Clothing style duplicate checking method, device and equipment and medium

Abstract

The invention discloses a costume style duplicate checking method, device and equipment and a medium, and relates to the technical field of costume numeralization. The costume style duplicate checking method comprises the steps that costume information to be checked is acquired, the costume information comprises a costume source design drawing, then a costume three-dimensional source design drawing is generated based on the costume source design drawing, and the costume three-dimensional source design drawing comprises labels; performing style optimization, color optimization and label optimization on the garment three-dimensional source design drawing to obtain a preliminary garment style drawing; performing duplicate checking operation based on a clothing style element point database according to the preliminary clothing style drawing and the optimized label to obtain first similarity information, the clothing style element point database being established according to a clothing line draft drawing and a planar graph; and outputting the clothing style information with the first similarity information greater than or equal to a preset threshold value. By executing the operation, the missed judgment and misjudgment rate of costume duplicate checking can be reduced, and the costume style duplicate checking precision and accuracy are improved.

Description

Technical Field

[0001] This application relates to the field of clothing digitization technology, and particularly to a method, device, equipment and medium for checking duplicate clothing styles. Background Art

[0002] In the rapidly developing clothing design industry today, intellectual property protection has become an increasingly prominent issue. With the acceleration of the fashion cycle and the diversification of consumer demands, clothing designers and brands are facing huge innovation pressures. However, this pressure has also led to an increase in adverse phenomena such as plagiarism and excessive reference.

[0003] In recent years, with the development of computer vision and artificial intelligence technologies, some digital clothing style duplicate-checking methods have emerged. These methods usually adopt image processing and pattern recognition technologies to attempt to automatically identify similar clothing designs. However, there are still some obvious deficiencies in the related digital duplicate-checking methods, resulting in missed or misjudged cases during the duplicate-checking process. Summary of the Invention

[0004] The main purpose of the embodiments of this application is to provide a method, device, equipment and medium for checking duplicate clothing styles, aiming to improve the accuracy of clothing style duplicate-checking and reduce the occurrence of missed or misjudged cases.

[0005] To achieve the above purpose, on the one hand, an embodiment of this application proposes a method for checking duplicate clothing styles, including the following steps:

[0006] Obtain clothing information to be checked for duplication, where the clothing information includes the original clothing design drawing;

[0007] Generate a 3D original clothing design drawing based on the original clothing design drawing, where the 3D original clothing design drawing includes labels, and the labels include the material, style and seasonal adaptability of the clothing;

[0008] Perform style optimization, color optimization and label optimization on the 3D original clothing design drawing to obtain a preliminary clothing style drawing;

[0009] Execute a duplicate-checking operation based on the preliminary clothing style drawing and the optimized labels on the clothing style element point database, and obtain first similarity information, where the clothing style element point database is established according to clothing line drawings and floor plans;

[0010] Output the clothing style information whose first similarity information is greater than or equal to a preset threshold.

[0011] In some embodiments, after outputting the clothing style information whose first similarity information is greater than or equal to a preset threshold, the method further includes:

[0012] Analyze the features of the preliminary clothing style diagram corresponding to the label information based on the label of the preliminary clothing style diagram to obtain target features;

[0013] Perform a duplicate check operation based on the target features to obtain second similarity information;

[0014] Determine similar clothing style information based on the second similarity information.

[0015] In some embodiments, generating the 3D source design diagram of the clothing based on the source design diagram of the clothing includes:

[0016] Collect images of the source design diagram of the clothing, and generate a source design image pixel matrix according to the collected images;

[0017] Determine a first parameter and a second parameter, where the first parameter is the maximum pixel distance of the source design image pixel matrix, and the second parameter is the maximum pixel distance of the template design image pixel matrix;

[0018] Calculate the ratio of the maximum pixel distance of the first parameter to the second parameter to obtain a first ratio;

[0019] Determine a target proportionality coefficient according to the first ratio, the initial proportionality coefficient, and the standard ratio;

[0020] Adjust the pixel distance in the source design image pixel matrix through the target proportionality coefficient to obtain the 3D source design diagram of the clothing.

[0021] In some embodiments, the preliminary clothing style diagram includes color information. The optimizing the style, color, and label of the 3D source design diagram of the clothing to obtain the preliminary clothing style diagram includes:

[0022] Determine the style category of the 3D source design diagram of the clothing according to the 3D source design diagram of the clothing and the template design diagram;

[0023] Adjust the 3D source design diagram of the clothing according to the style category to obtain the preliminary clothing style diagram;

[0024] Compare the colors of the preliminary clothing style diagram and the template design diagram according to a preset color analysis algorithm to obtain the color information;

[0025] Perform integrity, standardization, and automatic correction processing on the label to obtain an optimized label corresponding to the preliminary clothing style diagram.

[0026] In some embodiments, the comparing the colors of the preliminary clothing style diagram and the template design diagram according to a preset color analysis algorithm to obtain the color information includes:

[0027] Process the pixel samples in the preset sample color library to obtain an RGB value matrix;

[0028] According to the structural characteristics of the preliminary clothing style diagram, divide the RGB value matrix into multiple regions;

[0029] Determine the RGB difference and the number of pixel samples between the pixel samples in the preliminary clothing style diagram and the pixel samples in the template design diagram corresponding to the same region;

[0030] Determine the color analysis value according to the RGB difference and the number of pixel samples;

[0031] Compare the color analysis value with the analysis preset value, and determine the color information according to the comparison result.

[0032] In some embodiments, the duplicate checking operation is performed based on the preliminary clothing style diagram and the optimized label in the clothing style element point database to obtain the first similarity information, including:

[0033] Match the preliminary clothing style diagram with the design diagrams in the clothing style element point database through the clothing style element point retrieval model to obtain the first similarity information;

[0034] Among them, the clothing style element point retrieval model is established by splitting and establishing a region index based on the marking of key points and vertices in the plane contour lines of the clothing line drawing and the plan view, as well as the key points and vertices of clothing elements.

[0035] In some embodiments, the first similarity information includes a first similarity value. The duplicate checking operation is performed based on the preliminary clothing style diagram and the optimized label in the clothing style element point database to obtain the first similarity information, including:

[0036] When the preliminary clothing style diagram is the same as the original style in the clothing style element point database, determine that the first similarity value is 100% and stop performing the duplicate checking operation;

[0037] When the preliminary clothing style diagram and the original style are both different, determine the first difference between the starting sequence numbers of the broken lines of the preliminary clothing style diagram and the original style, and the second difference between the ending sequence numbers of the broken lines of the preliminary clothing style diagram and the original style;

[0038] Determine the median of the first difference and the second difference as the first similarity value.

[0039] To achieve the above object, on the other hand, an embodiment of the present application proposes a clothing style duplicate checking device, and the device includes:

[0040] An acquisition module, configured to acquire clothing information to be checked for duplication, where the clothing information includes a clothing source design drawing;

[0041] A generation module, configured to generate a three-dimensional clothing source design drawing based on the clothing source design drawing, where the three-dimensional clothing source design drawing includes tags, and the tags include the material, style, and season adaptability of the clothing;

[0042] An optimization module, configured to perform style optimization, color optimization, and tag optimization on the three-dimensional clothing source design drawing to obtain a preliminary clothing style drawing;

[0043] A duplication-checking module, configured to perform a duplication-checking operation based on the preliminary clothing style drawing and the optimized tags on a clothing style element point database to obtain first similarity information, where the clothing style element point database is established based on clothing line drawings and floor plans;

[0044] An output module, configured to output clothing style information for which the first similarity information is greater than or equal to a preset threshold.

