Traditional art 3D content conversion system and method based on artificial intelligence

Abstract

The present invention relates to the field of traditional fine arts content processing technology, and in particular to a traditional fine arts 3D content conversion system and method based on artificial intelligence. The present invention analyzes the painting effect of traditional fine arts paintings according to pigment type data and pigment drawing data; analyzes the effect of 3D painting images according to 3D painting image data of traditional fine arts paintings after 3D content conversion; analyzes the 3D content conversion effect of traditional fine arts paintings according to the painting effect analysis results of traditional fine arts paintings and the effect analysis results of 3D painting images; and re-converts the 3D content of traditional fine arts paintings according to the 3D content conversion effect analysis results. By analyzing the effects of traditional art pigments and 3D painting images, analyzing the 3D content conversion effect and re-converting it, the content conversion effect of traditional fine arts works is improved, and the development of traditional fine arts 3D content conversion is promoted.

Description

Technical Field

[0001] The present invention relates to the technical field of traditional art content processing, and in particular to a traditional art 3D content conversion system and method based on artificial intelligence. Background Art

[0002] With the rapid development of science and technology, human society has fully entered the digital age. With the increasing popularity of modern art works, the inheritance and innovation of traditional art works are facing unprecedented opportunities and challenges. Digital technology provides a new way for the preservation, display and dissemination of traditional art works, and 3D content conversion, as one of the important applications of digital technology, provides the possibility for the modern presentation of traditional art works. Through 3D content conversion, traditional art works can get rid of the limitations of time and space and be presented to the audience in a more vivid and intuitive way, thereby attracting more people's attention and love, and promoting the inheritance and development of art.

[0003] Most of the pigments used in modern art are artificially synthesized pigments obtained through industrial production, which have good stability and color expression. Therefore, when converting 3D content, content conversion can often be performed through simple and direct color processing. The stone color and water color pigments used in traditional art works come from natural minerals and plants respectively. Stone color pigments are insoluble pigments. After being mixed with water, they will naturally separate and precipitate after a long time. Therefore, in 3D content conversion, it is necessary to consider the situation where the stone color pigment separates or precipitates to cause uneven color. Water color pigments are soluble pigments, which are well mixed with water, but have a certain degree of photophobia. Long-term direct sunlight will decompose and fade. Therefore, in the process of 3D content conversion, it is necessary to more finely control the superposition and mixing effects of colors to obtain ideal color levels and three-dimensional sense. However, the existing technology often ignores the difference in the properties of pigments in traditional art and modern art when performing 3D content conversion, resulting in traditional art works generated by 3D content conversion being closer to the style of modern art works, but losing the profound cultural heritage contained in traditional art works. Summary of the invention

[0004] In order to overcome the defects and shortcomings of the prior art, the present invention provides a traditional art 3D content conversion system and method based on artificial intelligence. By analyzing the effects of traditional art pigments and 3D painting images, the 3D content conversion effect is analyzed and re-converted, thereby improving the content conversion effect of traditional art works and promoting the development of traditional art 3D content conversion.

[0005] In order to achieve the above object, the present invention adopts the following technical solutions:

[0006] In a first aspect, an embodiment of the present invention provides a method for converting traditional fine art 3D content based on artificial intelligence, comprising the following steps:

[0007] S1, obtaining pigment type data and pigment drawing data used in traditional fine art paintings, and simultaneously obtaining 3D painting image data of the traditional fine art paintings after 3D content conversion;

[0008] S2, importing the pigment type data and the pigment drawing data into the drawing effect analysis model to analyze the drawing effect of the traditional art painting works;

[0009] S3, importing the 3D painting image data of the traditional fine art painting after the 3D content conversion into the 3D painting effect analysis model, and analyzing the effect of the 3D painting image of the traditional fine art painting after the 3D content conversion;

[0010] S4, analyzing the 3D content conversion effect of the traditional art painting works according to the painting effect analysis results of the traditional art painting works and the effect analysis results of the 3D painting images;

[0011] S5. Re-convert the traditional art paintings into 3D contents according to the analysis results of the 3D content conversion effect.

[0012] In one implementation of the present invention, step S2 includes the following specific steps:

[0013] S21, obtaining pigment type data and pigment drawing data used in traditional fine art paintings, wherein the pigment type data includes stone color pigment type data and water color pigment type data; the pigment drawing data includes pigment drawing areas and pigment concentration data, pigment drawing area data and pigment chromaticity value data in each pigment drawing area; the pigment drawing areas are obtained by dividing the traditional fine art paintings into equal areas;

[0014] S22, obtaining stone color pigment sample data from historical traditional art paintings for training a stone color pigment chromaticity value prediction model, wherein the stone color pigment sample data includes stone color pigment type data, pigment concentration data of each stone color pigment in multiple pigment drawing areas, pigment drawing area data, and pigment chromaticity value data, dividing the stone color pigment sample data for training the stone color pigment chromaticity value prediction model into a stone color pigment sample training set and a stone color pigment sample test set, constructing a first regression network model, using the stone color pigment type data, pigment concentration data of each stone color pigment in multiple pigment drawing areas, and pigment drawing area data in the stone color pigment training set as inputs of the first regression network model, using the pigment chromaticity value data of each stone color pigment in multiple pigment drawing areas in the stone color pigment training set as outputs of the first regression network model, training the first regression network model to obtain a first initial regression network model; evaluating the model effect of the first initial regression network model using an average error algorithm, and selecting a corresponding first initial regression network model having a value greater than or equal to a preset first evaluation value as a stone color pigment chromaticity value prediction model;

