1, X2, X3, X4, X5] 48 , [y] 48 The normalized values ​​of the color rendering evaluations from 34 subjects under 48 experimental scenarios were used as the training set (70%), validation set (15%), and test set (15%) for the initial evaluation model. The training set served as the dataset used for training and learning the initial evaluation model; the validation set was used to test the model's performance, allowing the model to adjust its parameters and hyperparameters during training to avoid overfitting or underfitting; the test set, which did not overlap with the training and validation sets, evaluated the model's performance on unseen data, thus determining whether the trained model's evaluation results met the accuracy requirements.

[0107] To avoid errors caused by random selection, a random function (such as a random number generation method based on the Mason twitch algorithm or a shuffle function) can be used to randomly perturb the sampling order of each dataset, reducing the risk that the training order will affect the training results. The model uses mean squared error (MSE) as the algorithm for optimizing the nonlinear least squares problem to train the network. The regression coefficients of the entire dataset can be selected as the evaluation metric for the network's prediction accuracy.

[0108] According to the disclosed embodiments, the target parameters are determined based on the intermediate evaluation results and verification information output by the intermediate evaluation model to obtain the evaluation model, including: determining the index result using the intermediate evaluation results, verification information and average value, wherein the average value is obtained based on the intermediate evaluation results and verification information; obtaining the target parameter when the index result is greater than or equal to a preset index threshold; updating the intermediate evaluation model using the target parameter to obtain the evaluation model.

[0109] In the embodiments of this disclosure, the index result can characterize the regression coefficient between the model's predicted value and the target value, denoted as R. The preset index threshold (e.g., 0.8) can be determined according to the actual situation, and is not specifically limited here.

[0110] Figure 4 The diagram illustrates the mean square error of the model parameters and a regression analysis of the evaluation model according to an embodiment of the present disclosure.

[0111] like Figure 4 As shown in Figure (4a), the initial evaluation model is trained using the training and validation sets, and then tested using the test set. It can be seen that the model parameters achieve optimal evaluation performance in the third iteration. Figure 4As shown in Figure (4b), the R-value between the model's predicted value and the target value is 0.83 (R>0.8), indicating that the model has high prediction accuracy. The Y=T line represents the ideal situation where the evaluation result is exactly equal to the target value. The specific parameters of the model are shown in Table 3 below.

[0112] Table 3

[0113]

[0114] The target parameters ω' obtained during training can be... ij b' 1j ,ω' j Substituting b'2 into the above formula (4), we can obtain the matrix model for calculating the color rendering properties of traditional painting lighting, as shown in the following formula (5):

[0115] (5);

[0116] Where y can represent the color rendering prediction value, and X1, X2, X3, X4, and X5 can represent the values ​​of the five principal components, respectively.

[0117] In one feasible embodiment, when evaluating the color rendering index (CRI) of a light source using an evaluation model, the five principal component values ​​X1, X2, X3, X4, and X5 of the light source can be calculated according to formula (1) and the eigenvector matrix in Table 4. The normalized parameters X1, X2, X3, X4, and X5 of these five principal component values ​​are then substituted into formula (5) to obtain the normalized CRI prediction value. Furthermore, y is inversely normalized to obtain the CRI prediction value. By comparing with Table 1A, the CRI level corresponding to the CRI prediction value can be obtained. Table 4 (including Tables 4-1 and 4-2) schematically shows the eigenvector matrix of the principal components according to an embodiment of this disclosure.

[0118] Table 4-1

[0119]

[0120] Table 4-2

[0121]

[0122] In the embodiments of this disclosure, to further verify the accuracy of the model, after calculating the color rendering evaluation results for the above 48 working conditions, a comparative analysis can be performed with the initial evaluation information obtained from the experiment to determine the accuracy of the evaluation model in calculating the color rendering of traditional museum paintings based on the light source spectrum. The accuracy can be the percentage of correct predictions for a given dataset. Table 5 shows the number of model evaluation results that match the initial evaluation information under the three color rendering levels. It can be seen that in 48 working conditions, the model evaluation results for 41 working conditions match the initial evaluation information, that is, the accuracy of the color rendering level of traditional paintings predicted by the evaluation model is 85.4%. Table 5 schematically shows examples of the number of model evaluation results that match the initial evaluation information for the working conditions in embodiment 48 of this disclosure.

