A Multi-Clothing Feature Fusion Method and System

Abstract

The present invention relates to a multi-clothing feature fusion method and system, belonging to the technical field of clothing, and comprising: obtaining a reference clothing image, a reference clothing image, and trigger information; obtaining a marked fusion mode according to the trigger information; when the marked fusion mode is a preset orientation mode, determining a reference clothing contour according to the reference clothing image; determining the clothing color style according to the reference clothing image; determining a fused clothing image according to the reference clothing contour and the clothing color style; when the marked fusion mode is a preset creative mode, determining the reference clothing type according to the reference clothing image; determining the reference clothing features according to the reference clothing image, and determining a creative clothing image according to the reference clothing features and the reference clothing type; outputting the fused clothing image or the creative clothing image to a preset display area. This application has the effect of improving the production efficiency of clothing.

Description

Technical Field

[0001] The present invention relates to the technical field of clothing, and in particular to a multi-clothing feature fusion method and system. Background Art

[0002] Clothing is a general term for fabrics and ornaments that cover the human body, and has both practical functions and cultural connotations.

[0003] In the process of clothing design, designers obtain inspiration by observing nature, society, and culture, studying clothing history and the clothing of different ethnic groups, collecting materials through various channels at the same time, then carrying out design ideas, determining the theme and drawing sketches, clarifying the clothing outline and details, matching colors. Secondly, it is the pattern making. The pattern is designed in combination with ergonomics, and appropriate fabrics and accessories are selected according to the use and style of the clothing for cutting and production. The sewn clothing after production is tried on by models to facilitate subsequent adjustments.

[0004] In the process of clothing design, when manually solving problems such as style conflicts, cultural misunderstandings, and large differences in production processes, fusing clothing features such as the outline, color, and fabric of clothing takes a lot of time and reduces the production efficiency of clothing. Summary of the Invention

[0005] In order to improve the production efficiency of clothing, the present invention provides a multi-clothing feature fusion method and system.

[0006] In the first aspect, the present invention provides a multi-clothing feature fusion method, adopting the following technical solutions:

[0007] A multi-clothing feature fusion method includes:

[0008] Obtaining a reference clothing image, a reference clothing image, and trigger information;

[0009] Obtaining a marked fusion mode according to the trigger information;

[0010] When the marked fusion mode is a preset directional mode, determining a reference clothing outline according to the reference clothing image;

[0011] Determining the clothing color style according to the reference clothing image;

[0012] Determining a fused clothing image according to the reference clothing outline and the clothing color style;

[0013] When the marked fusion mode is a preset creative mode, determining a reference clothing type according to the reference clothing image;

[0014] Determining the reference clothing features according to the reference clothing image, and determining a creative clothing image according to the reference clothing features and the reference clothing type;

[0015] Output the fused clothing image or the creative clothing image to a preset display area.

[0016] By adopting the above technical solution, the fused clothing image or the creative clothing image is obtained by analyzing the reference clothing image and the reference clothing image in the directional mode or the creative mode, and output to the display area, so that clothing can be automatically designed by pictures, reducing the time required for manual design and improving the production efficiency of clothing.

[0017] Optionally, the method for determining the reference clothing contour further includes:

[0018] When the reference clothing image only contains preset line features, determine the line-drawn contour according to the reference clothing image and the line features;

[0019] Determine different numbers of line combination contours according to the line-drawn contour;

[0020] Screen according to the line combination contour and the preset portrait line contour, and use the line combination contour that is not the portrait line contour as the marked combination contour;

[0021] Determine the contour distribution range according to the marked combination contour;

[0022] Determine the line drawing clothing contour according to the contour distribution range and the preset clothing wearing range, and use the line drawing clothing contour as the reference clothing contour.

[0023] By adopting the above technical solution, the line combination contour is obtained by analyzing the lines in the reference clothing image, and the reference clothing contour is obtained by screening the line combination contour according to the portrait line contour and the clothing wearing range, so that the clothing contour can be extracted from the image with only lines.

[0024] Optionally, the method for determining the creative clothing image includes:

[0025] Determine the marked reference clothing according to the reference clothing features and the reference clothing type;

[0026] Input the marked reference clothing into a preset clothing repository to match similar clothing images with various similar features;

[0027] Determine the matching clothing type according to the marked reference clothing;

[0028] Determine the creative clothing features according to the marked reference clothing and the similar clothing images;

[0029] Determine the matching clothing features according to the matching clothing type and the creative clothing features;

[0030] Form a creative clothing image based on the matching clothing features, matching clothing types, creative clothing features, and marked reference clothing.

[0031] By adopting the above technical solution, analyze the marked reference clothing and similar clothing images to obtain the matching clothing type and matching clothing features, and fuse the matching clothing features, matching clothing type, creative clothing features, and marked reference clothing to form a creative clothing image, thereby being able to produce an image of a creative clothing.

[0032] Optionally, the method after outputting to a preset display area includes:

[0033] Obtain the model body information;

[0034] Determine a human model based on the model body information;

[0035] Define the fused clothing image or creative clothing image output to the display area as marked image information;

[0036] Determine the reference contour size based on the marked image information;

[0037] Determine the detected clothing size based on the human model and the reference contour size;

[0038] Determine a clothing model based on the detected clothing size and the marked image information, and output the clothing model to the display area.

