Integrated template generation method fusing pattern characteristics and garment structure

Abstract

The invention provides an integrated template generation method fusing pattern features and a garment structure, and belongs to the technical field of garment customization. Establishing a parameterized loose body model, extracting curvature-perceived plane pattern feature points, and constructing mapping between the plane pattern and the loose body model; according to the style drawing of the to-be-generated garment, garment structure lines are drawn on the loose human body model, the curvature of the loose human body model is calculated, curvature distribution lines are obtained, and curved surface segmentation lines of the loose human body model are determined by integrating the garment structure lines and the curvature distribution lines; and flattening the segmented curved surface, constructing constraint conditions of pattern features and garment structure boundaries, and optimizing flattening of the segmented curved surface to obtain a garment template. According to the method, the integrated process design from a plane pattern and a clothing structure to a two-dimensional template is realized.

Description

Technical Field

[0001] The present application relates to an integrated sample generation method that combines flower pattern features and clothing structure, belonging to the technical field of clothing customization. Background Technique

[0002] With the growth of the demand for personalized and refined clothing, digital clothing sample generation technology has become an important research direction in the textile and clothing field. In the traditional clothing design process, the flower pattern design and clothing structure design adopt a separate mode: the flat flower pattern designer creates based on two-dimensional patterns, and then the pattern maker adapts the flower pattern to the clothing sample according to experience. On the one hand, this mode ignores the human body form, overly relies on empirical judgment, and it is difficult to accurately establish the correspondence between flower pattern features and clothing samples, resulting in a relatively high trial-and-error cost; on the other hand, there is a lack of collaborative optimization in the process of flower pattern design and clothing structure design, leading to deviation in flower pattern positioning and poor shape retention of the sample.

[0003] Among them, CN 115034954 A discloses a three-dimensional clothing design and pattern-making system and method, which solves the problem of matching the clothing pattern with the three-dimensional form by directly drawing the clothing pattern on the three-dimensional form and converting it into a two-dimensional clothing pattern structure, but does not consider the generation rule from the flower pattern to the sample; CN 112365584 A discloses a method for generating a printing effect on a three-dimensional clothing model, which is simulated based on UV coordinates and three-dimensional clothing information to achieve a real clothing printing effect on the three-dimensional clothing model, belonging to a three-dimensional visual effect, and does not consider the two-dimensional clothing sample for production. Summary of the Invention

[0004] In view of this, the present application provides an integrated sample generation method that combines flower pattern features and clothing structure, realizing an integrated process design from flat flower patterns, clothing structures to two-dimensional samples.

[0005] Specifically, the present application is implemented through the following solutions:

[0006] An integrated sample generation method that combines flower pattern features and clothing structure, the steps are as follows:

[0007] Step 1, establish a parametric ease human body model, extract the curvature-aware flat flower pattern feature points, and construct the mapping between the flat flower pattern and the ease human body model;

[0008] Step 2, according to the style drawing of the clothing to be generated, draw the clothing structure line on the ease human body model, calculate the curvature of the ease human body model, and obtain the curvature distribution line. Combine the clothing structure line and the curvature distribution line to determine the surface segmentation line of the ease human body model;

[0009] Step three: flatten the segmented surface, construct the constraints of the pattern features and the clothing structure boundary, optimize the segmented surface flattening, and obtain the clothing sample.

[0010] Furthermore, as a preference:

[0011] In step one,

[0012] By [TC] 2 Scan the target human body to obtain dimensional data, add the looseness value of each part, and establish a parameterized looseness human body model. More preferably, the dimensional data includes chest circumference, underbust circumference, waist circumference, hip circumference, and neck circumference.

[0013] The looseness value includes chest looseness value, waist looseness value and hip looseness value, which are set in three levels:

[0014] (1) Tight fit: bust looseness value BL is 0-10 cm, waist looseness value WL is BL-(12-18) cm, and hip looseness value HL is BL-(0-10) cm;

[0015] (2) Fit: The chest circumference looseness value BL is 10-15 cm, the waist circumference looseness value WL is BL-(6-12) cm, and the hip circumference looseness value HL is BL+(0-2) cm;

[0016] (3) Loose: The chest looseness value BL is 15 to 20 cm, the waist looseness value WL is BL-(0 to 6) cm, and the hip looseness value HL is BL+(3 to 10) cm.