[0123] Table 5

[0124]

[0125] Based on the above-described method for evaluating the colorimetric properties of paintings based on the light source spectrum, this disclosure also provides an apparatus for evaluating the colorimetric properties of paintings based on the light source spectrum. The following will be combined with... Figure 5 The device is described in detail.

[0126] Figure 5 A schematic block diagram of a painting illumination colorimetric evaluation apparatus based on a light source spectrum according to an embodiment of the present disclosure is shown.

[0127] like Figure 5 As shown, the painting illumination colorimetric evaluation device based on the light source spectrum of this embodiment includes an acquisition module 510, a determination module 520, an information determination module 530, and an input module 540.

[0128] The acquisition module 510 is used to acquire initial evaluation information corresponding to multiple paintings obtained through evaluation experiments in a preset lighting environment. The initial evaluation information represents the evaluation results of multiple objects on multiple paintings. In one embodiment, the acquisition module 510 can be used to perform the operation S210 described above, which will not be repeated here.

[0129] The determining module 520 is used to determine the initial information to be evaluated that meets the first evaluation condition from the initial evaluation information, wherein the first evaluation condition includes at least one of a reliability evaluation condition and a correlation evaluation condition. In one embodiment, the determining module 520 can be used to perform the operation S220 described above, which will not be repeated here.

[0130] The information determination module 530 is used to determine target information to be evaluated that meets the second evaluation condition from the initial information to be evaluated. The target information to be evaluated characterizes the radiant power distribution information of the light source spectrum at different wavelengths in a preset lighting environment. The second evaluation condition includes at least one of a feature evaluation condition and a contribution evaluation condition. In one embodiment, the information determination module 530 can be used to perform the operation S230 described above, which will not be repeated here.

[0131] The input module 540 is used to input the target information to be evaluated into the evaluation model to obtain the evaluation result corresponding to the color rendering properties of the light source. In one embodiment, the input module 540 can be used to perform the operation S240 described above, which will not be repeated here.

[0132] According to embodiments of this disclosure, the acquisition module 510, determination module 520, information determination module 530, and input module 540 in the painting color rendering evaluation device based on light source spectrum perform targeted evaluation processing on the information to be evaluated at different stages to obtain target information to be evaluated that meets multi-level evaluation conditions. Since the target information to be evaluated after evaluation processing is objective information on the radiant power distribution of the light source at different wavelengths in a preset lighting environment, it is compatible with the actual lighting environment of the painting and the overall color of the picture, avoiding the bias problems caused by traditional human eye color recognition, improving the objectivity and data quality of the target information to be evaluated, and further enhancing the applicability of the light source color rendering evaluation method and the accuracy of the evaluation results.

[0133] According to embodiments of this disclosure, the initial evaluation information includes intra-observer evaluation information and inter-observer evaluation information based on the different objects; the determining module 520 includes an evaluation result obtaining submodule and an evaluation information obtaining submodule. The evaluation result obtaining submodule is used to evaluate the intra-observer evaluation information using a reliability evaluation strategy to obtain a first evaluation result, and to evaluate the inter-observer evaluation information using a reliability evaluation strategy to obtain a second evaluation result; the evaluation information obtaining submodule is used to obtain initial information to be evaluated if the first evaluation result and the second evaluation result are greater than or equal to a preset evaluation threshold.

[0134] According to embodiments of this disclosure, the determining module 520 further includes: an average value evaluation submodule and an initial information to be evaluated acquisition submodule. The average value evaluation submodule is used to evaluate the average value of the initial evaluation information using a correlation evaluation strategy to obtain multiple correlation values ​​between multiple paintings; the initial information to be evaluated acquisition submodule is used to obtain the initial information to be evaluated when multiple correlation values ​​are greater than or equal to a preset correlation threshold.

