Anti-wrinkle treatment method for overcoat fabric

Abstract

The invention discloses an overcoat fabric anti-wrinkle treatment method, and relates to the related field of garment manufacturing, and the method comprises the steps: obtaining the use scene information of a target overcoat fabric, carrying out the test state analysis, and obtaining an overcoat fabric test state parameter table; carrying out an anti-wrinkle test, and carrying out image acquisition on the test process through a high-resolution camera device to obtain an overcoat fabric image data set; preprocessing the overcoat fabric image data set based on an image data preprocessing program to obtain a standard overcoat fabric image data set; performing wrinkle area detection and characteristic quantitative analysis to obtain an overcoat fabric wrinkle characteristic quantitative result; and performing statistical analysis according to the anti-wrinkle performance index set, generating an overcoat fabric anti-wrinkle performance report, and performing anti-wrinkle optimization treatment on the target overcoat fabric. The technical problem that the optimization effect is limited due to inaccurate crease resistance evaluation in the crease resistance treatment of the existing overcoat fabric is solved, and the technical effects of improving the crease resistance evaluation accuracy and optimization pertinence are achieved.

Description

Technical Field

[0001] The present application relates to the field of clothing manufacturing, and in particular to a method for anti-wrinkle treatment of coat fabrics. Background Art

[0002] In the field of clothing manufacturing, coats are important outerwear garments, and the selection and processing of their fabrics are directly related to the appearance quality, wearing comfort and durability of the garments. As consumers' requirements for clothing quality continue to increase, the wrinkle resistance of coat fabrics has become one of the important indicators for measuring clothing quality. Fabrics with good wrinkle resistance can effectively resist deformation under the action of external forces, maintain the flatness and aesthetics of clothing, and extend the service life of clothing. Existing wrinkle resistance treatment methods for coat fabrics rely on the experience of fabric manufacturers or clothing designers to judge the wrinkle resistance of fabrics. They lack objective and accurate evaluation standards and cannot accurately quantify the wrinkle degree and distribution characteristics of fabrics. Due to the inaccuracy of the evaluation method, the wrinkle resistance optimization treatment of coat fabrics lacks pertinence and effectiveness, and the optimization effect is limited.

[0003] In the current relevant technologies, the anti-wrinkle treatment of coat fabrics has the technical problem of inaccurate anti-wrinkle performance evaluation, resulting in limited optimization effect. Summary of the invention

[0004] The present application provides an anti-wrinkle treatment method for coat fabrics, obtains usage scenario information of target coat fabrics, performs test status analysis, performs anti-wrinkle testing according to a coat fabric test status parameter table, uses a high-resolution camera to capture images of the test process, obtains a coat fabric image data set, pre-processes the image data set through an image data pre-processing program, obtains a standard coat fabric image data set, further performs wrinkle area detection and feature quantification analysis on the standard image data set, obtains a quantitative result of wrinkle features of the coat fabric, performs statistical analysis on the quantitative result of wrinkle features according to an anti-wrinkle performance index set, generates an anti-wrinkle performance report for the coat fabric, and performs anti-wrinkle optimization processing on the target coat fabric based on the report, thereby achieving the technical effect of improving the accuracy of anti-wrinkle performance evaluation and optimizing the pertinence.

[0005] The present application provides a method for anti-wrinkle treatment of coat fabrics, comprising: The method comprises the following steps: obtaining usage scenario information of a target coat fabric, performing a test status analysis on the usage scenario information, and obtaining a coat fabric test status parameter table; performing an anti-wrinkle test on the target coat fabric according to the coat fabric test status parameter table, and simultaneously performing image acquisition of the test process through a high-resolution camera device to obtain a coat fabric image data set; obtaining an image data preprocessing program, and preprocessing the coat fabric image data set based on the image data preprocessing program to obtain a standard coat fabric image data set; performing wrinkle area detection and feature quantification analysis on the standard coat fabric image data set to obtain a coat fabric wrinkle feature quantification result; performing statistical analysis on the coat fabric wrinkle feature quantification result according to an anti-wrinkle performance index set to generate a coat fabric wrinkle performance report, and performing anti-wrinkle optimization processing on the target coat fabric based on the coat fabric wrinkle performance report.

[0006] In a possible implementation, the coat fabric test state parameter table is obtained, and the following processing is performed: Acquire coat usage scenario factor information, wherein the coat usage scenario factor information includes usage environment, usage status and usage behavior; perform usage status analysis on the usage scenario information based on the coat usage scenario factor information to obtain a usage scenario factor status set; perform test parameter analysis on the usage scenario factor status set to obtain a usage scenario factor test parameter set; perform parameter orthogonal arrangement on the usage scenario factor test parameter set to obtain a coat fabric test status parameter table.

