Digital Fabric Physical Property Recognition Method and System Based on Graphic Recognition Technology

Abstract

The present invention relates to the field of artificial intelligence technology, and specifically relates to a method and system for identifying the physical properties of digital fabrics based on graphic recognition technology. The method includes: constructing a digital fabric picture library, determining the significance of the influence of each physical property parameter on the fabric appearance, performing corresponding sampling on each physical property parameter based on the influence significance to obtain the sample physical properties of the digital fabric picture; determining the image area of the digital fabric picture, and endowing the digital fabric picture with the image attributes of the image area; constructing a training sample based on the image attributes and sample physical properties of the digital fabric picture, inputting the training sample into a neural network for training to obtain a physical property recognition model of the digital fabric; collecting image data of a real fabric, preprocessing the collected image data, and then inputting it into the physical property recognition model to obtain the physical properties predicted for the real fabric; the present invention can accurately obtain the physical property parameters of the fabric.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and particularly to a method and system for identifying the physical properties of digital fabrics based on graphic recognition technology. Background Art

[0002] Digital fabric is a technology that uses digital technology to simulate the characteristics of real fabrics. It collects basic scientific data of real fabrics, combines various targeted algorithms of computer software, and uses high-performance computing clusters for simulation to achieve high-precision virtual simulation of fabrics. It can simulate the texture properties of fabrics through various fabric image information such as texture maps, normal maps, and displacement maps, and can also simulate the physical properties of fabrics by setting various fabric data information such as the strength, bending strength, density, and thickness of yarns.

[0003] The simulation authenticity of digital fabrics depends to a large extent on the accurate capture and reproduction of physical property information. Virtual simulation of mechanical properties, by simulating the physical properties of real fabrics, such as elasticity, thickness, weight, drape, etc., simulates the behavior of fabrics under states such as stretching, bending, and compression, ensuring that the mechanical response of virtual fabrics is consistent with that of real fabrics and endowing virtual fabrics with realistic physical characteristics.

[0004] In the existing technology, the direct measurement method using professional measuring instruments is usually used to obtain the physical properties of fabrics: using professional fabric physical property measuring instruments, such as the Style3D tensile measuring instrument Style3D SST1000 and the bending strength measuring instrument Style3D SBE1000, to conduct precise physical property tests on fabrics. The measured data can be directly applied in Style3D software to achieve the digitization and virtual simulation of fabrics. Similarly, these data can also be manually input into other virtual simulation software to construct digital fabrics with corresponding physical properties.

[0005] However, this traditional method is time-consuming and costly when dealing with a large number of fabric samples, and it is difficult to meet the identification requirements of high efficiency and high precision. Summary of the Invention

[0006] In order to meet the user's needs for a more personalized and interactive multimedia experience, the present invention proposes a method and system for identifying the physical properties of digital fabrics based on graphic recognition technology, which can accurately obtain the physical property parameters of fabrics without traditional measuring tools.

[0007] To achieve the above object, the present invention provides the following technical solutions:

[0008] On the one hand, an embodiment of the present invention provides a method for identifying the physical properties of digital fabrics based on graphic recognition technology, and the method includes the following steps:

[0009] S100, construct a digital fabric image library, where the digital fabric image library includes multiple digital fabric images, and each digital fabric image is configured with corresponding physical property parameters;

[0010] S200, determine the influence significance of each physical property parameter on the fabric appearance, and based on the influence significance, perform corresponding sampling on each physical property parameter to obtain the sample physical properties of the digital fabric image;

[0011] S300, determine the image area of the digital fabric image, and assign the area, graphic features, and inflection points of the image area as image attributes to the digital fabric image;

[0012] S400, construct a training sample based on the image attributes and sample physical properties of the digital fabric image, and input the training sample into a neural network for training to obtain a physical property recognition model of the digital fabric; wherein, the input data of the training sample is the image attributes of the digital fabric image, and the output data of the training sample is the sample physical properties of the digital fabric image;

[0013] S500, collect image data of a real fabric, and input the collected image data into the physical property recognition model to obtain the predicted physical properties of the real fabric.

[0014] Optionally, in S200, the determining the influence significance of each physical property parameter on the fabric appearance, and based on the influence significance, performing corresponding sampling on each physical property parameter to obtain the sample physical properties of the digital fabric image includes:

[0015] S201, perform a mechanical drapability simulation on the digital fabric to obtain a first draping strength;

[0016] S202, for each physical property parameter, reduce or increase the physical property parameter to half of its original value, and perform a mechanical drapability simulation on the digital fabric again to obtain a second draping strength;

[0017] S203, replace the digital fabric, and perform a mechanical drapability simulation on the replaced digital fabric with this physical property parameter to obtain a third draping strength;

[0018] S204, determine the influence significance of this physical property parameter on the mechanical drapability of the digital fabric according to the first draping strength, the second draping strength, and the third draping strength;

[0019] S205. Select physical property parameters with relatively high significance of influence. For the selected physical property parameters, determine the sampling density corresponding to the physical property parameters based on the significance of influence, sample the physical property parameters of the digital fabric based on the sampling density, and use the sampled physical property parameters as the sample physical properties of the digital fabric picture; wherein, the sampling density is positively correlated with the significance of influence.

