Tension regulation and control method and device for cloth inspecting machine

Abstract

The invention discloses a tension regulation and control method and device for a cloth inspecting machine. The method comprises the following steps: acquiring first cloth images of target cloth at a plurality of preset points on a cloth inspecting machine and attribute parameters of the target cloth; for each first cloth image, extracting a first cloth state feature in the first cloth image, the first cloth state feature comprising at least one of the following: a wrinkle degree, a stretching degree and a relaxation degree; the attribute parameters and the first cloth state characteristics are substituted into a cloth deformation model for analysis, target tension enabling the target cloth to be kept flat and free of wrinkles at a target preset point position corresponding to the first cloth image is obtained, and the cloth deformation model is used for reflecting form change conditions of various kinds of cloth under different tensions; and adjusting the tension output by a tension device of the cloth inspecting machine at the target preset point based on the target tension. The technical problems that in a traditional cloth inspecting machine control scheme, due to inaccurate tension regulation and control, the cloth inspecting precision is low, and the cloth quality is poor are solved.

Description

Technical Field

[0001] The present application relates to the field of industrial control technology, and in particular to a method and device for controlling the tension of a cloth inspection machine. Background Art

[0002] In the textile industry, fabric inspection is a crucial process, directly impacting the quality and aesthetics of finished products. Traditional fabric inspection machines often rely on manual monitoring and adjustment, a method of operation that presents numerous limitations and challenges. On the one hand, manual monitoring makes it difficult to continuously monitor subtle changes in the fabric, especially on high-speed production lines. The naked eye struggles to capture the fabric's real-time state, leading to inaccurate tension control. Fabric is prone to wrinkling, stretching, or sagging during transport, which in turn affects the accuracy of fabric inspection results. On the other hand, manual adjustment is not only time-consuming and inefficient, but can also produce inconsistent results due to differences in operator experience, increasing production costs while reducing efficiency.

[0003] While some existing automated fabric inspection machines incorporate simple sensors to monitor fabric tension, these sensors typically provide only limited information, such as changes in linear tension, and fail to fully reflect the true condition of the fabric's flatness. Furthermore, even in higher-level automated equipment, tension adjustment is often based on fixed programs and preset parameters. This lacks the ability to respond to dynamic changes in the fabric, and prevents personalized adjustments for fabrics of different types, materials, and thicknesses. This limits the versatility and adaptability of the equipment, particularly in applications requiring high-precision fabric inspection and optimal fabric condition. Currently, no effective solutions have been proposed for these issues.

[0004] To address the above-mentioned problems, no effective solutions have been proposed so far. Summary of the Invention

[0005] The embodiments of the present application provide a method and device for controlling the tension of a cloth inspection machine, so as to at least solve the technical problem of low cloth inspection accuracy and poor cloth quality caused by inaccurate tension control in traditional cloth inspection machine control solutions.

[0006] According to one aspect of an embodiment of the present application, a tension control method for a fabric inspection machine is provided, comprising: obtaining first fabric images of a target fabric at a plurality of preset points on the fabric inspection machine, and obtaining attribute parameters of the target fabric; for each first fabric image, extracting first fabric state features in the first fabric image, wherein the first fabric state features include at least one of the following: a degree of wrinkle, a degree of stretch, and a degree of relaxation; substituting the attribute parameters and the first fabric state features into a fabric deformation model for analysis, to obtain a target tension for keeping the target fabric flat and wrinkle-free at a target preset point corresponding to the first fabric image, wherein the fabric deformation model is used to reflect the morphological changes of various fabrics under different tensions; and adjusting the tension output by a tension device of the fabric inspection machine at the target preset point based on the target tension.

[0007] Optionally, obtaining first fabric images of the target fabric at multiple preset points on the fabric inspection machine includes: using industrial cameras preset at multiple preset points on the fabric inspection machine to collect the first fabric images of the target fabric at each preset point; performing an image preprocessing operation on each first fabric image, wherein the image preprocessing operation includes at least one of the following: denoising processing, contrast enhancement processing, and grayscale processing.

[0008] Optionally, the process of determining the degree of wrinkles includes: extracting texture features in the first cloth image using a texture feature extraction method, and determining whether there is a wrinkle area in the first cloth image based on the texture features, wherein the texture feature extraction method includes at least one of the following: local binary pattern, gray level co-occurrence matrix; when there is a wrinkle area in the first cloth image, extracting shape features of the wrinkle area using a shape feature extraction method, and comparing the shape features of the wrinkle area with the shape features of the cloth of a preset standard form to determine the degree of wrinkles in the wrinkle area, wherein the shape feature extraction method includes at least one of the following: Hough transform, contour detection.

[0009] Optionally, the process of determining the degree of stretch includes: determining a strain distribution state in the first fabric image using a strain analysis method, and determining whether a stretch area exists in the first fabric image based on the strain distribution state, wherein the strain analysis method includes at least one of the following: a grid method, a feature point-based strain calculation method; when a stretch area exists in the first fabric image, measuring dimensional parameters of the stretch area using an image measurement method, and comparing the dimensional parameters of the stretch area with dimensional parameters of a preset standard fabric form to determine the degree of stretch in the stretch area, wherein the image measurement method includes at least one of the following: an edge detection method, and an image segmentation method.

[0010] Optionally, the process of determining the degree of relaxation includes: using a morphological processing method to determine morphological features in the first cloth image, and determining whether there is a relaxation area in the first cloth image based on the morphological features, wherein the morphological processing method includes at least one of the following: corrosion processing, expansion processing; when there is a relaxation area in the first cloth image, using a texture feature extraction method to extract texture features of the relaxation area, and comparing the texture features of the relaxation area with texture features of a preset standard morphology of the cloth to determine the degree of relaxation of the relaxation area, wherein the texture feature extraction method includes at least one of the following: local binary pattern, gray level co-occurrence matrix.

[0011] Optionally, before using the cloth deformation model to analyze the attribute parameters and the first cloth state characteristics, the method further includes: when the degree of wrinkle is less than a first preset threshold, the degree of stretch is within a first preset range, and the degree of relaxation is within a second preset range, determining that the tension at the preset point corresponding to the first cloth image does not need to be adjusted; when the degree of wrinkle is not less than the first preset threshold, or the degree of stretch is not within the first preset range, or the degree of relaxation is not within the second preset range, continuing to use the cloth deformation model to analyze the attribute parameters and the first cloth state characteristics.

[0012] Optionally, the attribute parameters and the first cloth state characteristics are substituted into the cloth deformation model for analysis to obtain a target tension for keeping the target cloth flat and wrinkle-free at a target preset point corresponding to the first cloth image, including: substituting the attribute parameters and the first cloth state characteristics as variables into the cloth deformation model, wherein the cloth deformation model is a set of equations for describing the morphological changes of the cloth under different tensions; and solving the cloth deformation model to obtain a target tension for keeping the target cloth flat and wrinkle-free at the target preset point.

[0013] Optionally, the tension output by the tension device of the cloth inspection machine at the target preset point is adjusted based on the target tension, including: determining the difference between the target tension and the current tension at the target preset point, and determining a control signal based on the difference; sending the control signal to the tension device of the cloth inspection machine, and the tension device adjusting the motion state of the tension output component at the target preset point based on the control signal, wherein the type of the tension output component includes one of the following: tension roller, spring device.