[0017] The pattern feature points include the positioning point p′ and the pattern value point p i The positioning point p′ is determined by solving the center point of the plane pattern using the minimum circumscribed rectangle method; the pattern value point p i The perception points with larger curvature are extracted by initially mapping the pattern positions on the loose human body model.

[0018] The mapping satisfies:

[0019] (x, y) is the coordinate of the plane pattern feature point; a1, a2, a3 define the affine transformation; U(r) is the basis function that controls the smoothness; w i is the weight, ||(x, y)-p i || is the Euclidean distance from the feature point to the target point.

[0020] In step 2,

[0021] There are three types of surface split lines:

[0022] (1) Clothing outer contour line: directly used as the dividing line;

[0023] (2) Inner structure lines of the garment: Treat them approximately as the outer contour lines, and divide the complete garment piece containing the inner structure lines into two independent parts. Vertically extend the upper and lower vertices of the vertical structure lines in the vertical direction until they intersect with the outer contour line of the garment, and horizontally extend the left and right vertices of the horizontal structure lines in the horizontal direction until they intersect with the outer contour line of the garment;

[0024] (3) Curvature distribution lines: Calculate the Gaussian curvature values of the ease human body model, and add lines penetrating the outer contour line of the garment in areas with larger curvatures.

[0025] In step three,

[0026] The method for optimizing the flattening of the divided surface is as follows:

[0027] S1. Establish a surface flattening function: Through least squares conformal mapping, introduce complex numbers for conformal mapping. In the mapping, the surface flattening function C(T) satisfies:

[0028] C(T k ) is the conformal energy of the k-th triangular patch, is the gradient value of the triangular patch, is the area of the k-th triangular patch;

[0029] S2. Construct the constraint conditions for the pattern features and the garment structure boundary: Each local coordinate on the three-dimensional model of the to-be-formed garment is represented as χ = x + i y , and the local coordinate of the two-dimensional pattern is represented as U = u + i v , and the point N k on the garment dividing line is decomposed into two points U k1 and U k2 on the two-dimensional pattern during the flattening process. For such boundary points, set two constraint conditions: 1) Constrain the distance between the two flattened points to be the smallest in the two-dimensional space coordinate system; 2) Constrain the triangular patches on the boundary line to maintain the same triangle side lengths in the three-dimensional and two-dimensional spaces, so as to ensure continuous mapping at the boundary. Thus, the dividing line boundary constraint C b and the pattern feature point constraint C p satisfy:

[0030] n b is the number of dividing line boundary points, m b is the number of triangular patches at the boundary, and w1, w2 are weight coefficients;

[0031] n p is the number of pattern feature points, U f * is the ideal position of the feature point, m pis the number of triangular patches corresponding to feature points, θ are the three interior angles of the triangular patches on the 3D model, are the three interior angles of the triangular patches on the 2D template, w3 and w4 are weight coefficients;

[0032] S3, optimize the flattening of the segmented surface: generate a 2D template by minimizing the energy function, and the minimized energy function minC satisfies:

[0033] min C = C(T) + λ1C b + λ2C p where λ1 and λ2 are weight coefficients used to balance different types of constraints.

[0034] In the process of segmenting the surface, the modeling lines are approximated as multiple shortest surface distances through the piecewise idea for segmentation.

[0035] In the process of flattening, the 3D boundary points are decomposed into two planar points, adding two constraint conditions of the shortest distance between the bisecting points and the same corresponding side lengths to ensure consistent dimensions and continuous mapping at the boundary; for the conformability of the 3D pattern, initial position optimization and angle constraints are added.

[0036] The above solution realizes the flexible change of the planar pattern to adapt to the three-dimensional human form by constructing the mapping relationship between the planar pattern feature points and the slack human body model. The curvature of the clothing structure and the slack human body model are fused to determine the surface segmentation, and the 3D clothing pieces with the pattern dressing effect are obtained. With the pattern features and clothing structure as constraints, the least squares conformal flattening function is optimized to ensure the pattern integrity and conformability during the generation of the clothing template. The present invention is based on the UV coordinate transformation and realizes the integrated process design from the planar pattern, clothing structure to the 2D template through digital technology. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] To more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings required for use in the embodiments or the description of the prior art. Obviously, the following drawings are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0038] Figure 1 is the schematic diagram of the generation process of the present application;

[0039] Figure 2 is the schematic diagram of the mapping relationship between the planar pattern and the slack human body model in the present application;

[0040] Figure 3 is the schematic diagram of the segmentation line of the slack human body model in the present application;

[0041] Figure 4The generation of 2D garment patterns based on pattern features and garment structure constraints in this application. Detailed implementation manners

[0042] In order to make the technical problems, technical solutions and beneficial effects to be solved by this application more clear and understandable, the technical solutions in the embodiments of this application will be further described in detail below with reference to the accompanying drawings in the embodiments of this application. It should be understood that the specific embodiments described herein are only used to explain this application and are not used to limit the technical solutions of this application. Based on the embodiments in this application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of this application.