[0007] In a possible implementation, the standard coat fabric image dataset is obtained and the following processing is performed: According to the image data preprocessing procedure, an image denoising processing procedure and an image enhancement processing procedure are determined; the coat fabric image dataset is converted into a fabric grayscale image dataset, noise identification and classification are performed on the fabric grayscale image dataset to obtain multi-scale image data noise; multi-scale noise filtering rules are obtained according to the image denoising processing procedure, and filtering preprocessing is performed on the multi-scale image data noise based on the multi-scale noise filtering rules to obtain a denoised coat fabric image dataset; image enhancement processing is performed on the denoised coat fabric image dataset based on the image enhancement processing procedure to obtain the standard coat fabric image dataset.

[0008] In a possible implementation, the standard coat fabric image dataset is obtained, and the following processing is performed: According to the denoised coat fabric image dataset, an image grayscale distribution histogram is generated; based on the image enhancement processing program, the image grayscale distribution histogram is equalized to obtain a fabric balanced image dataset; edge detection is performed on the fabric balanced image dataset through a Canny edge detector to obtain fabric edge detection information; edge contour screening is performed on the fabric edge detection information by using a preset edge threshold to obtain fabric edge contour information; image enhancement processing is performed on the denoised coat fabric image dataset based on the fabric edge contour information to obtain the standard coat fabric image dataset.

[0009] In a possible implementation, the process of obtaining the quantitative result of the wrinkle feature of the coat fabric is as follows: A convolutional neural network is used to perform morphological annotation training on a historical coat fabric wrinkle dataset to generate a fabric image wrinkle recognition network; wrinkle detection is performed on the standard coat fabric image dataset based on the fabric image wrinkle recognition network to determine a coat fabric wrinkle morphology detection set; wrinkle areas of the standard coat fabric image dataset are marked according to the coat fabric wrinkle morphology detection set to obtain a coat fabric wrinkle area anchor frame set; feature clustering and quantitative analysis is performed on the coat fabric wrinkle area anchor frame set in turn to obtain a coat fabric wrinkle feature quantification result.

[0010] In a possible implementation, the obtaining of the coat fabric wrinkle feature quantification result may include performing the following processing: According to the coat fabric wrinkle morphology detection set, the coat fabric wrinkle area anchor frame set is clustered by morphological features to obtain a fabric wrinkle morphology clustered area set; a wrinkle feature evaluation index set is obtained, and the wrinkle feature evaluation index set includes wrinkle area, wrinkle depth and wrinkle distribution; based on the wrinkle feature evaluation index set, the fabric wrinkle morphology clustered area set is evaluated and calculated to obtain a fabric clustered area wrinkle feature set; statistical quantitative analysis is performed on the fabric clustered area wrinkle feature set in turn to obtain a quantitative result of the coat fabric wrinkle feature.

[0011] In a possible implementation, the anti-wrinkle optimization process is performed on the target coat fabric based on the anti-wrinkle performance report of the coat fabric, and the following processes are performed: A coat fabric treatment process database is constructed, wherein the coat fabric treatment process database includes fabric treatment process data of different fabric attributes and corresponding wrinkle treatment effect data; the coat fabric treatment process database is matched and divided based on the attribute information of the target coat fabric to obtain a coat fabric treatment process selection space; the coat fabric anti-wrinkle performance report is used as a constraint parameter, a global optimization is performed in the coat fabric treatment process selection space to obtain coat fabric anti-wrinkle process parameters; and anti-wrinkle optimization treatment is performed on the target coat fabric based on the coat fabric anti-wrinkle process parameters.

[0012] In a possible implementation, the anti-wrinkle optimization process is performed on the target coat fabric based on the anti-wrinkle process parameters of the coat fabric, and the following processes are performed: Based on the anti-wrinkle process parameters of the coat fabric, the target coat fabric is subjected to anti-wrinkle treatment to obtain feedback parameters of the fabric anti-wrinkle effect; the feedback parameters of the fabric anti-wrinkle effect are optimized and analyzed to obtain parameter variation rules; based on the parameter variation rules, the anti-wrinkle process parameters of the coat fabric are mutated and fine-tuned to obtain optimized anti-wrinkle process parameters of the coat fabric.

[0013] The present application proposes an anti-wrinkle treatment method for coat fabrics. First, usage scenario information of the target coat fabric is obtained, and a test status analysis is performed on the usage scenario information to obtain a coat fabric test status parameter table. Then, an anti-wrinkle test is performed on the target coat fabric according to the coat fabric test status parameter table. At the same time, images of the test process are captured by a high-resolution camera to obtain a coat fabric image data set. Then, an image data preprocessing program is obtained, and the coat fabric image data set is preprocessed based on the image data preprocessing program to obtain a standard coat fabric image data set. Then, wrinkle area detection and feature quantification analysis are performed on the standard coat fabric image data set to obtain a coat fabric wrinkle feature quantification result. Finally, a statistical analysis is performed on the coat fabric wrinkle feature quantification result according to an anti-wrinkle performance index set to generate a coat fabric anti-wrinkle performance report. Based on the coat fabric anti-wrinkle performance report, the target coat fabric is subjected to anti-wrinkle optimization treatment, thereby achieving the technical effect of improving the accuracy of anti-wrinkle performance evaluation and optimizing targetedness. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the technical solution of the embodiment of the present invention, the accompanying drawings of the embodiment of the present invention will be briefly introduced below. A flow chart is used in the present application to illustrate the operations performed by the method according to the embodiment of the present application. It should be understood that the preceding or following operations are not necessarily performed accurately in order. On the contrary, various steps can be processed in reverse order or simultaneously as needed. At the same time, other operations can also be added to these processes, or one or more operations can be removed from these processes.

