Visual inspection method based on fabric physical structure simulation

Abstract

The invention provides a visual detection method based on fabric physical structure simulation. The visual detection method based on fabric physical structure simulation comprises the following steps: a, fabric physical modeling: establishing a physical structure model of a fabric, wherein the physical structure model is woven structure characteristics, warp and weft material characteristics and warp and weft arrangement modes; b, light source automatic calibration: detecting the angle and the intensity of a light source in real time by using a sensor; the irradiation angle and brightness of the light source are dynamically adjusted through the calibration model so as to eliminate the influence of the light source change on the detection. According to the visual detection method based on the fabric physical structure simulation, the influence of the light angle and intensity change on the detection precision in the prior art is innovatively solved. Through multi-angle light source control and an illumination compensation algorithm, the angle and the intensity of the light source are detected and calibrated in real time by using a sensor, so that the surface of the fabric can present consistent detection effects under different illumination conditions.

Description

Technical Field

[0001] The invention relates to the technical field of visual inspection, and in particular to a visual inspection method based on fabric physical structure simulation. Background Art

[0002] Visual inspection method based on fabric physical structure simulation: mainly used to detect fabric defects during the weaving process of the tube belt. This method generates simulated cloth belts or belt blanks by simulating the texture structure of the fabric. Under the illumination of the light, the fabric forms a base image with a color difference of 3-4 degrees, which serves as a comparison data source. The inspection system compares this base image with the fabric image generated online to identify possible defects. This method can automatically monitor quality during the fabric production process, thereby improving production efficiency.

[0003] However, this detection method also has some defects. The angle and intensity of the light will directly affect the accuracy of the detection. If the lighting conditions change, it may lead to misjudgment of color difference, which in turn affects the detection effect. The system's simulation effect on fabric texture may not perfectly cover the real situation, especially for complex fabric structures. Summary of the invention

[0004] In view of the shortcomings of the prior art, the present invention provides a visual inspection method based on the simulation of the physical structure of the fabric, which solves the problem that the angle and intensity of the light will directly affect the accuracy of the inspection; the system's simulation effect on the fabric texture may not perfectly cover the actual situation, especially the problem that the inspection effect on complex fabric structures is weak.

[0005] To achieve the above objectives, the present invention is implemented through the following technical solutions: a visual inspection method based on fabric physical structure simulation, specifically comprising the following steps:

[0006] a. Fabric physical modeling: Establish the fabric physical structure model M = f(T, E, W), where T is the weaving structure characteristics, E is the material characteristics of the warp and weft yarns, and W is the arrangement of the warp and weft yarns;

[0007] b. Automatic calibration of light source: Use sensors to detect the angle α and intensity I of the light source in real time, and dynamically adjust the illumination angle and brightness of the light source through the calibration model C(α,I) to eliminate the impact of light source changes on detection;

[0008] c. Color difference detection area division: According to the fabric structure model M, the color difference detection area is divided to generate the color difference simulation image S r , and the online detection image S t Perform local comparison to improve detection accuracy;

[0009] d. Image acquisition and preprocessing: Use a multi-angle, multi-light source camera system to acquire images of the fabric, remove noise and adjust contrast through the preprocessing function P(·), and obtain the preprocessed image I p =P(I raw );

[0010] e. Texture feature extraction: Based on the physical structure model of the fabric, the texture feature F = g(M) is extracted, including the arrangement of the warp and weft yarns, texture density and direction data, and g(·) is the texture feature extraction function;

[0011] f. Multi-angle light source control: According to the texture feature F and the light source calibration data C(α,I), the multi-angle light source is dynamically adjusted to ensure that the fabric can present clear texture features under different angles and lighting conditions;

[0012] g. Light compensation algorithm: for preprocessed image I p Perform illumination compensation, calculate the illumination difference compensation amount ΔL, and obtain the compensated detection image I c =I p -ΔL, to reduce the detection impact caused by uneven lighting;

[0013] h. Color difference detection and comparison: Based on the color difference detection algorithm, calculate the simulated image S r and compensation image I c The color difference ΔC = | S r -I c| , identify areas with abnormal color difference;