[0135] According to embodiments of this disclosure, the information determination module 530 includes: a combination submodule, an information determination submodule, and a target information to be evaluated determination submodule. The combination submodule is used to linearly combine the initial information to be evaluated to obtain intermediate information to be evaluated. The information determination submodule is used to determine the feature evaluation information and contribution information corresponding to the intermediate information to be evaluated, wherein the feature evaluation information includes feature weights and feature vectors, and the contribution information represents the information contribution corresponding to the feature vectors. The target information to be evaluated determination submodule is used to determine the target information to be evaluated when the feature evaluation information meets the feature evaluation conditions and when the contribution information meets the contribution evaluation conditions.

[0136] According to embodiments of this disclosure, the target information to be evaluated determination submodule includes: a sorting unit, a feature vector sorting unit, a feature vector determination unit, and a matrix construction unit. The sorting unit sorts feature weights by numerical value to obtain sorted feature weights; the feature vector sorting unit sorts feature vectors based on the sorting information of the sorted feature weights to obtain sorted feature vectors; the feature vector determination unit determines multiple feature vectors from the sorted feature vectors that correspond to sorted feature weights greater than or equal to a weight threshold, as target feature vectors; and the matrix construction unit constructs a feature matrix when the sum of the information contributions of the target feature vectors is greater than or equal to a contribution threshold, thereby obtaining the target information to be evaluated.

[0137] According to embodiments of this disclosure, the preset lighting environment is determined based on the light intensity information corresponding to the painting and the color information of the light source; the evaluation experiment includes: building the preset lighting environment based on the light intensity information and color information; multiple objects evaluate the color rendering of the painting under multiple working conditions through a random strategy to obtain initial evaluation information, wherein the multiple paintings have different color styles and the light source colors corresponding to the multiple working conditions are different.

[0138] According to embodiments of this disclosure, the evaluation model is determined through the following operations: obtaining initial evaluation information of samples corresponding to multiple sample paintings obtained through evaluation experiments in a preset lighting environment, wherein the initial evaluation information of samples represents the evaluation results of multiple sample objects on multiple sample paintings; normalizing the initial evaluation information of samples to obtain sample evaluation information; constructing an initial evaluation model based on the sample evaluation information and initial parameters, wherein the initial parameters include multiple weight parameters and multiple update parameters; training the initial evaluation model using training information and validation information in the sample evaluation information to obtain the evaluation model.

[0139] According to embodiments of this disclosure, an initial evaluation model is trained using training information and validation information from the sample information to be evaluated, and an evaluation model is obtained. This includes: repeatedly using the training information to train the initial evaluation model to obtain an intermediate evaluation model; and determining target parameters based on the intermediate evaluation results and validation information output by the intermediate evaluation model to obtain the evaluation model.

[0140] According to embodiments of this disclosure, determining target parameters based on intermediate evaluation results and verification information output by an intermediate evaluation model to obtain an evaluation model includes: determining index results using intermediate evaluation results, verification information, and average values, wherein the average value is obtained based on intermediate evaluation results and verification information; obtaining target parameters when the index results are greater than or equal to a preset index threshold; updating the intermediate evaluation model using the target parameters to obtain the evaluation model.

[0141] According to embodiments of this disclosure, any plurality of modules among the acquisition module 510, determination module 520, information determination module 530, and input module 540 may be combined into one module, or any one of these modules may be split into multiple modules. Alternatively, at least part of the functionality of one or more of these modules may be combined with at least part of the functionality of other modules and implemented in one module. According to embodiments of this disclosure, at least one of the acquisition module 510, determination module 520, information determination module 530, and input module 540 may be at least partially implemented as hardware circuitry, such as a field-programmable gate array (FPGA), a programmable logic array (PLA), a system-on-a-chip, a system-on-a-substrate, a system-on-package, an application-specific integrated circuit (ASIC), or implemented in hardware or firmware by any other reasonable means of integrating or packaging circuitry, or implemented in any one of software, hardware, and firmware methods, or in a suitable combination of any of these methods. Alternatively, at least one of the acquisition module 510, determination module 520, information determination module 530, and input module 540 may be implemented at least partially as a computer program module, which can perform corresponding functions when the computer program module is run.