[0045] To achieve the above object, another aspect of the embodiments of the present application provides an electronic device, where the electronic device includes a memory and a processor, the memory stores a computer program, and when the processor executes the computer program, the above clothing style duplication-checking method is implemented.

[0046] To achieve the above object, yet another aspect of the embodiments of the present application provides a computer-readable storage medium, where the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the above clothing style duplication-checking method is implemented.

[0047] The embodiments of the present application at least include the following beneficial effects:

[0048] The present application provides a method, apparatus, device and medium for checking duplicate clothing styles. The solution obtains clothing information to be checked for duplication, where the clothing information includes the original clothing design drawing. Then, based on the original clothing design drawing, a three-dimensional original clothing design drawing is generated, and the three-dimensional original clothing design drawing includes tags, and the tags include the material, style and seasonal adaptability of the clothing; perform style optimization, color optimization and tag optimization on the three-dimensional original clothing design drawing to obtain a preliminary clothing style drawing; perform a duplicate check operation based on the preliminary clothing style drawing and the optimized tags on the clothing style element point database, and obtain first similarity information, where the clothing style element point database is established according to the clothing line drawing and the plan view; output the clothing style information with the first similarity information greater than or equal to a preset threshold. By performing style optimization, color optimization and tag optimization on the three-dimensional original clothing design drawing and the tags, the present application obtains a preliminary clothing style drawing. Since the three-dimensional original clothing design drawing includes three-dimensional structure information; the tags include information such as the material, style and seasonal adaptability of the clothing, so the structural information and semantic information of the clothing can be paid more attention to during the duplicate check, thereby reducing the missed judgment and misjudgment rates; further, due to performing style optimization, color optimization and tag optimization on the three-dimensional original clothing design drawing, the color information and style details can be paid attention to during the duplicate check process, further improving the accuracy of the duplicate check; in addition, the present application performs a duplicate check operation based on the clothing style element point database, and the clothing style element point database is established according to the clothing line drawing and the plan view, so the geometric and topological information associated with the clothing line drawing and the plan view can be captured, thereby further improving the accuracy and precision of the clothing style duplicate check.

[0049] Additional aspects and advantages of the present application will be given in part in the following description, become apparent in part from the following description, or be learned through the practice of the present application. Brief Description of the Drawings

[0050] The above and / or additional aspects and advantages of the present application will become apparent and be readily understood from the description of the embodiments in conjunction with the following drawings, where:

[0051] Figure 1 is a flowchart of a method for checking duplicate clothing styles provided by some embodiments of the present application;

[0052] Figure 2 is another flowchart of a method for checking duplicate clothing styles provided by some embodiments of the present application;

[0053] Figure 3 is a block diagram of modules of a device for checking duplicate clothing styles provided by some embodiments of the present application;

[0054] Figure 4 is a schematic hardware structure diagram of checking duplicate clothing styles provided by some embodiments of the present application. Detailed Embodiments

[0055] In order to make the objectives, technical solutions, and advantages of the present application more clear and understandable, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that referring to "embodiments" herein means that the specific features, structures, or characteristics described in connection with the embodiments may be included in at least one embodiment of the present application. The phrase does not necessarily refer to the same embodiment at various positions in the specification, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art explicitly and implicitly understand that the embodiments described herein may be combined with other embodiments. The implementation manners described in the following exemplary embodiments do not represent all implementation manners consistent with the embodiments of the present application. They are merely examples of devices and methods consistent with some aspects of the embodiments of the present application as detailed in the appended claims.

[0056] It can be understood that the terms "first", "second", etc. used in the present application may be used herein to describe various concepts, but unless otherwise specified, these concepts are not limited by these terms. These terms are only used to distinguish one concept from another. For example, without departing from the scope of the embodiments of the present application, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the words "if", "when" as used herein may be interpreted as "when...", "while...", or "in response to determining".

[0057] The terms "at least one", "a plurality of", "each", "any one", etc. used in the present application, at least one includes one, two, or more than two, a plurality of includes two or more than two, each refers to each one of the corresponding plurality, and any one refers to any one of the plurality.

[0058] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which the present application belongs. The terms used herein are only for the purpose of describing the embodiments of the present application and are not intended to limit the present application.

[0059] In the following description, specific details such as specific system structures and technologies are presented for the purpose of illustration rather than limitation, so as to thoroughly understand the embodiments of the present application. However, those skilled in the art should clearly understand that the present application can also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid unnecessary details from interfering with the description of the present application.

[0060] In today's rapidly developing fashion design industry, intellectual property protection has become an increasingly prominent issue. With the acceleration of the fashion cycle and the diversification of consumer demands, fashion designers and brands are facing huge innovation pressures. However, this pressure has also led to an increase in adverse phenomena such as plagiarism and excessive reference. Traditional methods for checking duplicate clothing styles mainly rely on manual comparison, which is not only time-consuming and laborious but also vulnerable to subjective factors and difficult to handle a large amount of design data.

[0061] In recent years, with the development of computer vision and artificial intelligence technologies, some digital methods for checking duplicate clothing styles have emerged. These methods usually adopt image processing and pattern recognition technologies and attempt to automatically identify similar fashion designs. However, there are still some obvious deficiencies in existing digital duplicate-checking methods.

[0062] First of all, most existing methods mainly focus on the two-dimensional image features of clothing and are difficult to comprehensively capture the three-dimensional structure and details of fashion designs. This results in easy omission or misjudgment when dealing with some complex designs.

[0063] Secondly, existing methods often compare clothing as a whole and ignore the detail differences of different parts (such as necklines, sleeves, hemlines, etc.), which reduces the accuracy of duplicate checking. Moreover, many methods do not consider the semantic information of fashion designs, such as style categories, fabric materials, seasons, etc., and these information are crucial for judging the similarity of designs.

[0064] In addition, existing duplicate-checking methods often have efficiency problems when dealing with large-scale data. With the increase in the number of fashion brands and the shortening of the design cycle, the number of designs to be compared has increased exponentially. How to improve the duplicate-checking efficiency while ensuring accuracy has become an urgent problem to be solved.

[0065] Finally, existing methods generally lack flexibility and adjustability. Different types of fashion brands may have different duplicate-checking requirements. For example, high-end custom brands may require stricter originality standards, while fast fashion brands may allow a certain degree of design reference. However, most duplicate-checking methods cannot flexibly adjust their judgment criteria according to different application scenarios.

[0066] In view of this, the present application proposes a method, apparatus, device and medium for checking duplicate clothing styles. In the embodiments of the present application, by obtaining clothing information to be checked for duplicates, the clothing information includes the original clothing design drawing. Then, based on the original clothing design drawing, a three-dimensional original clothing design drawing is generated. The three-dimensional original clothing design drawing includes tags, and the tags include the material, style and seasonal adaptability of the clothing. Perform style optimization, color optimization and tag optimization on the three-dimensional original clothing design drawing to obtain a preliminary clothing style drawing. Perform a duplicate check operation based on the preliminary clothing style drawing and the optimized tags on the clothing style element point database to obtain first similarity information, where the clothing style element point database is established according to the clothing line drawing and the plan view. Output the clothing style information whose first similarity information is greater than or equal to the preset threshold. In the present application, by performing style optimization, color optimization and tag optimization on the three-dimensional original clothing design drawing and the tags, a preliminary clothing style drawing is obtained. Since the three-dimensional original clothing design drawing includes three-dimensional structure information; the tags include information such as the material, style and seasonal adaptability of the clothing, so when checking for duplicates, more attention can be paid to the structure information and semantic information of the clothing, thereby reducing the missed judgment and misjudgment rates; further, due to performing style optimization, color optimization and tag optimization on the three-dimensional original clothing design drawing, color information and style details can be taken into account during the duplicate check process, further improving the accuracy of the duplicate check; in addition, the present application performs a duplicate check operation based on the clothing style element point database, and the clothing style element point database is established according to the clothing line drawing and the plan view, so geometric and topological information associated with the clothing line drawing and the plan view can be captured, thereby further improving the accuracy of clothing style duplicate check.

