Yarn detection system based on image processing
By adopting a variety of feature extraction technologies and machine learning models in the yarn detection system, the robustness problem of the existing technology in complex environments is solved, efficient and accurate yarn detection is achieved, and yarn quality control is improved. ability.
Patent Information
- Application Number
- CN202411277774.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-12
- Publication Date
- 2024-11-12
AI Technical Summary
The existing computer vision-based textile yarn yarn detection method has poor robustness in complex environments such as light changes and noise interference, resulting in a degradation of system performance.
A yarn detection system based on image processing is adopted, including image acquisition module, image preprocessing module, feature extraction module, yarn detection module and system management module, through edge detection, texture feature extraction, color feature extraction, shape feature extraction and grayscale feature extraction and other technologies, combined with machine learning models for yarn detection and recognition, to improve the robustness and accuracy of the system.
Significantly improves the accuracy and reliability of yarn image analysis, improves the accuracy and efficiency of yarn detection, enhances resistance to light changes and noise interference, and provides higher quality yarn quality control and automated detection support. .
Smart Images

Figure CN118941553A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of yarn detection, and in particular to a yarn detection system based on image processing. Background Art
[0002] With the rapid development of the textile industry, the requirements for yarn quality are getting higher and higher. Traditional yarn detection methods mainly rely on manual visual inspection, which is inefficient and prone to errors, and it is difficult to meet the rapid and intelligent needs of modern textile production. The yarn detection system based on image processing came into being. The system uses cameras and image processing technology to analyze yarn images in real time, automatically identify and detect yarn defects such as broken wires, knots, color differences, impurities, etc., so as to achieve fast, accurate and efficient detection of yarn quality. Automated yarn detection can improve production efficiency, reduce labor costs, and reduce production costs. Improve yarn quality, reduce scrap rate, and increase product added value. Therefore, the yarn detection system based on image processing is an important direction for automated production and intelligent upgrading in the textile industry, and has broad application prospects.
[0003] After searching, the Chinese patent application number CN2022109896531 discloses a textile bobbin yarn detection method based on computer vision. This method can be integrated into an artificial intelligence system in the production field, can be used as an artificial intelligence optimization operating system, artificial intelligence middleware, etc., and can be used for the development of computer vision software. The method includes: capturing and identifying the surface image of the yarn tube, and preprocessing the image to obtain a yarn tube grayscale image; obtaining the probability that the suspected yarn pixel point is a yarn pixel point based on the grayscale fluctuation degree and gradient direction consistency of the suspected yarn pixel point in the yarn tube grayscale image, and using this probability to obtain the number of yarn pixels. A textile bobbin yarn detection method based on computer vision in the above patent has the following deficiencies:
[0004] Although the above system can accurately distinguish the situation where there is a small amount of yarn on the bobbin, and can adapt to complex working conditions and avoid false detection of residual yarn on the bobbin due to lighting or other complex working conditions, the feature extraction within the system is not perfect, which makes the system less robust to environmental privacy such as lighting changes and noise interference, resulting in reduced performance of the system in complex scenarios. Summary of the invention
[0005] The purpose of the present invention is to solve the shortcomings of the prior art and to propose a yarn detection system based on image processing.
[0006] In order to achieve the above object, the present invention adopts the following technical solutions:
[0007] A yarn detection system based on image processing comprises an image acquisition module, an image preprocessing module, a feature extraction module, a yarn detection module, a result display module and a system management module. The image acquisition module acquires yarn image data presented in different forms through a camera. The image preprocessing module preprocesses the image data after image acquisition. The feature extraction module extracts features for describing various information of the yarn from the image data after preprocessing the image data. The yarn detection module analyzes and judges the features of the special zone by using image processing technology to realize the detection and identification of the yarn. The result display module displays the detection result to the user in the form of image or text. The system management module manages and monitors the entire system.
[0008] Preferably, the image acquisition module operates in the following specific steps: A1: Set the position and angle of the camera to ensure that the image of the yarn is captured at all angles; A2: Start the acquisition program, the camera starts to collect image data during the yarn running process, and transmits it to the computer for storage for subsequent image processing and analysis; A3: During the image data acquisition process, the acquired images are monitored and displayed in real time; A4: The computer corrects and adjusts the collected image data, corrects the color deviation of the image data, and deletes image data with poor clarity.