[0142] Figure 6 A block diagram schematically illustrates an electronic device suitable for implementing an evaluation method for the colorimetric properties of painting illumination based on a light source spectrum, according to an embodiment of the present disclosure.

[0143] like Figure 6As shown, an electronic device according to an embodiment of this disclosure includes a processor 601, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage portion 608 into a random access memory (RAM) 603. The processor 601 may include, for example, a general-purpose microprocessor (e.g., a CPU), an instruction set processor and / or an associated chipset and / or a special-purpose microprocessor (e.g., an application-specific integrated circuit (ASIC)), etc. The processor 601 may also include onboard memory for caching purposes. The processor 601 may include a single processing unit or multiple processing units for performing different actions of the method flow according to an embodiment of this disclosure.

[0144] RAM 603 stores various programs and data required for the operation of the electronic device. Processor 601, ROM 602, and RAM 603 are interconnected via bus 604. Processor 601 performs various operations of the method flow according to embodiments of the present disclosure by executing programs in ROM 602 and / or RAM 603. It should be noted that the programs may also be stored in one or more memories other than ROM 602 and RAM 603. Processor 601 may also perform various operations of the method flow according to embodiments of the present disclosure by executing programs stored in said one or more memories.

[0145] According to embodiments of this disclosure, the electronic device may further include an input / output (I / O) interface 605, which is also connected to a bus 604. The electronic device may also include one or more of the following components connected to the input / output (I / O) interface 605: an input section 606 including a keyboard, mouse, etc.; an output section 607 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 608 including a hard disk, etc.; and a communication section 609 including a network interface card such as a LAN card, modem, etc. The communication section 609 performs communication processing via a network such as the Internet. A drive 610 is also connected to the input / output (I / O) interface 605 as needed. A removable medium 611, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on the drive 610 as needed so that computer programs read from it can be installed into the storage section 608 as needed.

[0146] This disclosure also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments; or it may exist independently and not assembled into the device / apparatus / system. The computer-readable storage medium carries one or more programs that, when executed, implement the method according to the embodiments of this disclosure.

[0147] According to embodiments of this disclosure, the computer-readable storage medium may be a non-volatile computer-readable storage medium, such as including, but not limited to: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this disclosure, the computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. For example, according to embodiments of this disclosure, the computer-readable storage medium may include ROM 602 and / or RAM 603 and / or one or more memories other than ROM 602 and RAM 603 described above.

[0148] Embodiments of this disclosure also include a computer program product comprising a computer program containing program code for performing the methods shown in the flowchart. When the computer program product is run on a computer system, the program code enables the computer system to implement the method for evaluating the colorimetric properties of painting based on the spectral light source provided in embodiments of this disclosure.

[0149] When the computer program is executed by the processor 601, it performs the functions defined in the system / apparatus of this disclosure embodiments. According to embodiments of this disclosure, the systems, apparatuses, modules, units, etc., described above can be implemented by computer program modules.

[0150] In one embodiment, the computer program may rely on a tangible storage medium such as an optical storage device or a magnetic storage device. In another embodiment, the computer program may also be transmitted and distributed in the form of signals over a network medium, and downloaded and installed via the communication section 609, and / or installed from the removable medium 611. The program code contained in the computer program can be transmitted using any suitable network medium, including but not limited to: wireless, wired, etc., or any suitable combination thereof.

[0151] In such an embodiment, the computer program can be downloaded and installed from a network via the communication section 609, and / or installed from the removable medium 611. When the computer program is executed by the processor 601, it performs the functions defined in the system of this disclosure embodiment. According to embodiments of this disclosure, the systems, devices, apparatuses, modules, units, etc., described above can be implemented by computer program modules.