[0014] Optionally, after adjusting the tension output by the tension device of the fabric inspection machine at the target preset point based on the target tension, the method further includes: looping the following steps: reacquiring a second fabric image of the target fabric at the target preset point, and extracting a second fabric state feature in the second fabric image using an image processing algorithm; if the second fabric state feature indicates that the target fabric is flat and wrinkle-free at the target preset point, stopping the loop; if the second fabric state feature indicates that the target fabric is uneven at the target preset point, determining a tension adjustment strategy matching the second fabric state feature from a preset strategy library, and adjusting the tension output by the tension device at the target preset point based on the tension adjustment strategy, wherein the tension adjustment strategy includes one of the following: if the second fabric state feature indicates that the target fabric is stretched at the target preset point, reducing the tension output by the tension device at the target preset point according to a preset step size; if the second fabric state feature indicates that the target fabric is relaxed at the target preset point, increasing the tension output by the tension device at the target preset point according to a preset step size.

[0015] Optionally, the method further includes: substituting the tension, attribute parameters and first cloth state characteristics output by the tension device at the target preset point at the end of the cycle into the cloth deformation model, re-solving the cloth deformation model using the inherent parameters in the cloth deformation model as the parameters to be solved, and updating the inherent parameters in the cloth deformation model based on the solution results.

[0016] According to another aspect of an embodiment of the present application, a tension control device for a cloth inspection machine is further provided, including: an acquisition module for acquiring a first cloth image of a target cloth at a plurality of preset points on the cloth inspection machine, and acquiring attribute parameters of the target cloth; a feature extraction module for extracting, for each first cloth image, a first cloth state feature in the first cloth image, wherein the first cloth state feature includes at least one of the following: degree of wrinkle, degree of stretching, and degree of relaxation; a tension calculation module for substituting the attribute parameters and the first cloth state feature into a cloth deformation model for analysis, to obtain a target tension for keeping the target cloth flat and wrinkle-free at the target preset point corresponding to the first cloth image, wherein the cloth deformation model is used to reflect the morphological changes of various cloths under different tensions; and a control module for adjusting the tension output by the tension device of the cloth inspection machine at the target preset point based on the target tension.

[0017] According to another aspect of an embodiment of the present application, a computer program product is further provided, the computer program product comprising: a computer program, wherein when the computer program is executed by a processor, the above-mentioned method for controlling tension of a cloth inspection machine is implemented.

[0018] According to another aspect of an embodiment of the present application, an electronic device is further provided, comprising: a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to execute the above-mentioned tension control method of the cloth inspection machine through the computer program.

[0019] In an embodiment of the present application, first fabric images of a target fabric at a plurality of preset points on a fabric inspection machine are obtained, and attribute parameters of the target fabric are obtained; for each first fabric image, a first fabric state feature in the first fabric image is extracted using an image processing algorithm, wherein the first fabric state feature includes at least one of the following: a degree of wrinkle, a degree of stretch, and a degree of relaxation; the attribute parameters and the first fabric state feature are substituted into a fabric deformation model for analysis to obtain a target tension for keeping the target fabric flat and wrinkle-free at the target preset points corresponding to the first fabric image, wherein the fabric deformation model is used to reflect the morphological changes of various fabrics under different tensions; and the tension output by a tension device of the fabric inspection machine at the target preset points is adjusted based on the target tension. Among them, the fabric images at each preset point are processed and analyzed to facilitate the segmented control of the target fabric. Furthermore, combined with the attribute parameters and state characteristics of the target fabric, the fabric deformation model can be used to accurately calculate the target tension required for the fabric at the preset point to achieve a flat and wrinkle-free state, thereby solving the technical problems of low fabric inspection accuracy and poor fabric quality caused by inaccurate tension control in traditional fabric inspection machine control schemes. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0021] Figure 1 This is a flow chart of an optional method for controlling tension of a cloth inspection machine according to an embodiment of the present application;

[0022] Figure 2 1 is a schematic structural diagram of an optional tension control device for a cloth inspection machine according to an embodiment of the present application;

[0023] Figure 3 is a schematic diagram of an optional electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0024] In order to enable those skilled in the art to better understand the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of this application.

[0025] It should be noted that the terms "first", "second", etc. in the specification, claims, and drawings of the present application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products, or devices.

[0026] In order to better understand the embodiments of the present application, some nouns or terms that appear in the description of the embodiments of the present application are first translated and explained as follows:

[0027] Preset points: Specific locations on the fabric inspection machine designated for image capture and tension control. These locations are typically used to monitor fabric state changes during transport and implement localized tension control. These locations are key locations on the machine where image capture equipment and tension control components are installed. These locations are selected based on an understanding of the fabric transport path and inspection process, such as the fabric inlet, before and after the intermediate processing platform, and at the fabric outlet. By capturing images and adjusting tension at these locations, fabric flatness and tension stability are ensured throughout the inspection process.

[0028] Tension output assembly: A mechanical or electrical component used to apply and adjust tension on a fabric inspection machine. These components typically include tension rollers and springs, which directly contact the fabric and adjust the tension by changing their position or force. In intelligent fabric inspection machines, these components are connected to a control system, automatically adjusting tension based on real-time inspection results to accommodate varying fabrics and production conditions.

[0029] Example 1

[0030] According to an embodiment of the present application, a method for controlling the tension of a fabric inspection machine is provided. 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 a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0031] Figure 1 : is a flow chart of a tension control method for a cloth inspection machine according to an embodiment of the present application, such as Figure 1 As shown, the method includes the following steps:

[0032] Step S102, obtaining a first fabric image of the target fabric at a plurality of preset points on a fabric inspection machine, and obtaining attribute parameters of the target fabric;

[0033] Step S104: for each first cloth image, extracting a first cloth state feature in the first cloth image, wherein the first cloth state feature includes at least one of the following: a wrinkle degree, a stretch degree, and a looseness degree;

[0034] Step S106: Substituting the attribute parameters and the first cloth state characteristics into a cloth deformation model for analysis, and obtaining a target tension that keeps the target cloth flat and wrinkle-free at a target preset point corresponding to the first cloth image. The cloth deformation model is used to reflect the shape changes of various cloths under different tensions.

[0035] Step S108: adjusting the tension output by the tension device of the fabric inspection machine at the target preset point based on the target tension.

[0036] Specifically, by comprehensively analyzing the fabric's property parameters and state characteristics, this application can intelligently determine the fabric's deformation at different locations, thereby precisely regulating tension and ensuring the fabric remains flat and wrinkle-free throughout the inspection process. This addresses the problems of fabric damage and inspection errors caused by inaccurate tension control in traditional fabric inspection machines. For example, when the fabric is made of silk, it is much more sensitive to tension than cotton. In this case, the system will adjust the tension more finely to prevent irreversible deformation of the silk.

[0037] The following describes the various steps of the tension control method for the cloth inspection machine in conjunction with a specific implementation process.