[0039] By adopting the above technical solution, analyze the model body information and the marked image information to obtain the detected clothing size, and obtain a clothing model through the detected clothing size and the model body information, and output the clothing model to the display area, thereby facilitating the operator to view the upper body effect of the clothing.

[0040] Optionally, the method after determining the clothing model includes:

[0041] Obtain the clothing wearing scenario;

[0042] Determine a wearing model based on the human model and the clothing model;

[0043] Determine a movement trajectory based on the clothing wearing scenario and the human model, and control the wearing model to perform a simulated movement along the movement trajectory;

[0044] Determine the clothing contraction position based on the movement trajectory and the wearing model;

[0045] Determine the marked detection fabric at the clothing contraction position based on the wearing model, a preset reference fabric, and the movement trajectory;

[0046] Update the wearing model based on the marked detection fabric, and output the updated wearing model to the display area.

[0047] By adopting the above technical solution, through further analysis of the upper body effect of the clothing, when the model wears the clothing and moves along a movement trajectory, the marked detection fabric is obtained and the wearing model is updated by means of the wearing model, the preset reference fabric and the movement trajectory, and then the updated wearing model is output to the display area, so that the clothing can be adjusted in time to reduce the influence of the clothing on the activities of the person.

[0048] Optionally, the method for determining the marked detection fabric includes:

[0049] Determine the detection extension coefficient and the detection stretching distance according to the wearing model, the reference fabric and the movement trajectory;

[0050] Determine the contact pressure value according to the detection extension coefficient and the detection stretching distance;

[0051] When the contact pressure value exceeds the preset reference pressure value, determine the marked pressure value according to the wearing model, the preset detection fabric and the movement trajectory;

[0052] Select the detection fabric with a marked pressure value less than the reference pressure value as the marked detection fabric.

[0053] By adopting the above technical solution, the contact pressure value is obtained by analyzing the wearing model, the reference fabric and the movement trajectory. When the contact pressure value exceeds the preset reference pressure value, the marked detection fabric is selected by means of the wearing model, the preset detection fabric and the movement trajectory, so that the clothing can be adjusted in time to reduce the influence of the restraint of the clothing on the activities of the person.

[0054] Optionally, the method after determining the clothing model further includes:

[0055] When the contact pressure value does not exceed the reference pressure value, determine the detected deformation degree of the clothing contraction position according to the wearing model, the reference fabric and the movement trajectory;

[0056] Determine the total force applied by the movement according to the detected deformation degree;

[0057] Determine the fabric contraction force according to the total force applied by the movement and the contact pressure value;

[0058] Determine the reference friction force according to the reference fabric and the total force applied by the movement;

[0059] Determine the fabric contraction distance according to the reference friction force and the fabric contraction force;

[0060] When the fabric contraction distance exceeds the preset reference retraction distance, determine the target contraction distance according to the wearing model, the preset detection fabric and the movement trajectory;

[0061] Select the detected fabric corresponding to the target contraction distance greater than the reference retraction distance from the target contraction distances as the target detected fabric;

[0062] Update the wearing model based on the target detected fabric.

[0063] By adopting the above technical solution, when the model wears the clothing and moves, analyze the wearing model, the reference fabric, and the movement trajectory to obtain the fabric contraction distance. When the fabric contraction distance exceeds the reference retraction distance, select the target detected fabric through the wearing model, the detected fabric, and the movement trajectory to update the wearing model, so as to be able to timely adjust the fabric of the clothing to reduce the impact on the visual effect of the clothing caused by too long a contraction distance.

[0064] Optionally, the method after updating the wearing model further includes:

[0065] Use the target detected fabric and the marked detected fabric as the adjustment fabrics;

[0066] Determine the adjustment color according to the updated wearing model and the adjustment fabrics;

[0067] Determine the reference ambient light intensity according to the clothing wearing scenario;

[0068] Determine the adjustment gloss according to the reference ambient light intensity, the adjustment color, and the adjustment fabrics;

[0069] Determine the reference gloss according to the reference fabric;

[0070] When the adjustment gloss exceeds the reference gloss, determine the detected gloss according to the adjustment color, the detected fabric, and the reference ambient light intensity;

[0071] Select the detected fabric corresponding to the non-exceeded reference gloss from the detected glosses and define it as the marked adjustment fabric;

[0072] Update the wearing model according to the marked adjustment fabric.

[0073] By adopting the above technical solution, analyze the gloss of the adjustment fabrics. When the adjustment gloss exceeds the reference gloss, it indicates that there is a visual deviation in the effect presented by the clothing. Then, analyze the adjustment color, the detected fabric, and the reference ambient light intensity to select the marked adjustment fabric to update the wearing model, so as to be able to reduce the probability of visual deviation of the clothing when adjusting the fabric of the clothing.

[0074] Optionally, the method after updating the wearing model further includes:

[0075] Determine the gloss gradient part according to the wearing model;

[0076] Determine the gloss change range according to the gloss gradient part and the adjusted glossiness;

[0077] Determine the selection range according to the gloss change range;

[0078] Select the adjusted glossiness that falls within the selection range from the adjusted glossiness as the marked glossiness;

[0079] Determine the continuous fabric according to the marked glossiness;

[0080] Update the wearing model according to the continuous fabric and the gloss gradient part.

[0081] By adopting the above technical solution, by analyzing the situation of gloss gradient and selecting the continuous fabric according to the selection range to adjust the wearing model, the diversity of clothing production can be improved when selecting the fabric of clothing.