[0015] S23, obtaining water-color pigment sample data from historical traditional art paintings for training a water-color pigment chromaticity value prediction model, wherein the water-color pigment sample data includes water-color pigment type data, pigment concentration data of each water-color pigment in multiple pigment drawing areas, pigment drawing area data, and pigment chromaticity value data; dividing the water-color pigment sample data for training the water-color pigment chromaticity value prediction model into a water-color pigment sample training set and a water-color pigment sample test set; constructing a second regression network model; using the water-color pigment type data, pigment concentration data of each water-color pigment in multiple pigment drawing areas, and pigment drawing area data in the water-color pigment training set as inputs of the second regression network model; using the pigment chromaticity value data of each water-color pigment in multiple pigment drawing areas in the water-color pigment training set as outputs of the second regression network model; training the second regression network model to obtain a second initial regression network model; evaluating the model effect of the second initial regression network model using an average error algorithm, and selecting a corresponding second initial regression network model that is greater than or equal to a preset second evaluation value as the water-color pigment chromaticity value prediction model;

[0016] S24, using the pigment concentration data and pigment drawing area data of the i-th stone color pigment in the j-th pigment drawing area in the traditional art painting as the input of the stone color pigment chromaticity value prediction model, and obtaining the pigment chromaticity value data of the i-th stone color pigment in the j-th pigment drawing area predicted by the stone color pigment chromaticity value prediction model;

[0017] S25. Use the pigment concentration data and pigment drawing area data of the qth water color pigment in the jth pigment drawing area in the traditional art painting as the input of the water color pigment chromaticity value prediction model to obtain the pigment chromaticity value data of the qth water color pigment in the jth pigment drawing area predicted by the water color pigment chromaticity value prediction model.

[0018] In one implementation of the present invention, step S2 further includes the following specific steps:

[0019] S26, obtaining the predicted pigment chromaticity value data of all stone color pigments in all pigment drawing areas and the predicted pigment chromaticity value data of all water color pigments in all pigment drawing areas;

[0020] S27, substituting the pigment chromaticity value data of all stone color pigments in all pigment drawing areas and the predicted pigment chromaticity value data of all water color pigments in all pigment drawing areas into the painting effect contrast coefficient calculation formula to calculate the painting effect contrast coefficient of the j-th pigment drawing area in the traditional art painting, the painting effect contrast coefficient calculation formula is:

[0021] ;

[0022] In the formula It represents the contrast coefficient of the painting effect of the jth pigment painting area in traditional art paintings. The pigment drawing area data for the i-th stone color pigment in the j-th pigment drawing area, The pigment chromaticity value data of the i-th stone pigment in the j-th pigment drawing area, The pigment drawing area data for the qth water color pigment in the jth pigment drawing area, is the pigment chromaticity value data of the qth water-color pigment in the jth pigment drawing area, S is the area of ​​the jth pigment drawing area, i is any item from 1 to n, q is any item from 1 to m, n is the number of stone color pigments, m is the number of water color pigments, and ln() is a natural logarithm function.

[0023] In one implementation of the present invention, step S3 specifically includes:

[0024] S31, obtaining 3D painting image data of the traditional fine art painting after 3D content conversion, wherein the 3D painting image data includes color data in all stone color pigment sub-regions corresponding to all types of stone color pigments and color data in all water color pigment sub-regions corresponding to all types of water color pigments in the 3D painting image regions corresponding to the pigment drawing regions one by one;

[0025] S32, substituting the color data in the stone color pigment sub-area and the color data in the water color pigment sub-area into the 3D painting image effect contrast coefficient calculation formula to calculate the 3D painting image effect contrast coefficient of the 3D painting image area corresponding to the j-th pigment drawing area in the 3D painting image; the 3D painting image effect contrast coefficient calculation formula is:

[0026] ;

[0027] In the formula represents the 3D painting image effect contrast coefficient of the 3D painting image area corresponding to the j-th pigment painting area in the 3D painting image, respectively represent the red component, green component, and blue component in the color data of the stone color pigment sub-region corresponding to the i-th stone color pigment in the 3D painting image region corresponding to the j-th pigment drawing region, They respectively represent the red component, green component, and blue component in the color data of the watercolor pigment sub-region corresponding to the qth watercolor pigment in the 3D painting image region corresponding to the jth pigment drawing region.

[0028] In one implementation of the present invention, the specific steps of step S4 are:

[0029] S41, obtaining the calculated painting effect contrast coefficients of all pigment drawing areas in the traditional fine art painting and the 3D painting image effect contrast coefficients of the 3D painting image areas corresponding to all pigment drawing areas in the 3D painting image;

[0030] S42, substituting the painting effect contrast coefficient and the 3D painting image effect contrast coefficient into the 3D content conversion effect difference coefficient calculation formula to calculate the 3D content conversion effect difference coefficient of the j-th pigment drawing area in the traditional art painting, the 3D content conversion effect difference coefficient calculation formula is:

[0031] ;

[0032] In the formula It represents the difference coefficient of 3D content conversion effect of the j-th pigment drawing area in traditional art paintings, and Q is the number of pigment drawing areas.

[0033] In one implementation of the present invention, step S5 includes the following specific steps:

[0034] S51, obtaining the calculated 3D content conversion effect difference coefficients of all pigment drawing areas in the traditional art painting;

[0035] S52, presetting a 3D content conversion effect difference threshold, when the 3D content conversion effect difference coefficient of the ith pigment drawing area in the traditional art painting is less than the 3D content conversion effect difference threshold, not performing a content re-conversion operation of the ith pigment drawing area in the traditional art painting; when the 3D content conversion effect difference coefficient of the ith pigment drawing area in the traditional art painting is greater than or equal to the 3D content conversion effect difference threshold, issuing an instruction to the operator to perform a content re-conversion operation of the ith pigment drawing area in the traditional art painting.