[0020] Optionally, in S204, the determining the significance of influence of the physical property parameter on the mechanical drapability of the digital fabric according to the first draping strength, the second draping strength, and the third draping strength includes:

[0021] S241. Calculate the difference between the second draping strength and the first draping strength corresponding to each physical property parameter to obtain the property difference of each physical property parameter.

[0022] S242. Calculate the difference between the third draping strength and the first draping strength corresponding to each physical property parameter to obtain the fabric difference of each physical property parameter.

[0023] S243. Determine the significance of influence of each physical property parameter based on the property difference and the fabric difference; wherein, the property difference is positively correlated with the significance of influence, and the fabric difference is negatively correlated with the significance of influence.

[0024] Optionally, the method further includes:

[0025] Perform numerical adjustment on the sampling samples of the digital fabric picture to obtain derivative samples.

[0026] Use the sampling samples and the derivative samples as the sample physical properties of the digital fabric picture.

[0027] Optionally, in S300, the determining the image area of the digital fabric picture and endowing the area, graphic features, and inflection points of the image area as image attributes to the digital fabric picture includes:

[0028] S310. Adjust the size of the digital fabric picture to the target size, determine the outer contour of the adjusted digital fabric picture, and generate a vector graph of the image area within the outer contour.

[0029] S320. Establish a plane coordinate system with the center of the image area as the coordinate origin, the horizontal direction as the X-axis, and the vertical direction as the Y-axis.

[0030] S330. In the plane coordinate system, determine the coordinates of each curve point on the outer contour line, start from the curve point with the smallest X-axis coordinate in the first quadrant, and number each curve point in the clockwise direction along the outer contour line in the vector graph.

[0031] S340, calculate and summarize the slopes of line segments between adjacent curve points, and generate a curvature data table for each curve point based on the slopes of the line segments;

[0032] S350, generate a curvature change graph according to the curvature data table, where the X-axis in the curvature change graph is the length of the outer contour, and the Y-axis is the curvature of the curvature points;

[0033] S360, determine the graphic features and inflection points of the curvature change graph: wherein, the graphic features include the number of wrinkles, the depth of convex wrinkles, the depth of concave wrinkles, the width of convex wrinkles, and the width of concave wrinkles;

[0034] S370, assign the area of the image region, the graphic features and inflection points of the curvature change graph as image attributes to the digital fabric picture.

[0035] Optionally, in S400, the training samples are constructed based on the image attributes and sample physical attributes of the digital fabric picture, and the training samples are input into a neural network for training to obtain a physical attribute recognition model for digital fabrics, including:

[0036] S410, divide each sample physical attribute into multiple descending-ordered grades according to the order of influence significance from large to small, and determine the digital fabric pictures corresponding to the sample physical attributes of each grade,

[0037] S420, for each grade, obtain the sample physical attributes and image attributes of the digital fabric pictures in this grade as training samples,

[0038] S430, input the training samples of each grade into the neural network for training in turn, and establish the mapping relationship between each sample physical attribute and the corresponding image attribute in sequence to obtain a physical attribute recognition model for digital fabrics.

[0039] On the other hand, an embodiment of the present invention provides a digital fabric physical attribute recognition system based on graphic recognition technology, including:

[0040] At least one processor;

[0041] At least one memory for storing at least one program;

[0042] When the at least one program is executed by the at least one processor, the at least one processor implements the above method.

[0043] The beneficial effects of the present invention are as follows: The present invention discloses a method and system for identifying the physical properties of digital fabrics based on graphic recognition technology. By constructing a digital fabric picture library, the significance of the influence of each physical property parameter on the fabric appearance is determined, and corresponding sampling is performed on each physical property parameter based on the influence significance to obtain the sample physical properties of the digital fabric pictures; accurate identification of the fabric physical properties can be achieved, improving the efficiency and accuracy of fabric design. By determining the image area of the digital fabric pictures, the area, graphic features, and inflection points of the image area are used as image attributes and assigned to the digital fabric pictures; based on the image attributes and sample physical properties of the digital fabric pictures, training samples are constructed, and the training samples are input into a neural network for training to obtain a physical property recognition model of the digital fabric; by training the neural network, the association between the fabric image attributes and physical properties is automatically established, greatly improving the recognition efficiency. The present invention can accurately obtain the physical property parameters of the fabric without the need for traditional measurement tools. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required in the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention, and those of ordinary skill in the art can obtain other drawings without creative efforts based on these drawings.

[0045] Figure 1 It is a schematic flowchart of a method for identifying the physical properties of digital fabrics based on graphic recognition technology according to an embodiment of the present invention;

[0046] Figure 2 It is a top view of the fabric in an embodiment of the present invention;

[0047] Figure 3 It is an effect diagram showing the influence of different strengths on the draping strength in an embodiment of the present invention;

[0048] Figure 4 It is an effect diagram showing the influence of different bending strengths on the draping strength in an embodiment of the present invention;

[0049] Figure 5 It is a bar chart showing the numerical distribution of the bending strength in an embodiment of the present invention;

[0050] Figure 6 It is a line chart showing the numerical distribution of the bending strength in an embodiment of the present invention;

[0051] Figure 7 It is a bar chart showing the numerical distribution of the strength in an embodiment of the present invention;

[0052] Figure 8 It is a line chart showing the numerical distribution of the strength in an embodiment of the present invention;

[0053] Figure 9 It is a schematic diagram of the plane coordinate system in the embodiment of the present invention;

[0054] Figure 10 It is a scatter plot of the line segment slopes between adjacent two curve points in the embodiment of the present invention;

[0055] Figure 11 is Figure 10 a schematic diagram of the graphic features in

[0056] Figure 12 It is a schematic structural diagram of a digital fabric physical property recognition system based on graphic recognition technology in the embodiment of the present invention. Detailed implementation manners

[0057] The following will clearly and completely describe the concept, specific structure and technical effects generated by the present invention in combination with the embodiments and the drawings, so as to fully understand the purpose, solution and effects of the present invention. It should be noted that, without conflict, the embodiments in the present application and the features in the embodiments can be combined with each other.