[0014] i. Defect location: Determine the specific location P of the defect based on the color difference detection result ΔC w (x, y, z) and marked in the fabric physical model;

[0015] j. Defect feature analysis: Perform feature analysis on the detected defects and calculate the defect type probability P(d i |F) to distinguish common defects such as broken yarn, missing stitches and intertwined yarns, so as to classify and archive them;

[0016] k. Data storage and feedback: store the test data and analysis results in the system database, and transmit the feedback data back to the control system to adjust the production process parameters to improve production efficiency;

[0017] I. System adaptive control: Based on the accumulated detection data, the algorithm adaptively adjusts the light source and detection parameters, automatically optimizes the detection process, and improves the detection accuracy.

[0018] Preferably, the fabric physical modeling further adopts a multi-level refined model, including microscopic and macroscopic features, so as to be closer to the real fabric structure, and the light source automatic calibration module includes a light source intensity sensor and an angle sensor to ensure that a stable light source is provided in different environments.

[0019] Preferably, the color difference detection area division is an automatic generation algorithm based on the fabric weaving structure, so that each area can respond to complex textures, and the image acquisition device adopts a multi-band imaging mode to collect multiple spectral images of the same detection area to improve detection accuracy.

[0020] Preferably, the texture feature extraction adopts a machine learning algorithm to automatically identify and classify different texture features of the fabric, and the multi-angle light source control system automatically adjusts the light source angle and brightness according to the color difference changes of the fabric to adapt to the detection requirements of different fabrics.

[0021] Preferably, the illumination compensation algorithm further includes a region-based dynamic compensation algorithm to adapt to uneven image illumination, and the color difference detection and contrast algorithm is based on a deep learning model to identify slight color difference changes to improve detection sensitivity.

[0022] Preferably, the defect positioning is based on three-dimensional coordinate annotation to accurately record the defect position, and the defect feature analysis module includes a defect sample database to store detected defect samples to enhance system recognition capabilities.

[0023] Preferably, the data storage module is integrated with a real-time feedback system, and the defect detection data can be directly fed back to the production equipment for real-time adjustment. The production process adjustment module performs adaptive production parameter adjustment by statistically analyzing the detection data.

[0024] Preferably, the color difference detection algorithm has an adaptive threshold adjustment function to meet the detection needs of fabrics of different materials. The detection system is suitable for a variety of fabric weaving methods and can automatically adapt to fabrics with different warp and weft densities, thereby expanding the application range of the system.

[0025] The present invention provides a visual inspection method based on fabric physical structure simulation, which has the following beneficial effects:

[0026] This visual inspection method based on the simulation of the physical structure of fabrics innovatively solves the impact of changes in light angle and intensity on detection accuracy in existing technologies. Through multi-angle light source control and lighting compensation algorithms, sensors are used to detect and calibrate the angle and intensity of the light source in real time to ensure that the fabric surface can present consistent detection results under different lighting conditions. By constructing a detailed model of the physical structure of the fabric, covering the fabric weaving structure and the material properties of the warp and weft yarns, and combining machine learning algorithms to extract texture features, the solution can more effectively simulate the real texture characteristics of the fabric, especially improving the detection effect of complex fabric structures.

[0027] The advantages of the present invention are that its automatic calibration and adaptive control detection method can automatically adjust the light source and color difference detection parameters to ensure that the detection accuracy is maintained in a complex production environment. In addition, the fabric is physically modeled through a multi-level refinement model, so that the detection system can adapt to different fabric materials and weaving methods, enhancing the applicability of the system. At the same time, the technical solution also has the function of accurate defect positioning based on three-dimensional coordinates, and feeds back the defect data to the production equipment in real time for automatic adjustment, thereby effectively improving production efficiency and product quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] Figure 1 It is a schematic diagram of the process of the present invention. DETAILED DESCRIPTION

[0029] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions 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 of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0030] like Figure 1 As shown, an embodiment of the present invention provides a visual inspection method based on fabric physical structure simulation, including: a. fabric physical modeling: establishing a physical structure model of the fabric M=f(T,E,W), wherein T is the weaving structure feature, E is the material property of the warp and weft yarns, and W is the arrangement of the warp and weft yarns. The fabric physical modeling further adopts a multi-level refinement model, including microscopic and macroscopic features, so as to be closer to the real fabric structure. The light source automatic calibration module includes a light source intensity sensor and an angle sensor to ensure that a stable light source is provided under different environments.