[0038] To monitor the condition of fabric during transport in real time, key locations on the inspection machine, such as the fabric inlet, outlet, and intermediate processing platform, can be equipped with high-precision cameras or image sensors. These capture images of the fabric surface at regular or continuous intervals. These images are known as "first fabric images." By analyzing these images, real-time information about the fabric's condition, including wrinkles, stretch, and slack, can be obtained.

[0039] For the multiple acquired first cloth images, the first cloth images may be preprocessed first and then feature extracted.

[0040] As an optional implementation, obtaining the first fabric image of the target fabric at multiple preset points on the fabric inspection machine can be specifically achieved in the following manner: using industrial cameras pre-placed at multiple preset points on the fabric inspection machine to collect the first fabric image of the target fabric at each preset point; performing image preprocessing operations on each first fabric image, wherein the image preprocessing operations include at least one of the following: denoising processing, contrast enhancement processing, and grayscale processing.

[0041] Specifically, the relevant image preprocessing operation process is explained below.

[0042] Denoising: You can apply algorithms such as mean filtering, median filtering, or Gaussian filtering to the first fabric image to remove random noise and ensure that wrinkle features are clearer and easier to identify. This denoising process statistically analyzes and filters the image pixels, preserving the fabric's surface texture and reducing misjudgments in the subsequent feature extraction phase.

[0043] Contrast Enhancement: Using histogram equalization and adaptive contrast enhancement techniques, the brightness and contrast of the first fabric image are adjusted to highlight the details of defective areas. This processing step is particularly important for enhancing the visibility of wrinkles, stretch, and relaxation in the fabric. It significantly improves the system's recognition capabilities, especially in complex lighting conditions and with diverse fabric materials. It ensures that image features are fully highlighted, thereby improving the accuracy and efficiency of tension control.

[0044] Grayscale processing: Converting the color image of the first fabric into a grayscale image simplifies the image's color dimension and reduces the computational effort involved in image processing. Grayscale images better reflect the light and dark variations on the fabric surface, making them particularly useful for extracting texture features. Through grayscale processing, the system can more accurately capture subtle changes in the fabric surface, including wrinkles, stretch, and relaxation, providing more reliable data support for tension control.

[0045] After image preprocessing, advanced image processing algorithms can be used to extract the first fabric state characteristics from the preprocessed first fabric image, including the degree of wrinkles, stretch, and slack. By carefully analyzing the texture, shape, and dimensional parameters in the image, the intelligent fabric inspection machine can accurately identify the actual state of the fabric during inspection, providing a key basis for subsequent tension control decisions.

[0046] As an optional embodiment, the process of determining the degree of wrinkles includes: extracting texture features in the first cloth image using a texture feature extraction method, and determining whether there is a wrinkle area in the first cloth image based on the texture features, wherein the texture feature extraction method includes at least one of the following: local binary pattern, gray level co-occurrence matrix; when there is a wrinkle area in the first cloth image, extracting shape features of the wrinkle area using a shape feature extraction method, and comparing the shape features of the wrinkle area with the shape features of the cloth of a preset standard form to determine the degree of wrinkles in the wrinkle area, wherein the shape feature extraction method includes at least one of the following: Hough transform, contour detection.

[0047] Specifically, when extracting the wrinkle degree reflecting the wrinkle characteristics, the following steps are included:

[0048] Step S1: any combination of relevant common texture feature extraction methods is used to identify whether there is a wrinkle area. Common texture feature extraction methods include but are not limited to: local binary pattern and gray level co-occurrence matrix.

[0049] The local binary pattern recognition process involves analyzing each small area of ​​the first fabric image and constructing a binary representation of the local texture features by comparing the grayscale values ​​of the central pixel with those of its neighbors. This method can capture subtle texture variations on the fabric surface, particularly the texture features of wrinkled areas, and thus identify the presence of wrinkles.

[0050] The gray-level co-occurrence matrix recognition process involves calculating the spatial correlation between pixels of different grayscale levels in the first fabric image and constructing a gray-level co-occurrence matrix. This matrix reflects the statistical properties of the image texture, such as orientation, contrast, and homogeneity. This helps the system identify and quantify the texture complexity and variation of wrinkles, and thus determine whether wrinkles exist in the first fabric image.

[0051] Step S2: After wrinkle regions are detected in the first cloth image, a shape feature extraction method may be further used to perform in-depth analysis on these regions.

[0052] Common shape feature extraction methods include but are not limited to: Hough transform and contour detection.

[0053] The Hough transform extraction process includes: detecting the edges of the wrinkle area in the first fabric image, converting the edges into a series of straight lines or curves, and calculating the length, direction, and distribution of these lines to evaluate the curvature and shape change of the wrinkle area, thereby quantifying the degree of wrinkles.

[0054] The contour detection process includes gradient-based directional contour detection or edge-based contour tracing, which accurately depicts the outer contours of the wrinkle area and further analyzes the morphological characteristics of the wrinkles. The contour detection results are compared with the fabric shape characteristics of a preset standard form to determine the degree and distribution of wrinkles in the wrinkle area, providing precise guidance for subsequent tension control.

[0055] Step S3: determining the wrinkle degree.

[0056] After extracting texture and shape features, these features can be compared with a preset standard for fabric shape to determine the specific degree of wrinkling in the wrinkled area. The preset standard shape can be derived from extensive experiments or expert experience data analysis, and it defines the texture and shape characteristics of the fabric under ideal conditions. If the texture characteristics of the wrinkled area differ significantly from the preset standard, the system will determine that a wrinkle problem exists and further quantify the severity of the wrinkles, including their depth, width, and distribution density, through comparative analysis of the shape characteristics.

[0057] By combining texture feature analysis and shape feature analysis, the adaptive tension control system of the intelligent fabric inspection machine can comprehensively and meticulously identify and quantify the wrinkle features on the fabric, and then accurately judge the degree of wrinkles on the first fabric image, laying a solid foundation for achieving precise tension control.

[0058] In addition to the fact that the degree of wrinkles is closely related to the state of the target fabric, the degree of stretch is also directly related to the quality and stability of the fabric during transmission. Therefore, determining the degree of stretch is one of the key steps in the adaptive tension control process of the intelligent fabric inspection machine.

[0059] As an optional embodiment, the process of determining the degree of stretch includes: determining a strain distribution state in the first fabric image using a strain analysis method, and determining whether a stretch region exists in the first fabric image based on the strain distribution state, wherein the strain analysis method includes at least one of the following: a grid method, a feature point-based strain calculation method; when a stretch region exists in the first fabric image, measuring dimensional parameters of the stretch region using an image measurement method, and comparing the dimensional parameters of the stretch region with dimensional parameters of a preset standard fabric form to determine the degree of stretch of the stretch region, wherein the image measurement method includes at least one of the following: an edge detection method, and an image segmentation method.

[0060] Common strain analysis methods include but are not limited to: grid method and strain calculation method based on characteristic points.

[0061] The grid method works as follows: On a first fabric image, the system constructs a virtual grid structure, dividing the fabric area into multiple small grid cells. Subsequently, by comparing the dimensional changes of each grid cell in the image with the original fabric dimensions, the system analyzes the strain distribution in different regions of the fabric. This method is particularly suitable for detecting whether certain local areas of fabric have experienced excessive stretching, as the grid method can meticulously capture the dimensional changes within each small area of ​​the fabric, thereby identifying areas of stretch.