[0036] In a second aspect, an embodiment of the present invention further provides a traditional art 3D content conversion system based on artificial intelligence, including:

[0037] A data acquisition module, used to acquire data on the types of pigments used in traditional fine art paintings and pigment drawing data, and to acquire 3D painting image data of the traditional fine art paintings after 3D content conversion;

[0038] A painting effect analysis module is used to import pigment type data and pigment drawing data into a painting effect analysis model to analyze the painting effects of traditional art paintings;

[0039] A 3D painting image effect analysis module, used to import the 3D painting image data of the traditional fine art painting after the 3D content conversion into the 3D painting effect analysis model, and analyze the effect of the 3D painting image of the traditional fine art painting after the 3D content conversion;

[0040] A 3D content conversion effect analysis module, used to analyze the 3D content conversion effect of traditional fine art paintings based on the painting effect analysis results of traditional fine art paintings and the effect analysis results of 3D painting images;

[0041] A re-conversion execution module is used to re-convert the 3D content of the traditional art painting works according to the 3D content conversion effect analysis result;

[0042] A control module is used to control the operation of the data acquisition module, the painting effect analysis module, the 3D painting image effect analysis module, the 3D content conversion effect analysis module and the re-conversion execution module.

[0043] In a third aspect, an embodiment of the present invention provides an electronic device, comprising: a processor and a memory, wherein the memory stores a computer program that can be called by the processor, and the processor executes a traditional art 3D content conversion method based on artificial intelligence by calling the computer program stored in the memory.

[0044] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium storing instructions, which, when executed on a computer, enables the computer to execute a traditional art 3D content conversion method based on artificial intelligence.

[0045] Compared with the prior art, the present invention has the following advantages and beneficial effects:

[0046] The present invention analyzes the painting effect of traditional fine art paintings according to pigment type data and pigment drawing data; analyzes the effect of 3D painting images according to 3D painting image data of traditional fine art paintings after 3D content conversion; analyzes the 3D content conversion effect of traditional fine art paintings according to the painting effect analysis results of traditional fine art paintings and the effect analysis results of 3D painting images; and re-converts the 3D content of traditional fine art paintings according to the 3D content conversion effect analysis results. By analyzing the effects of traditional art pigments and 3D painting images, analyzing the 3D content conversion effect and re-converting it, the content conversion effect of traditional fine art works is improved, and the development of traditional fine art 3D content conversion is promoted. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Other features, objects and advantages of the present invention will become more apparent from the detailed description of non-limiting embodiments made with reference to the following drawings:

[0048] Figure 1 It is a schematic diagram of the overall process of the traditional art 3D content conversion method based on artificial intelligence of the present invention;

[0049] Figure 2 The flowchart of the regression network model in the traditional art 3D content conversion method based on artificial intelligence of the present invention;

[0050] Figure 3 It is a structural schematic diagram of the traditional art 3D content conversion system based on artificial intelligence of the present invention. DETAILED DESCRIPTION

[0051] The technical solution of the present invention is described in detail below through the accompanying drawings and specific embodiments. It should be understood that the embodiments of the present invention and the specific features in the embodiments are detailed descriptions of the technical solution of the present invention, rather than limitations on the technical solution of the present invention. The embodiments of the present invention and the technical features in the embodiments may be combined with each other unless there is a conflict.

[0052] Example 1

[0053] like Figure 1 As shown, this embodiment provides a traditional art 3D content conversion method based on artificial intelligence, which specifically includes the following steps:

[0054] S1, obtaining pigment type data and pigment drawing data used in traditional fine art paintings, and simultaneously obtaining 3D painting image data of the traditional fine art paintings after 3D content conversion;

[0055] S2, importing the pigment type data and the pigment drawing data into the drawing effect analysis model to analyze the drawing effect of the traditional art painting works;

[0056] In this embodiment, analyzing the painting effect of traditional fine art paintings includes the following specific steps:

[0057] S21, obtaining pigment type data and pigment drawing data used in traditional fine art paintings, wherein the pigment type data includes stone color pigment type data and water color pigment type data; the pigment drawing data includes pigment drawing areas and pigment concentration data, pigment drawing area data and pigment chromaticity value data in each pigment drawing area; the pigment drawing areas are obtained by dividing the traditional fine art paintings into equal areas;

[0058] In this embodiment, the pigment concentration data of the stone color pigment and the water color pigment can be obtained by measuring the light absorption characteristics of the pigment solution using a spectrophotometer. The pigment concentration of the stone color pigment and the water color pigment is calculated according to the absorbance; and the pigment chromaticity value data is measured and obtained by a chromaticity detector.

[0059] S22, obtaining stone color pigment sample data from historical traditional art paintings for training a stone color pigment chromaticity value prediction model, wherein the stone color pigment sample data includes stone color pigment type data, pigment concentration data of each stone color pigment in multiple pigment drawing areas, pigment drawing area data, and pigment chromaticity value data, dividing the stone color pigment sample data for training the stone color pigment chromaticity value prediction model into a stone color pigment sample training set and a stone color pigment sample test set, constructing a first regression network model, using the stone color pigment type data, pigment concentration data of each stone color pigment in multiple pigment drawing areas, and pigment drawing area data in the stone color pigment training set as inputs of the first regression network model, using the pigment chromaticity value data of each stone color pigment in multiple pigment drawing areas in the stone color pigment training set as outputs of the first regression network model, training the first regression network model to obtain a first initial regression network model; evaluating the model effect of the first initial regression network model using an average error algorithm, and selecting a corresponding first initial regression network model having a value greater than or equal to a preset first evaluation value as a stone color pigment chromaticity value prediction model;

[0060] S23, obtaining water-color pigment sample data from historical traditional art paintings for training a water-color pigment chromaticity value prediction model, wherein the water-color pigment sample data includes water-color pigment type data, pigment concentration data of each water-color pigment in multiple pigment drawing areas, pigment drawing area data, and pigment chromaticity value data; dividing the water-color pigment sample data for training the water-color pigment chromaticity value prediction model into a water-color pigment sample training set and a water-color pigment sample test set; constructing a second regression network model; using the water-color pigment type data, pigment concentration data of each water-color pigment in multiple pigment drawing areas, and pigment drawing area data in the water-color pigment training set as inputs of the second regression network model; using the pigment chromaticity value data of each water-color pigment in multiple pigment drawing areas in the water-color pigment training set as outputs of the second regression network model; training the second regression network model to obtain a second initial regression network model; evaluating the model effect of the second initial regression network model using an average error algorithm, and selecting a corresponding second initial regression network model that is greater than or equal to a preset second evaluation value as the water-color pigment chromaticity value prediction model;

[0061] In this embodiment, the workflow diagram of the regression network model used to train the stone color pigment chromaticity value prediction model and the water color pigment chromaticity value prediction model is as follows: Figure 2 shown.