[0015] Figure 1 A schematic flow chart of a method for anti-wrinkle treatment of coat fabric provided in an embodiment of the present application.

[0016] Figure 2 A schematic diagram of a process for obtaining quantitative results of wrinkle characteristics of a coat fabric in a method for anti-wrinkle treatment of a coat fabric provided in an embodiment of the present application. DETAILED DESCRIPTION

[0017] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below.

[0018] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.

[0019] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict. The terms "including" and "having" and any variations are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by technicians in the technical field of this application. The terms used herein are for the purpose of describing the embodiments of the present application only.

[0020] The present application embodiment provides a method for anti-wrinkle treatment of coat fabrics, such as Figure 1 As shown, the method includes: Step S100, obtaining the usage scenario information of the target coat fabric, performing a test status analysis on the usage scenario information, and obtaining a coat fabric test status parameter table. Specifically, information about the expected usage scenarios of the target coat fabric is collected, that is, various environments and conditions that the coat fabric may encounter in actual use, including environmental conditions (such as temperature, humidity), the wearer's activity level, washing and maintenance methods, etc. These usage scenario information are analyzed to determine how they affect the performance and performance of the coat fabric. Based on the analysis results, a coat fabric test status parameter table is formulated, which describes how to test the anti-wrinkle performance of the coat fabric in different usage scenarios, that is, the parameters and conditions required to test the anti-wrinkle performance of the coat fabric in different usage scenarios.

[0021] In a possible implementation, the coat fabric test state parameter table is obtained, and step S100 further includes step S110, obtaining the coat use scenario factor information, and the coat use scenario factor information includes the use environment, use state and use behavior. Specifically, through market research, user interviews, experimental tests and other methods, information about various scenario factors that the coat fabric may encounter in actual use is collected, including but not limited to the use environment of the coat (the environmental conditions of the coat fabric in actual use, such as temperature, humidity, lighting conditions, etc.), the use state of the coat (the specific form or state of the coat fabric during use, such as hanging, washing, wearing, etc.) and use behavior (the specific operation or behavior performed by the user or wearer on the coat fabric, such as the wearer's activity habits, etc.). Step S120, based on the coat use scenario factor information, the use scenario information is analyzed for the use scenario to obtain a use scenario factor state set. Specifically, after obtaining information on coat usage scenario factors, we analyze how they affect the performance and appearance of the coat fabric, including analyzing the impact of different environmental factors on the fabric (such as high temperature and high humidity environment may cause fabric deformation), and the impact of different usage conditions and behaviors on the anti-wrinkle performance of the fabric (such as rubbing and washing may cause fabric wrinkles).

[0022] Step S130, respectively perform test parameter analysis on the usage scenario factor state set to obtain the usage scenario factor test parameter set. Specifically, after the usage scenario information is analyzed for the usage state, the analysis results are converted into specific test parameters, including determining the physical parameters such as temperature, humidity, pressure, etc. required for the test, as well as the test conditions such as the test time and the number of tests. Such test parameter analysis is performed for each usage scenario factor state set. Step S140, perform orthogonal arrangement of parameters on the usage scenario factor test parameter set to obtain the coat fabric test state parameter table. Specifically, after obtaining all the usage scenario factor test parameters, these parameters are orthogonally arranged to form a comprehensive coat fabric test state parameter table. Through orthogonal arrangement, it is ensured that different levels (or values) of each factor have the opportunity to appear in the test, thereby more comprehensively evaluating the anti-wrinkle performance of the coat fabric. Finally, this coat fabric test state parameter table is used as the basis for subsequent anti-wrinkle tests. This implementation method ensures that the test fully reflects the anti-wrinkle performance of coat fabrics in actual use by taking into account multiple usage scenario factors, thereby improving the comprehensiveness of the test. By analyzing the test parameters and arranging them orthogonally, it ensures that the test conditions are closer to actual usage, thereby improving the accuracy of the test.

[0023] Step S200, performing an anti-wrinkle test on the target coat fabric according to the coat fabric test state parameter table, and collecting images of the test process through a high-resolution camera device to obtain a coat fabric image dataset. Specifically, using the formulated coat fabric test state parameter table, the target coat fabric is subjected to an anti-wrinkle test (a test that evaluates the ability of a fabric to restore its original shape after being subjected to an external force). During the test, a high-resolution camera device (a photographic device that can capture images with rich details) is used to record the reaction and changes of the fabric under different test conditions, and these image data are collected to form a coat fabric image dataset.