[0067] The method for checking duplicate clothing styles provided by the embodiments of the present application relates to the field of clothing digitization technology. It can be applied to the electronic device provided by the present application. The electronic device can be a terminal or a server.

[0068] In some embodiments, the terminal can be a smart phone, a tablet computer, a notebook computer, a desktop computer, a smart speaker, a smart watch, a vehicle-mounted terminal, etc., but is not limited thereto.

[0069] The server side can be configured as an independent physical server, or can be configured as a server cluster or distributed system composed of multiple physical servers, or can also be configured as a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. The server can also be a node server in a blockchain network.

[0070] This application can be used in numerous general-purpose or special-purpose computer system environments or configurations. For example: personal computers, server computers, handheld devices or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronic devices, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, and so on. This application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. This application can also be practiced in a distributed computing environment, where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0071] The implementation steps of a clothing style duplicate checking method provided by an embodiment of this application will be described in detail below in conjunction with the accompanying drawings.

[0072] Please refer to Figure 1 , Figure 1 , which is a flowchart of the clothing style duplicate checking method provided by some embodiments of this application. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order than here.

[0073] The method of the embodiment of this application includes the following steps:

[0074] Step 101: Obtain the clothing information to be checked for duplicates, where the clothing information includes the clothing source design drawing;

[0075] Step 102: Generate a 3D clothing source design drawing based on the clothing source design drawing, where the 3D clothing source design drawing includes tags, and the tags include the material, style, and seasonal adaptability of the clothing;

[0076] Step 103: Perform style optimization, color optimization, and tag optimization on the 3D clothing source design drawing to obtain a preliminary clothing style drawing;

[0077] Step 104: Perform a duplicate checking operation based on the preliminary clothing style drawing and the optimized tags on the clothing style element point database to obtain first similarity information, where the clothing style element point database is established based on the clothing line drawing and the floor plan;

[0078] Step 105: Output the clothing style information whose first similarity information is greater than or equal to a preset threshold.

[0079] Steps 101 to 105 illustrated in the embodiments of the present application can obtain a preliminary clothing style drawing by optimizing the style, color, and label of the 3D source design drawing and label of the clothing. Since the 3D source design drawing of the clothing includes three-dimensional structure information, and the label includes information such as the material, style, and seasonal adaptability of the clothing, when performing duplicate checking, more attention can be paid to the structural information and semantic information of the clothing, thereby reducing the missed judgment and misjudgment rates. Further, since the style, color, and label of the 3D source design drawing of the clothing are optimized, color information and style details can be noticed during the duplicate checking process, further improving the accuracy of duplicate checking. In addition, the present application performs duplicate checking operations based on the clothing style element point database, and the clothing style element point database is established according to the clothing line drawing and plan drawing, so geometric and topological information associated with the clothing line drawing and plan drawing can be captured, thereby further improving the accuracy of clothing style duplicate checking.

[0080] The specific implementation methods of the above steps are introduced below.

[0081] In step 101, clothing information to be checked for duplicates is obtained, and the clothing information includes the source design drawing of the clothing.

[0082] Optionally, the clothing information includes the source design drawing of the clothing and some other relevant information, and these relevant information includes the style, category, line drawing, plan drawing, name of the 3D source design drawing, and label of the 3D source design drawing of the clothing, etc.

[0083] Optionally, the style of the clothing can include jackets, trousers, half-arms, socks, shirts, or windbreakers, etc., and the category can be men's clothing, women's clothing, or children's clothing, etc. The label of the 3D source design drawing usually contains information such as the collar type, sleeve type, style, and material of the clothing.

[0084] Optionally, obtaining the clothing information to be checked for duplicates can be to collect relevant information of the clothing through the information collection unit, and import the source design drawing into the cloud platform through the information upload unit.

[0085] Among them, the information collection unit can be a local computer or a terminal server. Preferably, the terminal server is located at the design side, so as to ensure the timeliness and accuracy of the design information. The method of the present application further includes a user login unit for a user to log in to the local computer or terminal server to access the source design drawing of the clothing. The user can be a design user or an audit user, and this distinction can achieve different levels of permission management and improve the security of the system.

[0086] For example, the design users may be fashion designers who need to upload new designs and check for duplicates. The review users may be personnel from the company's intellectual property department who need to view the duplicate check results and make corresponding decisions. By differentiating these two types of users, the system can provide customized functions and interfaces for different roles.

[0087] In practical applications, the method of this application can execute different operation processes according to the user's identity. Specifically, if a design user logs in, the system will execute the whole process from generating a 3D source design drawing to performing a style duplicate check operation. If a review user logs in, the system will mainly execute the step of outputting clothing style drawings with a similarity exceeding a preset threshold.

[0088] This process design based on user identity can improve the security of the system, ensuring that only authorized users can access sensitive design information; improve the efficiency of the system, allowing different users to focus on their job responsibilities; and facilitate management and tracking, as the system can record the operations of each user, which is helpful for subsequent auditing and management.

[0089] It can be understood that the data in the local computer and the terminal server is usually stored in the cloud platform. This cloud storage method has multiple advantages: First, it improves the security of the data because the cloud platform usually has better backup and security measures; second, it facilitates data sharing and collaboration, as users in different locations can easily access the same set of data; finally, it improves the scalability of the system, allowing for flexible increase or decrease of computing resources according to needs.

[0090] The method provided by the embodiments of this application can improve the accuracy and efficiency of duplicate checking, and can also improve the security and usability of the system through reasonable user permission management. In practical applications, this method can effectively help fashion design companies protect their intellectual property rights, and at the same time provide a convenient duplicate checking tool for designers, which helps to promote the healthy development of the fashion design industry.

[0091] In the implementation manner of this application, by obtaining the clothing information to be checked for duplicates, where the clothing information includes the clothing source design drawing, it can provide data support for further processing and duplicate checking based on the clothing source design drawing.

[0092] In step 102, a 3D clothing source design drawing is generated based on the clothing source design drawing, and the 3D clothing source design drawing includes tags, where the tags include the material, style, and seasonal adaptability of the clothing.

[0093] Generating a 3D source design drawing of a garment based on a source design drawing of the garment can involve performing 3D modeling on the styles, cuts, and details in the 2D design drawing using professional software, and simulating the three-dimensional form and fabric characteristics of the garment using computer graphics technology. Subsequently, by adjusting the model parameters and rendering effects, the 3D image can display the final effect of the garment as realistically as possible.