[0009] Furthermore, the image preprocessing module has the following specific working steps: B1: De-noising and image enhancement of yarn images; B2: Convert the image from RGB color space to HSV color space to separate the brightness and color information of the image; B3: Convert the image to black and white, separate the yarn from the background, remove small noise points and broken connection areas in the image, and highlight the outline and edge of the yarn; B4: According to the actual position in the yarn image, the image is cropped, the unnecessary parts are removed, and the image is resized.
[0010] Based on the above scheme: the feature extraction module has the following specific working steps: C1: Edge detection: Edge detection technology is used to extract edge information from yarn images; C2: Texture feature extraction: Through image texture feature analysis, the texture information in the yarn image is extracted and the texture features of the yarn are identified; C3: Color feature extraction: Extract the color features of the yarn based on the image after color space conversion; C4: Shape feature extraction: shape analysis technology is used to extract the shape features of the yarn; C5: Regional feature extraction: Segment the image into different regions and extract the feature information of each region, including the color features, texture features and shape features within the region; C6: Grayscale feature extraction: Based on the grayscale information of the image, the grayscale features of the yarn image are described by calculating the grayscale histogram, mean, variance, texture features and grayscale gradient features.
[0011] A better solution among the above solutions is: in the step C1, the edge detection technology used to extract edge information in the yarn image has the following algorithm formula: Given a grayscale image I (x, y), edge detection is performed using horizontal edge detection operators and vertical edge detection operators; Horizontal edge detection operator: ; Vertical edge detection operator: ; Perform convolution operation on image I (x, y) with horizontal edge detection operator and vertical edge detection operator to obtain horizontal edge strength and vertical edge strength : , ; Finally, calculate the edge strength and edge direction: , ; Among them, G is the edge strength and θ is the edge direction, which are used to determine the gradient and direction of the edge.
[0012] As a further solution of the present invention: in the step C2, the algorithm formula for image texture feature analysis and extraction is as follows: ; in, is the pixel value of the two-dimensional image, It is a two-dimensional wavelet function. By performing wavelet transform on the image at different scales and directions, the decomposition coefficient of the image can be obtained, which is used to analyze the frequency domain characteristics of the image.
[0013] At the same time, in the C3 step, after the image is converted from the RGB color space to the HSV color space, the number of pixels of different color components is counted in the HSV color space image to construct a color histogram. According to the color histogram, the color characteristics of the yarn are extracted, including the mean and variance of the color distribution, the peak position and height of the color histogram, the shape characteristics of the color histogram, and the energy and entropy of the color histogram.
[0014] As a preferred embodiment of the present invention, the yarn detection module has the following specific working steps: D1: Collect and annotate image datasets containing positive samples (yarn) and negative samples (non-yarn), and divide the datasets into training and test sets for model training and evaluation; D2: Extract features from images in the training set and test set; D3: After feature extraction, the extracted features are input into the machine learning model for training and classification; D4: Construct a convolutional neural network model, take the image as input, extract features through multi-layer convolution and pooling operations, and finally perform classification through a fully connected layer; D5: Apply the trained model to specific areas in the image to detect and identify yarns. Based on the output of the model, determine whether there are yarns in the image.
[0015] Meanwhile, the specific working steps of the result display module are as follows: Image display: The detected yarn area is directly marked on the original image, marked with boxes, lines or dots of different colors or shapes, and the original image is divided into multiple areas, each of which contains only one or more yarns, and each area is marked. At the same time, a heat map is used to show the confidence of yarn detection, with high confidence areas using darker colors and low confidence areas using lighter colors; Text display: Display the detected yarn information in list form, including the coordinates, length, width, color and type of the yarn, and display the yarn information in table form. At the same time, the detected yarn is described in text.
[0016] As a better solution of the present invention: the system management module, its specific working steps include user management (adding, deleting, modifying user accounts and permission settings), log management (recording system operation logs, error logs, access logs), system settings (setting system parameters and configurations, backup and recovery operations), permission management (setting permission levels of user roles, managing user groups and permission groups), data management (backup, migration, clearing data), system monitoring (monitoring system operating status, performance indicators), system maintenance (software updates, troubleshooting) and report generation (generating system operation reports).