[0024] Step S300, obtaining an image data preprocessing program, and preprocessing the coat fabric image dataset based on the image data preprocessing program to obtain a standard coat fabric image dataset. Specifically, a program for processing image data is obtained, and the program is used to improve the image quality and make it more suitable for further analysis, including steps such as denoising, enhancement, and correction. The coat fabric image dataset is processed using this program to eliminate noise, improve image quality, etc. The processed image dataset is the standard coat fabric image dataset.

[0025] In a possible implementation, the standard coat fabric image dataset is obtained, and step S300 further includes step S310, determining an image denoising processing program and an image enhancement processing program according to the image data preprocessing program. Specifically, according to the preset image data preprocessing program, two key processing subroutines are clarified: an image denoising processing program and an image enhancement processing program. The image denoising processing program is used to identify and remove noise in the image and improve the clarity of the image. The image enhancement processing program is used to enhance the contrast, brightness and other attributes of the image, so that the details in the image are clearer and convenient for subsequent analysis and processing. Step S320, converting the coat fabric image dataset into a fabric grayscale image dataset, performing noise identification and classification on the fabric grayscale image dataset, and obtaining multi-scale image data noise. Specifically, converting the color coat fabric image dataset into a grayscale image dataset. Grayscale images only contain brightness information, not color information, which helps to simplify subsequent processing steps. On the fabric grayscale image dataset, the noise is identified and classified according to its characteristics (such as frequency, amplitude, etc.) so that the noise can be removed in a targeted manner in the subsequent steps.

[0026] Step S330, obtaining a multiscale noise filtering rule according to the image denoising processing program, filtering and preprocessing the noise of the multiscale image data based on the multiscale noise filtering rule, and obtaining a denoised coat fabric image data set. Specifically, according to the result of noise identification and classification, a multiscale noise filtering rule is obtained, which takes into account the performance of noise at different scales and can remove noise more effectively. The multiscale noise filtering rule is applied to filter the image to remove the noise in the image, and obtain a denoised coat fabric image data set. Step S340, performing image enhancement processing on the denoised coat fabric image data set based on the image enhancement processing program, and obtaining the standard coat fabric image data set. Specifically, after removing the noise, the image is enhanced to improve the image's contrast, brightness and other attributes, so that the details in the image are clearer, which is convenient for subsequent wrinkle area detection and feature quantitative analysis. This implementation method improves the image quality through denoising and enhancement processing, makes the details in the image clearer, and the high-quality image can more accurately reflect the wrinkle situation of the coat fabric, thereby improving the accuracy of the analysis.

[0027] In a possible implementation, the standard coat fabric image dataset is obtained, and step S340 further includes step S341, generating an image grayscale distribution histogram according to the denoised coat fabric image dataset. Specifically, the grayscale value of each image is extracted from the denoised coat fabric image dataset, and then the frequency or number of pixels of each grayscale value is counted, and these frequencies or numbers are plotted into an image grayscale distribution histogram. This histogram shows the grayscale distribution of the image and is the basis for subsequent image enhancement processing. Step S342, based on the image enhancement processing program, the image grayscale distribution histogram is equalized to obtain a fabric balanced image dataset. Specifically, the image grayscale distribution histogram generated in step S341 is equalized, and the equalization processing is achieved by redistributing the grayscale value, the purpose of which is to adjust the grayscale distribution of the image so that the grayscale value distribution of the output image is more uniform, thereby enhancing the contrast of the image and improving the visual effect of the image. Step S343, edge detection is performed on the fabric balanced image dataset through a Canny edge detector to obtain fabric edge detection information. Specifically, the Canny edge detector is used to perform edge detection on the fabric equalization image data set that has been equalized. The Canny edge detector is a multi-stage algorithm, including steps such as noise removal, image gradient calculation, non-maximum suppression and dual threshold detection, and finally generates an edge image. Step S344, the edge threshold is preset to perform edge contour screening on the fabric edge detection information to obtain fabric edge contour information. Specifically, according to the preset edge threshold, the edge image generated in step S343 is screened to remove the pseudo edges caused by noise and retain the true fabric edge contour information. Step S345, based on the fabric edge contour information, the denoised coat fabric image data set is subjected to image enhancement processing to obtain the standard coat fabric image data set. Specifically, using the fabric edge contour information obtained in step S344, the denoised coat fabric image data set is further subjected to image enhancement processing, including contrast enhancement, sharpening and other processing, to highlight the edge contour of the fabric and make the image clearer. This implementation method improves the contrast and clarity of the image through grayscale distribution histogram equalization and edge detection, making the edge contour of the fabric more prominent, providing high-quality image data for subsequent fabric wrinkle area detection and feature quantitative analysis, and improving the accuracy and reliability of the evaluation of the anti-wrinkle performance of coat fabrics.