[0082] In a second aspect, the present application provides a multi-clothing feature fusion system, adopting the following technical solution:

[0083] A multi-clothing feature fusion system, comprising:

[0084] An acquisition module, configured to acquire a reference clothing image, a reference clothing image, a trigger information, a marked fusion mode, a model body information, and a clothing wearing scenario;

[0085] A memory, configured to store a multi-clothing feature fusion method;

[0086] A processor, configured to load and execute and implement the program stored in the memory.

[0087] In summary, the present application includes at least one of the following beneficial technical effects:

[0088] 1. By analyzing the reference clothing image and the reference clothing image in the orientation mode or the creative mode to obtain a fused clothing image or a creative clothing image, and outputting it to the display area, the clothing can be automatically designed by pictures, reducing the time required for manual design and improving the production efficiency of clothing;

[0089] 2. By analyzing the lines in the reference clothing image to obtain a combined line contour, and screening the combined line contour according to the portrait line contour and the clothing wearing range to obtain a reference clothing contour, the clothing contour can be extracted from an image with only lines;

[0090] 3. By analyzing the situation of gloss gradient and selecting the continuous fabric according to the selection range to adjust the wearing model, the diversity of clothing production can be improved when selecting the fabric of clothing. Brief Description of the Drawings

[0091] Figure 1 is the flowchart of a multi - clothing feature fusion method according to an embodiment of the present invention;

[0092] Figure 2 is the flowchart of the method for determining the reference clothing contour according to an embodiment of the present invention;

[0093] Figure 3 is the flowchart of the method for determining the creative clothing image according to an embodiment of the present invention;

[0094] Figure 4 is the flowchart of the method after outputting to a preset display area according to an embodiment of the present invention;

[0095] Figure 5 is the method flow after determining the clothing model according to an embodiment of the present invention Figure 1 ;

[0096] Figure 6 is the flowchart of the method for determining the marked detection fabric according to an embodiment of the present invention;

[0097] Figure 7 is the method flow after determining the clothing model according to an embodiment of the present invention Figure 2 ;

[0098] Figure 8 is the method flow after updating the wearing model according to an embodiment of the present invention Figure 1 ;

[0099] Figure 9 is the method flow after updating the wearing model according to an embodiment of the present invention Figure 2 . Detailed implementation manners

[0100] The present invention will be further described in detail below with reference to the accompanying drawings and embodiments.

[0101] Referring to Figure 1 , an embodiment of the present application discloses a multi - clothing feature fusion method, including the following steps:

[0102] Step S100: Obtain a reference clothing image, a reference clothing image, and trigger information.

[0103] The benchmark clothing image refers to the benchmark image required by the operator when designing clothing. The benchmark acquisition module is a module set by the technician to acquire the benchmark clothing image, and the image retrieved from the benchmark acquisition module is used as the benchmark clothing image. The reference clothing image refers to the clothing image used as a reference when the operator designs clothing with the benchmark clothing image. The reference acquisition module is a module set by the technician to acquire the reference clothing image, and the image retrieved from the reference acquisition module is used as the reference clothing image. In this embodiment, the benchmark acquisition module and the reference acquisition module are set in the clothing software platform.

[0104] The trigger information refers to the control information of the clothing software platform when the operator clicks on it, and the trigger information is retrieved from the system of the clothing software platform.

[0105] Step S101: Acquire a marker fusion mode according to trigger information.

[0106] The preset reference mode is a mode used for designing clothing in a clothing software platform set by technical personnel.

[0107] The directional mode is a mode set by the technicians to retain the outline of the clothing in the reference clothing image and integrate the style of the reference clothing for design. The creative mode is a mode set by the technicians to retain the type of clothing in the reference clothing image and integrate the clothing features of the reference clothing for design. Clothing features are the color, style, outline, and pattern of clothing.

[0108] The basic modes include Directional Mode and Creative Mode.

[0109] Step S102: when the marker fusion mode is a preset orientation mode, a reference clothing outline is determined according to a reference clothing image.

[0110] The reference clothing contour refers to the contour of clothing in the reference clothing image. When the marker fusion mode is the directional mode, it is necessary to retrieve the contour of clothing in the reference clothing image, and the reference clothing image is analyzed to obtain the reference clothing contour.

[0111] Step S103: Determine the clothing color style according to the reference clothing image.

[0112] The clothing color style refers to the style of color arrangement of clothing in the reference clothing image, and the style of color arrangement of clothing in the reference clothing image is retrieved as the clothing color style.

[0113] Step S104: determining a fused clothing image according to the reference clothing outline and clothing color style.

[0114] The fused clothing image refers to the image formed by fusing the reference clothing image with the benchmark clothing image in the specified mode. The image obtained by combining the benchmark clothing contour with the clothing color style is used as the fused clothing image.

[0115] Step S105: When the marked fusion mode is a preset creative mode, determine the benchmark clothing type based on the benchmark clothing image.

[0116] The clothing repository is a gallery designed for technicians that stores all the clothing that can be queried. The benchmark clothing type refers to the type of clothing in the benchmark clothing image. When the marked fusion mode is the creative mode and it is necessary to create clothing that has not appeared in the clothing repository, the type of clothing is identified from the benchmark clothing image. Image recognition technology is common knowledge for those skilled in the art and will not be elaborated here.

[0117] Step S106: Determine the reference clothing features based on the reference clothing image, and determine the creative clothing image based on the reference clothing features and the benchmark clothing type.