[0058] The present invention proposes a method and system for recognizing the physical properties of digital fabrics based on graphic recognition technology. This method is based on artificial intelligence graphic recognition technology and can accurately obtain the physical property parameters of fabrics without traditional measuring tools.

[0059] Refer to Figure 1 , as Figure 1 shown is a method for recognizing the physical properties of digital fabrics based on graphic recognition technology provided by the embodiment of the present invention. The method includes the following steps:

[0060] S100. Construct a digital fabric picture library, where the digital fabric picture library includes multiple digital fabric pictures, and each digital fabric picture is configured with corresponding physical property parameters;

[0061] S200. Determine the influence significance of each physical property parameter on the fabric appearance, and perform corresponding sampling on each physical property parameter based on the influence significance to obtain the sample physical properties of the digital fabric pictures;

[0062] S300. Determine the image area of the digital fabric picture, and assign the area, graphic features and inflection points of the image area as image attributes to the digital fabric picture;

[0063] S400. Construct training samples based on the image attributes and sample physical attributes of the digital fabric pictures, and input the training samples into a neural network for training to obtain a physical attribute recognition model for digital fabrics. Among them, the input data of the training samples is the image attributes of the digital fabric pictures, and the output data of the training samples is the sample physical attributes of the digital fabric pictures.

[0064] S500. Collect image data of real fabrics, preprocess the collected image data, and then input it into the physical attribute recognition model to obtain the predicted physical attributes of the real fabrics.

[0065] Specifically, construct a database containing digital fabric pictures. Each fabric graphic has a size of a circle with a radius of 13 cm and is placed at the center of a circular tabletop with a radius of 8 cm and a height of 30 cm.

[0066] By setting a virtual camera 20 cm above the top, obtain the top views of the fabrics respectively. As Figure 2 shown. Each digital fabric picture is equipped with corresponding physical attribute parameters, including warp, weft, diagonal strength, bending strength, deformation rate, and deformation strength.

[0067] As shown in the following table;

[0068]

[0069]

[0070] In some embodiments, in S200, to determine the significance of the influence of each physical attribute parameter on the appearance of the fabric, and based on the significance of the influence, perform corresponding sampling on each physical attribute parameter to obtain the sample physical attributes of the digital fabric pictures, including:

[0071] S201. Simulate the mechanical drapability of the digital fabric to obtain the first draping strength.

[0072] S202. For each physical attribute parameter, reduce or increase this physical attribute parameter to half of its original value, and then simulate the mechanical drapability of the digital fabric again to obtain the second draping strength.

[0073] S203. Replace the digital fabric, and use this physical attribute parameter to simulate the mechanical drapability of the replaced digital fabric to obtain the third draping strength.

[0074] S204. Determine the significance of the influence of this physical attribute parameter on the mechanical drapability of the digital fabric according to the first draping strength, the second draping strength, and the third draping strength.

[0075] S205. Select physical property parameters with relatively high influence significance. For the selected physical property parameters, determine the sampling density corresponding to the physical property parameters based on the influence significance, sample the physical property parameters of the digital fabric based on the sampling density, and use the sampled physical property parameters as the sample physical properties of the digital fabric picture; wherein, the sampling density is positively correlated with the influence significance.

[0076] In this embodiment, after determining the influence significance of each physical property parameter on the mechanical drapability of the digital fabric, physical properties with relatively high influence significance can be determined for targeted sampling.

[0077] In some embodiments, in S204, the determining the influence significance of the physical property parameter on the mechanical drapability of the digital fabric according to the first draping strength, the second draping strength, and the third draping strength includes:

[0078] S241. Calculate the difference between the second draping strength and the first draping strength corresponding to each physical property parameter to obtain the property difference of each physical property parameter.

[0079] S242. Calculate the difference between the third draping strength and the first draping strength corresponding to each physical property parameter to obtain the fabric difference of each physical property parameter.

[0080] S243. Determine the influence significance of each physical property parameter based on the property difference and the fabric difference; wherein, the property difference is positively correlated with the influence significance, and the fabric difference is negatively correlated with the influence significance.

[0081] Specifically, to accurately quantify the influence of fabric physical property parameters on the appearance performance, a series of experimental evaluations were carried out. Through these experiments, we were able to determine the specific influence degree of each physical property parameter on the fabric appearance, and thus provided the necessary data basis for constructing the digital fabric database. The experimental steps are as follows:

[0082] (1) Initial experiment: First, simulate the mechanical drapability of digital denim fabric and record its draping characteristics.

[0083] (2) Physical property parameter adjustment: Then, reduce or increase a certain type of physical property parameter of the denim fabric to twice or half of the original value, and perform the mechanical drapability simulation again to observe the draping change.