[0062] The feature point-based strain calculation method works by selecting multiple fixed feature points within a first fabric image. These feature points can be natural texture points or artificially placed markers. By tracking the displacement of these feature points across the image sequence, the system calculates the strain distribution of the fabric and identifies areas experiencing stretching. Compared to grid-based methods, feature point-based strain calculation is more flexible and can handle fabrics with complex shapes. It also provides a more direct solution for detecting dynamic stretch during fabric transport. Therefore, feature points can be selected as needed during actual calculations.

[0063] After determining that there is a stretched area in the fabric image, the size parameters of the stretched area can be measured using relevant image measurement methods. Common image measurement methods include but are not limited to edge detection methods and image segmentation methods.

[0064] The edge detection process involves automatically identifying fabric edges from specific areas within the first fabric image. Edge detection methods typically include Canny edge detection and the Sobel operator, which effectively isolate the edge contours of objects from the image, facilitating subsequent dimensional measurement. Using the contour information obtained through edge detection, the system can measure dimensional parameters such as the length and width of the stretched area. These parameters are then compared and analyzed with pre-set standard fabric dimensions to calculate the actual stretch level of the stretched area.

[0065] The image segmentation method involves accurately separating the stretched region from the background in the first fabric image to form a separate image object. Common image segmentation methods include threshold-based segmentation and region-based segmentation, which automatically identify and segment regions of interest based on pixel grayscale values ​​or color characteristics. The dimensional parameters of the segmented stretched region are also measured and compared to standard fabric dimensions to assess the degree of stretch. The advantage of image segmentation methods is that they can handle more complex image backgrounds and lighting conditions, ensuring accurate and robust stretch region measurements.

[0066] For fabric images with stretched areas, after measuring the size parameters of the stretched areas using an image measurement method, the size parameters can be compared with the preset standard fabric size to quantify the degree of stretch. Specifically, the actual size parameters are compared with the preset standard fabric size, and the percentage or degree of stretch is calculated based on the difference in the comparison results, which serves as the basis for adjusting the tension.

[0067] In addition, the degree of fabric relaxation is closely related to the state of the fabric under tension.

[0068] As an optional embodiment, the process of determining the degree of relaxation includes: using a morphological processing method to determine the morphological features in the first cloth image, and determining whether there is a relaxation area in the first cloth image based on the morphological features, wherein the morphological processing method includes at least one of the following: corrosion processing, expansion processing; when there is a relaxation area in the first cloth image, using a texture feature extraction method to extract texture features of the relaxation area, and comparing the texture features of the relaxation area with texture features of a preset standard morphology of the cloth to determine the degree of relaxation of the relaxation area, wherein the texture feature extraction method includes at least one of the following: local binary pattern, gray level co-occurrence matrix.

[0069] Specifically, when determining the degree of slack on the first cloth image, a strategy combining morphological analysis with texture change detection is adopted to ensure comprehensive and accurate recognition of the cloth's slack state.

[0070] Common morphological processing methods include but are not limited to: corrosion processing and expansion processing.

[0071] The erosion process shrinks the boundaries of objects in the image and removes subtle protrusions, helping the system identify and distinguish detailed features of the fabric, particularly changes in shape caused by slack. The erosion process clearly reveals the edges and shape of slack areas, providing a more accurate reference area for subsequent texture feature extraction and improving the accuracy of slack detection.

[0072] Dilation, in contrast to erosion, enlarges the boundaries of objects in the image, filling holes and disconnected edges, thereby enhancing their connectivity and integrity. When identifying areas of loose fabric, dilation compensates for image segmentation deviations caused by minor loose fabric, ensuring the integrity and accuracy of these areas. Dilation allows the system to capture a wider range of loose fabric areas, even if these areas may not be readily apparent in the original image, thereby improving detection sensitivity.

[0073] After identifying the existence of loose areas in the first fabric, the system can further use texture feature extraction methods to evaluate the degree of looseness in these areas. This step is based on the changes in texture features and can analyze the status of the loose areas in more detail.

[0074] Common texture feature extraction methods include, but are not limited to, local binary patterns and gray-level co-occurrence matrices. These two texture feature extraction methods have been explained in the above description of the wrinkle degree determination process and will not be repeated here.

[0075] As an optional embodiment, before using the cloth deformation model to analyze the attribute parameters and the first cloth state characteristics, the method also includes: when the degree of wrinkle is less than a first preset threshold, the degree of stretching is within a first preset range, and the degree of relaxation is within a second preset range, determining that the tension at the preset point corresponding to the first cloth image does not need to be adjusted; when the degree of wrinkle is not less than the first preset threshold, or the degree of stretching is not within the first preset range, or the degree of relaxation is not within the second preset range, continuing to use the cloth deformation model to analyze the attribute parameters and the first cloth state characteristics.

[0076] For the preset points corresponding to the first fabric image, the system first performs a series of data analysis and judgments before using the fabric deformation model for in-depth analysis to quickly determine whether tension adjustment is necessary. This strategy effectively improves the system's response speed and efficiency while avoiding unnecessary resource consumption. The specific analysis process is as follows:

[0077] Step S1, comparing the state characteristics with a preset threshold.

[0078] The wrinkle feature extraction results from the first fabric image can be examined and compared with a preset first wrinkle threshold. If the wrinkle level is below the first preset threshold, the fabric surface condition at that point is good and there are no significant wrinkle issues. The stretch characteristics of the first fabric image can also be evaluated and compared with a first preset stretch range. If the stretch state of the fabric falls within the preset range, it indicates that there is no overstretching and that the tension is appropriate. The relaxation characteristics of the first fabric image can also be analyzed to determine if they fall within a second preset relaxation range. If the relaxation state of the fabric falls within this range, it indicates that the tension is not too low and the fabric surface maintains a reasonable degree of flatness.

[0079] Step S2: Comprehensively judge the tension state.

[0080] If the wrinkle level of the first fabric image is below a first preset threshold, the stretched state is within a first preset range, and the relaxed state is within a second preset range, the system will determine that the fabric tension at the preset point is moderate and no further adjustment is required. In this case, the fabric surface is smooth, with no noticeable wrinkles, stretch, or relaxation, and meets the inspection standards.

[0081] Conversely, if the wrinkle level is no less than a first preset threshold, the stretch level exceeds a first preset range, or the slack level deviates from a second preset range, the system will determine that there is a problem with the fabric and require tension adjustment. In this case, whether the fabric has excessive wrinkles, stretch, or slack, it indicates that the current tension setting is inappropriate, requiring further analysis and calculation using a fabric deformation model to find the optimal tension adjustment strategy.

[0082] When a preliminary determination indicates that tension adjustment is necessary, the system activates the fabric deformation model, which takes into account fabric properties (such as material type and thickness) and initial fabric state characteristics (such as wrinkle level, stretch level, and slack level). Through mathematical modeling and calculation, the fabric deformation model simulates and calculates the target tension required to maintain a flat, wrinkle-free fabric at that predetermined point.