[0017] The beneficial effects of the present invention are: 1. This is a yarn detection system based on image processing. The feature extraction module comprehensively and deeply extracts multi-dimensional feature information from yarn images through multiple technologies such as edge detection, texture feature extraction, color feature extraction, shape feature extraction, regional feature extraction and grayscale feature extraction. This series of steps not only improves the accuracy and richness of feature extraction, but also provides a high-quality data foundation for subsequent image analysis and pattern recognition, thereby significantly improving the accuracy and reliability of yarn image analysis.
[0018] 2. This is a yarn detection system based on image processing. The yarn detection module collects and annotates image datasets containing positive and negative samples, extracts features, and inputs the extracted features into the machine learning model for training and classification. At the same time, a convolutional neural network model is constructed to extract image features through multi-layer convolution and pooling operations, and finally classifies through the fully connected layer. The trained model is applied to specific areas in the image for yarn detection and identification. This process not only improves the accuracy and efficiency of detection, but also effectively distinguishes yarn from non-yarn, providing strong technical support for yarn quality control and automated detection.
[0019] 3. This is a yarn detection system based on image processing. The image preprocessing module improves the image quality by denoising and enhancing the yarn image; converting the image from RGB to HSV color space to facilitate the separation of brightness and color information; converting the image to black and white and separating the yarn, removing noise and repairing the broken area, highlighting the outline and edge of the yarn; cropping and adjusting the image size according to the actual position. This series of steps not only improves the clarity and usability of the image, but also provides high-quality input data for subsequent image analysis and processing, thereby improving the accuracy and efficiency of the overall analysis.
[0020] 4. This is a yarn detection system based on image processing. The image acquisition module captures yarn images at all angles by setting the camera position and angle. The acquisition program is started to monitor and display image data in real time. After being transferred to the computer for storage, color deviation correction and clarity screening are performed. This process not only ensures the integrity and high quality of the data, but also improves work efficiency and analysis accuracy, providing a reliable basis for yarn monitoring and quality control.
[0021] 5. This is a yarn detection system based on image processing. The image acquisition module captures yarn images at all angles by setting the camera position and angle. The acquisition program is started to monitor and display image data in real time. After being transferred to the computer for storage, color deviation correction and clarity screening are performed. This process not only ensures the integrity and high quality of the data, but also improves work efficiency and analysis accuracy, providing a reliable basis for yarn monitoring and quality control. BRIEF DESCRIPTION OF THE DRAWINGS
[0022] Figure 1 This is an architecture diagram of a yarn detection system based on image processing proposed by the present invention;
[0023] Figure 2 A flowchart of an image acquisition module in a yarn detection system based on image processing proposed by the present invention;
[0024] Figure 3 A flowchart of an image preprocessing module in a yarn detection system based on image processing proposed by the present invention;
[0025] Figure 4 A flow chart of a feature extraction module in a yarn detection system based on image processing proposed by the present invention;
[0026] Figure 5 The present invention provides a flowchart of a yarn detection module in a yarn detection system based on image processing. DETAILED DESCRIPTION
[0027] The technical solution of the present invention is further described in detail below in conjunction with specific implementation methods.
[0028] Embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and cannot be understood as limiting the present invention.
[0029] A yarn detection system based on image processing, such as Figure 1 As shown, it includes an image acquisition module, an image preprocessing module, a feature extraction module, a yarn detection module, a result display module and a system management module. The image acquisition module acquires yarn image data presented in different forms through a camera. The image preprocessing module preprocesses the image data after image acquisition. The feature extraction module extracts features for describing various information of the yarn from the image data after preprocessing the image data. The yarn detection module analyzes and judges the features of the special zone by using image processing technology to realize the detection and identification of the yarn. The result display module displays the detection results to the user in the form of images or texts. The system management module manages and monitors the entire system.
[0030] In order to provide necessary input for subsequent image processing and yarn detection; Figure 2 As shown, the specific working steps of the image acquisition module are as follows: A1: Set the position and angle of the camera to ensure that the image of the yarn is captured at all angles; A2: Start the acquisition program, the camera starts to collect image data during the yarn running process, and transmits it to the computer for storage for subsequent image processing and analysis; A3: During the image data acquisition process, the acquired images are monitored and displayed in real time; A4: The computer corrects and adjusts the collected image data, corrects the color deviation of the image data, and deletes image data with poor clarity.
[0031] The image acquisition module captures yarn images at all angles by setting the camera position and angle, starts the acquisition program to monitor and display image data in real time, and performs color deviation correction and clarity screening after transferring it to the computer for storage. This process not only ensures the integrity and high quality of the data, but also improves work efficiency and analysis accuracy, providing a reliable basis for yarn monitoring and quality control.