[0084] (3) Material replacement: Then, replace it with poplin fabric, adjust its this type of physical property parameter to match the original strength of the denim fabric, and perform the mechanical drapability simulation.

[0085] Result comparison: Finally, by comparing the simulation results of the three groups, analyze the specific influence of a certain type of physical property parameter on the mechanical drapability of the digital fabric.

[0086] The specific operation process of conducting experiments on various physical property parameters is as follows:

[0087] 1. Strength: It includes four physical property parameters: weft strength, warp strength, diagonal tension (right), and diagonal tension (left). Generally, these four physical property parameters will increase synchronously to represent the physical property of the fabric being stiff and inelastic.

[0088] Conclusion: The experimental results show that for the same type of fabric, an increase in strength will lead to a corresponding increase in the draping strength. However, due to the differences in their physical property parameters, different fabrics will exhibit differences in their draping strengths even when they have the same strength. This indicates that the mechanical draping strength is not solely determined by strength, but is the result of the combined action of multiple physical property parameters. Among these physical property parameters, strength has a relatively significant impact on the draping strength.

[0089] 2. Bending strength: It includes bending strength - weft, bending strength - warp, bending strength - diagonal (right), and bending strength - diagonal (left), which represent the stiffness degree and the ease of bending of the fabric.

[0090] Conclusion: The experimental results show that for the same type of fabric, a decrease in bending strength will lead to a very significant increase in the draping strength. Different fabrics with the same bending strength will exhibit differences in their draping strengths, but the differences are not very obvious. This indicates that among these physical property parameters, bending strength has the most significant impact on the draping strength.

[0091] 3. Deformation rate: It includes deformation rate - weft, deformation rate - warp, deformation rate - diagonal (right), and deformation rate - diagonal (left), which represents the ratio of the elongation or shortening of the warp when the fabric is longitudinally stretched or compressed.

[0092] Conclusion: The experimental results show that for the same type of fabric, doubling the deformation rate will not lead to a very significant increase in the draping strength. Different fabrics with the same deformation rate will exhibit relatively large differences in their draping strengths. This indicates that among these physical property parameters, the deformation rate has an insignificant impact on the draping strength.

[0093] 4. Deformation strength: It includes deformation strength - weft, deformation strength - warp, deformation strength - diagonal (right), and deformation strength - diagonal (left), which represents the physical property parameter of the ease of fabric bending.

[0094] Conclusion: The experimental results show that for the same type of fabric, doubling the deformation strength will lead to an increase in the draping strength. Different fabrics with the same deformation strength will exhibit relatively large differences in their draping strengths. This indicates that among these physical property parameters, the deformation strength has a relatively significant impact on the draping strength.

[0095] Reference Figure 3 and Figure 4 , according to the degree of influence of the physical properties of the fabric on the appearance performance, the influence is divided into three levels: most significant, relatively significant, and insignificant. As shown in the following table:

[0096]

[0097] When collecting pictures, we will implement intensive step difference settings for the most significant physical property parameter (bending strength) to ensure data coverage. On the contrary, for physical property parameters with relatively significant strength, we will adopt relatively loose step difference settings to reduce unnecessary collection workload. Although the influence degree of the deformation strength is considered significant, for most conventional fabrics, its values tend to be consistent. For particularly stiff materials such as stiff interfacing and pearl leather, the values of this physical property parameter may be close to 100. Therefore, we consider the setting of this physical property parameter to be standard and do not take it as an independent variable to participate in step difference setting and picture collection. Similarly, for those physical property parameters with insignificant influence (deformation rate), we will not take them as independent variables into consideration for step difference setting and picture collection. Such a method aims to optimize the collection process, ensure the effective use of resources, and improve the efficiency and quality of data collection. Through permutation and combination, it is determined that 1,188 digital fabric data are required to cover all property classifications.

[0098] The data collection of the physical data of conventional digital fabrics is as shown in the following table:

[0099]

[0100]

[0101] In some embodiments, the method further includes:

[0102] Performing numerical adjustment on the sampling samples of the digital fabric pictures to obtain derivative samples;

[0103] Taking the sampling samples and derivative samples as the sample physical properties of the digital fabric pictures.

[0104] Specifically, collecting pictures of 63 commonly used digital fabrics to obtain multiple jpg format pictures:

[0105] 1. Obtaining sampling samples for bending strength: When analyzing the bending strength of fabrics, we considered the strength in three directions: weft, warp, and diagonal. The research data shows that the bending strength value of the diagonal is usually between that of the weft and the warp, indicating that it can more comprehensively reflect the overall bending performance of the fabric. Therefore, we selected the bending strength of the diagonal as the main analysis index to ensure the accuracy and representativeness of the evaluation results. When analyzing the numerical distribution of the bending strength, we observed through Figure 5 and Figure 6 that the bending strength of the fabric mainly concentrated in the range of 41 - 55. Fabrics in this range accounted for the highest proportion and had a small numerical variation. Followed by the range of 55 - 69, with the second-highest proportion. There was also a certain proportion of fabrics in the range of 13 - 27, while the range of 27 - 41 was relatively small. As for the fabrics with a bending strength of 97 - 100, due to their extremely stiff characteristics, they are usually used for specific accessories and are not considered in this analysis. Accordingly, we excluded this group of data from the analysis. The number of fabrics with a bending strength value in the range of 30 - 43 was small, and the numerical variation among the fabrics was large, so the adjustment range was large.