[0062] S24, using the pigment concentration data and pigment drawing area data of the i-th stone color pigment in the j-th pigment drawing area in the traditional art painting as the input of the stone color pigment chromaticity value prediction model, and obtaining the pigment chromaticity value data of the i-th stone color pigment in the j-th pigment drawing area predicted by the stone color pigment chromaticity value prediction model;

[0063] S25. Use the pigment concentration data and pigment drawing area data of the qth water color pigment in the jth pigment drawing area in the traditional art painting as the input of the water color pigment chromaticity value prediction model to obtain the pigment chromaticity value data of the qth water color pigment in the jth pigment drawing area predicted by the water color pigment chromaticity value prediction model.

[0064] In this embodiment, analyzing the painting effect of traditional fine art paintings also includes the following specific steps:

[0065] S26, obtaining the predicted pigment chromaticity value data of all stone color pigments in all pigment drawing areas and the predicted pigment chromaticity value data of all water color pigments in all pigment drawing areas;

[0066] S27, substituting the pigment chromaticity value data of all stone color pigments in all pigment drawing areas and the predicted pigment chromaticity value data of all water color pigments in all pigment drawing areas into the painting effect contrast coefficient calculation formula to calculate the painting effect contrast coefficient of the j-th pigment drawing area in the traditional art painting, the painting effect contrast coefficient calculation formula is:

[0067] ;

[0068] In the formula It represents the contrast coefficient of the painting effect of the jth pigment painting area in traditional art paintings. The pigment drawing area data for the i-th stone color pigment in the j-th pigment drawing area, The pigment chromaticity value data of the i-th stone pigment in the j-th pigment drawing area, The pigment drawing area data for the qth water color pigment in the jth pigment drawing area, is the pigment chromaticity value data of the qth water-color pigment in the jth pigment drawing area, S is the area of ​​the jth pigment drawing area, i is any item from 1 to n, q is any item from 1 to m, n is the number of stone color pigments, m is the number of water color pigments, and ln() is a natural logarithm function.

[0069] In this embodiment, the stone color pigment and water color pigment used in traditional art paintings will naturally separate and precipitate over time, resulting in uneven colors in traditional art paintings, or fading after long-term exposure to direct sunlight. Therefore, by directly using a colorimeter for measurement, and then analyzing the drawing effect based on the measurement results, so as to determine the effect of 3D content conversion, the converted 3D painting image will have partial color distortion or missing. Therefore, in this embodiment, the original color parameters of the drawing area are predicted based on the type, concentration and area of ​​the stone color pigment and water color pigment, and the drawing effect is analyzed based on the original color parameters, so as to determine the 3D content conversion effect. The method is more accurate than directly using a colorimeter for measurement and analysis.

[0070] S3, importing the 3D painting image data of the traditional fine art painting after the 3D content conversion into the 3D painting effect analysis model, and analyzing the effect of the 3D painting image of the traditional fine art painting after the 3D content conversion;

[0071] In this embodiment, the effect of the 3D painting image of the traditional fine art painting after the 3D content conversion is analyzed, specifically including:

[0072] S31, obtaining 3D painting image data of the traditional fine art painting after 3D content conversion, wherein the 3D painting image data includes color data in all stone color pigment sub-regions corresponding to all types of stone color pigments and color data in all water color pigment sub-regions corresponding to all types of water color pigments in the 3D painting image regions corresponding to the pigment drawing regions one by one;

[0073] S32, substituting the color data in the stone color pigment sub-area and the color data in the water color pigment sub-area into the 3D painting image effect contrast coefficient calculation formula to calculate the 3D painting image effect contrast coefficient of the 3D painting image area corresponding to the j-th pigment drawing area in the 3D painting image; the 3D painting image effect contrast coefficient calculation formula is:

[0074] ;

[0075] In the formula represents the 3D painting image effect contrast coefficient of the 3D painting image area corresponding to the j-th pigment painting area in the 3D painting image, They respectively represent the red component, green component, and blue component in the color data of the stone color pigment sub-region corresponding to the i-th stone color pigment in the 3D painting image region corresponding to the j-th pigment drawing region, They respectively represent the red component, green component, and blue component in the color data of the watercolor pigment sub-region corresponding to the qth watercolor pigment in the 3D painting image region corresponding to the jth pigment drawing region.

[0076] In this embodiment, the 3D painting image effect contrast coefficient is calculated by using the color data in the stone color pigment sub-region and the color data in the water color pigment sub-region. The contrast and difference in color between the stone color pigment and the water color pigment in the corresponding regions in the 3D painting image can be compared and analyzed, thereby helping to evaluate whether the color effect in the 3D painting image generated after the traditional art painting is converted into 3D content retains the characteristics of the original painting.