[0043] It should be noted that when a component is referred to as "fixed to" or "disposed on" another component, it can be directly or indirectly located on the other component. When a component is referred to as "connected to" another component, it can be directly or indirectly connected to the other component. The orientations or positions indicated by the terms "upper", "lower", "left", "right", "front", "rear", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc. are based on the orientations or positions shown in the accompanying drawings, and are only for the convenience of description and cannot be construed as limitations on the technical solutions of this application.

[0044] In addition, the terms "first" and "second" are only used for the purpose of convenient description and cannot be construed as indicating or implying relative importance or implicitly specifying the quantity of technical features. The meaning of "a plurality" is two or more unless otherwise specifically defined.

[0045] This embodiment provides an integrated pattern generation method that combines pattern features and garment structures. The embodiments of this application will be described below with reference to the accompanying drawings.

[0046] Refer to Figure 1 , Figure 1 which shows the schematic diagram of the generation process of this embodiment. The integrated pattern generation method that combines pattern features and garment structures includes the following steps:

[0047] Step 1, construct the mapping relationship between the planar pattern feature points and the loose-fit human body model.

[0048] (1) Establish a loose-fit human body model:

[0049] By using [TC] 2 scan the target human body, input the obtained dimension data into the parametric human body model, establish a three-dimensional human body model that is consistent with the shape and size of the target human body, and according to the garment pattern making rules, pre-add looseness at the corresponding parts to establish a parametric loose-fit human body model

[0050] Table 1: Ease Allowance Values for Corresponding Parts of the Eased Human Body Model (cm)

[0051] Clothing ease Bust line (BL) Waist line (WL) Hip line (HL) Fitted 0～10 BL - (12 to 18) BL - (0 to 2) Semi - fitted 10～15 BL - (6 to 12) BL + (0 to 2) Loose 15～20 BL - (0 to 6) BL + (3 to 10)

[0052] (2) Extract pattern feature points:

[0053] The pattern feature points include the pattern mapping and positioning point p′ and the planar pattern value point p of curvature perception i ; The positioning point p′ is determined by solving the center point of the planar pattern through the minimum circumscribed rectangle method, thereby determining the initial mapping position on the eased human body model; The value point p i Extracts the perceptible points with larger curvature at the initial mapped pattern position on the eased human body model to characterize the pattern mapping features and improve the mapping fineness of the pattern from the plane to the eased human body model.

[0054] Positioning point p′: Determine the maximum and minimum values of the x-axis and the maximum and minimum values of the y-axis on the planar pattern, construct the circumscribed rectangle of the pattern, and its center point is the mapping and positioning point. The three-dimensional clothing target point p′ is subjectively determined.

[0055] Value point p i : Preprocess the planar pattern by denoising, edge detection, etc. to improve the detection accuracy. Initialize the mapping of the pattern to the eased human body model through the traditional UV mapping method, calculate the Gaussian curvature value of the pattern mapping grid position, and extract the points with larger curvature as the pattern value points.

[0056] (3) Construct the mapping relationship:

[0057] Construct the planar pattern and the eased human body model mapping relationship φ: Establish the UV scaling rule of the pattern feature points, optimize the pattern mapping position through the thin plate spline transformation method, map the planar pattern to the eased human body model to obtain texture details. And make the pattern flexibly change to adapt to the human body shape, see Figure 2 .

[0058]

[0059] Among them, (x, y) are the coordinates of the planar pattern feature points; a1, a2, a3 define the affine transformation; w i is the weight, U(r) is the basis function, controlling the smoothness, where r is ||(x, y) - p i || is the Euclidean distance from the feature point to the target point.

[0060] Step 2, fuse the surface segmentation of the clothing structure and the eased human body model.