[0094] Optionally, generating a 3D source design drawing of a garment based on a source design drawing of the garment can also involve image acquisition of the source design drawing of the garment, generating a source design image pixel matrix based on the acquired image; determining a first parameter and a second parameter, where the first parameter is the maximum pixel distance of the source design image pixel matrix, and the second parameter is the maximum pixel distance of the template design image pixel matrix; calculating the ratio of the maximum pixel distances of the first parameter and the second parameter to obtain a first ratio; determining a target scale factor based on the first ratio, an initial scale factor, and a standard ratio; and adjusting the pixel distances in the source design image pixel matrix through the target scale factor to obtain a 3D source design drawing of the garment.

[0095] Exemplarily, for image acquisition of the source design drawing, a digital image can be directly obtained, or a high-definition digital image of the design drawing can be obtained using a high-precision scanning device or a professional camera, and then the digital image is preprocessed through image processing software, including adjusting color, contrast, sharpness, etc., to optimize the image quality. Subsequently, image recognition technology is used to extract the pixel matrix of the image, converting each pixel point in the design drawing into numerical information to form a source design image pixel matrix. This process not only retains all the details of the design drawing but also provides an accurate and reliable data basis for subsequent image analysis and 3D modeling.

[0096] After that, the first parameter and the second parameter are determined. Among them, the first parameter is the maximum pixel distance of the source design image pixel matrix, and the second parameter is the maximum pixel distance of the image matrix of the template design. For example, the first parameter can be 1000 pixels, and the second parameter can be 800 pixels. The selection of these parameters can be adjusted according to the actual image resolution and processing requirements.

[0097] After determining the first parameter and the second parameter, the ratio of the maximum pixel distance of the source design image pixel matrix to the maximum pixel distance of the image matrix of the template design can be calculated, and the ratio is denoted as δ. This ratio reflects the size difference between the source design drawing and the template design drawing.

[0098] The scale factor τ is calculated according to a preset formula. The formula is as follows:

[0099] τ = (δ / α) * β;

[0100] Among them, α is the standard ratio, and β is the proportionality coefficient. The standard ratio α can usually be set to 1, representing the ideal situation where the source design drawing and the template design drawing have the same size. The proportionality coefficient β can be adjusted according to actual needs. For example, it can be set to a value between 0.8 and 1.2 to meet different scaling requirements.

[0101] Adjust the pixel distance in the pixel matrix of the source design image according to the proportionality coefficient τ. Specifically, when τ < 1, increase the pixel distance in the pixel matrix of the source design image; when τ = 1, keep the pixel distance in the pixel matrix of the source design image unchanged; when τ > 1, decrease the pixel distance in the pixel matrix of the source design image. Finally, enlarge the pixel matrix of the source design image to obtain a three-dimensional source design drawing.

[0102] This adjustment method can effectively standardize source design drawings of different sizes, making subsequent comparisons more accurate.

[0103] In step 103, perform style optimization, color optimization, and label optimization on the three-dimensional source design drawing of the clothing to obtain a preliminary clothing style drawing.

[0104] In this step, based on the generated three-dimensional source design drawing, a preliminary clothing style drawing is optimized, specifically involving multiple aspects such as style optimization, color optimization, and label optimization.

[0105] Optionally, in an embodiment of the present application, the style optimization step can analyze the three-dimensional source design drawing of the clothing and the image of the template design to obtain the style category. For example, the system can identify whether the clothing is a jacket, trousers, a shirt, etc. Then, adjust the three-dimensional source design drawing according to the identified style category to obtain a preliminary style drawing.

[0106] In terms of color optimization, compare the color of the preliminary style drawing with the image of the template design to obtain color data.

[0107] In terms of label optimization, optimize the labels of the three-dimensional source design drawing to ensure the accuracy and integrity of the label information. This is crucial for the subsequent duplicate checking process because the label information often contains the key features of the clothing design.

[0108] Finally, based on the optimized preliminary clothing style drawing, perform a style duplicate checking operation to obtain the similarity.

[0109] Optionally, the style category of the three-dimensional source design drawing of the clothing can be determined according to the three-dimensional source design drawing of the clothing and the template design drawing; adjust the three-dimensional source design drawing of the clothing according to the style category to obtain a preliminary clothing style drawing; compare the color of the preliminary clothing style drawing and the template design drawing according to a preset color analysis algorithm to obtain color information; perform integrity, standardization, and automatic correction processing on the label to obtain the optimized label corresponding to the preliminary clothing style drawing.

[0110] Specifically, the style optimization step can analyze the 3D source design drawing of the clothing and the image of the template design to obtain the style category. This process involves image recognition and classification algorithms. For example, the system may use a Convolutional Neural Network (CNN) to identify the key features of the clothing, such as collar type, sleeve type, and garment length, and then determine the style category based on these features. Among them, the style category can include jackets, trousers, half-arms, socks, shirts, or windbreakers, etc.

[0111] After determining the style category, the source design drawing can be adjusted according to this category to obtain a preliminary style drawing. This adjustment process may involve operations such as image scaling, rotation, or feature enhancement. For example, if the identified style is a jacket, the system may enhance the features of the shoulders and cuffs for subsequent comparison.

[0112] The color optimization step compares the colors of the preliminary clothing style drawing and the image of the template design to obtain color data. This process is crucial for accurately identifying the similarity of clothing styles because color is often the most intuitive and easily imitated element in clothing design.

[0113] Specifically, pixel samples in a preset sample color library can be processed to obtain an RGB numerical matrix; according to the structural features of the preliminary clothing style drawing, the RGB numerical matrix is divided into multiple regions; the RGB differences and the number of pixel samples of the pixel samples in the preliminary clothing style drawing and the pixel samples in the template design drawing corresponding to the same region are determined; the color analysis value is determined based on the RGB differences and the number of pixel samples; the color analysis value is compared with the preset analysis value, and the color information is determined according to the comparison result.

[0114] Exemplarily, first, a sample color library can be preset. This color library should cover various colors commonly used in clothing design, including basic colors, popular colors, and special colors, etc. After that, the pixel samples in the sample color library are processed to obtain an RGB numerical matrix. This step digitizes the color information for subsequent calculation and comparison.

[0115] The RGB numerical matrix is divided into multiple regions. This division can be based on the structural features of the image (such as the structural features of the preliminary clothing style drawing), for example, dividing the main body of the clothes, sleeves, collars, etc. into different regions.

[0116] Pixel samples are selected as the pixel samples to be analyzed and the comparison pixel samples in each region. Pixel samples in the preliminary clothing style drawing and the pixel samples in the template design drawing corresponding to the same region can be selected. Optionally, the center point of the region or multiple points can be randomly selected as samples.

[0117] Calculate the RGB differences and the number of pixel samples between the pixel samples to be analyzed and the comparison pixel samples. The RGB differences reflect the degree of color difference, while the number of pixel samples reflects the representativeness of this difference in the entire area.

[0118] Calculate the color analysis value ε according to a preset formula. This formula can be expressed as:

[0119]

[0120] Where R1, G1, and B1 are the RGB values of the pixel samples to be analyzed, R2, G2, and B2 are the RGB values of the comparison pixel samples, and H is the number of pixel samples between the pixel samples to be analyzed and the comparison pixel samples.

[0121] Based on the comparison result between the color analysis value ε and the analysis preset value, mark the color of the pixel sample. For example, a threshold can be set. When ε is less than this threshold, the colors of the two samples are considered similar; otherwise, there is an obvious color difference.

[0122] Through this method, the present invention can accurately quantify the color differences between different clothing designs, providing an important basis for subsequent similarity calculation.