[0077] S4, analyzing the 3D content conversion effect of the traditional art painting works according to the painting effect analysis results of the traditional art painting works and the effect analysis results of the 3D painting images;

[0078] In this embodiment, the specific steps of analyzing the 3D content conversion effect of traditional art paintings are as follows:

[0079] S41, obtaining the calculated painting effect contrast coefficients of all pigment drawing areas in the traditional fine art painting and the 3D painting image effect contrast coefficients of the 3D painting image areas corresponding to all pigment drawing areas in the 3D painting image;

[0080] S42, substituting the painting effect contrast coefficient and the 3D painting image effect contrast coefficient into the 3D content conversion effect difference coefficient calculation formula to calculate the 3D content conversion effect difference coefficient of the j-th pigment drawing area in the traditional art painting, the 3D content conversion effect difference coefficient calculation formula is:

[0081] ;

[0082] In the formula It represents the difference coefficient of 3D content conversion effect of the j-th pigment drawing area in the traditional art painting, and Q is the number of pigment drawing areas.

[0083] In this embodiment, by calculating the painting effect contrast coefficient of traditional art paintings and the effect contrast coefficient of 3D painting images, and substituting them into the 3D content conversion effect difference coefficient calculation formula, a quantitative reference can be provided for analyzing the conversion effect of traditional art paintings to 3D content. By introducing the 3D content conversion effect difference coefficient, the difference in visual effects between traditional art paintings and their corresponding 3D painting images can be quantified. In this embodiment, the 3D content conversion effect difference coefficient reflects whether the traditional flat painting retains the characteristics of the original painting after being converted into a 3D image. It can help designers and technicians evaluate whether the conversion effect meets expectations. By comparing the 3D content conversion effect difference coefficients of different pigment painting areas, it is possible to find out which areas have better conversion effects and which areas have larger differences, so that the performance of 3D images can be optimized in a targeted manner.

[0084] S5. Re-convert the traditional art paintings into 3D contents according to the analysis results of the 3D content conversion effect.

[0085] In this embodiment, re-converting the traditional fine art painting into 3D content includes the following specific steps:

[0086] S51, obtaining the calculated 3D content conversion effect difference coefficients of all pigment drawing areas in the traditional art painting;

[0087] S52, presetting a 3D content conversion effect difference threshold, when the 3D content conversion effect difference coefficient of the i-th pigment drawing area in the traditional art painting is less than the 3D content conversion effect difference threshold, not performing a content re-conversion operation of the i-th pigment drawing area in the traditional art painting; when the 3D content conversion effect difference coefficient of the i-th pigment drawing area in the traditional art painting is greater than or equal to the 3D content conversion effect difference threshold, issuing an instruction to the operator to re-convert the content of the i-th pigment drawing area in the traditional art painting, wherein the 3D content conversion effect difference threshold is set by those skilled in the art according to actual needs and specific circumstances.

[0088] Example 2

[0089] like Figure 3 As shown, this embodiment provides a traditional art 3D content conversion system based on artificial intelligence, including:

[0090] A data acquisition module, used to acquire data on the types of pigments used in traditional fine art paintings and pigment drawing data, and to acquire 3D painting image data of the traditional fine art paintings after 3D content conversion;

[0091] A painting effect analysis module is used to import pigment type data and pigment drawing data into a painting effect analysis model to analyze the painting effects of traditional art paintings;

[0092] A 3D painting image effect analysis module, used to import the 3D painting image data of the traditional fine art painting after the 3D content conversion into the 3D painting effect analysis model, and analyze the effect of the 3D painting image of the traditional fine art painting after the 3D content conversion;

[0093] A 3D content conversion effect analysis module, used to analyze the 3D content conversion effect of traditional fine art paintings based on the painting effect analysis results of traditional fine art paintings and the effect analysis results of 3D painting images;

[0094] A re-conversion execution module is used to re-convert the 3D content of the traditional art painting works according to the 3D content conversion effect analysis result;

[0095] The control module is used to control the operation of the data acquisition module, the painting effect analysis module, the 3D painting image effect analysis module, the 3D content conversion effect analysis module and the re-conversion execution module.

[0096] In this embodiment, the painting effect analysis module is used to import the pigment type data and the pigment drawing data into the painting effect analysis model to analyze the painting effect of the traditional art painting works; it specifically includes:

[0097] Obtaining pigment type data and pigment drawing data used in traditional fine art paintings, wherein the pigment type data includes stone color pigment type data and water color pigment type data; the pigment drawing data includes pigment drawing areas and pigment concentration data, pigment drawing area data and pigment chromaticity value data in each pigment drawing area; the pigment drawing area is obtained by dividing the traditional fine art paintings into equal areas;

[0098] Obtain stone color pigment sample data from historical traditional art paintings for training a stone color pigment chromaticity value prediction model, wherein the stone color pigment sample data includes stone color pigment type data, pigment concentration data of each stone color pigment in multiple pigment drawing areas, pigment drawing area data, and pigment chromaticity value data; divide the stone color pigment sample data for training the stone color pigment chromaticity value prediction model into a stone color pigment sample training set and a stone color pigment sample test set; construct a first regression network model; use the stone color pigment type data, pigment concentration data of each stone color pigment in multiple pigment drawing areas, and pigment drawing area data in the stone color pigment training set as inputs of the first regression network model; use the pigment chromaticity value data of each stone color pigment in multiple pigment drawing areas in the stone color pigment training set as outputs of the first regression network model; train the first regression network model to obtain a first initial regression network model; evaluate the model effect of the first initial regression network model using an average error algorithm, and select the corresponding first initial regression network model that is greater than or equal to a preset first evaluation value as the stone color pigment chromaticity value prediction model;