[0028] Step S400, performing wrinkle region detection and feature quantitative analysis on the standard coat fabric image dataset to obtain a coat fabric wrinkle feature quantitative result. Specifically, using image processing technology (such as morphological analysis, etc.) to detect wrinkle regions in the standard coat fabric image dataset, performing feature quantitative analysis on these wrinkle regions, such as measuring the area, depth, distribution, etc. of the wrinkles, collating these quantitative data, and forming a coat fabric wrinkle feature quantitative result, that is, the coat fabric wrinkle feature quantitative result is a document or dataset containing coat fabric wrinkle feature quantitative data.

[0029] In a possible implementation, the step S400 of obtaining the quantitative result of the coat fabric wrinkle feature further includes step S410, using a convolutional neural network to perform morphological annotation training on the historical coat fabric wrinkle dataset to generate a fabric image wrinkle recognition network. Specifically, a large number of historical coat fabric wrinkle datasets are collected, which contain various wrinkle morphologies and wrinkle images of different degrees. The collected data are annotated to clarify the morphology and characteristics of the wrinkles in each image to form an annotated dataset. A fabric image wrinkle recognition network model is constructed using a convolutional neural network (CNN), the annotated dataset is input into the CNN model, and the model parameters are adjusted through forward propagation and back propagation algorithms so that the model can accurately identify the wrinkle morphology in the fabric image. The model is verified and tested using a validation dataset that is not involved in the training to ensure the accuracy and generalization ability of the model. Step S420, wrinkle detection is performed on the standard coat fabric image dataset based on the fabric image wrinkle recognition network to determine a coat fabric wrinkle morphology detection set. Specifically, the standard coat fabric image dataset is input into the trained fabric image wrinkle recognition network. The network extracts and classifies the input images, identifies the wrinkle morphology in the images, and outputs the identified wrinkle morphology to form a coat fabric wrinkle morphology detection set.

[0030] Step S430, marking the wrinkle area of ​​the standard coat fabric image data set according to the coat fabric wrinkle morphology detection set, and obtaining the coat fabric wrinkle area anchor frame set. Specifically, according to the coat fabric wrinkle morphology detection set, determine the specific position of each wrinkle in the image, and generate one or more anchor frames (i.e., rectangular frames) around each wrinkle position to mark the wrinkle area. Output all generated anchor frames to form the coat fabric wrinkle area anchor frame set. Step S440, perform feature clustering quantitative analysis on the coat fabric wrinkle area anchor frame set in turn to obtain the coat fabric wrinkle feature quantitative result. Specifically, extract features of the wrinkle area in each anchor frame, including features such as the area, depth, and shape of the wrinkles. Use a clustering algorithm (such as K-means clustering) to perform cluster analysis on the extracted features, and classify similar wrinkle features together. Perform quantitative analysis on the clustered features, and calculate quantitative indicators such as the average wrinkle area and the maximum wrinkle depth of each category. Output the quantitative analysis results to form the coat fabric wrinkle feature quantitative result. This implementation uses a convolutional neural network for wrinkle recognition training, which can learn the complex features of wrinkles in fabric images and improve the accuracy and robustness of recognition. By performing feature clustering and quantitative analysis on the wrinkle area, the wrinkle resistance of the fabric is comprehensively evaluated, including indicators such as the area, depth, and distribution uniformity of the wrinkles, providing strong data support for fabric optimization.

[0031] like Figure 2 As shown, in a possible implementation, the step of obtaining the quantitative result of the coat fabric wrinkle feature, step S440 further includes step S441, clustering the morphological features of the coat fabric wrinkle region anchor frame set according to the coat fabric wrinkle morphology detection set, and obtaining a fabric wrinkle morphology clustered region set. Specifically, according to the coat fabric wrinkle morphology detection set, the wrinkle morphology in each anchor frame is determined. The morphological features of the wrinkles are extracted from each anchor frame, including the shape, direction, curvature, etc. of the wrinkles. Using a clustering algorithm, the anchor frames are clustered according to the extracted morphological features, and the anchor frames with similar morphological features are classified into one category to form a fabric wrinkle morphology clustered region set. Step S442, obtaining a set of wrinkle feature evaluation indicators, the set of wrinkle feature evaluation indicators including wrinkle area, wrinkle depth and wrinkle distribution. Specifically, according to the needs of anti-wrinkle performance evaluation, a set of wrinkle feature evaluation indicators is determined, and these indicators include wrinkle area, wrinkle depth and wrinkle distribution. The wrinkle area refers to the area of ​​the wrinkle region in the image (which can be the number of pixels in the wrinkle region in the image); the wrinkle depth refers to the vertical depth of the wrinkle (the distance from the highest point to the lowest point of the wrinkle), which reflects the severity of the wrinkle; the wrinkle distribution refers to the distribution of wrinkles on the fabric, such as uniform distribution or local concentration.