[0061] (1) Draw the clothing structure lines:

[0062] Determine the feature points and feature lines on the loose-fit mannequin according to the garment style drawing, and draw the garment structure lines.

[0063] Taking a vest as an example, according to the given garment style drawing, determine the feature points and feature lines on the loose-fit mannequin, and then draw the garment structure lines. The feature points include the front neck point, side neck point, shoulder point, underarm point, etc.; the feature lines include the chest line, waist line, and hip line, etc.

[0064] (2) Detect the curvature of the loose-fit mannequin:

[0065] For the complex characteristics of the human body shape, it is necessary to calculate the global Gaussian curvature value of the loose-fit mannequin, and add curvature distribution lines that penetrate the garment structure lines in areas with large curvature for subsequent segmentation.

[0066] K = k1 × k2 ………………… (2).

[0067] Where K is the Gaussian curvature, and k1 and k2 are the maximum and minimum principal curvatures of the surface at that point, respectively.

[0068] (3) Construct surface segmentation:

[0069] The three-dimensional surface segmentation line is composed of the fusion of the garment structure line and the curvature distribution line. The three-dimensional garment surface is segmented by comprehensively considering the garment structure line and the curvature distribution line.

[0070] Combined with Figure 3 , the surface segmentation lines are mainly divided into three categories:

[0071] 1) The outer contour line of the garment is the structure line that divides a garment surface into two independent surfaces. Such a structure line can be directly used as a segmentation line, such as Figure 3 the red segmentation line in

[0072] 2) The internal structure line of the garment can be approximately processed as an outer contour line, and the complete piece of clothing containing the internal structure line is divided into two independent parts: the vertical structure line extends its upper and lower vertices vertically to intersect with the outer contour line of the garment, and the horizontal structure line extends its left and right vertices horizontally to intersect with the outer contour line of the garment, such as Figure 3 the green segmentation line in

[0073] 3) The curvature distribution line must penetrate the garment contour line to ensure that the surface can be independently cut, such as Figure 3 the blue segmentation line in

[0074] In the definition of the segmentation line, to meet the requirements of garment pattern making, in the case where two types of segmentation lines are concentrated, the curvature distribution line is discarded and the garment structure line is retained.

[0075] In surface segmentation, calculate the Gaussian curvature value of the ease-fit human body model, and add lines that penetrate the clothing outline in areas with larger curvature. For styling lines that are set for aesthetic purposes and do not conform to the shortest distance on the surface, they can be segmented by the piecewise idea and approximated as multiple shortest surface distances.

[0076] Step 3: Generate a 2D pattern based on the pattern features and clothing structure constraints.

[0077] (1) Establish a surface flattening function:

[0078] Through the least squares conformal mapping (LSCM), introduce complex numbers for conformal mapping, and flatten the ease-fit human body model with pattern information into a 2D pattern. Each local coordinate on the 3D clothing model is represented as χ = x + iy, and the local coordinate of the 2D pattern is represented as U = u + iv. By defining a conformal energy function, as shown in Equation (4), the vertex coordinates of the 2D pattern are obtained by minimizing the energy. During the solution process, the solution of the vertex coordinates is independent of the conjugate part of the complex number to ensure that the mapping is determined only by the regular part and satisfies conformality.

[0079] The surface flattening function C(T) is expressed as:

[0080]

[0081] where C(T k ) is the conformal energy of the kth triangular patch, is the gradient value of the triangular patch, which is a constant. is the area of the kth triangular patch. m is the number of triangular patches.

[0082] (2) Construct the constraint conditions for the pattern features and clothing structure boundaries:

[0083] The point N on the clothing segmentation line k is decomposed into two points U on the 2D pattern during the flattening process k1 and U k2 . For such boundary points, two constraint conditions are set: 1) Constrain the two points after flattening to have the minimum distance in the 2D space coordinate system; 2) Constrain the triangular patches on the boundary line to maintain the same triangle side lengths in the 3D and 2D spaces, so as to ensure continuous mapping at the boundary.

[0084] The conformal energy function, that is, the segmentation line boundary constraint C b is expressed as:

[0085] [[ID=;47]]

[0086] where n b is the number of segmentation line boundary points, m bis the number of triangular patches at the boundary, w1 and w2 are weight coefficients, and L χj -L Uj is the length difference of the segmentation line before and after flattening at the boundary of the triangular patch.