[0031] b. Automatic calibration of light source: Use sensors to detect the angle α and intensity I of the light source in real time, and dynamically adjust the illumination angle and brightness of the light source through the calibration model C(α,I) to eliminate the impact of light source changes on detection.

[0032] c. Color difference detection area division: According to the fabric structure model M, the color difference detection area is divided to generate the color difference simulation image S r , and the online detection image S t Local comparison is performed to improve detection accuracy. The color difference detection area division is an automatic generation algorithm based on the fabric weaving structure, so that each area can respond to complex textures. The image acquisition device adopts a multi-band imaging mode to collect multiple spectral images of the same detection area to improve detection accuracy.

[0033] d. Image acquisition and preprocessing: Use a multi-angle, multi-light source camera system to acquire images of the fabric, remove noise and adjust contrast through the preprocessing function P(·), and obtain the preprocessed image I p =P(I raw ).

[0034] e. Texture feature extraction: Based on the physical structure model of the fabric, the texture feature F = g(M) is extracted, including the arrangement of the warp and weft yarns, texture density and direction data. g(·) is the texture feature extraction function. The texture feature extraction uses a machine learning algorithm to automatically identify and classify different texture features of the fabric. The multi-angle light source control system automatically adjusts the light source angle and brightness according to the color difference of the fabric to meet the detection requirements of different fabrics.

[0035] f. Multi-angle light source control: According to the texture feature F and the light source calibration data C(α,I), the multi-angle light source is dynamically adjusted to ensure that the fabric can present clear texture features under different angles and lighting conditions;

[0036] g. Light compensation algorithm: for preprocessed image I p Perform illumination compensation, calculate the illumination difference compensation amount ΔL, and obtain the compensated detection image I c =I p -ΔL to reduce the detection impact caused by uneven lighting. The lighting compensation algorithm further includes a region-based dynamic compensation algorithm to adapt to the uneven lighting of the image. The color difference detection and contrast algorithm is based on a deep learning model to identify tiny color difference changes to improve detection sensitivity.

[0037] h. Color difference detection and comparison: Based on the color difference detection algorithm, calculate the simulated image S r and compensation image I c The color difference ΔC = | S r -I c |, identify areas with abnormal color difference.

[0038] i. Defect location: Determine the specific location P of the defect based on the color difference detection result ΔC w(x, y, z) and marked in the fabric physical model. Defect location is based on three-dimensional coordinate marking to accurately record the defect location. The defect feature analysis module contains a defect sample database to store the detected defect samples and improve the system recognition capability.

[0039] j. Defect feature analysis: Perform feature analysis on the detected defects and calculate the defect type probability P ( d i ∣F ) , distinguish common defects such as yarn breakage, missing stitches and intertwining, so as to classify and archive them.

[0040] k. Data storage and feedback: The test data and analysis results are stored in the system database, and the feedback data is sent back to the control system to adjust the production process parameters to improve production efficiency. The data storage module is integrated with the real-time feedback system to directly feed back the defect detection data to the production equipment for real-time adjustment. The production process adjustment module performs adaptive production parameter adjustments through statistical analysis of the test data.

[0041] I. System adaptive control: Based on the accumulated detection data, the algorithm adaptively adjusts the light source and detection parameters, automatically optimizes the detection process, and improves the detection accuracy. The color difference detection algorithm has an adaptive threshold adjustment function to meet the detection needs of fabrics of different materials. The detection system is suitable for a variety of fabric weaving methods and can automatically adapt to fabrics with different warp and weft densities to expand the application range of the system.