[0032] Step S443, based on the wrinkle feature evaluation index set, the fabric wrinkle morphology clustering region set is evaluated and calculated respectively to obtain the fabric clustering region wrinkle feature set. Specifically, for each anchor frame in the clustering region set, the corresponding wrinkle feature data is extracted, and each clustering region is evaluated and calculated separately according to the wrinkle feature evaluation index set. For example, the average wrinkle area, maximum wrinkle depth, etc. of each clustering region are calculated. The evaluation calculation results are recorded to form the fabric clustering region wrinkle feature set. Step S444, statistical quantitative analysis is performed on the fabric clustering region wrinkle feature set in turn to obtain the quantitative results of the coat fabric wrinkle features. Specifically, the data of each type of wrinkle morphology in the fabric clustering region wrinkle feature set is summarized to form an overall fabric wrinkle feature data set. Statistical analysis is performed on the overall fabric wrinkle feature data set, such as calculating the average wrinkle area, the average value of the maximum wrinkle depth, the discrete degree of wrinkle distribution, etc. The statistical analysis results are output to form the quantitative results of the coat fabric wrinkle features. This implementation method uses a clear set of wrinkle feature evaluation indicators for quantitative analysis. The wrinkle feature evaluation indicator set covers multiple aspects such as wrinkle area, wrinkle depth and wrinkle distribution, and comprehensively reflects the anti-wrinkle performance of the fabric. By conducting statistical analysis on these indicators, the comprehensiveness of the fabric anti-wrinkle performance evaluation is improved, providing strong data support for fabric optimization and quality control.

[0033] Step S500, statistically analyzing the quantitative results of the wrinkle characteristics of the coat fabric according to the anti-wrinkle performance index set, generating a coat fabric anti-wrinkle performance report, and performing anti-wrinkle optimization processing on the target coat fabric based on the coat fabric anti-wrinkle performance report. Specifically, statistically analyzing the quantitative results of the wrinkle characteristics of the coat fabric according to the preset anti-wrinkle performance index set (a set of indicators for evaluating the anti-wrinkle performance of the fabric, such as the average wrinkle area, the maximum wrinkle depth, the uniformity of the wrinkle distribution, etc.). Based on the results of the statistical analysis, a coat fabric anti-wrinkle performance report is generated, which describes the anti-wrinkle performance of the fabric in detail. According to the data in the report, the target coat fabric is subjected to anti-wrinkle optimization processing, such as adjusting the fabric composition, production process, etc. The embodiment of the present application obtains the usage scenario information of the target coat fabric, performs test status analysis, and performs anti-wrinkle test according to the coat fabric test status parameter table, uses a high-resolution camera to collect images of the test process, obtains a coat fabric image data set, pre-processes the image data set through an image data pre-processing program to obtain a standard coat fabric image data set, further performs wrinkle area detection and feature quantification analysis on the standard image data set to obtain a quantification result of the coat fabric wrinkle feature, performs statistical analysis on the quantification result of the wrinkle feature according to the anti-wrinkle performance index set, generates an anti-wrinkle performance report of the coat fabric, and performs anti-wrinkle optimization processing on the target coat fabric based on the report, and other technical means, thereby achieving the technical effect of improving the accuracy of anti-wrinkle performance evaluation and optimizing the pertinence.

[0034] In a possible implementation, the anti-wrinkle optimization treatment of the target coat fabric is performed based on the anti-wrinkle performance report of the coat fabric, and step S500 further includes step S510, constructing a coat fabric treatment process database, wherein the coat fabric treatment process database includes fabric treatment process data of different fabric attributes and corresponding wrinkle treatment effect data. Specifically, a large amount of coat fabric treatment process data (such as temperature, time, pressure, type of chemical reagent, etc.) of different fabric attributes (fabric material, fiber type, weaving method, dye type, etc.) is collected. For coat fabrics of each fabric attribute, the wrinkle treatment effect data after different treatment processes are recorded, such as the average wrinkle area after treatment, the maximum wrinkle depth, etc. The collected fabric attribute information, treatment process data and wrinkle treatment effect data are integrated to construct a coat fabric treatment process database, which is used for query, matching and data analysis.

[0035] Step S520, matching and dividing the coat fabric treatment process database based on the attribute information of the target coat fabric, and obtaining a coat fabric treatment process selection space. Specifically, extract the attribute information of the target coat fabric, such as material, fiber type, etc. Match the extracted attribute information with the fabric attribute information in the coat fabric treatment process database, and filter out fabric treatment process data with similar attributes to the target coat fabric. According to the matching result, integrate the filtered fabric treatment process data into a coat fabric treatment process selection space, which contains a series of treatment processes that may be applicable to the target coat fabric.