[0099] Acquire water-color pigment sample data from historical traditional art paintings for training a water-color pigment chromaticity value prediction model, wherein the water-color pigment sample data includes water-color pigment type data, pigment concentration data of each water-color pigment in multiple pigment drawing areas, pigment drawing area data, and pigment chromaticity value data; divide the water-color pigment sample data for training the water-color pigment chromaticity value prediction model into a water-color pigment sample training set and a water-color pigment sample test set; construct a second regression network model; use the water-color pigment type data, pigment concentration data of each water-color pigment in multiple pigment drawing areas, and pigment drawing area data in the water-color pigment training set as inputs of the second regression network model; use the pigment chromaticity value data of each water-color pigment in multiple pigment drawing areas in the water-color pigment training set as outputs of the second regression network model; train the second regression network model to obtain a second initial regression network model; evaluate the model effect of the second initial regression network model using an average error algorithm, and select the corresponding second initial regression network model that is greater than or equal to a preset second evaluation value as the water-color pigment chromaticity value prediction model;

[0100] The pigment concentration data and pigment drawing area data of the i-th stone color pigment in the j-th pigment drawing area in the traditional art painting are used as the input of the stone color pigment chromaticity value prediction model to obtain the pigment chromaticity value data of the i-th stone color pigment in the j-th pigment drawing area predicted by the stone color pigment chromaticity value prediction model;

[0101] The pigment concentration data and pigment drawing area data of the qth water color pigment in the jth pigment drawing area in the traditional art painting are used as the input of the water color pigment chromaticity value prediction model to obtain the pigment chromaticity value data of the qth water color pigment in the jth pigment drawing area predicted by the water color pigment chromaticity value prediction model.

[0102] In this embodiment, analyzing the painting effect of traditional fine art paintings also includes the following specific steps:

[0103] Obtaining the predicted pigment chromaticity value data of all stone color pigments in all pigment drawing areas and the predicted pigment chromaticity value data of all water color pigments in all pigment drawing areas;

[0104] Substitute the pigment chromaticity value data of all stone pigments in all pigment drawing areas and the predicted pigment chromaticity value data of all water-colored pigments in all pigment drawing areas into the painting effect contrast coefficient calculation formula to calculate the painting effect contrast coefficient of the jth pigment drawing area in the traditional art painting. The painting effect contrast coefficient calculation formula is:

[0105] ;

[0106] In the formula It represents the contrast coefficient of the painting effect of the jth pigment painting area in traditional art paintings. The pigment drawing area data for the i-th stone color pigment in the j-th pigment drawing area, The pigment chromaticity value data of the i-th stone pigment in the j-th pigment drawing area, The pigment drawing area data for the qth water color pigment in the jth pigment drawing area, is the pigment chromaticity value data of the qth water-color pigment in the jth pigment drawing area, S is the area of ​​the jth pigment drawing area, i is any item from 1 to n, q is any item from 1 to m, n is the number of stone color pigments, m is the number of water color pigments, and ln() is a natural logarithm function.

[0107] In this embodiment, the 3D painting image effect analysis module is used to import the 3D painting image data of the traditional art painting after the 3D content conversion into the 3D painting effect analysis model, and analyze the effect of the 3D painting image of the traditional art painting after the 3D content conversion; the specific steps of analyzing the effect of the 3D painting image of the traditional art painting after the 3D content conversion include:

[0108] Acquire 3D painting image data of the traditional fine art painting after 3D content conversion, wherein the 3D painting image data includes color data of all stone color pigment sub-regions corresponding to all types of stone color pigments and color data of all water color pigment sub-regions corresponding to all types of water color pigments in the 3D painting image regions corresponding to the pigment drawing regions one by one;

[0109] Substitute the color data in the stone color pigment sub-area and the color data in the water color pigment sub-area into the 3D painting image effect contrast coefficient calculation formula to calculate the 3D painting image effect contrast coefficient of the 3D painting image area corresponding to the j-th pigment painting area in the 3D painting image; the 3D painting image effect contrast coefficient calculation formula is:

[0110] ;

[0111] In the formula represents the 3D painting image effect contrast coefficient of the 3D painting image area corresponding to the j-th pigment painting area in the 3D painting image, respectively represent the red component, green component, and blue component in the color data of the stone color pigment sub-region corresponding to the i-th stone color pigment in the 3D painting image region corresponding to the j-th pigment drawing region, They respectively represent the red component, green component, and blue component in the color data of the watercolor pigment sub-region corresponding to the qth watercolor pigment in the 3D painting image region corresponding to the jth pigment drawing region.

[0112] In this embodiment, the 3D content conversion effect analysis module is used to analyze the 3D content conversion effect of the traditional art painting according to the painting effect analysis result of the traditional art painting and the effect analysis result of the 3D painting image. The specific steps of analyzing the 3D content conversion effect of the traditional art painting include:

[0113] Obtaining the calculated painting effect contrast coefficients of all pigment drawing areas in the traditional fine art painting and the 3D painting image effect contrast coefficients of the 3D painting image areas corresponding to all pigment drawing areas in the 3D painting image;

[0114] Substitute the painting effect contrast coefficient and the 3D painting image effect contrast coefficient into the 3D content conversion effect difference coefficient calculation formula to calculate the 3D content conversion effect difference coefficient of the j-th pigment drawing area in the traditional art painting work. The 3D content conversion effect difference coefficient calculation formula is:

[0115] ;

[0116] In the formula It represents the difference coefficient of 3D content conversion effect of the j-th pigment drawing area in the traditional art painting, and Q is the number of pigment drawing areas.

[0117] In this embodiment, the re-conversion execution module is used to re-convert the 3D content of the traditional fine art painting according to the 3D content conversion effect analysis result. The re-converting of the 3D content of the traditional fine art painting includes the following specific steps:

[0118] Obtaining calculated 3D content conversion effect difference coefficients of all pigment drawing areas in traditional art paintings;

[0119] A 3D content conversion effect difference threshold is preset. When the 3D content conversion effect difference coefficient of the i-th pigment drawing area in the traditional art painting is less than the 3D content conversion effect difference threshold, the content re-conversion operation of the i-th pigment drawing area in the traditional art painting is not performed; when the 3D content conversion effect difference coefficient of the i-th pigment drawing area in the traditional art painting is greater than or equal to the 3D content conversion effect difference threshold, an instruction to re-convert the content of the i-th pigment drawing area in the traditional art painting is issued to the operator, wherein the 3D content conversion effect difference threshold is set by those skilled in the art according to actual needs and specific circumstances.