[0118] The reference clothing features refer to the features of the clothing in the reference clothing image, which are identified from the reference clothing image. Image recognition technology is common knowledge for those skilled in the art and will not be elaborated here. The creative clothing image refers to the clothing image that has not appeared in the clothing repository, and the creative clothing image is obtained by analyzing the reference clothing features and the benchmark clothing type.

[0119] Step S107: Output the fused clothing image or the creative clothing image to a preset display area.

[0120] The display area is the area set by technicians on the clothing software platform for displaying the fused clothing image or the creative clothing image, and the fused clothing image or the creative clothing image is output to the display area for the operator to select.

[0121] Refer to Figure 2 , the method for determining the benchmark clothing contour also includes:

[0122] Step S200: When the benchmark clothing image only contains preset line features, determine the line-drawn contour based on the benchmark clothing image and the line features.

[0123] The line features are the features such as the color and shape of the lines in the benchmark clothing image set by technicians. The line-drawn contour refers to the contour surrounded by the lines in the benchmark clothing image. When the benchmark clothing image only contains line features, it means that the benchmark clothing image is an image drawn by lines, and the contour surrounded by the line features is identified from the benchmark clothing image as the line-drawn contour.

[0124] Step S201: Determine the outlines of different combinations of lines by tracing the outlines according to the lines.

[0125] The outline of the line combination refers to the outline formed by combining the outlines of adjacent lines traced with different numbers of lines. By combining the outlines of adjacent lines traced with different numbers, the combined outline is used as the outline of the line combination.

[0126] Step S202: Screen according to the outline of the line combination and the preset outline of the portrait lines, and use the outline of the line combination that is not the outline of the portrait lines as the marked combination outline.

[0127] The outline of the portrait lines is the outline of the portrait traced by lines in the image set by the technician. The marked combination outline refers to the outline of the lines of the clothing in the reference clothing image. By screening different outlines of the line combination, the outline of the line combination that is not the outline of the portrait lines is used as the marked combination outline. For example, the line between the neck and the shoulder is a continuous line. When there is an outline of an upper garment in the portrait in the line drawing, there is a line gap between the neck and the shoulder, so it is divided into two outlines, and the outline of the neck line is removed.

[0128] Step S203: Determine the range of outline distribution according to the marked combination outline.

[0129] The range of outline distribution refers to the distribution range of the outlines traced by the lines in the marked combination outline in the reference clothing image. The distribution range of the outlines traced by the lines in the marked combination outline in the reference clothing image is used as the range of outline distribution.

[0130] Step S204: Determine the outline of the line drawing clothing according to the range of outline distribution and the preset clothing wearing range, and use the outline of the line drawing clothing as the reference clothing outline.

[0131] The clothing wearing range is the range where the clothing is worn on the human body set by the technician. For example, a reference ratio is set to divide the human body vertically, and the range included in the divided outline is used as the clothing wearing range.

[0132] The outline of the line drawing clothing is the outline that can identify the complete clothing type. For example, if the range area of a clothing in the upper division range exceeds the range area in the lower division range, it is defined as an upper garment; otherwise, it is defined as lower wear. If the outline of a whole spreads across the upper and lower divided outlines, the clothing is regarded as a one-piece type of clothing. The adjacent outlines traced by the lines within a divided range are recombined, and the combined outline is used as the outline of the line drawing clothing, and the outline of the line drawing clothing is used as the reference clothing outline.

[0133] Refer to Figure 3 , the method for determining the creative clothing image includes:

[0134] Step S300: Determine a marked reference garment based on the reference garment features and the reference garment type.

[0135] The marked reference garment refers to a garment formed by fusing the reference garment features and the reference garment type. The garment formed by fusing the reference garment type and the reference garment features is used as the marked reference garment.

[0136] Step S301: Input the marked reference garment into a preset garment repository to match similar garment images with various similar features.

[0137] A similar garment image refers to an image similar to the garment features in the marked reference garment. By inputting the marked reference garment into the garment repository and extracting the garment features in the marked reference garment for retrieval and matching in the garment repository, the retrieved and matched garment images are used as similar garment images.

[0138] Step S302: Determine the matching garment type based on the marked reference garment.

[0139] The matching garment type refers to the garment type that can be stitched and matched with the marked reference garment. The matching garment type is matched from a preset matching database through the marked reference garment. For example, a pair of jeans can be cut with holes and multiple layers of cotton threads can be stitched on the holes to obtain a new pair of jeans, and the cotton thread is the matching garment type.

[0140] The matching database stores the matching garment types corresponding to different marked reference garments. The matching database is set artificially in advance and will not be elaborated here.

[0141] Step S303: Determine the creative garment features based on the marked reference garment and the similar garment images.

[0142] The creative garment features refer to the garment features that can be matched on the marked reference garment and do not coincide with the garment features in the similar garment images. The garment features are matched from a preset creative feature library through the marked reference garment, and the garment features that do not coincide with the garment features in the similar garment images are selected from the matched garment features as the creative garment features. The creative feature library stores the garment features corresponding to different marked reference garments. The creative feature library is set artificially in advance and will not be elaborated here.

[0143] Step S304: Determine the matching garment features based on the matching garment type and the creative garment features.

[0144] The matching garment features refer to the garment features in the creative garment features that can be on the matching garment type as the matching garment features. The corresponding matching garment features are matched from the matching database through the matching garment type, and the garment features consistent with the creative garment features are selected as the matching garment features.