[0106] To enrich the sampling samples in the database, we will adjust the bending strength values of the existing 63 commonly used digital fabrics. Through this method, we aim to generate more diverse datasets and corresponding digital fabric images. The specific steps and methods for adjusting the bending strength will be guided by Table 4 shown below. Such a strategy can not only increase the diversity of the database but also provide a broader reference basis for the digital analysis of fabrics.

[0107] Region Adjustment value Derivative samples added to each sampling sample 13-22 ±2，±4 4 30-43 ±3，±6 4 48-69 ±1，±2 4

[0108] Since the bending strength is the most significantly influential physical property parameter, each inherent sampling sample will derive 4 samples. After the above operations, 63 regular sampling samples will each derive 4 derived samples, that is, 63 * 4 = 256 derived samples, and the database will have a total of 315 samples. The bending strength (weft) and the bending strength (warp) will also change by the same numerical value synchronously.

[0109] 2. Obtaining sampling samples for strength: From the same consideration angle as the bending strength, we selected the strength of the diagonal as the main analysis index. As shown in Figure 7 and Figure 8 , fabrics with a diagonal value in the range of 78 - 97 are stiff accessories and are not considered in this analysis. The samples with a diagonal value in the range of 2 - 40 are more concentrated, and the digital variation is small, so the adjustment range is large.

[0110] Region Adjustment value Database samples added to each sample 0-40 ±1 2 44-65 ±2 2

[0111] Since the flexural strength is a significantly influential physical property parameter, each inherent sample will generate 2 samples. After the above operations, 315 regular sampling samples will each generate 2 derivative samples, that is, 315 * 2 = 630 derivative samples are generated, and there are a total of 945 samples in the database.

[0112] In some embodiments, in S300, determining the image area of the digital fabric picture and endowing the digital fabric picture with the area, graphic features, and inflection points of the image area as image attributes includes:

[0113] S310, adjusting the size of the digital fabric picture to a target size, determining the outer contour of the adjusted digital fabric picture, and generating a vector map of the image area within the outer contour;

[0114] S320, taking the center of the image area as the coordinate origin, establishing a plane coordinate system with the horizontal direction as the X-axis and the vertical direction as the Y-axis;

[0115] S330, in the plane coordinate system, determining the coordinates of each curve point on the outer contour line, starting from the curve point with the smallest X-axis coordinate in the first quadrant, and numbering each curve point in the clockwise direction along the outer contour line in the vector map;

[0116] S340, calculating and summarizing the line segment slopes between adjacent two curve points, and generating a curvature data table for each curve point based on the line segment slopes;

[0117] S350, generating a curvature change diagram according to the curvature data table, where the X-axis in the curvature change diagram is the length of the outer contour and the Y-axis is the curvature of the curvature points;

[0118] S360, determining the graphic features and inflection points of the curvature change diagram: Among them, the graphic features include the number of folds, the depth of the protruding folds, the depth of the concave folds, the width of the protruding folds, and the width of the concave folds;

[0119] S370, endowing the digital fabric picture with the area of the image area, the graphic features, and the inflection points of the curvature change diagram as image attributes.

[0120] Specifically, the specific steps of this embodiment are as follows:

[0121] Define the length: Open the digital fabric picture using cad software and enlarge / shrink the picture according to the size of the grid on the picture. The size of the grid during 3D construction is 10CM * 10CM;

[0122] Generating a vector graph: Trace the outer contour of the figure based on the edge of the digital fabric image to generate a vector graph. Since the outer edge of the vector graph is a curve, curve points will be automatically generated according to the degree of curve bending. More curve points are generated for the part of the curve with a smaller radius of curvature, and fewer curve points are generated for the curve with a smaller radius of curvature;

[0123] Obtaining the area: Calculate the total area of the figure according to the vector graph obtained by using CAD software, and assign the area as an attribute to the digital fabric image;

[0124] Establishing coordinates: Draw a circle with a radius of 8 cm (simulating the shape and area of a table) at the center of the figure (the center of the figure automatically defaulted by cad), and define the center of the figure as the origin of coordinates, establish the horizontal direction as the X-axis and the vertical direction as the Y-axis; as Figure 9 shown.

[0125] Defining the coordinates of curve points: In the established coordinate system, first assign coordinates to each point on the curve. Then, sort these points. The starting point of the sorting is the point with the smallest X-axis coordinate in the first quadrant, which is marked as point No. 1. Starting from this starting point, number each point on the outer contour line of the vector graph in a clockwise direction. Such a sorting method ensures that the order of the points matches their physical positions on the figure, thus facilitating further analysis and processing.

[0126] As Figure 10 shown, then calculate and summarize the slope of the line segment between adjacent two curve points to generate a curvature data table for each point.

[0127] Generating a curvature change graph according to the curvature data table: The X-axis is the length of the outer contour, and the Y-axis is the curvature of that point;

[0128] Defining the graphic features and special points of the curvature change graph:

[0129] Defining characteristic points: As Figure 11 shown, an inflection point refers to a specific point where the slope of the function curve changes, specifically manifested as the slope changing from positive to negative or from negative to positive. In mathematics and graphic analysis, inflection points can be divided into two types:

[0130] 1. Inflection point (increasing - decreasing): When the slope of the function changes from increasing to decreasing, this inflection point is usually near the peak of the graph. This means that before this point, the slope of the function is positive (i.e., the function value increases as the independent variable increases), and after this point, the slope becomes negative (i.e., the function value decreases as the independent variable increases).