[0036] Step S530, taking the anti-wrinkle performance report of the coat fabric as a constraint parameter, performing global optimization in the coat fabric processing technology selection space, and obtaining the anti-wrinkle process parameters of the coat fabric. Specifically, the quantitative results (such as average wrinkle area, maximum wrinkle depth, etc.) in the anti-wrinkle performance report of the coat fabric are taken as constraint parameters. In the coat fabric processing technology selection space, a global optimization algorithm is applied to search and find the optimal processing process parameter combination that meets the constraint parameter requirements. According to the output result of the global optimization algorithm, the optimal processing process parameter combination is determined. Step S540, performing anti-wrinkle optimization treatment on the target coat fabric based on the anti-wrinkle process parameters of the coat fabric. Specifically, according to the optimal processing process parameter combination determined in step S530, the parameters of the processing equipment are set. The target coat fabric is placed in the processing equipment and processed according to the set parameters. After the processing is completed, the wrinkle characteristics of the target coat fabric are quantitatively analyzed to evaluate whether the processing effect meets the expected requirements. This implementation method can quickly screen out the processing technology that may be applicable to the target coat fabric by constructing a database and matching and dividing, thereby reducing the trial and error cost and time. The global optimization algorithm can search for the optimal solution in the space of coat fabric treatment process selection, ensuring that the treatment process parameters found can maximize the improvement of the fabric's anti-wrinkle performance and optimize the treatment effect.

[0037] In a possible implementation, the anti-wrinkle optimization treatment of the target coat fabric is performed based on the anti-wrinkle process parameters of the coat fabric, and step S540 further includes step S541, performing anti-wrinkle treatment on the target coat fabric based on the anti-wrinkle process parameters of the coat fabric to obtain feedback parameters of the anti-wrinkle effect of the fabric. Specifically, according to the anti-wrinkle process parameters of the coat fabric obtained in step S530, various parameters of the anti-wrinkle treatment equipment (such as steam iron, press, etc.) are adjusted, such as temperature, time, pressure, amount of chemical reagents, etc. The target coat fabric is placed in the anti-wrinkle treatment equipment and anti-wrinkle treatment is performed according to the set parameters. After the treatment is completed, the anti-wrinkle effect of the fabric is quantitatively evaluated by a high-resolution camera device to obtain feedback parameters of the anti-wrinkle effect of the fabric, such as the average wrinkle area after treatment, the maximum wrinkle depth, etc. Step S542, optimizing and analyzing the feedback parameters of the anti-wrinkle effect of the fabric to obtain parameter variation rules. Specifically, statistical analysis is performed on the feedback parameters of the anti-wrinkle effect of the fabric obtained in step S541 to compare the treatment effects under different parameter combinations. According to the statistical analysis results, the key parameters and their variation rules that affect the anti-wrinkle effect of the fabric, i.e., the parameter variation rules, are extracted, including the correlation between the parameters, the influence trend of the parameter changes on the anti-wrinkle effect of the fabric, etc. Step S543, based on the parameter variation rules, the anti-wrinkle process parameters of the coat fabric are variably fine-tuned and optimized to obtain the anti-wrinkle process optimization parameters of the coat fabric. Specifically, according to the parameter variation rules obtained in step S542, the anti-wrinkle process parameters of the coat fabric are fine-tuned to further improve the anti-wrinkle effect of the fabric. By fine-tuning and evaluating the feedback parameters of the anti-wrinkle effect of the fabric for multiple times, the optimal combination of anti-wrinkle process parameters is iteratively sought. When the anti-wrinkle effect of the fabric reaches the preset standard or cannot be significantly improved, the final anti-wrinkle process optimization parameters of the coat fabric are determined. This implementation method extracts the key parameters and their variation rules that affect the anti-wrinkle effect of the fabric by optimizing and analyzing the feedback parameters of the anti-wrinkle effect of the fabric, realizes the precise adjustment of the process parameters, improves the processing accuracy, and further improves the anti-wrinkle effect of the fabric through variation fine-tuning and optimization, so that the processed fabric is flatter and smoother, meeting higher quality requirements.

[0038] The above specific implementation manner does not constitute a limitation to the protection scope of the present application. It should be understood by those skilled in the art that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present application should be included in the protection scope of the present application. In some cases, the actions or steps recorded in the present application can be performed in an order different from that in the embodiment and can still achieve the desired results. In addition, the process depicted in the accompanying drawings does not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

Claims

1. A method for anti-wrinkle treatment of coat fabrics, characterized in that: The method comprises: Obtaining usage scenario information of the target coat fabric, performing test status analysis on the usage scenario information, and obtaining a coat fabric test status parameter table; Performing an anti-wrinkle test on the target coat fabric according to the coat fabric test state parameter table, and simultaneously collecting images of the test process through a high-resolution camera device to obtain a coat fabric image data set; Acquire an image data preprocessing program, and preprocess the coat fabric image dataset based on the image data preprocessing program to obtain a standard coat fabric image dataset; Performing wrinkle region detection and feature quantification analysis on the standard coat fabric image dataset to obtain a coat fabric wrinkle feature quantification result; The quantitative results of the wrinkle characteristics of the coat fabric are statistically analyzed according to the anti-wrinkle performance index set to generate an anti-wrinkle performance report for the coat fabric, and anti-wrinkle optimization processing is performed on the target coat fabric based on the anti-wrinkle performance report for the coat fabric.