[0145] The matching database also stores the clothing features corresponding to different types of matching clothing, which will not be elaborated here.

[0146] Step S305: Form a creative clothing image based on the matching clothing features, the type of matching clothing, the creative clothing features, and the marked reference clothing.

[0147] The clothing image formed by fusing the matching clothing features, the type of matching clothing, the creative clothing features, and the marked reference clothing is used as the creative clothing image.

[0148] Refer to Figure 4 , the method after outputting to the preset display area includes:

[0149] Step S400: Obtain the model body information.

[0150] The model body information refers to the body parameters of the model wearing the clothing on the clothing software platform, which can be obtained after being pre-entered by the operator.

[0151] Step S401: Determine the human model according to the model body information.

[0152] The human model refers to the three-dimensional model formed by the virtual data of the model. The human model is obtained by analyzing the model body information. The method for generating the model is common knowledge in the art and will not be elaborated here.

[0153] Step S402: Define the fused clothing image or the creative clothing image output to the display area as the marked image information.

[0154] The marked image information refers to the fused clothing image or the creative clothing image output to the display area.

[0155] Step S403: Determine the reference contour size according to the marked image information.

[0156] The reference contour size refers to the size of the clothing in the marked image information displayed in the image. The reference contour size is obtained by analyzing the marked image information. The method for identifying the size of the image is common knowledge in the art and will not be elaborated here.

[0157] Step S404: Determine the detected clothing size according to the human model and the reference contour size.

[0158] The detected clothing size refers to the size of the clothing worn on the human model in the marked image information. By identifying the overlapping situation between the clothing and the human model, the proportional value of the clothing size change is obtained. For example, the distance corresponding to the position where the human shoulder touches the clothing is calculated with the size of the clothing at the shoulder position in the reference contour size to obtain the proportional value. Then, the detected clothing size is obtained by using the proportional value and the reference contour size.

[0159] Step S405: Determine the clothing model based on the detected clothing size and the marked image information, and output the clothing model to the display area.

[0160] The clothing model refers to the three-dimensional model corresponding to the virtual data of the clothing. By analyzing the detected clothing size and the marked image information, the clothing model is obtained and output to the display area. The method for generating the model is common knowledge for those skilled in the art and will not be elaborated here.

[0161] Refer to Figure 5 , the methods after determining the clothing model include:

[0162] Step S500: Obtain the clothing wearing scenario.

[0163] The clothing wearing scenario refers to the scenario where the person is wearing the clothing, which can be obtained by pre-input from the operator.

[0164] Step S501: Determine the wearing model based on the human model and the clothing model.

[0165] The wearing model refers to the model formed after the human model wears the clothing model. By combining the human model and the clothing model, the wearing model is formed.

[0166] Step S502: Determine the movement trajectory based on the clothing wearing scenario and the human model, and control the wearing model to simulate movement along the movement trajectory.

[0167] The movement trajectory refers to the trajectory of the person moving in the clothing wearing scenario. By inputting the clothing wearing scenario into the preset movement database to match the movement amplitude, combining the movement amplitude with the human model to obtain the movement trajectory, and controlling the wearing model to simulate movement along the movement trajectory. The movement database stores the body amplitudes required for the person to move in different clothing wearing scenarios. The movement database is set artificially in advance and will not be elaborated here.

[0168] Step S503: Determine the clothing contraction position based on the movement trajectory and the wearing model.

[0169] The clothing contraction position refers to the position where the clothing contracts when the wearing model performs simulated movements. The clothing contraction position can be positions such as the shoulder joint, elbow joint, and wrist joint. By extracting the positions where the clothing wrinkles from the wearing model performing simulated movements, and the position points where the clothing wrinkles retract are used as the clothing contraction positions.

[0170] Step S504: Determine the marked detection fabric for the clothing contraction position based on the wearing model, the preset reference fabric, and the movement trajectory.

[0171] The reference fabric is the fabric used when the clothing model is initially generated as set by the technician. The marked detection fabric refers to the fabric sewn at the clothing contraction position, and the marked detection fabric is obtained by analyzing the wearing model, the reference fabric, and the movement trajectory. In this embodiment, the operator can select other fabrics as the reference fabric.

[0172] Step S505: Update the wearing model according to the marked detection fabric and output the updated wearing model to the display area.

[0173] The marked detection fabric and the clothing contraction position are input into the wearing model to form a new wearing model, and the updated wearing model is output to the display area.

[0174] Refer to Figure 6 , and the method for determining the marked detection fabric includes:

[0175] Step S600: Determine the detection extension coefficient and the detection stretching distance based on the wearing model, the reference fabric, and the movement trajectory.

[0176] The detection extension coefficient refers to the coefficient of the extension of the reference fabric at the clothing contraction position when the wearing model performs simulated movements along the movement trajectory. The detection extension coefficient is obtained by inputting the reference fabric and the body amplitude in the movement trajectory into a preset extension database for matching. The detection stretching distance refers to the distance of the extension and stretching of the reference fabric at the clothing contraction position when the wearing model performs simulated movements along the movement trajectory. When performing simulated movements on the wearing model and the movement trajectory, record the changed clothing size at the clothing contraction position, and compare the recorded size with the detected clothing size to obtain the stretching distance.

[0177] Step S601: Determine the contact pressure value based on the detection extension coefficient and the detection stretching distance.

