Leather surface texture analysis system based on 3D vision

Abstract

The invention relates to the technical field of computer vision and image processing, and discloses a leather surface texture analysis system based on 3D vision, which comprises a 3D vision data acquisition module, a 3D vision data analysis module, an early warning module, a leather surface quality evaluation module, a processing module and a control module, the 3D visual data acquisition module is used for performing omnibearing data acquisition on the leather surface by using a 3D visual system, and the 3D visual data analysis module is used for calculating a leather surface roughness index Cz, a leather color consistency index Yx and a leather texture defect severity Rv through the acquired data; the early warning module monitors leather production whole process data collected and analyzed by the 3D visual system in real time, an early warning mechanism is automatically triggered when a result is abnormal, the leather surface quality evaluation module comprehensively evaluates a calculation result of the 3D visual data analysis module, and the processing module pre-judges and provides corresponding processing measures according to an early warning result of the warning module. And the control module applies the optimized treatment measures to the leather production line.

Description

Technical Field

[0001] The present invention relates to the technical field of computer vision and image processing, and in particular to a leather surface texture analysis system based on 3D vision. Background Art

[0002] In the leather product production process, surface quality is a key indicator of product quality. Traditional methods for leather surface quality inspection rely primarily on manual visual inspection, which is not only inefficient but also susceptible to human interference, leading to inconsistent and inaccurate test results. With increasing consumer demand for leather product quality and the leather manufacturing industry's growing need for production efficiency and cost control, traditional inspection methods are no longer able to meet the demands of modern production.

[0003] In recent years, with the development of 3D vision and image processing technologies, computer vision-based surface quality inspection methods have gradually become a research hotspot. These technologies provide non-contact, high-precision surface quality inspection, with advantages such as high automation, fast inspection speed, and good repeatability. 3D vision technology, in particular, can capture three-dimensional surface information, including depth, texture details, and color, enabling comprehensive analysis of leather surface quality.

[0004] However, existing 3D vision-based leather surface texture analysis systems still have some shortcomings. For example, some systems lack accuracy and robustness when processing the complex textures of leather surfaces, making it difficult to accurately identify and quantify minor surface defects. Other systems lack real-time monitoring and early warning capabilities, making it difficult to promptly detect quality issues during the production process. Furthermore, when addressing color consistency issues on leather surfaces, existing systems often use simple threshold judgment methods, lacking in-depth analysis of color distribution characteristics, resulting in low accuracy in color consistency assessment. Summary of the Invention

[0005] In response to the shortcomings of the existing technology, the present invention provides a leather surface texture analysis system based on 3D vision, which has the advantages of high-precision defect recognition, real-time monitoring and early warning, and in-depth color analysis. It solves the problems of insufficient accuracy and robustness in complex texture analysis of leather surfaces, inability to detect quality problems in a timely manner, and inaccurate color consistency assessment.

[0006] To achieve the above-mentioned object, the present invention provides the following technical solution: a leather surface texture analysis system based on 3D vision, comprising a 3D vision data acquisition module, a 3D vision data analysis module, an early warning module, a leather surface quality assessment module, a processing module and a control module; The 3D vision data acquisition module uses a 3D vision system to perform all-round data acquisition on the leather surface and transmits the acquired data to the 3D vision data analysis module; The 3D visual data analysis module calculates the leather surface roughness index through the collected data , leather color consistency index and severity of leather grain defects and transmit the calculation results to the early warning module and the leather surface quality assessment module; The early warning module monitors the leather production process data collected and analyzed by the 3D vision system in real time. When the leather color consistency index exceeds the set threshold; When the leather texture defect is severe When the warning level is reached and data anomalies are detected, the warning mechanism is immediately triggered and the warning information is transmitted to the processing module; The leather surface quality assessment module comprehensively evaluates the calculation results of the 3D visual data analysis module to determine whether the leather surface quality in the production process meets the standards, and transmits the assessment results to the control module; The processing module predicts and proposes corresponding treatment measures based on the warning results of the warning module, and transmits the treatment measure suggestions to the control module; The control module implements optimized treatment measures into the leather production line.

[0007] Preferably, the 3D visual data acquisition module includes a leather depth data acquisition unit, a leather color data acquisition unit and a leather texture data acquisition unit.

[0008] Preferably, the leather depth data acquisition unit acquires leather surface depth data, including the height value of each sampling point on the leather surface, through a 3D vision system.

[0009] Preferably, the leather color data acquisition unit acquires leather surface color distribution data through a 3D vision system, including color values ​​of sampling points on various color channels on the leather surface.

[0010] Preferably, the leather texture data acquisition unit acquires leather surface texture data, including texture feature values ​​of various sampling points on the leather surface, through a 3D vision system.