[0083] The process of using the fabric deformation model to determine target tension is based on extensive experimental data and algorithm optimization. The model accurately responds to various fabric types and varying state characteristics, providing personalized tension adjustment recommendations. Once the model calculates the target tension, the system fine-tunes the tension based on the resulting target tension through control signal generation and tension device adjustment, ultimately ensuring fabric flatness and tension stability during inspection.

[0084] As an optional implementation, the attribute parameters and the first cloth state characteristics are substituted into the cloth deformation model for analysis to obtain a target tension for keeping the target cloth flat and wrinkle-free at a target preset point corresponding to the first cloth image, including: substituting the attribute parameters and the first cloth state characteristics as variables into the cloth deformation model, wherein the cloth deformation model is a set of equations for describing the morphological changes of the cloth under different tensions; solving the cloth deformation model to obtain a target tension for keeping the target cloth flat and wrinkle-free at the target preset point.

[0085] Specifically, the cloth deformation model combines the mechanical principles of physics and knowledge of cloth materials, and can accurately describe the deformation behavior of cloth under different tensions, including shape changes and dimensional fluctuations.

[0086] Common attribute parameters include material properties and geometric characteristics. These attributes and the first cloth state characteristics can be used as variables and incorporated into the cloth deformation model. These parameters form the basis for solving the model, ensuring a close correlation between the calculated results and the actual cloth state.

[0087] By solving the equations in the fabric deformation model, the fabric's state changes under different tension settings are simulated, and the ideal tension value that keeps the fabric flat and wrinkle-free at the target preset point is found. This process may rely on numerical analysis methods such as finite element analysis or iterative algorithms, which can accurately calculate the stress-strain state of the fabric under nonlinear conditions.

[0088] Once the fabric deformation model is solved, the target tension required to maintain the fabric flat and wrinkle-free at the desired preset point can be determined. This tension is optimized based on the current fabric state characteristics and property parameters, effectively preventing new wrinkles during subsequent fabric inspections while also avoiding stretching and relaxation issues.

[0089] After the target tension is obtained, a specific control signal can be generated to adjust the output tension of the tension device at the target preset point.

[0090] As an optional embodiment, the tension output by the tension device of the cloth inspection machine at the target preset point is adjusted based on the target tension, including: determining the difference between the target tension and the current tension at the target preset point, and determining a control signal based on the difference; sending the control signal to the tension device of the cloth inspection machine, and the tension device adjusting the motion state of the tension output component at the target preset point based on the control signal, wherein the type of the tension output component includes one of the following: tension roller, spring device.

[0091] Specifically, when adjusting the tension output of the tension device of the fabric inspection machine at the target preset point, a refined control strategy is adopted to ensure that the tension fine-tuning can be performed accurately. The specific implementation process is as follows:

[0092] Step S1, determining a control signal, which may include the following steps S11 to S12.

[0093] Step S11: Calculate the tension difference. First, determine the difference between the target tension and the current tension at the target preset point. This difference reflects the direction and magnitude of tension adjustment. If the target tension is higher than the current tension, the difference will be positive, indicating a need for tension increase. Conversely, if the target tension is lower than the current tension, the difference will be negative, prompting the system to reduce tension.

[0094] Step S12: Control signal decision. Based on the magnitude and positive / negative nature of the tension difference, the type of control signal generated is further determined. The control signal design must take into account the response characteristics and adjustment range of the tension output components (e.g., tension rollers and spring devices) to ensure smooth tension transitions and avoid overshoot or undershoot.

[0095] Step S2, adjusting the tension output assembly. This step may include the following steps S21 to S22.

[0096] Step S21: Transmission and execution of control signals. The control signal is sent to the fabric inspection machine's tension device, which houses a motor and transmission mechanism and is tightly connected to the tension output assembly. During signal transmission, the system monitors the signal's integrity and timeliness to ensure that the tension adjustment command is transmitted promptly and accurately to the tension output assembly.

[0097] Step S22: After receiving the control signal, the tension device immediately starts the motor to drive the transmission mechanism to adjust the position or state of the tension output component.

[0098] Specifically, for the tension roller, if the tension needs to be increased, the motor will rotate forward, driving the tension roller to move toward the cloth, thereby increasing the contact pressure of the tension roller on the cloth, thereby increasing the tension level; conversely, if the tension needs to be reduced, the motor will rotate in the reverse direction, moving the tension roller away from the cloth, reducing the pressure on the cloth, and lowering the tension.

[0099] When tension adjustment is needed for the spring mechanism, the system controls the mechanical mechanism connected to the spring mechanism to change the compression or extension of the spring. Increasing the tension further compresses the spring, providing greater elastic force on the fabric; decreasing the tension releases the spring's compression, reducing the force on the fabric.

[0100] Through this process, continuous and precise tension control is achieved. By real-time monitoring of the fabric state and calculation of the target tension, the system can quickly respond to any changes in the fabric transmission process and promptly adjust the motion of the tension output component to ensure that the fabric tension at the target preset point is always maintained at the optimal state.

[0101] As an optional embodiment, after adjusting the tension output by the tension device of the fabric inspection machine at the target preset point based on the target tension, the method further includes: looping the following steps: reacquiring a second fabric image of the target fabric at the target preset point, and extracting a second fabric state feature in the second fabric image using an image processing algorithm; if the second fabric state feature indicates that the target fabric is flat and wrinkle-free at the target preset point, stopping the loop; if the second fabric state feature indicates that the target fabric is uneven at the target preset point, determining a tension adjustment strategy matching the second fabric state feature from a preset strategy library, and adjusting the tension output by the tension device at the target preset point based on the tension adjustment strategy, wherein the tension adjustment strategy includes one of the following: if the second fabric state feature indicates that the target fabric is stretched at the target preset point, reducing the tension output by the tension device at the target preset point according to a preset step size; if the second fabric state feature indicates that the target fabric is relaxed at the target preset point, increasing the tension output by the tension device at the target preset point according to a preset step size.

[0102] The above process mainly reflects the process of cyclic feedback adjustment. After the tension is adjusted, a second fabric image of the target fabric at the target preset point will be re-acquired. This image is used to monitor and evaluate the effect of the tension adjustment in real time.

[0103] The second cloth image is processed to extract the second cloth state features, including the degree of wrinkles, stretching, and relaxation, etc. These features will serve as the basis for subsequent judgment.

[0104] If the second fabric state characteristic shows that the fabric is flat and wrinkle-free at the target preset point, the system will determine that the tension adjustment is successful and immediately stop the loop feedback adjustment process.

[0105] However, if the second fabric state characteristic indicates that the fabric is still uneven at the target preset point, that is, the degree of wrinkling exceeds a preset threshold, or the stretch or relaxation state is outside the preset range, the system will quickly determine a tension adjustment strategy that matches the current fabric state characteristic from a preset strategy library. This strategy library contains a variety of tension adjustment schemes for different fabric states. By matching it with the second fabric state characteristic, the system can quickly locate the most appropriate adjustment strategy to address the current fabric state issue. Specifically, if the second fabric state characteristic indicates that the fabric is stretched at the target preset point, the tension adjustment strategy may instruct to reduce the tension output by the tensioning device at the target preset point by a preset step size to alleviate the stretch of the fabric. If the second fabric state characteristic indicates that the fabric is relaxed at the target preset point, the tension adjustment strategy may instruct to increase the tension output by the tensioning device at the target preset point by a preset step size to eliminate the relaxation and improve the flatness of the fabric.