[0131] 2. Inflection point (decrease - increase): When the slope of a function changes from decreasing to increasing, such an inflection point is usually near the trough of the graph. Before this point, the slope of the function is negative (i.e., the function value decreases as the independent variable increases), and after this point, the slope becomes positive (i.e., the function value increases as the independent variable increases).

[0132] These inflection points are very important in graph analysis because they mark significant changes in the behavior of the function, such as changing from increasing to decreasing or from decreasing to increasing, which is crucial for understanding the overall trend and characteristics of the function.

[0133] Define graph features:

[0134] Number of folds: In the analysis of the function graph, the number of inflection points is closely related to the concavity and convexity characteristics of the graph. Specifically:

[0135] 1. Inflection point (decrease - increase): When the slope of the function graph changes from decreasing to increasing, this inflection point corresponds to a convex fold in the graph. A convex fold refers to a local maximum region where the function graph bends upward at this point.

[0136] 2. Inflection point (increase - decrease): When the slope of the function graph changes from increasing to decreasing, this inflection point corresponds to a concave fold in the graph. A concave fold refers to a local minimum region where the function graph bends downward at this point.

[0137] According to the symmetry of the function graph and the properties of local extrema, the number of convex folds is equal to the number of concave folds. This means that in a continuous and smooth function graph, the number of inflection points (decrease - increase) is equal to the number of convex folds, and the number of inflection points (increase - decrease) is equal to the number of concave folds.

[0138] Depth of convex fold: When analyzing the depth of the convex fold of the function graph, we focus on each inflection point (increase - decrease), which marks the turning point where the function graph changes from an upward trend to a downward trend. To quantify the depth of each convex fold, we select 10 consecutive coordinate points after each inflection point as the research object. Among these 10 points, the point farthest from the origin is defined as the peak point of the convex fold. The depth of the convex fold can be determined by calculating the straight-line distance between the peak point and the origin of the graph, and then subtracting the circular radius of 18 cm.

[0139] Depth of the concave fold: When studying the depth of the concave fold of the function graph, we take each inflection point (decrease - increase) and the 10 coordinate points following it as the analysis object. The inflection point (decrease - increase) marks the turning point where the graph changes from a downward trend to an upward trend. Among these 10 points, the point with the shortest straight-line distance from the origin is identified as the trough point of the concave fold. The depth of the concave fold is calculated by measuring the straight-line distance between the trough point and the origin, and then subtracting the radius of the 18 - centimeter circle from this distance.

[0140] Width of the convex fold: The X - axis distance between two inflection points (increase - decrease) is the width of the peak, that is, the width of the convex fold;

[0141] Width of the concave fold: The X - axis distance between two inflection points (decrease - increase) is the width of the trough, that is, the width of the concave fold.

[0142] In some embodiments, in S400, constructing a training sample based on the image attributes and sample physical attributes of the digital fabric picture, and inputting the training sample into a neural network for training to obtain a physical attribute recognition model of the digital fabric, includes:

[0143] S410, dividing each sample physical attribute into multiple descending - order grades according to the influence significance from large to small, and determining the digital fabric pictures corresponding to the sample physical attributes of each grade,

[0144] S420, for each grade, obtaining the sample physical attribute and image attribute of the digital fabric pictures in this grade as a training sample,

[0145] S430, inputting the training samples of each grade into the neural network for training in sequence. After establishing the mapping relationship between each sample physical attribute and the corresponding image attribute in order, a physical attribute recognition model of the digital fabric is obtained.

[0146] This step is the artificial - intelligence learning stage. Using the graded digital fabric library, train the artificial intelligence to recognize the graphic change rules and the corresponding physical - attribute numerical changes.

[0147] Specifically, since the digital fabrics in the digital fabric library are graded, which means it is not a continuous change, artificial intelligence learning is required to obtain the graphic change rules and the corresponding physical - value changes between two grades;

[0148] Data processing: Perform the above - mentioned graphic processing and data definition on 945 pieces of data; and assign the physical - attribute numerical value corresponding to each picture as an attribute to the graphic (bending strength, strength);

[0149] Arrange the research objects according to the gear positions. First, arrange the factors with the most significant shape influence (bending strength), then arrange the factors with relatively significant shape influence (strength and deformation strength), and finally arrange the factors with insignificant shape influence (deformation rate). Conduct the learning in the artificial intelligence stage in this order.

[0150] First - layer learning:

[0151]

[0152]

[0153] Second - layer learning:

[0154]

[0155] Third - layer learning: Use the same method as above to learn the relationship between the highest convex height of the fold and bending strength, and strength;

[0156] Fourth - layer learning: Use the same method as above to learn the relationship between the lowest concave height of the fold and bending strength, and strength.

[0157] In this embodiment, multiple digital fabric pictures are randomly selected from the digital fabric pictures in each gear to construct a training set. First, identify the area feature of the image, then the wave number feature, then the wave peak value, and finally the wave trough value.