[0178] The contact pressure value refers to the pressure value received by a person when wearing the clothing. The stretching pressure value is obtained through the detection extension coefficient and the detection stretching distance, then the movement direction is extracted from the movement trajectory, and the movement component force in the movement direction is calculated from the stretching pressure value as the contact pressure value.

[0179] Step S602: When the contact pressure value exceeds the preset reference pressure value, determine the marked pressure value based on the wearing model, the preset detection fabric, and the movement trajectory.

[0180] The reference pressure value is the minimum pressure value that a person receives from the clothing set by the technician. The detection fabric is other types of fabrics stored in the clothing software platform set by the technician. When the contact pressure value exceeds the reference pressure value, it indicates that the person will be too tight when wearing the clothing and moving. Then, the pressure value obtained by referring to Step S600 and Step S601 through the detection fabric is used as the marked pressure value.

[0181] Step S603: Select the detection fabric with a marked pressure value less than the reference pressure value from the marked pressure values as the marked detection fabric.

[0182] The marked detection fabric refers to the detection fabric with a marked pressure value less than the reference pressure value. The detection fabric with a marked pressure value less than the reference pressure value is selected from the marked pressure values as the marked detection fabric.

[0183] Refer to Figure 7 , the method after determining the clothing model further includes:

[0184] Step S700: When the contact pressure value does not exceed the reference pressure value, determine the detected deformation degree of the clothing contraction position based on the wearing model, the reference fabric, and the movement trajectory.

[0185] The detected deformation degree refers to the degree of wrinkling that occurs in the clothing at the clothing contraction position. When the contact pressure value does not exceed the reference pressure value, it indicates that it is not easy for the person to be too tight when wearing the clothing and moving. Then, the number of wrinkles at the clothing contraction position is retrieved from the wearing model of the simulated movement, and the detected deformation degree is matched through the number of wrinkles and the reference fabric input into the preset deformation database.

[0186] The deformation database stores the detected deformation degrees corresponding to different numbers of wrinkles and reference fabrics. The deformation database is set artificially in advance and will not be elaborated here.

[0187] Step S701: Determine the total force applied by the movement based on the detected deformation degree.

[0188] The total force applied by the movement refers to the total force applied to the clothing contraction position when the wearing model simulates the movement along the movement trajectory. The total force applied by the movement is matched through the detected deformation degree and the reference fabric input into the preset movement database. The movement database stores the total forces applied by the movement corresponding to different detected deformation degrees and fabrics. The movement database is set artificially in advance and will not be elaborated here.

[0189] Step S702: Determine the fabric contraction force based on the total force applied by the movement and the contact pressure value.

[0190] The fabric shrinkage force refers to the force with which the fabric shrinks during the simulated movement of the wearing model. The fabric shrinkage force is calculated by taking the difference between the total force applied during the movement and the contact pressure value.

[0191] Step S703: Determine the reference friction force based on the reference fabric and the total force applied during the movement.

[0192] The reference friction force refers to the friction force between the reference fabric and the skin during the simulated movement of the wearing model. The friction coefficient is matched from a preset friction database for the reference fabric, and then the reference friction force is calculated by multiplying the friction coefficient by the total force applied during the movement. The calculation method of the friction force is common knowledge to those skilled in the art and will not be elaborated here. The friction database stores the reference friction forces corresponding to different reference fabrics and total forces applied during the movement. The friction database is set in advance by humans and will not be elaborated here.

[0193] Step S704: Determine the fabric shrinkage distance based on the reference friction force and the fabric shrinkage force.

[0194] The fabric shrinkage distance refers to the distance by which the fabric shrinks during the simulated movement of the wearing model. The fabric shrinkage distance is matched from a preset shrinkage database based on the reference friction force and the fabric shrinkage force. The shrinkage database stores the fabric shrinkage distances corresponding to different reference friction forces and fabric shrinkage forces. The shrinkage database is set in advance by humans and will not be elaborated here.

[0195] Step S705: When the fabric shrinkage distance exceeds the preset reference retraction distance, determine the target shrinkage distance based on the wearing model, the preset detection fabric, and the movement trajectory.

[0196] The reference retraction distance is the maximum distance by which the fabric of the garment shrinks as set by the technician. When the fabric shrinkage distance exceeds the reference retraction distance, it indicates that the garment needs to be adjusted. Then, the shrinkage distance obtained by referring to the detection fabric in Steps S700 and S704 is used as the target shrinkage distance.

[0197] Step S706: Select the detection fabric corresponding to the target shrinkage distance greater than the reference retraction distance from the target shrinkage distances as the target detection fabric.

[0198] The target detection fabric refers to the detection fabric for which the target shrinkage distance is greater than the reference retraction distance. The detection fabric corresponding to the target shrinkage distance greater than the reference retraction distance is selected from the target shrinkage distances as the target detection fabric.

[0199] Step S707: Update the wearing model based on the target detection fabric.

[0200] The target detection fabric and the garment shrinkage position are input into the wearing model to obtain a new wearing model.

[0201] Reference Figure 8 After updating the wearing model, the method further includes:

[0202] Step S800: Using the target detection fabric and the marker detection fabric as adjustment fabrics.

[0203] The adjustment fabric refers to the fabric that needs to adjust the shrinkage position of the clothing. By using the target detection fabric and the marker detection fabric as adjustment fabrics.

[0204] Step S801: Determining the adjustment color according to the updated wearing model and the adjustment fabric.