[0106] During the entire loop feedback adjustment process, not only can the tension be monitored and adjusted in real time, but the second cloth image and the corresponding tension adjustment data can also be continuously collected and analyzed for updating and optimizing the cloth deformation model.

[0107] As an optional implementation, the above method also includes: substituting the tension, attribute parameters and first cloth state characteristics output by the tension device at the target preset point at the end of the cycle into the cloth deformation model, using the inherent parameters in the cloth deformation model as the parameters to be solved to re-solve the cloth deformation model, and updating the inherent parameters in the cloth deformation model based on the solution results.

[0108] Furthermore, in the final stage of the cyclic adjustment, when the cloth state reaches a satisfactory state, the tension value, attribute parameters (such as cloth material, thickness) and the first cloth state characteristics (the cloth state evaluated initially) output by the tension device at the target preset point can be brought into the cloth deformation model, and the inherent parameters in the model (describing the mechanical properties of the cloth) are used as parameters to be solved. The system optimizes the model parameters based on the adjusted cloth state and tension value by re-solving the model.

[0109] Assume that stress-strain satisfies the linear relationship y = kx + b. Assume that the model parameter is k, which is an inherent parameter, and the attribute parameter is b. Different types of fabrics have different attribute parameters b. x represents the state characteristics of the current target fabric, and y represents the target tension value corresponding to this state characteristic. In the target tension solution phase, for a target fabric with certain attribute parameters, the model parameter k, attribute parameter b, and state characteristic x are all known, so the corresponding target tension value can be obtained. In the learning optimization phase, the actual optimal target tension value y′ determined in the cyclic adjustment phase, as well as the corresponding attribute parameter b and state characteristic x, can be substituted into the above stress-strain calculation formula. This allows the reverse solution of an optimized k′, thereby achieving optimal adjustment of the model parameter k.

[0110] In an embodiment of the present application, first fabric images of a target fabric at a plurality of preset points on a fabric inspection machine are obtained, and attribute parameters of the target fabric are obtained; for each first fabric image, a first fabric state feature in the first fabric image is extracted using an image processing algorithm, wherein the first fabric state feature includes at least one of the following: a degree of wrinkle, a degree of stretch, and a degree of relaxation; the attribute parameters and the first fabric state feature are substituted into a fabric deformation model for analysis to obtain a target tension for keeping the target fabric flat and wrinkle-free at the target preset points corresponding to the first fabric image, wherein the fabric deformation model is used to reflect the morphological changes of various fabrics under different tensions; and the tension output by a tension device of the fabric inspection machine at the target preset points is adjusted based on the target tension. Among them, the fabric images at each preset point are processed and analyzed to facilitate the segmented control of the target fabric. Furthermore, combined with the attribute parameters and state characteristics of the target fabric, the fabric deformation model can be used to accurately calculate the target tension required for the fabric at the preset point to achieve a flat and wrinkle-free state, thereby solving the technical problems of low fabric inspection accuracy and poor fabric quality caused by inaccurate tension control in traditional fabric inspection machine control schemes.

[0111] Example 2

[0112] According to an embodiment of the present application, a tension control device for a cloth inspection machine is provided for implementing the tension control method for the cloth inspection machine in Example 1. Figure 2 As shown, the tension control device of the cloth inspection machine includes at least: an acquisition module 21, a feature extraction module 22, a tension calculation module 23 and a control module 24, wherein:

[0113] The acquisition module 21 can acquire a first fabric image of the target fabric at a plurality of preset points on the fabric inspection machine and acquire attribute parameters of the target fabric;

[0114] The feature extraction module 22 may extract, for each first cloth image, a first cloth state feature from the first cloth image, wherein the first cloth state feature includes at least one of the following: a wrinkle degree, a stretch degree, and a looseness degree;

[0115] The tension calculation module 23 may substitute the attribute parameters and the first cloth state characteristics into the cloth deformation model for analysis to obtain a target tension that keeps the target cloth flat and wrinkle-free at the target preset point corresponding to the first cloth image. The cloth deformation model is used to reflect the shape changes of various cloths under different tensions.

[0116] The control module 24 can adjust the tension output by the tension device of the fabric inspection machine at the target preset point based on the target tension.

[0117] The functions of each module of the tension control device of the cloth inspection machine are explained below in conjunction with a specific implementation process.

[0118] As an optional implementation, the acquisition module acquires the first fabric image of the target fabric at multiple preset points on the fabric inspection machine, which can be specifically achieved in the following manner: using industrial cameras pre-placed at multiple preset points on the fabric inspection machine to collect the first fabric image of the target fabric at each preset point; performing image preprocessing operations on each first fabric image, wherein the image preprocessing operations include at least one of the following: denoising processing, contrast enhancement processing, and grayscale processing.

[0119] As an optional embodiment, the process of determining the degree of wrinkles includes: extracting texture features in the first cloth image using a texture feature extraction method, and determining whether there is a wrinkle area in the first cloth image based on the texture features, wherein the texture feature extraction method includes at least one of the following: local binary pattern, gray level co-occurrence matrix; when there is a wrinkle area in the first cloth image, extracting shape features of the wrinkle area using a shape feature extraction method, and comparing the shape features of the wrinkle area with the shape features of the cloth of a preset standard form to determine the degree of wrinkles in the wrinkle area, wherein the shape feature extraction method includes at least one of the following: Hough transform, contour detection.

[0120] As an optional embodiment, the process of determining the degree of stretch includes: determining a strain distribution state in the first fabric image using a strain analysis method, and determining whether a stretch region exists in the first fabric image based on the strain distribution state, wherein the strain analysis method includes at least one of the following: a grid method, a feature point-based strain calculation method; when a stretch region exists in the first fabric image, measuring dimensional parameters of the stretch region using an image measurement method, and comparing the dimensional parameters of the stretch region with dimensional parameters of a preset standard fabric form to determine the degree of stretch of the stretch region, wherein the image measurement method includes at least one of the following: an edge detection method, and an image segmentation method.

[0121] As an optional embodiment, the process of determining the degree of relaxation includes: using a morphological processing method to determine the morphological features in the first cloth image, and determining whether there is a relaxation area in the first cloth image based on the morphological features, wherein the morphological processing method includes at least one of the following: corrosion processing, expansion processing; when there is a relaxation area in the first cloth image, using a texture feature extraction method to extract texture features of the relaxation area, and comparing the texture features of the relaxation area with texture features of a preset standard morphology of the cloth to determine the degree of relaxation of the relaxation area, wherein the texture feature extraction method includes at least one of the following: local binary pattern, gray level co-occurrence matrix.