[0158] Virtual verification and training, including graphic recognition training in the database, graphic recognition training outside the database, and real - fabric verification training;

[0159] Graphic recognition training in the database: During the training process of the convolutional neural network (CNN), we randomly selected 100 images from the existing 945 images in the picture library to construct a training set. The training goal is to enable the model to identify and accurately match the image that is exactly the same as the query image. During the training process of the convolutional neural network (CNN), we set a specific recognition order for the model, with the priority in turn: First, identify the area feature of the image, then the wave number feature, then the wave peak value, and finally the wave trough value. Specifically, it includes:

[0160] 1. Area: Locate 10 pictures in the database whose areas are the same as or close to the area of the known graphic;

[0161] 2. Wave number: Match 5 pictures with the same or similar wave number as the known graphic among these 10 pictures;

[0162] 3. Maximum convex fold (wave peak): Find 3 pictures with the same or similar maximum convex fold (wave peak) as the known graphic among the 5 pictures;

[0163] 4. Minimum depression fold (trough): Find two pictures that are the same as or similar to the known picture with the largest convex fold (crest) in three pictures;

[0164] 5. Manual selection: Manually select one picture from the two pictures, and this action serves as the data guidance for the computer's self-learning.

[0165] According to the training results, it can be confirmed that the convolutional neural network (CNN) can accurately perform image recognition according to the established requirements. This indicates that the CNN model has successfully learned the feature representation of the images and can accurately identify the target images in practical applications.

[0166] Graphic recognition training outside the database: To train the convolutional neural network (CNN) for graphic recognition, we first artificially set a series of bending strength values for a series of fabrics and generated 100 new digital fabric pictures based on these values, which have never appeared in the database. Subsequently, we followed a specific recognition step, that is, the graphic recognition training process in the database, to train the CNN model so that it can recognize these new fabric pictures and give the corresponding physical properties. In this way, the results of the neural network learning stage can be verified. If the results are not satisfactory, learn again;

[0167] Real fabric verification training: During the training process, we collected 50 real fabric picture samples, and the physical property parameters of these samples have been obtained through professional measuring instruments. We used the graphic processing method previously used to process digital fabrics to analyze these real fabric pictures, and extracted the area, wave number, maximum convex fold value, and minimum depression fold value of the pictures. Then, we determined the physical property values of the fabrics according to the recognition order in the graphic recognition training outside the database, and found the pictures that were closest to these real fabric pictures from the virtual fabric picture library. Finally, we compared the differences between the physical property values obtained by the image processing method and the values measured by the professional measuring instrument, and evaluated the similarity between the real fabric pictures and the virtual fabric pictures located by the system to verify the effectiveness of the training.

[0168] Usage of this method:

[0169] To simulate real fabrics in a virtual environment and conduct trial fittings of sample garments, we need to obtain the physical properties of the fabrics. For this purpose, we collect image data of the fabrics according to the specified shooting requirements and perform subsequent processing on the collected images. The processed images and their data will be used to extract the physical properties of the fabrics, including their bending strength values. Subsequently, we apply these physical property values to the fabric simulation physical property module in the virtual simulation software to construct a digital version of the fabric and conduct simulation trials to evaluate its performance in virtual sample garments. This process ensures that the physical characteristics of the fabric can be accurately reflected in virtual design.

[0170] Initial completion and continuous optimization of the model:

[0171] After completing the initial model construction, the accuracy of the model and the authenticity of the physical properties of the simulation effect are improved by continuously adding new digital fabric data, such as different shooting angles and size specifications. For example, increasing the shooting angle, increasing the fabric specifications, or changing the display stand, etc.

[0172] Through the above steps, the present invention can not only quickly and accurately obtain the physical properties of digital fabrics, but also provide an efficient and low-cost solution for the fabric design and manufacturing fields.

[0173] Compared with the prior art, the embodiments provided by the present invention have the following improvements:

[0174] A method is proposed to obtain the physical property values required for fabric virtual simulation by comparing the fabric hanging shape pictures with the digital fabric virtual simulation picture database.

[0175] A grading of the influence degree of each physical property parameter on the appearance is proposed in the fabric virtual simulation stage.

[0176] A method for extracting the characteristics of digital fabric pictures is proposed. Area, curvature change, fold depth, fold width.

[0177] A method is proposed to combine artificial intelligence technology with image extraction features to learn the variation law of the influence of the change of each physical property parameter on the appearance.

[0178] Reference Figure 12 , the embodiments of the present invention also provide a digital fabric physical property recognition system based on graphic recognition technology, including:

[0179] At least one processor;

[0180] At least one memory for storing at least one program;

[0181] When the at least one program is executed by the at least one processor, the at least one processor implements the above method.

[0182] The content in the above method embodiments is applicable to this embodiment. The functions specifically implemented in this embodiment are the same as those in the above method embodiments, and the beneficial effects achieved are also the same as those in the above method embodiments, and will not be elaborated here.

[0183] Although the description of the present disclosure has been quite detailed and several of the described embodiments have been described in particular, it is not intended to be limited to any of these details or embodiments or any particular embodiment, but rather should be regarded as effectively covering the intended scope of the present disclosure by reference to the appended claims, considering the prior art to provide a broad interpretation of these claims. In addition, the present disclosure has been described above in terms of embodiments foreseeable by the inventors for the purpose of providing a useful description, and those non-substantive modifications to the present disclosure that are not currently foreseeable may still represent equivalent modifications of the present disclosure.