[0120] The above-mentioned parameters and steps for each unit module to implement corresponding functions in the traditional art 3D content conversion system based on artificial intelligence of the present invention can refer to the parameters and steps in the embodiment of the traditional art 3D content conversion method based on artificial intelligence above, and will not be repeated here.

[0121] Example 3

[0122] An electronic device according to an embodiment of the present invention includes: a processor and a memory, wherein the memory stores a computer program that can be called by the processor, and the processor executes a traditional art 3D content conversion method based on artificial intelligence by calling the computer program stored in the memory. It should be noted that all computer programs of the traditional art 3D content conversion method based on artificial intelligence are implemented in C language, wherein the data acquisition module, the painting effect analysis module, the 3D painting image effect analysis module, the 3D content conversion effect analysis module, the re-conversion execution module and the control module are all controlled by a remote server.

[0123] Example 4

[0124] This embodiment provides a computer-readable storage medium having a rewritable computer program stored thereon;

[0125] When the computer program runs on a computer device, the computer device executes the above-mentioned traditional art 3D content conversion method based on artificial intelligence.

[0126] Each embodiment of the present invention is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the IoT device and medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiments.

[0127] The system and medium provided in the embodiments of the present invention correspond one-to-one to the method, and therefore, the system and medium also have similar beneficial technical effects to the corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the system and medium will not be repeated here.

[0128] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0129] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0130] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0131] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0132] Memory may include non-permanent storage in a computer-readable medium, in the form of random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

[0133] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0134] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0135] The above are only embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent substitution, improvement, etc. made within the spirit and principle of the present invention should be included in the scope of the claims of the present invention.

Claims

1. A traditional art 3D content conversion method based on artificial intelligence, characterized in that: The steps include: S1, obtaining pigment type data and pigment drawing data used in traditional fine art paintings, and simultaneously obtaining 3D painting image data of the traditional fine art paintings after 3D content conversion; S2, importing the pigment type data and the pigment drawing data into the drawing effect analysis model to analyze the drawing effect of the traditional art painting works; S3, importing the 3D painting image data of the traditional fine art painting after the 3D content conversion into the 3D painting effect analysis model, and analyzing the effect of the 3D painting image of the traditional fine art painting after the 3D content conversion; S4, analyzing the 3D content conversion effect of the traditional art painting works according to the painting effect analysis results of the traditional art painting works and the effect analysis results of the 3D painting images; S5. Re-convert the traditional art paintings into 3D content according to the analysis results of the 3D content conversion effect; The step S2 comprises the following specific steps: S21, obtaining pigment type data and pigment drawing data used in traditional fine art paintings, wherein the pigment type data includes stone color pigment type data and water color pigment type data; the pigment drawing data includes pigment drawing areas and pigment concentration data, pigment drawing area data and pigment chromaticity value data in each pigment drawing area; the pigment drawing areas are obtained by dividing the traditional fine art paintings into equal areas; S22, obtaining stone color pigment sample data from historical traditional art paintings for training a stone color pigment chromaticity value prediction model, wherein the stone color pigment sample data includes stone color pigment type data, pigment concentration data of each stone color pigment in multiple pigment drawing areas, pigment drawing area data, and pigment chromaticity value data, dividing the stone color pigment sample data for training the stone color pigment chromaticity value prediction model into a stone color pigment sample training set and a stone color pigment sample test set, constructing a first regression network model, using the stone color pigment type data, pigment concentration data of each stone color pigment in multiple pigment drawing areas, and pigment drawing area data in the stone color pigment training set as inputs of the first regression network model, using the pigment chromaticity value data of each stone color pigment in multiple pigment drawing areas in the stone color pigment training set as outputs of the first regression network model, training the first regression network model to obtain a first initial regression network model; evaluating the model effect of the first initial regression network model using an average error algorithm, and selecting a corresponding first initial regression network model having a value greater than or equal to a preset first evaluation value as a stone color pigment chromaticity value prediction model; S23, obtaining water-color pigment sample data from historical traditional art paintings for training a water-color pigment chromaticity value prediction model, wherein the water-color pigment sample data includes water-color pigment type data, pigment concentration data of each water-color pigment in multiple pigment drawing areas, pigment drawing area data, and pigment chromaticity value data; dividing the water-color pigment sample data for training the water-color pigment chromaticity value prediction model into a water-color pigment sample training set and a water-color pigment sample test set; constructing a second regression network model; using the water-color pigment type data, pigment concentration data of each water-color pigment in multiple pigment drawing areas, and pigment drawing area data in the water-color pigment training set as inputs of the second regression network model; using the pigment chromaticity value data of each water-color pigment in multiple pigment drawing areas in the water-color pigment training set as outputs of the second regression network model; training the second regression network model to obtain a second initial regression network model; evaluating the model effect of the second initial regression network model using an average error algorithm, and selecting a corresponding second initial regression network model that is greater than or equal to a preset second evaluation value as the water-color pigment chromaticity value prediction model; S24, using the pigment concentration data and pigment drawing area data of the i-th stone color pigment in the j-th pigment drawing area in the traditional art painting as the input of the stone color pigment chromaticity value prediction model, and obtaining the pigment chromaticity value data of the i-th stone color pigment in the j-th pigment drawing area predicted by the stone color pigment chromaticity value prediction model; S25, using the pigment concentration data and pigment drawing area data of the qth water color pigment in the jth pigment drawing area in the traditional art painting as the input of the water color pigment chromaticity value prediction model, and obtaining the pigment chromaticity value data of the qth water color pigment in the jth pigment drawing area predicted by the water color pigment chromaticity value prediction model; The step S2 also includes the following specific steps: S26, obtaining the predicted pigment chromaticity value data of all stone color pigments in all pigment drawing areas and the predicted pigment chromaticity value data of all water color pigments in all pigment drawing areas; S27, substituting the pigment chromaticity value data of all stone color pigments in all pigment drawing areas and the predicted pigment chromaticity value data of all water color pigments in all pigment drawing areas into the painting effect contrast coefficient calculation formula to calculate the painting effect contrast coefficient of the j-th pigment drawing area in the traditional art painting, the painting effect contrast coefficient calculation formula is: ； In the formula It represents the contrast coefficient of the painting effect of the jth pigment painting area in traditional art paintings. The pigment drawing area data for the i-th stone color pigment in the j-th pigment drawing area, The pigment chromaticity value data of the i-th stone pigment in the j-th pigment drawing area, The pigment drawing area data for the qth water color pigment in the jth pigment drawing area, is the pigment chromaticity value data of the qth water color pigment in the jth pigment drawing area, S is the area of ​​the jth pigment drawing area, i is any item from 1 to n, q is any item from 1 to m, n is the number of stone color pigments, m is the number of water color pigments, and ln() is a natural logarithm function; The step S3 specifically includes: S31, obtaining 3D painting image data of the traditional fine art painting after 3D content conversion, wherein the 3D painting image data includes color data in all stone color pigment sub-regions corresponding to all types of stone color pigments and color data in all water color pigment sub-regions corresponding to all types of water color pigments in the 3D painting image regions corresponding to the pigment drawing regions one by one; S32, substituting the color data in the stone color pigment sub-area and the color data in the water color pigment sub-area into the 3D painting image effect contrast coefficient calculation formula to calculate the 3D painting image effect contrast coefficient of the 3D painting image area corresponding to the j-th pigment drawing area in the 3D painting image; the 3D painting image effect contrast coefficient calculation formula is: ； In the formula represents the 3D painting image effect contrast coefficient of the 3D painting image area corresponding to the j-th pigment painting area in the 3D painting image, respectively represent the red component, green component, and blue component in the color data of the stone color pigment sub-region corresponding to the i-th stone color pigment in the 3D painting image region corresponding to the j-th pigment drawing region, They respectively represent the red component, green component, and blue component in the color data of the watercolor pigment sub-region corresponding to the qth watercolor pigment in the 3D painting image region corresponding to the jth pigment drawing region.