[0122] As an optional embodiment, before the tension calculation module uses the cloth deformation model to analyze the attribute parameters and the first cloth state characteristics, the further steps are included: when the degree of wrinkle is less than a first preset threshold, the degree of stretching is within a first preset range, and the degree of relaxation is within a second preset range, determining that the tension at the preset point corresponding to the first cloth image does not need to be adjusted; when the degree of wrinkle is not less than the first preset threshold, or the degree of stretching is not within the first preset range, or the degree of relaxation is not within the second preset range, continuing to use the cloth deformation model to analyze the attribute parameters and the first cloth state characteristics.

[0123] As an optional implementation, the tension calculation module substitutes the attribute parameters and the first cloth state characteristics into the cloth deformation model for analysis to obtain a target tension for keeping the target cloth flat and wrinkle-free at a target preset point corresponding to the first cloth image, including: substituting the attribute parameters and the first cloth state characteristics as variables into the cloth deformation model, wherein the cloth deformation model is a set of equations for describing the morphological changes of the cloth under different tensions; solving the cloth deformation model to obtain a target tension for keeping the target cloth flat and wrinkle-free at the target preset point.

[0124] As an optional embodiment, the control module adjusts the tension output by the tension device of the cloth inspection machine at the target preset point based on the target tension, including: determining the difference between the target tension and the current tension at the target preset point, and determining the control signal based on the difference; sending the control signal to the tension device of the cloth inspection machine, and the tension device adjusts the motion state of the tension output component at the target preset point based on the control signal, wherein the type of the tension output component includes one of the following: tension roller, spring device.

[0125] As an optional embodiment, the tension control device of the cloth inspection machine may further include a feedback optimization module. After adjusting the tension output by the tension device of the cloth inspection machine at the target preset point based on the target tension, the feedback optimization module may further cyclically perform the following steps: reacquiring a second cloth image of the target cloth at the target preset point, and extracting a second cloth state feature in the second cloth image using an image processing algorithm; if the second cloth state feature indicates that the target cloth is flat and wrinkle-free at the target preset point, stopping the loop; if the second cloth state feature indicates that the target cloth is uneven at the target preset point, determining a tension adjustment strategy matching the second cloth state feature from a preset strategy library, and adjusting the tension output by the tension device at the target preset point based on the tension adjustment strategy, wherein the tension adjustment strategy includes one of the following: if the second cloth state feature indicates that the target cloth is stretched at the target preset point, reducing the tension output by the tension device at the target preset point according to a preset step size; if the second cloth state feature indicates that the target cloth is relaxed at the target preset point, increasing the tension output by the tension device at the target preset point according to a preset step size.

[0126] As an optional implementation, the feedback optimization module can also substitute the tension, attribute parameters and first cloth state characteristics output by the tension device at the target preset point at the end of the cycle into the cloth deformation model, use the inherent parameters in the cloth deformation model as the parameters to be solved to re-solve the cloth deformation model, and update the inherent parameters in the cloth deformation model based on the solution results.

[0127] It should be noted that each module in the tension control device of the cloth inspection machine in the embodiment of the present application corresponds one-to-one to each implementation step of the tension control method of the cloth inspection machine in Example 1. Since a detailed description has been given in Example 1, some details not reflected in this embodiment can be referred to Example 1 and will not be elaborated here.

[0128] Example 3

[0129] According to an embodiment of the present application, a computer program product is further provided, which includes a computer program, wherein when the computer program is executed by a processor, the tension control method of the cloth inspection machine in Example 1 is implemented.

[0130] According to an embodiment of the present application, a non-volatile storage medium is further provided, which includes a stored computer program, wherein the device where the non-volatile storage medium is located executes the tension control method of the cloth inspection machine in Example 1 by running the computer program.

[0131] According to an embodiment of the present application, a processor is further provided, which is used to run a computer program, wherein the tension control method of the cloth inspection machine in Example 1 is executed when the computer program is running.

[0132] According to an embodiment of the present application, an electronic device is also provided, which includes: a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to execute the tension control method of the cloth inspection machine in Example 1 through the computer program.

[0133] Specifically, the computer program executes the following steps when it is running: obtaining first fabric images of the target fabric at multiple preset points on a fabric inspection machine, and obtaining attribute parameters of the target fabric; for each first fabric image, extracting first fabric state features in the first fabric image, wherein the first fabric state features include at least one of the following: degree of wrinkles, degree of stretching, and degree of relaxation; substituting the attribute parameters and the first fabric state features into a fabric deformation model for analysis, and obtaining a target tension for keeping the target fabric flat and wrinkle-free at the target preset points corresponding to the first fabric image, wherein the fabric deformation model is used to reflect the morphological changes of various fabrics under different tensions; and adjusting the tension output by the tension device of the fabric inspection machine at the target preset points based on the target tension.

[0134] As an optional implementation, the electronic device may be in the form of a mobile terminal, a computer terminal or a similar computing device. Figure 3 The hardware structure block diagram of an electronic device for implementing a tension control method for a cloth inspection machine is shown. Figure 3 As shown, the electronic device 30 may include one or more (illustrated as 302a, 302b, ..., 302n in the figure) processors 302 (the processor 302 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory 304 for storing data, and a transmission device 306 for communication functions. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of the BUS bus), a network interface, a power supply and / or a camera. It will be understood by those skilled in the art that Figure 3 The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 3 More or fewer components than shown, or with Figure 3 Different configurations shown.

[0135] It should be noted that the one or more processors 302 and / or other data processing circuits described above may generally be referred to herein as "data processing circuitry". The data processing circuitry may be embodied in whole or in part as software, hardware, firmware, or any other combination thereof. In addition, the data processing circuitry may be a single independent processing module, or may be incorporated in whole or in part into any of the other components of the electronic device 30. As described in the embodiments of the present application, the data processing circuitry serves as a processor control (e.g., selection of a variable resistor terminal path connected to an interface).

[0136] The memory 304 can be used to store software programs and modules for application software, such as the program instructions / data storage device corresponding to the tension control method for the fabric inspection machine in the embodiments of the present application. The processor 302 executes the software programs and modules stored in the memory 304 to execute various functional applications and data processing, thereby implementing the aforementioned application vulnerability detection method. The memory 304 may include high-speed random access memory and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 304 may further include memory remotely located relative to the processor 302, and such remote memory may be connected to the electronic device 30 via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0137] The transmission device 306 is used to receive or send data via a network. Specific examples of the aforementioned network may include a wireless network provided by the communications provider of the electronic device 30. In one embodiment, the transmission device 306 includes a network interface controller (NIC), which can be connected to other network devices via a base station to enable communication with the Internet. In one embodiment, the transmission device 306 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0138] The display may be, for example, a touch screen liquid crystal display (LCD) that enables a user to interact with a user interface of the electronic device 30 .

[0139] The serial numbers of the above embodiments are for description only and do not represent the advantages or disadvantages of the embodiments.

[0140] In the above embodiments of the present application, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0141] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only exemplary. For example, the division of units can be a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0142] Units described as separate components may or may not be physically separate, and components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple units. Some or all of the units may be selected to achieve the purpose of the present embodiment according to actual needs.

[0143] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0144] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for enabling a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the various embodiments of the present application. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk and other media that can store program code.