2. The method for anti-wrinkle treatment of coat fabric according to claim 1, characterized in that: The method of obtaining the coat fabric test state parameter table includes: Acquire coat usage scenario factor information, wherein the coat usage scenario factor information includes usage environment, usage status, and usage behavior; Performing a usage status analysis on the usage scenario information based on the coat usage scenario factor information to obtain a usage scenario factor status set; Performing test parameter analysis on the usage scenario factor state sets respectively to obtain a usage scenario factor test parameter set; The parameter set of the usage scenario factor test parameters is orthogonally arranged to obtain the coat fabric test state parameter table.

3. The method for anti-wrinkle treatment of coat fabric according to claim 1, characterized in that: The standard coat fabric image dataset is obtained, including: Determine an image denoising process and an image enhancement process according to the image data preprocessing process; Converting the coat fabric image dataset into a fabric grayscale image dataset, performing noise identification and classification on the fabric grayscale image dataset, and obtaining multi-scale image data noise; Obtaining a multi-scale noise filtering rule according to the image denoising processing program, and performing filtering preprocessing on the multi-scale image data noise based on the multi-scale noise filtering rule to obtain a denoised coat fabric image data set; The denoised coat fabric image dataset is subjected to image enhancement processing based on the image enhancement processing program to obtain the standard coat fabric image dataset.

4. The method for anti-wrinkle treatment of coat fabric according to claim 3, characterized in that: The step of obtaining the standard coat fabric image dataset comprises: Generate an image grayscale distribution histogram according to the denoised coat fabric image dataset; Based on the image enhancement processing program, the image grayscale distribution histogram is equalized to obtain a fabric balanced image data set; Performing edge detection on the fabric balanced image dataset using a Canny edge detector to obtain fabric edge detection information; Preset edge threshold to perform edge contour screening on the fabric edge detection information to obtain fabric edge contour information; The denoised coat fabric image dataset is subjected to image enhancement processing based on the fabric edge contour information to obtain the standard coat fabric image dataset.

5. The method for anti-wrinkle treatment of coat fabric according to claim 1, characterized in that: The method of obtaining the quantitative result of the wrinkle feature of the coat fabric comprises: Use convolutional neural networks to perform morphological annotation training on a historical coat fabric wrinkle dataset and generate a fabric image wrinkle recognition network; Performing wrinkle detection on the standard coat fabric image dataset based on the fabric image wrinkle recognition network to determine a coat fabric wrinkle morphology detection set; Marking wrinkle regions of the standard coat fabric image dataset according to the coat fabric wrinkle morphology detection set to obtain a coat fabric wrinkle region anchor frame set; The anchor frame sets of the coat fabric wrinkle region are sequentially subjected to feature clustering quantitative analysis to obtain the coat fabric wrinkle feature quantitative results.

6. The method for anti-wrinkle treatment of coat fabric according to claim 5, characterized in that: The step of obtaining the quantitative result of the wrinkle feature of the coat fabric comprises: According to the coat fabric wrinkle morphology detection set, the coat fabric wrinkle region anchor frame set is clustered by morphological features to obtain a fabric wrinkle morphology clustered region set; Obtaining a set of wrinkle feature evaluation indicators, wherein the set of wrinkle feature evaluation indicators includes wrinkle area, wrinkle depth, and wrinkle distribution; Based on the wrinkle feature evaluation index set, the fabric wrinkle morphology clustering region set is evaluated and calculated respectively to obtain a fabric clustering region wrinkle feature set; Statistical quantitative analysis is performed on the wrinkle feature sets of the fabric clustering regions in turn to obtain quantitative results of the wrinkle features of the coat fabric.

7. The method for anti-wrinkle treatment of coat fabric according to claim 1, characterized in that: The anti-wrinkle optimization treatment of the target coat fabric based on the anti-wrinkle performance report of the coat fabric comprises: Constructing a coat fabric treatment process database, wherein the coat fabric treatment process database includes fabric treatment process data of different fabric properties and corresponding wrinkle treatment effect data; Matching and dividing the coat fabric treatment process database based on the attribute information of the target coat fabric to obtain a coat fabric treatment process selection space; Taking the anti-wrinkle performance report of the coat fabric as a constraint parameter, performing global optimization in the coat fabric treatment process selection space to obtain the anti-wrinkle process parameters of the coat fabric; The target coat fabric is subjected to anti-wrinkle optimization treatment based on the anti-wrinkle process parameters of the coat fabric.

8. The method for anti-wrinkle treatment of coat fabric according to claim 7, characterized in that: The anti-wrinkle optimization treatment of the target coat fabric based on the anti-wrinkle process parameters of the coat fabric comprises: Performing anti-wrinkle treatment on the target coat fabric based on the anti-wrinkle process parameters of the coat fabric to obtain anti-wrinkle effect feedback parameters of the fabric; Optimizing and analyzing the feedback parameters of the anti-wrinkle effect of the fabric to obtain parameter variation rules; Based on the parameter variation rules, the anti-wrinkle process parameters of the coat fabric are mutated and fine-tuned to obtain the optimized anti-wrinkle process parameters of the coat fabric.

Images