[0032] In order to select and adjust according to the specific yarn detection scene and image characteristics; Figure 3 As shown, the specific steps of the image preprocessing module are as follows: B1: De-noising and image enhancement of yarn images; B2: Convert the image from RGB color space to HSV color space to separate the brightness and color information of the image; B3: Convert the image to black and white, separate the yarn from the background, remove small noise points and broken connection areas in the image, and highlight the outline and edge of the yarn; B4: According to the actual position in the yarn image, the image is cropped, the unnecessary parts are removed, and the image is resized.
[0033] The above image preprocessing module improves the image quality by denoising and enhancing the yarn image; converting the image from RGB to HSV color space to facilitate the separation of brightness and color information; converting the image to black and white and separating the yarn, removing noise and repairing the broken area, highlighting the outline and edge of the yarn; cropping and adjusting the image size according to the actual position. This series of steps not only improves the clarity and usability of the image, but also provides high-quality input data for subsequent image analysis and processing, thereby improving the accuracy and efficiency of the overall analysis.
[0034] In order to effectively extract information describing yarn characteristics; Figure 4 As shown, the feature extraction module has the following specific working steps: C1: Edge detection: Edge detection technology is used to extract edge information from yarn images; C2: Texture feature extraction: Through image texture feature analysis, the texture information in the yarn image is extracted and the texture features of the yarn are identified; C3: Color feature extraction: Extract the color features of the yarn based on the image after color space conversion; C4: Shape feature extraction: shape analysis technology is used to extract the shape features of the yarn; C5: Regional feature extraction: Segment the image into different regions and extract the feature information of each region, including the color features, texture features and shape features within the region; C6: Grayscale feature extraction: Based on the grayscale information of the image, the grayscale features of the yarn image are described by calculating the grayscale histogram, mean, variance, texture features and grayscale gradient features.
[0035] The feature extraction module above comprehensively and deeply extracts multi-dimensional feature information from yarn images through multiple technologies such as edge detection, texture feature extraction, color feature extraction, shape feature extraction, regional feature extraction, and grayscale feature extraction. This series of steps not only improves the accuracy and richness of feature extraction, but also provides a high-quality data foundation for subsequent image analysis and pattern recognition, thereby significantly improving the accuracy and reliability of yarn image analysis.
[0036] In the step C1, the edge detection technology used to extract edge information in the yarn image has an algorithm formula as follows: Given a grayscale image I (x, y), edge detection is performed using horizontal edge detection operators and vertical edge detection operators; Horizontal edge detection operator: ; Vertical edge detection operator: ; Convolve the image I (x, y) with the horizontal edge detection operator and the vertical edge detection operator to obtain the horizontal edge strength and vertical edge strength : , ; Finally, calculate the edge strength and edge direction: , ; Among them, G is the edge strength and θ is the edge direction, which is used to determine the gradient and direction of the edge;
[0037] In the C2 step, the algorithm for image texture feature analysis and extraction is as follows: ; in, is the pixel value of the two-dimensional image, It is a two-dimensional wavelet function. By performing wavelet transform on the image at different scales and directions, the decomposition coefficient of the image can be obtained, which is used to analyze the frequency domain characteristics of the image.
[0038] In the C3 step, after the image is converted from the RGB color space to the HSV color space, the number of pixels of different color components is counted in the HSV color space image to construct a color histogram. According to the color histogram, the color characteristics of the yarn are extracted, including the mean and variance of the color distribution, the peak position and height of the color histogram, the shape characteristics of the color histogram, and the energy and entropy of the color histogram.
[0039] In the C4 step, the shape feature technology used for the shape feature of the yarn has an algorithm formula as follows: ; Among them, F represents the shape factor, A represents the area of the object, and P represents the perimeter of the object. The value range of the shape factor is between 0 and 1. When the shape factor is close to 1, it means that the yarn is close to being smooth; when the shape factor is close to 0, it means that the yarn is close to being long and thin.
[0040] In order to realize the yarn detection and identification function in the specified area; Figure 5 As shown, the yarn detection module has the following specific working steps: D1: Collect and annotate image datasets containing positive samples (yarn) and negative samples (non-yarn), and divide the datasets into training and test sets for model training and evaluation; D2: Extract features from images in the training set and test set; D3: After feature extraction, the extracted features are input into the machine learning model for training and classification; D4: Construct a convolutional neural network model, take the image as input, extract features through multi-layer convolution and pooling operations, and finally perform classification through a fully connected layer; D5: Apply the trained model to specific areas in the image to detect and identify yarns. Based on the output of the model, determine whether there are yarns in the image.