Claims

1. A method for identifying physical properties of digital fabrics based on pattern recognition technology, characterized in that: The method comprises the following steps: S100, constructing a digital fabric image library, wherein the digital fabric image library includes a plurality of digital fabric images, each of which is configured with corresponding physical property parameters; S200, determining the significance of the influence of each physical property parameter on the appearance of the fabric, and sampling each physical property parameter accordingly based on the significance of the influence to obtain sample physical properties of the digital fabric image; S300, determining an image region of the digital fabric image, and assigning the area, graphic features and inflection points of the image region as image attributes to the digital fabric image; S400, constructing a training sample based on the image attributes and sample physical attributes of the digital fabric image, inputting the training sample into a neural network for training, and obtaining a physical attribute recognition model of the digital fabric; wherein the input data of the training sample is the image attribute of the digital fabric image, and the output data of the training sample is the sample physical attribute of the digital fabric image; S500, collecting image data of real fabrics, inputting the collected image data into a physical property recognition model, and obtaining predicted physical properties of the real fabrics; S200 specifically includes: S201, performing mechanical drape simulation on the digital fabric to obtain a first drape strength; S202, for each physical property parameter, increasing the physical property parameter to one-fold or reducing it to one-half of the original value, and performing mechanical drape simulation on the digital fabric again to obtain a second drape strength; S203, replacing the digital fabric, and using the physical property parameters to perform mechanical drape simulation on the replaced digital fabric to obtain a third drape strength; S204, determining the significance of the influence of the physical property parameter on the mechanical drape of the digital fabric according to the first drape strength, the second drape strength and the third drape strength; S205, selecting physical property parameters with higher impact significance, for the selected physical property parameters, determining the sampling density of the corresponding physical property parameters based on the impact significance, sampling the physical property parameters of the digital fabric based on the sampling density, and using the sampled physical property parameters as sample physical properties of the digital fabric image; wherein the sampling density is positively correlated with the impact significance.

2. According to claim 1, a method for identifying physical properties of digital fabrics based on pattern recognition technology is characterized in that: In S204, determining the significance of the influence of the physical property parameter on the mechanical drape of the digital fabric according to the first drape strength, the second drape strength and the third drape strength includes: S241, performing a difference calculation on the second draping strength and the first draping strength corresponding to each physical property parameter to obtain a property difference of each physical property parameter, S242, performing a difference calculation on the third drape strength and the first drape strength corresponding to each physical property parameter to obtain a fabric difference of each physical property parameter, S243, determining the influence significance of each physical property parameter based on the property difference and the fabric difference; wherein the property difference and the influence significance are positively correlated, and the fabric difference and the influence significance are negatively correlated.

3. The method for identifying physical properties of digital fabrics based on pattern recognition technology according to claim 2, characterized in that: The method further comprises: Performing numerical adjustments on the sampled samples of the digital fabric image to obtain derivative samples; The sampling samples and the derived samples are used as sample physical properties of the digital fabric image.

4. The method for identifying physical properties of digital fabrics based on pattern recognition technology according to claim 1, characterized in that: In S300, determining the image region of the digital fabric image and assigning the area, graphic features and inflection points of the image region as image attributes to the digital fabric image includes: S310, adjusting the size of the digital fabric image to a target size, determining an outer contour of the adjusted digital fabric image, and generating a vector graph of an image area within the outer contour; S320, taking the center of the image area as the coordinate origin, establishing a plane coordinate system with the horizontal direction as the X-axis and the vertical direction as the Y-axis; S330, determining the coordinates of each curve point on the outer contour line in the plane coordinate system, taking the curve point with the smallest X-axis coordinate in the first quadrant as the starting point, and numbering each curve point in a clockwise direction along the outer contour line in the vector diagram; S340, calculating and summarizing the line segment slopes between two adjacent curve points, and generating a curvature data table of each curve point based on the line segment slopes; S350, generating a curvature change graph according to the curvature data table, wherein the X-axis in the curvature change graph is the length of the outer contour, and the Y-axis is the curvature of the curvature point; S360, determining the graphic features and inflection points of the curvature change graph: wherein the graphic features include the number of wrinkles, the depth of convex wrinkles, the depth of concave wrinkles, the width of convex wrinkles, and the width of concave wrinkles; S370: Assign the area of ​​the image region, the graphic features and the inflection points of the curvature change graph as image attributes to the digital fabric image.

5. The method for identifying physical properties of digital fabrics based on pattern recognition technology according to claim 1, characterized in that: In S400, the step of constructing a training sample based on the image attributes of the digital fabric image and the sample physical attributes, and inputting the training sample into a neural network for training to obtain a physical attribute recognition model for the digital fabric includes: S410, dividing the physical properties of each sample into a plurality of levels arranged in descending order according to the order of influence significance from large to small, and determining the digital fabric image corresponding to the physical properties of the sample in each level, S420, for each gear, obtaining sample physical properties and image properties of the digital fabric image in the gear as training samples, S430, inputting the training samples of each gear into the neural network for training in sequence, and establishing the mapping relationship between the physical properties of each sample and the corresponding image properties in sequence, thereby obtaining a physical property recognition model of the digital fabric.

6. A digital fabric physical property recognition system based on pattern recognition technology, characterized in that: include: at least one processor; at least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor implements the method according to any one of claims 1 to 5.

Images