[0123] The label optimization step is responsible for optimizing the labels of the 3D source design drawings. These labels usually contain key feature information of the clothing, such as material, style, season, etc.

[0124] Among them, the material refers to the materials used to make the clothing, such as cotton, linen, silk, wool, chemical fiber, etc. Different materials have different characteristics, such as breathability, moisture absorption, warmth retention, abrasion resistance, etc., which directly affect the comfort and practicality of the clothing.

[0125] The style refers to the design features and aesthetic orientations of the clothing, such as casual, formal, retro, modern, simple, gorgeous, etc. The style determines the visual effect and applicable occasions of the clothing, reflecting the personal taste and lifestyle of the wearer.

[0126] The season adaptability refers to the ability of the clothing to adapt to different seasonal climates. For example, summer clothing needs to be light, breathable, and moisture-absorbing, while winter clothing needs to be warm and thick. Season adaptability ensures the comfort of the wearer under different climate conditions.

[0127] These three are interrelated and jointly constitute the complete image of the clothing. For example, a cotton T-shirt may have a casual style and is suitable for summer wear; while a woolen overcoat may have a formal style and is suitable for winter wear. When designing, selecting, and wearing clothing, it is very important to consider these three aspects of attributes.

[0128] The purpose of label optimization is to ensure the accuracy and completeness of this information for the subsequent duplicate checking process.

[0129] Specifically, label optimization may involve the following steps:

[0130] Check the integrity of the labels. If any key information is missing, the user needs to be prompted to supplement it.

[0131] Normalize the labels. For example, unify the synonyms for subsequent comparison.

[0132] Automatically generate or correct some labels based on the visual features of the design drawing. For example, the system may automatically add or correct style labels according to the image recognition results.

[0133] Through the collaborative work of the three specific processes of style optimization, color optimization, and label optimization, the method of the present application can comprehensively optimize the preliminary clothing style drawing, laying a solid foundation for the subsequent duplicate checking operation.

[0134] In step 104, a duplicate checking operation is performed based on the preliminary clothing style drawing and the optimized labels on the clothing style element point database to obtain the first similarity information, where the clothing style element point database is established according to the clothing line drawing and the plan drawing.

[0135] In some embodiments, the preliminary style drawing can be first matched with the design drawings in the database to obtain the similarity. It should be understood that the database can be the clothing style element point database. This matching process may involve the comprehensive application of multiple algorithms, such as image feature extraction, contour matching, texture analysis, etc. For example, the system may use the SIFT (Scale-Invariant Feature Transform) algorithm to extract the key points and descriptors of the image, and then calculate the similarity by comparing these features.

[0136] It can be understood that the calculation of similarity does not only depend on visual features, but also considers the previously optimized label information. For example, even if two pieces of clothing are very similar visually, but if their season labels are different (one is summer clothing and the other is winter clothing), the system will appropriately reduce the similarity score.

[0137] After obtaining the preliminary similarity, the system will compare this similarity with a preset value. This preset value can be adjusted according to actual needs and is usually set between 70% and 90%. If the similarity is greater than the preset value, the system will output the corresponding clothing style information. Further, the system may also perform a style review step (this step will be introduced in detail later). It can be understood that the setting of this preset value needs to balance the recall rate and the precision rate. Setting it too high may miss some similar cases, and setting it too low may generate a large number of false positives.

[0138] In some embodiments, the clothing style element point database is established based on clothing line drawings and floor plans.

[0139] The clothing style element point database is the basis of the entire duplicate checking system. Exemplarily, the establishment process includes the following steps:

[0140] 1. Obtain the line drawing and floor plan of a piece of clothing from the style information library. These images are the original information for establishing the database.

[0141] 2. Determine the vertex coordinates of the outline of the line drawing and the floor plan of the clothing and the point coordinates of the key points on the outline. This step actually transforms the clothing design into data points that can be quantitatively compared.

[0142] 3. Divide the style drawing into five large blocks according to the clothing style: collar, body, sleeve, cuff, and trouser leg. Each large block is further divided into four small areas: upper and lower, left and right, and inner and outer. This fine division enables the system to more accurately locate and compare each part of the clothing.

[0143] 4. Mark the key points and vertices on the outline of the style drawing, and the key points and vertices of the clothing elements corresponding to the vertices on the floor plan as 0 or 1. This binary marking method simplifies the subsequent comparison process and improves efficiency.

[0144] 5. Calculate the cosine value of the vertices from top to bottom within the coordinate system quadrant of the style drawing and the corresponding vertices on the floor plan, and find the maximum value of the cosine values of each vertex and each small area to obtain the cosine value extreme points. This step introduces cosine similarity and can better capture the geometric features of clothing design.

[0145] 6. Mark the cosine value extreme points as 0 or 1, and merge them to finally form the clothing style element database.

[0146] Specifically, the previously calculated cosine value extreme points can be converted into binary data (i.e., 0 or 1), and then these data are integrated together to form a comprehensive feature descriptor or feature vector. This process is to simplify the data representation form while retaining key information for subsequent comparison and duplicate checking work.

[0147] In the process of establishing the clothing style element database, in order to integrate the cosine value extreme points into a data format convenient for subsequent duplicate checking, a threshold (for example, 0.85) needs to be set first to distinguish which cosine values are considered significant, and based on this, these values are converted into binary form: if the cosine value of a certain point is greater than or equal to the threshold, it is marked as 1; otherwise, it is marked as 0.

[0148] After that, the cosine values calculated for all key contour points according to this rule are transformed to generate a feature vector composed of a series of 0s and 1s, such as a sequence like [1, 0, 1, 0]. Each clothing style corresponds to such a feature vector. By combining these vectors in a certain order, a unique digital descriptor for each design is formed.

[0149] Finally, in the database, these feature vectors are used to compare the similarity between different clothing styles. Common methods include calculating the Hamming distance, etc., so as to achieve efficient and accurate identification of repeated or similar designs. In this way, not only is the processing flow of the original data simplified, but the main geometric features of the clothing design are effectively captured, providing strong support for quickly locating repeated designs.

[0150] The database established by this method not only contains the visual features of clothing design, but also incorporates geometric and topological information, providing rich and accurate reference data for the subsequent duplicate checking process.

[0151] In some embodiments, a duplicate checking operation is performed based on the preliminary clothing style diagram and the optimized label against the clothing style element point database to obtain the first similarity information. It can also be to match the preliminary clothing style diagram with the design diagrams in the clothing style element point database through the clothing style element point retrieval model to obtain the first similarity information; wherein, the clothing style element point retrieval model is established by splitting and establishing a region index based on the markings of key points and vertices in the plane contour lines of the clothing line drawing and the plan view, as well as the key points and vertices of clothing elements.

[0152] Optionally, the steps for constructing the clothing style element point retrieval model are as follows:

[0153] First, it can be determined whether there are markings of key points and vertices in the plane contour lines of the clothing line drawing and the plan view, as well as the key points and vertices of clothing elements. This step is to ensure the integrity and consistency of the data. If it is found that the markings of some key points or vertices are missing, the system will give a warning to prompt the user to supplement the relevant information.

[0154] If the markings exist, the system will split the markings of key points and vertices in the plane contour lines of the clothing line drawing and the plan view, as well as the key points and vertices of clothing elements. The purpose of this splitting operation is to decompose the complex clothing structure into smaller and more manageable units. For example, a dress may be split into multiple parts such as the neckline, sleeves, waist, and skirt.