[0041] The yarn detection module collects and annotates image datasets containing positive and negative samples, extracts features, and inputs the extracted features into the machine learning model for training and classification. At the same time, a convolutional neural network model is constructed to extract image features through multi-layer convolution and pooling operations, and finally classified through the fully connected layer. The trained model is applied to specific areas in the image for yarn detection and identification. This process not only improves the accuracy and efficiency of detection, but also effectively distinguishes between yarn and non-yarn, providing strong technical support for yarn quality control and automated detection.
[0042] The specific working steps of the result display module are as follows: Image display: The detected yarn area is directly marked on the original image, marked with boxes, lines or dots of different colors or shapes, and the original image is divided into multiple areas, each of which contains only one or more yarns, and each area is marked. At the same time, a heat map is used to show the confidence of yarn detection, with high confidence areas using darker colors and low confidence areas using lighter colors; Text display: Display the detected yarn information in list form, including the coordinates, length, width, color and type of the yarn, and display the yarn information in table form. At the same time, the detected yarn is described in text.
[0043] The above result display module provides intuitive visual feedback by marking the detected yarn area on the original image and using markers of different colors or shapes and heat maps to display the confidence of yarn detection. In addition, the detected yarn information is displayed in list and table form, including coordinates, length, width, color and type, and text description is attached to provide detailed text information. This process not only enhances the visualization of the results, making the test results easier to understand and analyze, but also provides comprehensive yarn information, which is convenient for further processing and decision-making, and improves the practicality and accuracy of the test results.
[0044] The system management module has specific working steps including user management (adding, deleting, modifying user accounts and permission settings), log management (recording system operation logs, error logs, access logs), system settings (setting system parameters and configurations, backup and recovery operations), permission management (setting permission levels for user roles, managing user groups and permission groups), data management (backup, migration, clearing data), system monitoring (monitoring system operating status, performance indicators), system maintenance (software updates, troubleshooting) and report generation (generating system operation reports).
[0045] The above system management module provides comprehensive system management functions through a series of steps such as user management, log management, system settings, authority management, data management, system monitoring, system maintenance and report generation. User management and authority management ensure the security and controllability of the system, log management and system monitoring achieve real-time tracking and recording of the system operation status, system settings and maintenance ensure the stability and sustainability of the system, and data management and report generation improve the reliability and availability of data. This process not only improves the overall management efficiency of the system, but also enhances the security, stability and maintainability of the system, providing a solid guarantee for the efficient operation of the system.
[0046] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.
Claims
1. A yarn detection system based on image processing, comprising an image acquisition module, an image preprocessing module, a feature extraction module, a yarn detection module, a result display module and a system management module, characterized in that: The image acquisition module acquires yarn image data presented in different forms through a camera, the image preprocessing module preprocesses the image data after image acquisition, the feature extraction module extracts features for describing various information of the yarn from the image data after image data preprocessing, the yarn detection module analyzes and judges the features of the special zone using image processing technology to realize yarn detection and identification, the result display module displays the detection results to the user in the form of images or text, and the system management module manages and monitors the entire system.
2. A yarn detection system based on image processing according to claim 1, characterized in that: The specific steps of the image acquisition module are as follows: A1: Set the position and angle of the camera to ensure that the image of the yarn is captured at all angles; A2: Start the acquisition program, the camera starts to collect image data during the yarn running process, and transmits it to the computer for storage for subsequent image processing and analysis; A3: During the image data acquisition process, the acquired images are monitored and displayed in real time; A4: The computer corrects and adjusts the collected image data, corrects the color deviation of the image data, and deletes image data with poor clarity.
3. A yarn detection system based on image processing according to claim 1, characterized in that: The image preprocessing module has the following specific working steps: B1: De-noising and image enhancement of yarn images; B2: Convert the image from RGB color space to HSV color space to separate the brightness and color information of the image; B3: Convert the image to black and white, separate the yarn from the background, remove small noise points and broken connection areas in the image, and highlight the outline and edge of the yarn; B4: According to the actual position in the yarn image, the image is cropped, the unnecessary parts are removed, and the image is resized.