[0145] The above is only a preferred embodiment of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A method for controlling the tension of a cloth inspection machine, characterized in that: include: Acquire a first fabric image of a target fabric at a plurality of preset points on a fabric inspection machine, and acquire attribute parameters of the target fabric; For each first cloth image, extracting a first cloth state feature in the first cloth image, wherein the first cloth state feature includes at least one of the following: a wrinkle degree, a stretch degree, and a looseness degree; Substituting the attribute parameters and the first cloth state characteristics into a cloth deformation model for analysis, to obtain a target tension for maintaining the target cloth flat and wrinkle-free at a target preset point corresponding to the first cloth image, wherein the cloth deformation model is used to reflect the morphological changes of various cloths under different tensions; The tension output by the tension device of the cloth inspection machine at the target preset point is adjusted based on the target tension.

2. The method according to claim 1, characterized in that Acquiring a first fabric image of a target fabric at a plurality of preset points on a fabric inspection machine includes: Using industrial cameras pre-installed at a plurality of preset points on the cloth inspection machine, collecting first cloth images of the target cloth at each of the preset points; An image preprocessing operation is performed on each first cloth image, wherein the image preprocessing operation includes at least one of the following: denoising processing, contrast enhancement processing, and grayscale processing.

3. The method according to claim 1, characterized in that The process of determining the wrinkle degree includes: Extracting texture features from the first cloth image using a texture feature extraction method, and determining whether a wrinkle region exists in the first cloth image based on the texture features, wherein the texture feature extraction method includes at least one of the following: a local binary pattern and a gray level co-occurrence matrix; When there is a wrinkle area in the first cloth image, a shape feature extraction method is used to extract the shape features of the wrinkle area, and the shape features of the wrinkle area are compared with the shape features of the cloth of a preset standard form to determine the degree of wrinkles in the wrinkle area, wherein the shape feature extraction method includes at least one of the following: Hough transform and contour detection.

4. The method according to claim 1, wherein The process of determining the stretching degree includes: Determining a strain distribution state in the first cloth image using a strain analysis method, and determining whether a stretched region exists in the first cloth image based on the strain distribution state, wherein the strain analysis method includes at least one of the following: a grid method, a feature point-based strain calculation method; When a stretched area exists in the first fabric image, a size parameter of the stretched area is measured using an image measurement method, and the size parameter of the stretched area is compared with the size parameters of a preset standard fabric form to determine the stretching degree of the stretched area, wherein the image measurement method includes at least one of the following: an edge detection method and an image segmentation method.

5. The method according to claim 1, wherein The process of determining the degree of relaxation includes: Determining morphological features in the first cloth image using a morphological processing method, and determining whether there is a loose area in the first cloth image based on the morphological features, wherein the morphological processing method includes at least one of the following: erosion processing and dilation processing; When there is a loose area in the first cloth image, texture features of the loose area are extracted using a texture feature extraction method, and the texture features of the loose area are compared with texture features of cloth of a preset standard form to determine the degree of looseness of the loose area, wherein the texture feature extraction method includes at least one of the following: local binary pattern and gray level co-occurrence matrix.

6. The method according to claim 1, characterized in that Before analyzing the attribute parameters and the first cloth state characteristics using the cloth deformation model, the method further includes: When the wrinkle degree is less than a first preset threshold, the stretch degree is within a first preset range, and the relaxation degree is within a second preset range, determining that the tension at the preset point corresponding to the first cloth image does not need to be adjusted; When the wrinkle degree is not less than the first preset threshold, or the stretch degree is not within the first preset range, or the relaxation degree is not within the second preset range, the attribute parameters and the first cloth state characteristics continue to be analyzed using the cloth deformation model.

7. The method according to claim 1, characterized in that Substituting the attribute parameters and the first cloth state characteristics into a cloth deformation model for analysis to obtain a target tension for keeping the target cloth flat and wrinkle-free at a target preset point corresponding to the first cloth image, including: Substituting the attribute parameters and the first cloth state characteristics as variables into the cloth deformation model, wherein the cloth deformation model is a set of equations for describing the shape change of cloth under different tensions; The cloth deformation model is solved to obtain a target tension that enables the target cloth to remain flat and wrinkle-free at the target preset point.

8. The method according to claim 1, characterized in that Adjusting the tension output by the tension device of the cloth inspection machine at the target preset point based on the target tension includes: Determining a difference between the target tension and the current tension at the target preset point, and determining a control signal based on the difference; The control signal is sent to the tension device of the cloth inspection machine, and the tension device adjusts the motion state of the tension output component at the target preset point according to the control signal, wherein the type of the tension output component includes one of the following: tension roller, spring device.

9. The method according to claim 7, characterized in that After adjusting the tension output by the tension device of the fabric inspection machine at the target preset point based on the target tension, the method further includes: The following steps are executed in a loop: reacquiring a second fabric image of the target fabric at the target preset point, and extracting a second fabric state feature from the second fabric image using an image processing algorithm; If the second cloth state characteristic indicates that the target cloth is flat and wrinkle-free at the target preset point, stopping the cycle; If the second cloth state feature indicates that the target cloth is uneven at the target preset point, a tension adjustment strategy matching the second cloth state feature is determined from a preset strategy library, and the tension output by the tension device at the target preset point is adjusted based on the tension adjustment strategy, wherein the tension adjustment strategy includes one of the following: if the second cloth state feature indicates that the target cloth is stretched at the target preset point, reducing the tension output by the tension device at the target preset point according to a preset step size; if the second cloth state feature indicates that the target cloth is loose at the target preset point, increasing the tension output by the tension device at the target preset point according to a preset step size.

10. The method according to claim 9, characterized in that The method further comprises: The tension output by the tension device at the target preset point at the end of the cycle, the attribute parameter, and the first cloth state feature are substituted into the cloth deformation model, the inherent parameters in the cloth deformation model are used as the parameters to be solved to re-solve the cloth deformation model, and the inherent parameters in the cloth deformation model are updated based on the solution results.

11. A tension control device for a cloth inspection machine, characterized in that: include: an acquisition module, configured to acquire a first fabric image of a target fabric at a plurality of preset points on a fabric inspection machine, and to acquire attribute parameters of the target fabric; a feature extraction module, configured to extract, for each first cloth image, a first cloth state feature in the first cloth image, wherein the first cloth state feature comprises at least one of the following: a wrinkle degree, a stretch degree, and a slack degree; a tension calculation module, configured to substitute the attribute parameters and the first cloth state characteristics into a cloth deformation model for analysis to obtain a target tension for maintaining the target cloth flat and wrinkle-free at a target preset point corresponding to the first cloth image, wherein the cloth deformation model is configured to reflect the morphological changes of various cloths under different tensions; A control module is used to adjust the tension output by the tension device of the cloth inspection machine at the target preset point based on the target tension.

12. A computer program product, characterized in that include: A computer program, wherein when the computer program is executed by a processor, the method for controlling the tension of a fabric inspection machine according to any one of claims 1 to 10 is implemented.

13. An electronic device, characterized in that: include: A memory and a processor, wherein the memory stores a computer program, and the processor is configured to execute the tension control method of the fabric inspection machine according to any one of claims 1 to 10 through the computer program.

Images