[0152] According to embodiments of this disclosure, program code for executing the computer programs provided in embodiments of this disclosure can be written in any combination of one or more programming languages. Specifically, these computational programs can be implemented using high-level procedural and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages ​​include, but are not limited to, languages ​​such as Java, C++, Python, "C", or similar programming languages. The program code can execute entirely on a user's computing device, partially on a user's device, partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0153] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0154] Those skilled in the art will understand that the features described in the various embodiments of this disclosure can be combined and / or combined in various ways, even if such combinations or combinations are not explicitly described in this disclosure. In particular, the features described in the various embodiments of this disclosure can be combined and / or combined in various ways without departing from the spirit and teachings of this disclosure. All such combinations and / or combinations fall within the scope of this disclosure.

[0155] The embodiments of this disclosure have been described above. However, these embodiments are for illustrative purposes only and are not intended to limit the scope of this disclosure. Although various embodiments have been described above, this does not mean that the measures in the various embodiments cannot be used advantageously in combination. Various substitutions and modifications can be made by those skilled in the art without departing from the scope of this disclosure, and all such substitutions and modifications should fall within the scope of this disclosure.

Claims

1. A method for evaluating the colorimetric properties of painting illumination based on the spectrum of a light source, characterized in that, The method includes: Obtain initial evaluation information corresponding to multiple paintings obtained through evaluation experiments in a preset lighting environment, wherein the initial evaluation information represents the evaluation results of multiple objects on multiple paintings; From the initial evaluation information, determine the initial information to be evaluated that meets the first evaluation condition, wherein the first evaluation condition includes at least one of a reliability evaluation condition and a correlation evaluation condition. The reliability evaluation condition is used to evaluate the consistency between the evaluation information of different observation groups and the evaluation information of different observers. The correlation evaluation condition is used to determine whether there is a linear correlation between different paintings and the degree of correlation. From the initial information to be evaluated, target information to be evaluated that meets the second evaluation condition is determined, wherein the target information to be evaluated characterizes the radiant power distribution information of the light source spectrum at different wavelengths in the preset lighting environment, and the second evaluation condition includes at least one of feature evaluation condition and contribution evaluation condition; The target information to be evaluated is input into the evaluation model to obtain the evaluation result corresponding to the color rendering property of the light source; The process of determining the target information to be evaluated that meets the second evaluation condition from the initial information to be evaluated includes: The initial information to be evaluated is linearly combined to obtain intermediate information to be evaluated; Determine the feature evaluation information and contribution information corresponding to the intermediate information to be evaluated, wherein the feature evaluation information includes feature weights and feature vectors, and the contribution information represents the information contribution degree corresponding to the feature vectors; If the feature evaluation information satisfies the feature evaluation conditions, and if the contribution information satisfies the contribution evaluation conditions, the target information to be evaluated is determined.

2. The method according to claim 1, characterized in that, The initial evaluation information, based on the different objects, includes internal observer evaluation information and inter-observer evaluation information; Determining initial evaluation information from the initial evaluation information that meets the first evaluation condition includes: The reliability assessment strategy is used to evaluate the intra-observer evaluation information to obtain a first evaluation result, and the reliability assessment strategy is used to evaluate the inter-observer evaluation information to obtain a second evaluation result. If the first evaluation result and the second evaluation result are greater than or equal to a preset evaluation threshold, the initial evaluation information is obtained.

3. The method according to claim 2, characterized in that, Determining initial evaluation information that meets the first evaluation condition from the initial evaluation information further includes: The average value of the initial evaluation information is evaluated using a correlation assessment strategy to obtain multiple correlation values ​​between the multiple paintings. When multiple correlation values ​​are greater than or equal to a preset correlation threshold, the initial information to be evaluated is obtained.