[0155] Next, the system will establish a region index based on the markings of key points and vertices in the planar contour lines of each clothing line drawing and plan view, as well as the markings of key points and vertices of clothing elements. This region index is a multi-dimensional data structure that contains not only the spatial information of each part of the clothing but also the semantic information of design features. For example, for a shirt, the region index may include information such as the type of collar (e.g., lapel collar, stand-up collar), the length of the sleeves (e.g., long sleeves, short sleeves), the number and position of buttons, etc.

[0156] If the marking does not exist, the system will directly establish an index based on the vertex coordinates. This flexible processing method enables the method of the present invention to adapt to input data of different qualities and degrees of completeness.

[0157] Finally, based on the vertex index and region index, the system will substitute the markings of key points and vertices in the planar contour line and the markings of key points and vertices of clothing elements into the clothing style element library to retrieve the index of the clothing style element database. This retrieval process is actually a similarity calculation process in a multi-dimensional space. The system will use efficient algorithms, such as KD-tree or ball tree, to accelerate this retrieval process.

[0158] It should be understood that the clothing information to be checked for duplication includes the line drawing and plan view of the clothing to be checked for duplication, that is, the preliminary clothing style drawing corresponds to the corresponding line drawing and plan view, and the retrieval model can be implemented for retrieval based on the line drawing and plan view corresponding to the preliminary clothing style drawing.

[0159] The retrieval model constructed by this method can significantly improve the precision rate and retrieval speed while ensuring the recall rate. This is particularly important for processing large-scale clothing design databases.

[0160] In some embodiments, the first similarity information includes a first similarity value. The duplicate checking operation is performed based on the preliminary clothing style drawing and the optimized label in the clothing style element point database to obtain the first similarity information. It is also possible to determine that the first similarity value is 100% and stop performing the duplicate checking operation when the preliminary clothing style drawing is the same as the original style in the clothing style element point database; in the case where the preliminary clothing style drawing and the original style are both different, determine the first difference between the starting serial numbers of the broken lines of the preliminary clothing style drawing and the original style and the second difference between the ending serial numbers of the broken lines of the preliminary clothing style drawing and the original style; determine the median of the first difference and the second difference as the first similarity value.

[0161] Optionally, the data retrieval and query steps provided in this application adopt an innovative multi-level comparison strategy. First, when the style to be queried is exactly the same as the original style in the database, the system will directly determine that the similarity of the original style is 100%, and stop the database query. This fast path can greatly improve the response speed of the system, especially when dealing with exactly the same designs.

[0162] However, in most cases, the style to be queried is not exactly the same as the original style in the database. At this time, the system will adopt a more complex comparison strategy. Specifically, the system will calculate the difference between the starting point serial number of the polyline of the original drawing of all styles to be queried and the original styles in the clothing style database and the starting point serial number of the polyline of the style to be queried, as well as the difference in the ending point serial number of the polyline.

[0163] The "polyline" here transforms the two-dimensional clothing design drawing into a one-dimensional sequence, greatly simplifying the comparison process. The starting and ending point serial numbers of the polyline can be regarded as a kind of "fingerprint" of clothing design, which can effectively capture the key features of the clothing contour.

[0164] It should be understood that the "starting point of the polyline" generally refers to specific marked points in the clothing style drawing, and these points are used to define the shape, structure or specific design features of the clothing. In the fields of computer vision and image processing, these points may be used to establish a digital model of the clothing style for style matching, classification or other analyses.

[0165] Among them, the starting point of the polyline in the style to be queried is matched with the corresponding starting point of the polyline of each original style in the style database. This may be based on position, shape or other features.

[0166] After calculating these differences, the system will take the median of all differences as the similarity value of the style to be queried in the clothing style database. Choosing the median instead of the average is to reduce the influence of outliers and improve the stability of the results.

[0167] Optionally, styles with a similarity value exceeding 30% can be determined as similar styles. The setting of this threshold needs to balance the recall rate and the precision rate. Setting it too high may miss some similar cases, and setting it too low may result in a large number of false positives. In practical applications, this threshold can be adjusted according to specific needs. For example, for high-end custom-made clothing, the threshold may be set higher to ensure stricter originality; while for fast fashion brands, the threshold may be set slightly lower to allow a certain degree of design reference.

[0168] In addition, the polyline can be translated to further improve the accuracy of duplicate checking. This step is to eliminate the minor differences caused by factors such as shooting angle and scaling ratio by fine-tuning the position of the polyline, so as to more accurately capture the essential features of clothing design.

[0169] Specifically, the system will attempt to add the starting sequence number of the polyline of the style to be queried to the original style in the library, or subtract the ending sequence number of the polyline of the style to be queried from the style to be queried. If this translation operation can increase the similarity, the system will adopt the result after translation. This flexible adjustment mechanism can effectively handle the minor deviations generated during image shooting or processing.

[0170] After the translation operation, the system will compare the difference between the starting sequence number and the ending sequence number of the polyline. This comparison process is in order, first comparing the starting sequence number of the polyline, and then comparing the ending sequence number of the polyline. This ordered comparison can better capture the overall structural characteristics of fashion design.

[0171] Through this method of polyline translation and ordered comparison, the present invention can effectively handle the minor differences caused by factors such as shooting angle and scaling ratio, thereby improving the accuracy and reliability of the duplicate checking result. This is particularly important for identifying plagiarized designs with minor modifications.

[0172] In step 105, output the clothing style information whose first similarity information is greater than or equal to the preset threshold.

[0173] Optionally, the system will output the clothing style diagram whose similarity exceeds the preset threshold. This preset threshold can be adjusted according to actual needs.

[0174] In some embodiments, after outputting the clothing style information whose first similarity information is greater than or equal to the preset threshold, it further includes analyzing the characteristics of the information corresponding to the label of the preliminary clothing style diagram based on the label of the preliminary clothing style diagram to obtain the target characteristics, performing a duplicate checking operation according to the target characteristics to obtain the second similarity information, and determining the similar clothing style information based on the second similarity information.

[0175] Optionally, the label of the preliminary style diagram can be identified to obtain the label data. These labels may include information such as the type, style, material, and season of the clothing.

[0176] After that, analyze the characteristics of the preliminary style diagram according to the label data. For example, if the label indicates that this is a cotton T-shirt for summer, the system will pay special attention to features such as the sleeve length, neckline design, and pattern of the clothes.

[0177] According to these characteristics, the system will re-analyze the similarity between the preliminary style diagram and the design diagram in the database. This step takes into account more detailed information and can more accurately judge whether two designs are truly similar.

[0178] Through this multi-level duplicate checking and review mechanism, the method of the present invention can effectively reduce the misjudgment rate and improve the accuracy and reliability of duplicate checking. This is of great significance for protecting original designs and avoiding plagiarism disputes.

[0179] The following will be combined with Figure 2 to further describe the method provided by the embodiments of the present application.

[0180] Please refer to Figure 2 , Figure 2 which is another flowchart of the clothing style duplicate checking method provided by some embodiments of the present application.

[0181] After starting the style duplicate checking, the clothing style to be queried is matched with the database design drawings, and the similarity is calculated. When the similarity is not greater than the preset value, the similarity is recorded; when the similarity is greater than the preset value, style review is performed, tags are further identified, features are analyzed, and the similarity is recalculated. Finally, the similarity is recorded, and the style duplicate checking operation is ended.