[0087] The pattern feature point P on the ease mannequin i remains as a point U during the flattening process. i The constraint conditions of the pattern feature points are: 1) Constraining the mapped position of the feature points to ensure that the flattened pattern can best restore the three-dimensional shape of the pattern after actual production stitching; 2) Strengthening the angle constraint to minimize the shape preservation of the flattened pattern.

[0088] The energy function is shown in Equation (5), and the minimized energy function min C during flattening is shown in Equation (6).

[0089] The energy function is the pattern feature point constraint C p is expressed as:

[0090]

[0091] where n p is the number of pattern feature points, and U f * is the ideal position of the feature point. m p is the number of triangular patches corresponding to the feature point, θ is the three interior angles of the triangular patch on the three-dimensional model, is the three interior angles of the triangular patch on the two-dimensional pattern, and w3 and w4 are weight coefficients.

[0092] (3) Optimize the energy function and flatten the pattern:

[0093] By adding the segmentation line boundary constraint C b and the pattern feature point constraint C p , construct a surface flattening optimization function. Through numerical solution of the sparse linear equations, the obtained vertex coordinates U are the flattened pattern, and the RGB values of the pixels corresponding to the pattern coordinates are rendered onto the flattened pattern.

[0094] min C = C(t) + λ1C b + λ2C p …………(6).

[0095] where λ1 and λ2 are weight coefficients used to balance different types of constraints. The weight coefficients are adjusted using the cross-validation method. By testing the effects of different weight combinations on the validation set, the best weight configuration is selected.

[0096] Finally, according to the clothing style, splice the curvature segmentation line for surface flattening and the extension line of the internal structure line of the clothing to obtain a two-dimensional pattern for actual clothing production. SeeFigure 4 As shown in the figure. In the figure, U' is the corresponding point of the flower pattern positioning point on the clothing pattern.

[0097] During the flattening process of the curved surface boundary, the three-dimensional boundary points are decomposed into two planar points, and two constraints, namely the shortest distance between the bisection points and the same corresponding side lengths, are added to ensure consistent dimensions and continuous mapping at the boundary; for the conformability of the three-dimensional flower pattern, initial position optimization and angle constraints are added.

[0098] The above-described embodiments only represent several feasible implementation manners of the present invention. The description is relatively specific and detailed, but it should not be construed as a limitation on the scope of the patent of the present invention. The embodiments are not intended to limit the scope of protection in the claims of the present invention. For those of ordinary skill in the art, without departing from the concept of the present invention, several modifications and improvements can still be made. Any equivalent implementation or change made without departing from the present invention should be included in the technology of the present invention.

Claims

1. An integrated sample generation method that combines flower pattern features and clothing structure, characterized in that The steps are as follows: Step 1: Establish a parametric loose-fitting human body model, extract the plane pattern feature points with curvature perception, and construct the mapping between the plane pattern and the loose-fitting human body model; Step 2: According to the style drawing of the garment to be generated, draw the garment structure lines on the loose-fitting human body model, calculate the curvature of the loose-fitting human body model, and obtain the curvature distribution line. Integrate the garment structure line and the curvature distribution line to determine the surface segmentation line of the loose-fitting human body model; Step 3: Flatten the segmented surface, construct the constraint conditions between the pattern features and the garment structure boundary, optimize the flattening of the segmented surface, and obtain the garment pattern.

2. The integrated sample generation method for integrating flower pattern features and clothing structure according to claim 1, characterized in that In Step 1, through [TC] 2 scan the target human body to obtain dimensional data, add the ease values of each part, and establish a parametric ease human body model.

3. The integrated pattern generation method for integrating floral pattern features and clothing structure according to claim 2, wherein The size data includes chest circumference, lower chest circumference, waist circumference, hip circumference, and neck circumference. The loose-fitting values are set in three levels: (1) Tight: The bust ease value BL is 0 - 10 cm, the waist ease value WL is BL - (12 - 18) cm, and the hip ease value HL is BL - (0 - 10) cm; (2) Fitted: The bust ease value BL is 10 - 15 cm, the waist ease value WL is BL - (6 - 12) cm, and the hip ease value HL is BL + (0 - 2) cm; (3) Loose: The bust ease value BL is 15 - 20 cm, the waist ease value WL is BL - (0 - 6) cm, and the hip ease value HL is BL + (3 - 10) cm.