[0011] Preferably, the 3D visual data analysis module includes a leather surface roughness analysis unit, a leather color analysis unit and a leather texture analysis unit.

[0012] Preferably, the leather surface roughness analysis unit calculates the leather surface roughness index according to the leather surface depth data. , and its calculation formula is: ; In the formula, Represents the leather surface roughness index, 、 、 、… Indicates the height value of each sampling point on the leather surface, Indicates the height value of the i-th sampling point, Indicates the average height value, Reference altitude, Indicates the minimum height value among all sampling points. Indicates the maximum height value among all sampling points. Indicates the total number of sampling points.

[0013] Preferably, the leather color analysis unit calculates the leather color consistency index based on the surface color distribution data , and its calculation formula is: ; In the formula, Indicates the leather color consistency index, 、 、 Respectively 、 、 The color value of the jth sampling point on the three color channels, 、 、 Respectively 、 、 The color mean of the sampling points on the three color channels, is the total number of color measurement points, 、 、 Respectively 、 、 The standard deviation across the three color channels.

[0014] Preferably, the leather texture analysis unit calculates the severity of leather texture defects based on the leather surface texture data. , and its calculation formula is: ; In the formula, Indicates the severity of leather texture defects. Represents the texture feature value of the kth sampling point, Represents the mean value of texture features of all sampling points, represents the standard deviation of texture eigenvalues, represents the weight coefficient, represents the threshold of texture feature value, Indicates the total number of sampling points.

[0015] Preferably, the leather surface roughness index , used to evaluate the smoothness of the leather surface, the leather color consistency index , used to judge the color consistency of leather products, the severity of leather texture defects , used to identify texture defects on leather surfaces.

[0016] Compared with the existing technology, the present invention provides a leather surface texture analysis system based on 3D vision, which has the following beneficial effects: 1. The present invention calculates the leather surface roughness index , leather color consistency index and severity of leather grain defects , which enables the system to achieve comprehensive control of leather surface quality, improve product quality, optimize production processes, and enhance the level of intelligent production. Among them, the leather surface roughness index Effectively evaluate the flatness of the leather surface, thereby improving the texture and appearance quality of the final product, helping to identify and correct problems that may cause surface unevenness during the production process, and leather color consistency index The calculation can ensure the uniformity of leather color and meet the customer's demand for color consistency. At the same time, the severity of leather texture defects can be The system can identify and process texture defects such as scratches and holes, thereby further improving the overall quality of the leather.

[0017] 2. The present invention integrates advanced 3D vision systems and data analysis technologies to achieve automated monitoring, evaluation, and control of leather surface quality, which can reduce reliance on manual monitoring and improve the intelligence level of leather production. By using the early warning module to monitor and analyze leather surface data in real time, problems in the production process can be discovered in a timely manner, thereby reducing production interruptions and rework caused by quality problems, thereby improving overall production efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 This is a flow chart of the system of the present invention. DETAILED DESCRIPTION

[0019] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. 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 making creative efforts are within the scope of protection of the present invention.

[0020] See also Figure 1 , a leather surface texture analysis system based on 3D vision, including a 3D vision data acquisition module, a 3D vision data analysis module, an early warning module, a leather surface quality assessment module, a processing module and a control module; The 3D vision data acquisition module uses advanced 3D vision systems (such as laser scanning and structured light scanning) to collect all-round data on the leather surface, including depth, texture details, and color, and transmits the collected depth, texture, and color data to the 3D vision data analysis module; The 3D visual data analysis module calculates the leather surface roughness index through the collected data , leather color consistency index and severity of leather grain defects , transmitting the calculation results to the early warning module and the leather surface quality assessment module; The early warning module monitors the leather production process data collected and analyzed by the 3D vision system in real time. When any of the following conditions are met, the early warning mechanism is triggered immediately: Exceeds the set threshold; when the leather color consistency index When the leather texture defect is severe When the warning level is reached and data anomalies are detected, the warning mechanism is immediately triggered, an audible and visual alarm signal is issued, and relevant personnel are notified for emergency processing, and the warning information is transmitted to the processing module; The leather surface quality assessment module comprehensively evaluates the calculation results of the 3D visual data analysis module to determine whether the leather surface quality in this production link meets the standards and transmits the assessment results to the control module; Based on the warning results from the warning module, the processing module makes a pre-judgment and proposes corresponding treatment measures (when the surface roughness exceeds the standard, polish or reprocess; when there is a color consistency problem, perform color correction or re-dyeing; when there is a texture defect problem, adjust the processing technology or replace the raw materials), and transmits the treatment measure suggestions to the control module; The control module implements optimized treatment measures into the leather production line to ensure that the leather surface quality meets the standards and continuously monitors the production process to prevent quality problems from recurring.