4. A yarn detection system based on image processing according to claim 1, characterized in that: The specific steps of the feature extraction module are as follows: C1: Edge detection: Edge detection technology is used to extract edge information from yarn images; C2: Texture feature extraction: Through image texture feature analysis, the texture information in the yarn image is extracted and the texture features of the yarn are identified; C3: Color feature extraction: Extract the color features of the yarn based on the image after color space conversion; C4: Shape feature extraction: shape analysis technology is used to extract the shape features of the yarn; C5: Regional feature extraction: Segment the image into different regions and extract the feature information of each region, including the color features, texture features and shape features within the region; C6: Grayscale feature extraction: Based on the grayscale information of the image, the grayscale features of the yarn image are described by calculating the grayscale histogram, mean, variance, texture features and grayscale gradient features.
5. A yarn detection system based on image processing according to claim 4, characterized in that: In the step C1, the edge detection technology used to extract edge information in the yarn image has an algorithm formula as follows: Given a grayscale image I (x, y), edge detection is performed using horizontal edge detection operators and vertical edge detection operators; Horizontal edge detection operator: ; Vertical edge detection operator: ; Convolve the image I (x, y) with the horizontal edge detection operator and the vertical edge detection operator to obtain the horizontal edge strength and vertical edge strength : , ; Finally, calculate the edge strength and edge direction: , ; Among them, G is the edge strength and θ is the edge direction, which are used to determine the gradient and direction of the edge.
6. A yarn detection system based on image processing according to claim 4, characterized in that: In the C2 step, the algorithm for image texture feature analysis and extraction is as follows: ; in, is the pixel value of the two-dimensional image, It is a two-dimensional wavelet function. By performing wavelet transform on the image at different scales and directions, the decomposition coefficient of the image can be obtained, which is used to analyze the frequency domain characteristics of the image.
7. A yarn detection system based on image processing according to claim 4, characterized in that: In the C3 step, after the image is converted from the RGB color space to the HSV color space, the number of pixels of different color components is counted in the HSV color space image to construct a color histogram. According to the color histogram, the color characteristics of the yarn are extracted, including the mean and variance of the color distribution, the peak position and height of the color histogram, the shape characteristics of the color histogram, and the energy and entropy of the color histogram.
8. The yarn detection system based on image processing according to claim 1, characterized in that: The yarn detection module works in the following specific steps: D1: Collect and annotate image datasets containing positive samples (yarn) and negative samples (non-yarn), and divide the datasets into training and test sets for model training and evaluation; D2: Extract features from images in the training set and test set; D3: After feature extraction, the extracted features are input into the machine learning model for training and classification; D4: Construct a convolutional neural network model, take the image as input, extract features through multi-layer convolution and pooling operations, and finally perform classification through a fully connected layer; D5: Apply the trained model to specific areas in the image to detect and identify yarns. Based on the output of the model, determine whether there are yarns in the image.
9. The yarn detection system based on image processing according to claim 1, characterized in that: The specific working steps of the result display module are as follows: Image display: The detected yarn area is directly marked on the original image, marked with boxes, lines or dots of different colors or shapes, and the original image is divided into multiple areas, each of which contains only one or more yarns, and each area is marked. At the same time, a heat map is used to show the confidence of yarn detection, with high confidence areas using darker colors and low confidence areas using lighter colors; Text display: Display the detected yarn information in list form, including the coordinates, length, width, color and type of the yarn, and display the yarn information in table form. At the same time, the detected yarn is described in text.
10. The yarn detection system based on image processing according to claim 1, characterized in that: The system management module has specific working steps including user management (adding, deleting, modifying user accounts and permission settings), log management (recording system operation logs, error logs, access logs), system settings (setting system parameters and configurations, backup and recovery operations), permission management (setting permission levels for user roles, managing user groups and permission groups), data management (backup, migration, clearing data), system monitoring (monitoring system operating status, performance indicators), system maintenance (software updates, troubleshooting) and report generation (generating system operation reports).
Citation Information
Cited By
Textile spindle speed dynamic detection and feature extraction method
CN119313660A
Dynamic detection and feature extraction method of textile spindle speed
CN119313660B
Polyester filament broken filament detection method and system based on image processing technology
CN119887620A
Polyester Filament Hairiness Detection Method and System Based on Image Processing Technology
CN119887620B
Warping spool end finding image processing system
CN122115308A