[0205] The adjustment color refers to the color on the adjustment fabric. By extracting the color at the position of the adjustment fabric from the updated wearing model as the adjustment color.

[0206] Step S802: Determining the reference ambient illumination according to the clothing wearing scenario.

[0207] The reference ambient illumination refers to the illumination shown in the clothing wearing scenario. By extracting the reference ambient illumination from the clothing wearing scenario.

[0208] Step S803: Determining the adjustment gloss according to the reference ambient illumination, the adjustment color, and the adjustment fabric.

[0209] The adjustment gloss refers to the gloss of the adjustment fabric. By inputting the reference ambient illumination and the adjustment color into a preset gloss database to match the adjustment gloss. Different reference ambient illuminations and adjustment colors corresponding to the adjustment gloss are stored in the gloss database, which is set artificially in advance and will not be elaborated here.

[0210] Step S804: Determining the reference gloss according to the reference fabric.

[0211] The reference gloss refers to the gloss of the fabric that is not easily matched with the reference fabric. By using the reference fabric to match the reference gloss from the gloss database. Different fabrics corresponding to the reference gloss are also stored in the gloss database, which will not be elaborated here.

[0212] Step S805: When the adjustment gloss exceeds the reference gloss, determining the detection gloss according to the adjustment color, the detection fabric, and the reference ambient illumination.

[0213] When the adjustment gloss exceeds the reference gloss, it means that the fabric is not easily matched with the reference fabric. Then, the gloss obtained by referring to steps S801 and S803 with the detection fabric is used as the detection gloss.

[0214] Step S806: Select from the detected gloss levels the detected fabrics corresponding to those not exceeding the reference gloss level and define them as marked adjustment fabrics.

[0215] The marked adjustment fabric refers to the detected fabric corresponding to the detected gloss level that does not exceed the reference gloss level. By selecting from the detected gloss levels the detected fabrics corresponding to those not exceeding the reference gloss level, they are defined as marked adjustment fabrics.

[0216] Step S807: Update the wearing model according to the marked adjustment fabrics.

[0217] Input the marked adjustment fabrics and the clothing shrinkage positions into the wearing model to form a new wearing model.

[0218] Refer to Figure 9 , after updating the wearing model, the method further includes:

[0219] Step S900: Determine the gloss gradient areas according to the wearing model.

[0220] The gloss gradient areas refer to the areas on the clothing where gloss gradient is likely to occur. For example, when the clothing is a coat, the long sleeve parts of the coat can be gloss gradient areas. By extracting from the wearing model the areas where gradient can occur, and taking the gradient areas with clothing shrinkage positions as the gloss gradient areas.

[0221] Step S901: Determine the gloss change range according to the gloss gradient areas and the adjusted gloss levels.

[0222] The gloss change range refers to the range formed by the gloss level of the reference fabric and the adjusted gloss levels. By analyzing the adjusted color and the reference fabric according to Step S803 to obtain the gloss level, and combining this gloss level with the adjusted gloss levels to form the gloss change range.

[0223] Step S902: Determine the selection range according to the gloss change range.

[0224] The selection range refers to the range for selecting fabrics. The smallest range formed by extending the maximum and minimum values of the gloss change range is taken as the selection range. For example, if the gloss change range is 1 - 11, the selection range is 5 - 5; when the gloss change range is 1 - 10, the selection range is 4 - 6.

[0225] Step S903: Select from the adjusted gloss levels those that fall within the selection range as the marked gloss levels.

[0226] The marked gloss levels refer to the fabrics capable of gloss gradient. By selecting the adjusted gloss levels that fall within the selection range as the marked gloss levels.

[0227] Step S904: Determine the continuous fabrics according to the marked gloss levels.

[0228] The continuous fabric refers to the adjusted fabric corresponding to the marked glossiness, by taking the adjusted fabric with the marked glossiness as the continuous fabric.

[0229] Step S905: Update the wearing model according to the continuous fabric and the gloss gradient part.

[0230] Form a new wearing model by inputting the continuous fabric and the gloss gradient part into the wearing model.

[0231] Based on the same inventive concept, an embodiment of the present invention provides a multi-clothing feature fusion system, including:

[0232] An acquisition module, configured to acquire a reference clothing image, a reference clothing image, a trigger message, a marked fusion mode, a model body information, and a clothing wearing scenario;

[0233] A memory, configured to store a multi-clothing feature fusion method;

[0234] A processor, configured to load and execute and implement the program stored in the memory.

[0235] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the above division of each functional module is used as an example. In actual applications, the above functions can be allocated to different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. The specific working processes of the system, device, and unit described above can refer to the corresponding processes in the foregoing method embodiments and will not be repeated here.

[0236] The above are only the preferred embodiments of the present invention, and the protection scope of the present invention is not limited to the above embodiments. All technical solutions falling within the inventive concept of the present invention belong to the protection scope of the present invention. It should be noted that for those of ordinary skill in the art, without departing from the principle of the present invention, several improvements and refinements should also be regarded as the protection scope of the present invention.