[0182] The following will describe in detail the implementation manner of the clothing style duplicate checking device provided by the embodiments of the present application in conjunction with the accompanying drawings.

[0183] For the clothing style duplicate checking method provided in the above embodiments, the embodiments of the present application also provide a clothing style duplicate checking device for implementing the above method, as Figure 3 shown, Figure 3 which is a module schematic block diagram of the clothing style duplicate checking device 300 of the embodiments of the present application. The clothing style duplicate checking device 300 includes:

[0184] An acquisition module 301, configured to acquire clothing information to be checked for duplication, where the clothing information includes clothing source design drawings;

[0185] A generation module 302, configured to generate a three-dimensional clothing source design drawing based on the clothing source design drawing, where the three-dimensional clothing source design drawing includes tags, and the tags include the material, style, and seasonal adaptability of the clothing;

[0186] An optimization module 303, configured to perform style optimization, color optimization, and tag optimization on the three-dimensional clothing source design drawing to obtain a preliminary clothing style drawing;

[0187] A duplicate checking module 304, configured to perform a duplicate checking operation based on the preliminary clothing style drawing and the optimized tags on the clothing style element point database to obtain first similarity information, where the clothing style element point database is established according to clothing line drawings and floor plans;

[0188] An output module 305, configured to output clothing style information whose first similarity information is greater than or equal to a preset threshold.

[0189] It can be understood that the content in the above method embodiments is applicable to the device embodiments of the present application. The functions specifically implemented by the device embodiments of the present application are the same as those in the above method embodiments, and the beneficial effects achieved are also the same as those in the above method embodiments.

[0190] Referring to Figure 4 , an embodiment of the present application further provides an electronic device 400, which includes a memory 401, one or more processors 402( Figure 4 only 1 is shown in the figure), and a computer program stored on the memory 401 and executable on the processor 402. Among them: the memory 401 is used to store software programs and units, and the processor 402 executes various functional applications and data processing by running the software programs and units stored in the memory, so as to obtain the resources corresponding to the above preset events. Optionally, when the processor 402 runs the above computer program stored in the memory 401, the above clothing style duplicate checking method is implemented.

[0191] As a non-transitory computer-readable medium, the memory 401 can be used to store non-transitory software programs and non-transitory computer-executable programs. In addition, the memory 401 may include high-speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, a flash memory device, or other non-transitory solid-state storage devices. In some embodiments, the memory 401 may optionally include a memory remotely provided with respect to the processor, and these remote memories may be connected to the processor 402 through a network.

[0192] It can be understood that the content in the above method embodiments is applicable to the embodiment of this electronic device 400. The functions specifically implemented by the embodiment of this electronic device 400 are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those of the above method embodiments.

[0193] An embodiment of the present application further provides a computer-readable storage medium, which stores a computer program, and when the computer program is executed by a processor, the above clothing style duplicate checking method is implemented.

[0194] It can be understood that the content in the above method embodiments is applicable to the embodiment of this storage medium. The functions specifically implemented by the embodiment of this storage medium are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those of the above method embodiments.

[0195] An embodiment of the present application further provides a computer program product, the above computer program product includes a computer program, and when the above computer program is executed by one or more processors, the steps of the above clothing style duplicate checking method can be implemented.

[0196] It can be understood that the content in the above method embodiments is applicable to this computer program product. The functions specifically implemented by the embodiments of this computer program product are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those of the above method embodiments.

[0197] The clothing style duplicate checking method, device, electronic device, medium and computer program product provided by the embodiments of this application improve the accuracy of duplicate checking by converting two-dimensional source design drawings into three-dimensional source design drawings. A multi-dimensional optimization method is adopted, including style optimization, color optimization and label optimization, comprehensively considering all aspects of clothing design. An innovative similarity calculation method is introduced, which can better identify potential plagiarized or overly similar designs. The clothing style duplicate checking method provided by this application realizes efficient and accurate clothing style duplicate checking through innovative image processing technology, fine feature extraction and multi-level comparison mechanisms. This method can not only help designers protect their original designs, but also provide strong technical support for the intellectual property protection of the clothing industry.

[0198] The solution provided by this application comprehensively captures the three-dimensional structure and detailed features of clothing design through innovative three-dimensional image processing technology. It adopts a multi-dimensional feature extraction method, which not only considers the visual features of clothing, but also incorporates semantic information such as style category, material, and season. By introducing a clothing style element point database and a retrieval model, this method can efficiently process large-scale design data. At the same time, its flexible parameter adjustment mechanism enables this method to adapt to the duplicate checking requirements of different types of clothing brands.

[0199] The solution provided by this application has significant advantages in many aspects. First of all, it greatly improves the accuracy of clothing style duplicate checking. By comprehensively considering the three-dimensional structure, local details and semantic information of clothing, this method can more accurately identify similar designs, effectively reducing the probability of missed judgments and misjudgments. This not only helps to protect original designs, but also provides more reliable reference information for designers and promotes innovation.

[0200] Secondly, the solution provided by this application significantly improves the duplicate checking efficiency. The innovative clothing style element point retrieval model enables the system to quickly locate potential similar designs in a large amount of data. This high efficiency enables brands to conduct duplicate checking at the initial stage of design, timely discover and solve potential intellectual property problems, and greatly reduce the risk of later disputes.

[0201] Furthermore, the flexibility and adjustability of the solution provided by this application give it a wide range of application prospects. Whether it is a high-end custom brand or a fast fashion brand, it can meet its specific duplicate checking requirements by adjusting relevant parameters. This adaptability enables this method to be widely applied in the entire clothing industry, thereby promoting the improvement of the intellectual property protection level of the entire industry.

[0202] Finally, the implementation of the solution provided by this application not only benefits individual brands but also promotes the healthy development of the entire clothing industry. By providing a reliable duplicate-checking tool, it encourages original designs, suppresses plagiarism, and helps create a fair and innovative industry environment. In the long run, this will promote the diversity and innovation of clothing design, ultimately benefiting consumers.

[0203] In summary, the clothing style duplicate-checking method of the solution provided by this application solves many problems existing in the existing duplicate-checking methods through innovative technical means. It not only improves the accuracy and efficiency of duplicate-checking but also has good flexibility and adaptability. The wide application of this method will strongly promote the progress of intellectual property protection in the clothing industry and promote the healthy development of the industry.

[0204] The embodiments described in the embodiments of this application are for more clearly illustrating the technical solutions of the embodiments of this application and do not constitute a limitation on the technical solutions provided by the embodiments of this application. Those skilled in the art will know that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by the embodiments of this application are equally applicable to similar technical problems.

[0205] Although specific implementation schemes are described herein, those of ordinary skill in the art will recognize that many other modifications or alternative implementation schemes are also within the scope of this disclosure. For example, any one of the functions and / or processing capabilities described in connection with a particular device or component can be performed by any other device or component. Additionally, although various illustrative specific implementations and architectures have been described in accordance with the embodiments of this disclosure, those of ordinary skill in the art will recognize that many other modifications to the illustrative specific implementations and architectures described herein are also within the scope of this disclosure.

[0206] Certain aspects of the present disclosure have been described above with reference to block diagrams and flowcharts of systems, methods, systems, and / or computer program products according to exemplary embodiments. It should be understood that one or more blocks in the block diagrams and flowcharts, and combinations of blocks in the block diagrams and flowcharts, can be implemented respectively by executing computer-executable program instructions. Similarly, according to some embodiments, some blocks in the block diagrams and flowcharts may not need to be executed in the order shown, or may not need to be executed at all. Additionally, additional components and / or operations beyond those shown in the blocks of the block diagrams and flowcharts may exist in some embodiments.