[0021] Advantages: By calculating the leather surface roughness index , leather color consistency index and severity of leather grain defects The system has realized the comprehensive control of leather surface quality, improved product quality, optimized production process, and enhanced the intelligent level of production. Among them, the leather surface roughness index Effectively evaluate the flatness of the leather surface, thereby improving the texture and appearance quality of the final product, helping to identify and correct problems that may cause surface unevenness during the production process, and leather color consistency index The calculation can ensure the uniformity of leather color and meet the customer's demand for color consistency. At the same time, the severity of leather texture defects can be The system analyzes the uniformity of the leather surface texture based on the numerical range of the data. It can identify and process texture defects such as scratches and holes, thereby further improving the overall quality of the leather. The implementation of the above quality control measures depends on the early warning mechanism that is immediately triggered by the early warning module when data anomalies are found, and the leather surface quality assessment module's comprehensive assessment of the leather surface quality in the production process. The processing module proposes corresponding treatment measures based on the early warning results, such as polishing, reprocessing, color correction and re-dyeing, while the control module implements these optimized treatment measures on the production line to ensure that the leather surface quality meets the standards.

[0022] The 3D vision data acquisition module includes a leather depth data acquisition unit, a leather color data acquisition unit and a leather texture data acquisition unit.

[0023] The leather depth data acquisition unit collects leather surface depth data through a 3D vision system, including the height value of each sampling point on the leather surface.

[0024] The leather color data acquisition unit collects leather surface color distribution data through a 3D vision system, including the color values ​​of sampling points on various color channels on the leather surface.

[0025] The leather texture data acquisition unit acquires leather surface texture data through a 3D vision system, including texture feature values ​​of each sampling point on the leather surface.

[0026] The 3D visual data analysis module includes a leather surface roughness analysis unit, a leather color analysis unit, and a leather texture analysis unit.

[0027] The leather surface roughness analysis unit calculates the leather surface roughness index based on the leather surface depth data , and its calculation formula is: ; In the formula, Represents the leather surface roughness index, 、 、 、… Indicates the height value of each sampling point on the leather surface, Indicates the height value of the i-th sampling point, Indicates the average height value, Reference altitude, Indicates the minimum height value among all sampling points. Indicates the maximum height value among all sampling points. Indicates the total number of sampling points.

[0028] The advantage is that the leather surface roughness analysis unit calculates the deviation between the height of each sampling point and the average height to obtain the leather surface roughness index. Specifically, the larger the value, the more uneven the leather surface is; on the contrary, the smaller the value, the smoother the leather surface is. Therefore, by real-time monitoring of the leather surface roughness index The numerical range helps to promptly detect surface unevenness problems that may occur during the leather production process. When problems are found, the system can immediately take measures to correct them, thereby avoiding the production of unqualified products and improving production quality.

[0029] The leather color analysis unit calculates the leather color consistency index based on the surface color distribution data , and its calculation formula is: ; In the formula, Indicates the leather color consistency index, which is used to measure the consistency of leather surface color. The smaller the value, the more uniform the color; the larger the value, the greater the color difference. 、 、 Respectively 、 、 ( The axis represents the change in lightness from black (0) to white (100); The axis represents the change from green (negative values) to red (positive values); The axis represents the change from blue (negative value) to yellow (positive value)) The color value of the j-th sampling point on the three color channels, 、 、 Respectively 、 、 The color mean of the sampling points on the three color channels, is the total number of color measurement points, 、 、 Respectively 、 、 The standard deviation of the three color channels is used to normalize the magnitude of channel differences.

[0030] The advantage is that the leather color analysis unit calculates the deviation between the color value of the sampling point and the mean value of the three color channels respectively, and normalizes it by the standard deviation to obtain the leather color consistency index. , enabling the system to comprehensively measure the uniformity of leather surface color in terms of brightness, hue and saturation, thereby effectively avoiding product quality problems caused by uneven leather color, meeting customers' strict requirements for leather color consistency, and making it suitable for leather products with higher color requirements.

[0031] The leather texture analysis unit calculates the severity of leather texture defects based on the leather surface texture data , and its calculation formula is: ; In the formula, Indicates the severity of leather texture defects and reflects the uniformity of the leather surface texture. The larger the value, the more uneven the texture. Represents the texture feature value of the kth sampling point, Represents the mean value of texture features of all sampling points, represents the standard deviation of texture eigenvalues, Represents the weight coefficient, which is used to adjust the influence of texture feature values ​​exceeding the threshold. It usually ranges from 0 to 1, and the specific value is determined according to actual needs. Indicates the threshold value of the texture feature value, which is used to determine whether the texture feature value exceeds the normal range. Indicates the total number of sampling points.