2. The method for converting traditional fine art to 3D content based on artificial intelligence according to claim 1, characterized in that: The specific steps of step S4 are: S41, obtaining the calculated painting effect contrast coefficients of all pigment drawing areas in the traditional fine art painting and the 3D painting image effect contrast coefficients of the 3D painting image areas corresponding to all pigment drawing areas in the 3D painting image; S42, substituting the painting effect contrast coefficient and the 3D painting image effect contrast coefficient into the 3D content conversion effect difference coefficient calculation formula to calculate the 3D content conversion effect difference coefficient of the j-th pigment drawing area in the traditional art painting, the 3D content conversion effect difference coefficient calculation formula is: ； In the formula It represents the difference coefficient of 3D content conversion effect of the j-th pigment drawing area in the traditional art painting, and Q is the number of pigment drawing areas.

3. The method for converting traditional fine arts to 3D content based on artificial intelligence according to claim 2, characterized in that: The step S5 comprises the following specific steps: S51, obtaining the calculated 3D content conversion effect difference coefficients of all pigment drawing areas in the traditional art painting; S52, presetting a 3D content conversion effect difference threshold, when the 3D content conversion effect difference coefficient of the ith pigment drawing area in the traditional art painting is less than the 3D content conversion effect difference threshold, not performing a content re-conversion operation of the ith pigment drawing area in the traditional art painting; when the 3D content conversion effect difference coefficient of the ith pigment drawing area in the traditional art painting is greater than or equal to the 3D content conversion effect difference threshold, issuing an instruction to the operator to perform a content re-conversion operation of the ith pigment drawing area in the traditional art painting.

4. A traditional art 3D content conversion system based on artificial intelligence, which is implemented based on the traditional art 3D content conversion method based on artificial intelligence according to any one of claims 1 to 3, characterized in that: The system comprises: A data acquisition module, used to acquire data on the types of pigments used in traditional fine art paintings and pigment drawing data, and to acquire 3D painting image data of the traditional fine art paintings after 3D content conversion; A painting effect analysis module is used to import pigment type data and pigment drawing data into a painting effect analysis model to analyze the painting effects of traditional art paintings; A 3D painting image effect analysis module, used to import the 3D painting image data of the traditional fine art painting after the 3D content conversion into the 3D painting effect analysis model, and analyze the effect of the 3D painting image of the traditional fine art painting after the 3D content conversion; A 3D content conversion effect analysis module, used to analyze the 3D content conversion effect of traditional fine art paintings based on the painting effect analysis results of traditional fine art paintings and the effect analysis results of 3D painting images; A re-conversion execution module is used to re-convert the 3D content of the traditional art painting works according to the 3D content conversion effect analysis result; A control module is used to control the operation of the data acquisition module, the painting effect analysis module, the 3D painting image effect analysis module, the 3D content conversion effect analysis module and the re-conversion execution module.

5. An electronic device comprising: A processor and a memory, wherein the memory stores a computer program that can be called by the processor; characterized in that the processor executes the traditional art 3D content conversion method based on artificial intelligence as described in any one of claims 1-3 by calling the computer program stored in the memory.

6. A computer-readable storage medium, characterized in that: Instructions are stored, and when the instructions are executed on a computer, the computer executes the traditional art 3D content conversion method based on artificial intelligence as described in any one of claims 1-3.

Images