4. The method according to claim 1, characterized in that, If the feature evaluation information satisfies the feature evaluation conditions, and if the contribution information satisfies the contribution evaluation conditions, the target information to be evaluated is determined, including: The feature weights are sorted according to their numerical values ​​to obtain the sorted feature weights; The feature vectors are sorted based on the sorting information of the sorting feature weights to obtain sorted feature vectors; From the sorting feature vectors, determine the feature vectors corresponding to sorting feature weights that are greater than or equal to the weight threshold, and use them as target feature vectors; If the sum of the information contributions of the target feature vectors is greater than or equal to the contribution threshold, a feature matrix is ​​constructed to obtain the target information to be evaluated.

5. The method according to any one of claims 1 to 4, characterized in that, The preset lighting environment is determined based on the light intensity information corresponding to the painting and the color information of the light source; The evaluation experiments include: The preset lighting environment is constructed based on the light intensity information and the color information; Multiple objects evaluate the color rendering properties of the paintings under multiple working conditions using a random strategy to obtain the initial evaluation information, wherein the multiple paintings have different color styles and the multiple working conditions correspond to different light source colors.

6. The method according to claim 1, characterized in that, The evaluation model is determined through the following steps: Obtain initial evaluation information for each of the multiple sample paintings obtained through an evaluation experiment in a preset lighting environment, wherein the initial evaluation information represents the evaluation results of the multiple sample paintings by the multiple sample objects; The initial evaluation information of the sample is normalized to obtain the sample evaluation information; An initial evaluation model is constructed based on the sample information to be evaluated and the initial parameters, wherein the initial parameters include multiple weight parameters and multiple update parameters; The initial evaluation model is trained using the training and validation information in the sample information to be evaluated, thus obtaining the evaluation model.

7. The method according to claim 6, characterized in that, The initial evaluation model is trained using the training and validation information from the sample information to be evaluated, resulting in the evaluation model, including: The initial evaluation model is trained repeatedly using the training information to obtain an intermediate evaluation model; The target parameters are determined based on the intermediate evaluation results output by the intermediate evaluation model and the verification information, thus obtaining the evaluation model.

8. The method according to claim 7, characterized in that, Based on the intermediate evaluation results output by the intermediate evaluation model and the verification information, the target parameters are determined, and the evaluation model is obtained, including: The indicator result is determined using the intermediate evaluation results, the verification information, and the average value, wherein the average value is obtained based on the intermediate evaluation results and the verification information; If the indicator result is greater than or equal to the preset indicator threshold, the target parameter is obtained, and the intermediate evaluation model is updated using the target parameter to obtain the evaluation model.

9. An evaluation device for the colorimetric properties of painting illumination based on the spectrum of a light source, characterized in that, The device includes: The acquisition module is used to acquire initial evaluation information corresponding to multiple paintings obtained through an evaluation experiment in a preset lighting environment, wherein the initial evaluation information represents the evaluation results of multiple objects on multiple paintings; The determining module is used to determine the initial information to be evaluated that meets the first evaluation condition from the initial evaluation information. The first evaluation condition includes at least one of a reliability evaluation condition and a correlation evaluation condition. The reliability evaluation condition is used to evaluate the consistency between the evaluation information of different observation groups and the evaluation information of different observers. The correlation evaluation condition is used to determine whether there is a linear correlation between different paintings and the degree of correlation. An information determination module is used to determine target information to be evaluated that meets the second evaluation condition from the initial information to be evaluated, wherein the target information to be evaluated characterizes the radiant power distribution information of the light source spectrum at different wavelengths in the preset lighting environment, and the second evaluation condition includes at least one of feature evaluation condition and contribution evaluation condition; The input module is used to input the target information to be evaluated into the evaluation model to obtain the evaluation result corresponding to the color rendering property of the light source; The determining module includes: The combination submodule is used to linearly combine the initial information to be evaluated to obtain intermediate information to be evaluated. The information determination submodule is used to determine the feature evaluation information and contribution information corresponding to the intermediate information to be evaluated, wherein the feature evaluation information includes feature weights and feature vectors, and the contribution information represents the information contribution degree corresponding to the feature vectors; The target information to be evaluated determination submodule is used to determine the target information to be evaluated when the feature evaluation information meets the feature evaluation conditions and the contribution information meets the contribution evaluation conditions.

Images