4. A method for generating an integrated template that combines flower pattern features and clothing structure according to claim 1, characterized in that: In Step 1, the flower pattern feature points include a positioning point p' and a profile point p i , and the positioning point p' is determined by solving the center point of the planar flower pattern through the minimum circumscribed rectangle method; Pattern point p i Perceptual points with large curvatures are extracted by initially mapping the pattern positions on the ease mannequin.

5. The integrated pattern generation method combining flower pattern features and clothing structure according to claim 1, characterized in that In Step 1, the mapping satisfies: (x, y) are the coordinates of the characteristic points of the planar pattern; a1, a2, a3 define the affine transformation; w i is the weight; U(r) is the basis function that controls the smoothness, where r is the Euclidean distance from the characteristic point to the target point i ||.

6. The integrated sample generation method for integrating flower pattern features and clothing structure according to claim 1, characterized in that, In Step 2, the surface segmentation lines include three categories: (1) The outer contour line of the garment: directly used as the segmentation line; (2) The internal structure line of the garment: approximately process it as the outer contour line, divide the complete piece of clothing containing the internal structure line into two independent parts. The longitudinal structure line extends its upper and lower vertices vertically to intersect with the outer contour line of the garment, and the transverse structure line extends its left and right vertices horizontally to intersect with the outer contour line of the garment; (3) The curvature distribution line: Calculate the Gaussian curvature value of the loose-fitting human body model, add lines passing through the outer contour line of the garment in the regions with larger curvature. The Gaussian curvature K satisfies: K = k1 × k2, where k1 and k2 are the maximum and minimum principal curvatures of the surface at this point respectively.

7. A method for generating an integrated template that combines floral pattern features and clothing structure according to claim 1, characterized in that, In Step 3, the method for optimizing the flattening of the segmented surface is: S1: Establish a surface flattening function: Through the least squares conformal mapping, introduce complex numbers for conformal mapping. In the mapping, the surface flattening function C(T) satisfies: Let \(m\) be the number of triangular patches, and \(C(T k )\) be the conformal energy of the \(k\)-th triangular patch, be the gradient value of the triangular patch, and \(A_k\) be the area of the \(k\)-th triangular patch; S2. Construct the constraint conditions for the flower pattern features and the clothing structure boundary: Each local coordinate on the three-dimensional model of the to-be-formed clothing is represented as \(x = x+iy\), and the local coordinate of the two-dimensional pattern is represented as \(U = u + iv\). The point \(N\) on the clothing segmentation line k During the flattening process, it is decomposed into two points \(U\) on the two-dimensional pattern k1 and \(U\) k2 For such boundary points, two constraint conditions are set: 1) Constrain the distance between the two flattened points to be the smallest in the two-dimensional space coordinate system; 2) Constrain the triangular patches on the boundary line to maintain the same triangle side lengths in the three-dimensional and two-dimensional spaces, so as to ensure continuous mapping at the boundary. Thus, the segmentation line boundary constraint \(C\) b and the flower pattern feature point constraint \(C\) p are satisfied: n b is the number of boundary points of the dividing line, m b is the number of triangular patches at the boundary, w1 and w2 are weight coefficients, L χj -L Uj is the length difference of the line segment before and after the dividing line is flattened at the boundary of the triangular patch; n p is the number of flower pattern feature points, U f * is the ideal position of the feature point, m p is the number of triangular patches corresponding to the feature point, θ are the three interior angles of the triangular patches on the 3D model, are the three interior angles of the triangular patches on the 2D template, w3, w4 are the weight coefficients; S3: Optimize the flattening of the segmented surface: Generate a two-dimensional pattern by minimizing the energy function. The minimized energy function minC satisfies: min C = C(T) + λ1C b + λ2C p , where λ1 and λ2 are weighting coefficients used to balance different types of constraints.

8. A method for generating an integrated template that combines flower pattern features and clothing structure according to claim 1, characterized in that: During the process of segmenting the surface, the styling lines are segmented by the piecewise idea and approximated as the shortest surface distances in multiple segments for segmentation.

9. The integrated sample generation method for integrating flower pattern features and clothing structure according to claim 1, characterized in that: During the flattening process, the three-dimensional boundary points are decomposed into two planar points, and two constraint conditions of the shortest distance between the bisecting points and the same corresponding side lengths are added to ensure consistent dimensions and continuous mapping at the boundary; For the conformality of the three-dimensional pattern, initial position optimization and angle constraints are added.

Images