[0207] Accordingly, the blocks in the block diagrams and flowcharts support combinations of devices for performing the specified functions, combinations of elements or steps for performing the specified functions, and program instruction devices for performing the specified functions. It should also be understood that each block in the block diagrams and flowcharts, and combinations of blocks in the block diagrams and flowcharts, can be implemented by a special-purpose hardware computer system that performs a specific function, element, or step, or a combination of special-purpose hardware and computer instructions.

[0208] The program modules, applications, etc. described herein may include one or more software components, including, for example, software objects, methods, data structures, etc. Each such software component may include computer-executable instructions that, upon execution, cause at least a portion of the functions described herein (e.g., one or more operations of the exemplary methods described herein) to be performed.

[0209] Software components can be encoded in any of a variety of programming languages. An exemplary programming language can be a low-level programming language, such as an assembly language associated with a particular hardware architecture and / or operating system platform. Software components that include assembly language instructions may need to be converted to executable machine code by an assembler before being executed by the hardware architecture and / or platform. Another exemplary programming language can be a higher-level programming language that can be ported across multiple architectures. Software components that include higher-level programming languages may need to be converted to an intermediate representation by an interpreter or compiler before execution. Other examples of programming languages include, but are not limited to, macro languages, shell or command languages, job control languages, scripting languages, database query or search languages, or report writing languages. In one or more exemplary embodiments, software components that include instructions in one of the above examples of programming languages can be executed directly by the operating system or other software components without first being converted to another form.

[0210] The embodiments of the present application have been described in detail above with reference to the accompanying drawings. However, the present application is not limited to the above embodiments, and various changes can be made without departing from the spirit of the present application within the knowledge of those of ordinary skill in the art.

Claims

1. A method for checking duplicate clothing styles, characterized in that, It includes the following steps: Obtain the clothing information to be checked for duplication, where the clothing information includes the original clothing design drawing; Generate a three-dimensional original clothing design drawing based on the original clothing design drawing. The three-dimensional original clothing design drawing includes labels, and the labels include the material, style, and seasonal adaptability of the clothing; Perform style optimization, color optimization, and label optimization on the three-dimensional original clothing design drawing to obtain a preliminary clothing style drawing; Perform a duplication check operation based on the preliminary clothing style drawing and the optimized label on the clothing style element point database to obtain the first similarity information. Among them, the clothing style element point database is established based on the clothing line drawing and the plan view; Output the clothing style information whose first similarity information is greater than or equal to the preset threshold.

2. The method for checking duplicate clothing styles according to claim 1, wherein After outputting the clothing style information whose first similarity information is greater than or equal to the preset threshold, the method further includes: Analyze the characteristics of the information corresponding to the label of the preliminary clothing style drawing based on the label of the preliminary clothing style drawing to obtain the target characteristics; Perform a duplication check operation according to the target characteristics to obtain the second similarity information; Determine the similar clothing style information based on the second similarity information.

3. The method for checking duplicate clothing styles according to claim 1, characterized in that, The generating a three-dimensional original clothing design drawing based on the original clothing design drawing includes: Perform image acquisition on the original clothing design drawing, and generate an original design image pixel matrix according to the acquired image; Determine the first parameter and the second parameter. Among them, the first parameter is the maximum pixel distance of the original design image pixel matrix, and the second parameter is the maximum pixel distance of the template design image pixel matrix; Calculate the ratio of the maximum pixel distance of the first parameter to the second parameter to obtain the first ratio; Determine the target scale factor according to the first ratio, the initial scale factor, and the standard ratio; Adjust the pixel distance in the original design image pixel matrix through the target scale factor to obtain the three-dimensional original clothing design drawing.

4. The clothing style duplicate checking method according to claim 1, characterized in that, The preliminary clothing style drawing includes color information. The performing style optimization, color optimization, and label optimization on the three-dimensional original clothing design drawing to obtain the preliminary clothing style drawing includes: Determine the style category of the three-dimensional original clothing design drawing according to the three-dimensional original clothing design drawing and the template design drawing; Adjust the three-dimensional original clothing design drawing according to the style category to obtain the preliminary clothing style drawing; Compare the colors of the preliminary clothing style drawing and the template design drawing according to the preset color analysis algorithm to obtain the color information; Perform integrity, standardization, and automatic correction processing on the label to obtain the optimized label corresponding to the preliminary clothing style drawing.

5. The method for checking duplicate clothing styles according to claim 4, characterized in that, The comparing the colors of the preliminary clothing style drawing and the template design drawing according to the preset color analysis algorithm to obtain the color information includes: Process the pixel samples in the preset sample color library to obtain an RGB value matrix; Divide the RGB value matrix into multiple regions according to the structural characteristics of the preliminary clothing style drawing; Determine the RGB difference and the number of pixel samples of the pixel samples in the preliminary clothing style drawing and the pixel samples in the template design drawing corresponding to the same region; Determine the color analysis value according to the RGB difference and the number of pixel samples; Compare the color analysis value with the analysis preset value, and determine the color information according to the comparison result.

6. The method for checking duplicate clothing styles according to claim 1, wherein, Performing a duplicate check operation based on the preliminary clothing style diagram and the optimized label on the clothing style element point database to obtain first similarity information, including: Matching the preliminary clothing style diagram with the design diagrams in the clothing style element point database through a clothing style element point retrieval model to obtain first similarity information; Among them, the clothing style element point retrieval model is established by splitting and establishing a region index based on the marking of key points and vertices in the plane contour lines of the clothing line drawing and the plan view, as well as the key points and vertices of clothing elements.

7. The method for checking duplicate clothing styles according to claim 1, characterized in that The first similarity information includes a first similarity value. Performing a duplicate check operation based on the preliminary clothing style diagram and the optimized label on the clothing style element point database to obtain first similarity information, including: When the preliminary clothing style diagram is the same as the original style in the clothing style element point database, determining the first similarity value to be 100% and stopping the duplicate check operation; When the preliminary clothing style diagram and the original style are both different, determining a first difference between the starting serial numbers of the broken lines of the preliminary clothing style diagram and the original style and a second difference between the ending serial numbers of the broken lines of the preliminary clothing style diagram and the original style; Determining the median of the first difference and the second difference as the first similarity value.

8. A clothing style duplicate checking device, characterized in that, The device includes: An acquisition module for acquiring clothing information to be checked for duplicates, where the clothing information includes a clothing source design diagram; A generation module for generating a clothing three-dimensional source design diagram based on the clothing source design diagram, where the clothing three-dimensional source design diagram includes a label, and the label includes the material, style, and seasonal adaptability of the clothing; An optimization module for performing style optimization, color optimization, and label optimization on the clothing three-dimensional source design diagram to obtain a preliminary clothing style diagram; A duplicate check module for performing a duplicate check operation based on the preliminary clothing style diagram and the optimized label on the clothing style element point database to obtain first similarity information, where the clothing style element point database is established according to the clothing line drawing and the plan view; An output module for outputting clothing style information with the first similarity information greater than or equal to a preset threshold.

9. An electronic device, characterized in that, The electronic device includes a memory and a processor. When the processor executes the computer program, it implements the clothing style duplicate check method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program. When the computer program is executed by the processor, it implements the clothing style duplicate check method according to any one of claims 1 to 7.

Images