Claims

1. A multi-clothing feature fusion method, characterized in that: include: Acquire a baseline clothing image, a reference clothing image, and trigger information; Acquire a marking fusion mode according to the trigger information; When the marker fusion mode is a preset directional mode, determining a reference clothing outline according to the reference clothing image; Determine clothing color style based on reference clothing images; Determine a fused clothing image according to a reference clothing outline and clothing color style; When the tag-based fusion mode is a preset creative mode, a reference clothing type is determined according to a reference clothing image; Determine reference clothing features according to the reference clothing image, and determine a creative clothing image according to the reference clothing features and a benchmark clothing type; Outputting the fused clothing image or the creative clothing image to a preset display area; Methods for determining a baseline garment outline also include: When the reference clothing image only includes preset line features, determining the line drawing outline according to the reference clothing image and the line features; Delineate the contours based on the lines to determine contours with different numbers of line combinations; Screening is performed based on the line combination contours and the preset portrait line contours, and the line combination contours that are not portrait line contours are used as marked combination contours; Combine contours based on markers to determine contour distribution range; Determine the outline of the line drawing clothing according to the outline distribution range and the preset clothing wearing range, and use the outline of the line drawing clothing as the reference clothing outline; Methods for determining creative clothing images include: Determine the marked reference garment according to the reference garment characteristics and the benchmark garment type; According to the marked reference clothing input into the preset clothing storage library, similar clothing images with similar features are matched; Reference garments based on markings to determine matching garment types; Determine creative clothing features based on labeled reference clothing and similar clothing images; Determine the matching clothing features based on the matching clothing type and creative clothing features; A creative clothing image is formed according to matching clothing features, matching clothing types, creative clothing features and marked reference clothing.

2. A multi-clothing feature fusion method according to claim 1, characterized in that: The method after outputting to the preset display area includes: Get model body information; Determine the character model based on the model's body information; defining the fused clothing image or the creative clothing image output to the display area as the labeled image information; Determine the reference contour size according to the marked image information; Determine the size of the garment to be tested based on the figure model and the reference outline size; The clothing model is determined according to the detected clothing size and the marked image information, and the clothing model is output to the display area.

3. A multi-clothing feature fusion method according to claim 2, characterized in that: The methods after determining the clothing model include: Get the clothing wearing scene; Determine the wearing model based on the character model and clothing model; Determine the motion trajectory according to the clothing wearing scene and the character model, and control the wearing model to perform simulated movement according to the motion trajectory; Determine the garment contraction position based on the motion trajectory and wearing model; Fabric inspection based on wearing models, preset reference fabrics, and motion trajectories to identify markers where garments shrink; The fabric is detected according to the markers to update the wearing model, and the updated wearing model is output to the display area.

4. A multi-clothing feature fusion method according to claim 3, characterized in that: Methods for determining the marking of detected fabrics include: Determine the test extension coefficient and test stretch distance based on the wearing model, reference fabric and motion trajectory; Determine the contact pressure value according to the detection extension coefficient and the detection stretching distance; When the contact pressure value exceeds a preset reference pressure value, a marking pressure value is determined according to a wearing model, a preset detection fabric, and a motion trajectory; A detection fabric with a smaller pressure value than a reference pressure value is selected from the marked pressure values ​​as the marked detection fabric.

5. A multi-clothing feature fusion method according to claim 4, characterized in that: The method after determining the clothing model also includes: When the contact pressure value does not exceed the reference pressure value, the degree of deformation of the garment contraction position is determined according to the wearing model, the reference fabric and the motion trajectory; Determine the total force applied in the motion based on the degree of deformation detected; Determine the fabric contraction force based on the total force and contact pressure value applied in the motion; Apply total force based on the reference fabric and motion to determine the reference friction force; Determine the fabric shrinkage distance based on the reference friction force and the fabric shrinkage force; When the fabric shrinkage distance exceeds the preset reference retraction distance, the target retraction distance is determined according to the wearing model, the preset detection fabric and the motion trajectory; Selecting a detection fabric corresponding to a target shrinkage distance greater than a reference shrinkage distance from the target shrinkage distance as the target detection fabric; Fabric detection based on target to update the wear model.

6. A multi-clothing feature fusion method according to claim 5, characterized in that: The method after updating the wearing model also includes: The target detection fabric and the marker detection fabric are used as adjustment fabrics; Adjust colors based on updated wearing models and adjusted fabrics; Determine the baseline ambient light intensity based on the clothing wearing scenario; Adjust gloss according to baseline ambient light, adjust color, and adjust fabric; Determine the baseline gloss level based on the baseline fabric; When the adjusted glossiness exceeds the reference glossiness, the detection glossiness is determined according to the adjusted color, the detection fabric and the reference ambient light illumination; The test fabric corresponding to the test glossiness that does not exceed the reference glossiness is selected from the test glossiness and defined as the marking adjustment fabric; Adjust fabrics based on markings to update the wear model.

7. A multi-clothing feature fusion method according to claim 6, characterized in that: The method after updating the wearing model also includes: Determine the gloss gradient area based on the model being worn; According to the gloss gradient position and adjusting the glossiness to determine the gloss variation range; Determine the selection range based on the gloss variation range; Selecting the adjusted glossiness that falls within the selected range from the adjusted glossiness as the marked glossiness; Determine continuous fabrics based on marking glossiness; Update the wearing model based on continuous fabric and gloss gradient areas.

8. A multi-clothing feature fusion system, characterized in that: include: An acquisition module is used to acquire a benchmark clothing image, a reference clothing image, trigger information, a marker fusion mode, model body information, and clothing wearing scenes; A memory, used to store a multi-clothing feature fusion method according to any one of claims 1 to 7; The processor is used to load, execute and implement the program stored in the memory.

Images