[0042] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A visual inspection method based on fabric physical structure simulation, characterized in that: The specific steps include: a. Fabric physical modeling: Establish the physical structure model of the fabric M = f(T, E, W), where T is the weaving structure characteristics, E is the material characteristics of the warp and weft yarns, and W is the arrangement of the warp and weft yarns; b. Automatic calibration of light source: Use sensors to detect the angle α and intensity I of the light source in real time, and dynamically adjust the illumination angle and brightness of the light source through the calibration model C(α,I) to eliminate the impact of light source changes on detection; c. Color difference detection area division: According to the fabric structure model M, the color difference detection area is divided to generate the color difference simulation image S r , and the online detection image S t Perform local comparison to improve detection accuracy; d. Image acquisition and preprocessing: Use a multi-angle, multi-light source camera system to acquire images of the fabric, remove noise and adjust contrast through the preprocessing function P(·), and obtain the preprocessed image I p =P(I raw ); e. Texture feature extraction: Based on the physical structure model of the fabric, the texture feature F = g(M) is extracted, including the arrangement of the warp and weft yarns, texture density and direction data, and g(·) is the texture feature extraction function; f. Multi-angle light source control: According to the texture feature F and the light source calibration data C(α,I), the multi-angle light source is dynamically adjusted to ensure that the fabric can present clear texture features under different angles and lighting conditions; g. Light compensation algorithm: for preprocessed image I p Perform illumination compensation, calculate the illumination difference compensation amount ΔL, and obtain the compensated detection image I c =I p -ΔL, to reduce the detection impact caused by uneven lighting; h. Color difference detection and comparison: Based on the color difference detection algorithm, calculate the simulated image S r and compensation image I c The color difference ΔC = | S r -I c| , identify areas with abnormal color difference; i. Defect location: Determine the specific location P of the defect based on the color difference detection result ΔC w (x, y, z) and marked in the fabric physical model; j. Defect feature analysis: Perform feature analysis on the detected defects and calculate the defect type probability P(d i |F) to distinguish common defects such as broken yarn, missing stitches and intertwined yarns, so as to classify and archive them; k. Data storage and feedback: store the test data and analysis results in the system database, and transmit the feedback data back to the control system to adjust the production process parameters to improve production efficiency; I. System adaptive control: Based on the accumulated detection data, the algorithm adaptively adjusts the light source and detection parameters, automatically optimizes the detection process, and improves the detection accuracy.

2. The visual inspection method based on fabric physical structure simulation according to claim 1, characterized in that: The fabric physical modeling further adopts a multi-level refined model, including microscopic and macroscopic features, so as to be closer to the real fabric structure. The light source automatic calibration module includes a light source intensity sensor and an angle sensor to ensure a stable light source in different environments.

3. The visual inspection method based on fabric physical structure simulation according to claim 1, characterized in that: The color difference detection area division is based on an automatic generation algorithm of the fabric weaving structure, so that each area can respond to complex textures. The image acquisition device adopts a multi-band imaging mode to collect multiple spectral images of the same detection area to improve detection accuracy.

4. The visual inspection method based on fabric physical structure simulation according to claim 1, characterized in that: The texture feature extraction adopts a machine learning algorithm to automatically identify and classify different texture features of fabrics. The multi-angle light source control system automatically adjusts the light source angle and brightness according to the color difference changes of the fabric to meet the detection requirements of different fabrics.

5. The visual inspection method based on fabric physical structure simulation according to claim 1, characterized in that: The illumination compensation algorithm further includes a region-based dynamic compensation algorithm to adapt to uneven image illumination. The color difference detection and comparison algorithm is based on a deep learning model to identify subtle color difference changes to improve detection sensitivity.

6. The visual inspection method based on fabric physical structure simulation according to claim 1, characterized in that: The defect positioning is based on three-dimensional coordinate annotation, which is used to accurately record the defect position. The defect feature analysis module includes a defect sample database, which is used to store the detected defect samples to improve the system recognition capability.

7. The visual inspection method based on fabric physical structure simulation according to claim 1, characterized in that: The data storage module is integrated with the real-time feedback system, and can directly feed back the defect detection data to the production equipment for real-time adjustment. The production process adjustment module performs adaptive production parameter adjustment by statistically analyzing the detection data.

8. The visual inspection method based on fabric physical structure simulation according to claim 1, characterized in that: The color difference detection algorithm has an adaptive threshold adjustment function to meet the detection needs of fabrics of different materials. The detection system is suitable for a variety of fabric weaving methods and can automatically adapt to fabrics with different warp and weft densities, expanding the application range of the system.

Images