[0032] Advantages: According to the severity of leather grain defects The calculation formula introduces weight coefficient and threshold judgment to perform weighted processing on texture feature values ​​exceeding the threshold, which helps to comprehensively consider the deviation degree and standard deviation of texture feature values. The severity of leather texture defects calculated by the formula is The numerical value can accurately reflect the severity and unevenness of leather surface texture defects, enabling the system to quickly and accurately detect leather surface texture defects, including subtle texture inconsistencies, providing a basis for timely discovery and treatment of texture defects in leather production, thereby improving the efficiency and accuracy of product quality inspection.

[0033] Leather surface roughness index , used to evaluate the smoothness of the leather surface and the leather color consistency index , used to judge the color consistency of leather products and the severity of leather texture defects , used to identify texture defects on leather surfaces.

[0034] While 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 these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. The leather surface texture analysis system based on 3D vision is characterized by: It includes 3D vision data acquisition module, 3D vision data analysis module, early warning module, leather surface quality assessment module, processing module and control module; The 3D vision data acquisition module uses a 3D vision system to perform all-round data acquisition on the leather surface and transmits the acquired data to the 3D vision data analysis module; The 3D visual data analysis module calculates the leather surface roughness index through the collected data , leather color consistency index and severity of leather grain defects and transmit the calculation results to the early warning module and the leather surface quality assessment module; The early warning module monitors the leather production process data collected and analyzed by the 3D vision system in real time. When the leather color consistency index exceeds the set threshold; When the leather texture defect is severe When the warning level is reached, the warning mechanism is triggered immediately when data anomalies are found, and the warning information is transmitted to the processing module; The leather surface quality assessment module comprehensively evaluates the calculation results of the 3D visual data analysis module to determine whether the leather surface quality in the production process meets the standards, and transmits the assessment results to the control module; The processing module predicts and proposes corresponding treatment measures based on the warning results of the warning module, and transmits the treatment measure suggestions to the control module; The control module implements optimized treatment measures into the leather production line.

2. The leather surface texture analysis system based on 3D vision according to claim 1, characterized in that: The 3D visual data acquisition module includes a leather depth data acquisition unit, a leather color data acquisition unit and a leather texture data acquisition unit.

3. The leather surface texture analysis system based on 3D vision according to claim 2, characterized in that: The leather depth data acquisition unit acquires leather surface depth data, including the height value of each sampling point on the leather surface, through a 3D vision system.

4. The leather surface texture analysis system based on 3D vision according to claim 2, characterized in that: The leather color data acquisition unit acquires leather surface color distribution data, including color values ​​of sampling points on various color channels on the leather surface, through a 3D vision system.

5. The leather surface texture analysis system based on 3D vision according to claim 2, characterized in that: The leather texture data acquisition unit acquires leather surface texture data, including texture feature values ​​of each sampling point on the leather surface, through a 3D vision system.

6. The leather surface texture analysis system based on 3D vision according to claim 1, characterized in that: The 3D visual data analysis module includes a leather surface roughness analysis unit, a leather color analysis unit and a leather texture analysis unit.

7. The leather surface texture analysis system based on 3D vision according to claim 6, characterized in that: The leather surface roughness analysis unit calculates the leather surface roughness index based on the leather surface depth data , and its calculation formula is: ； In the formula, Represents the leather surface roughness index, 、 、 、… Indicates the height value of each sampling point on the leather surface, Indicates the height value of the i-th sampling point, Indicates the average height value, Reference altitude, Indicates the minimum height value among all sampling points. Indicates the maximum height value among all sampling points. Indicates the total number of sampling points.

8. The leather surface texture analysis system based on 3D vision according to claim 6, characterized in that: The leather color analysis unit calculates the leather color consistency index based on the surface color distribution data , and its calculation formula is: ； In the formula, Indicates the leather color consistency index, 、 、 Respectively 、 、 The color value of the jth sampling point on the three color channels, 、 、 Respectively 、 、 The color mean of the sampling points on the three color channels, is the total number of color measurement points, 、 、 Respectively 、 、 The standard deviation across the three color channels.

9. The leather surface texture analysis system based on 3D vision according to claim 1, characterized in that: The leather texture analysis unit calculates the severity of leather texture defects based on the leather surface texture data , and its calculation formula is: ； In the formula, Indicates the severity of leather texture defects. Represents the texture feature value of the kth sampling point, Represents the mean value of texture features of all sampling points, represents the standard deviation of texture eigenvalues, represents the weight coefficient, represents the threshold of texture feature value, Indicates the total number of sampling points.

10. The leather surface texture analysis system based on 3D vision according to claim 9, characterized in that: The leather surface roughness index , used to evaluate the smoothness of the leather surface, the leather color consistency index , used to judge the color consistency of leather products, the severity of leather texture defects , used to identify texture defects on leather surfaces.

Images