Rubber whole mold appearance defect detection method and system based on machine vision

Abstract

The invention relates to the technical field of appearance defect monitoring, in particular to a rubber whole mold appearance defect detection method and system based on machine vision. The method comprises the following steps: acquiring rubber whole mold parameter data; performing O-shaped ring inner and outer diameter setting on the rubber whole mold based on the rubber whole mold parameter data to obtain rubber whole mold built-in O-shaped ring inner and outer diameter adjustment data; performing first surface overall shooting on the rubber whole mold according to the inner and outer diameter adjustment data of the O-shaped ring arranged in the rubber whole mold to generate a first overall appearance image of the standard rubber whole mold; performing detection area division on the first overall appearance image of the standard rubber whole mold to generate rubber whole mold detection area data; and comparing the rubber whole mold detection area data with a preset detection area number range to generate rubber whole mold product specification data. Through accurate parameter setting, automatic region division, focal length adjustment, high-precision defect detection and comprehensive report generation, the accuracy and comprehensiveness of defect detection are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of appearance defect monitoring, and in particular to a method and system for detecting appearance defects of a rubber mold based on machine vision. Background Art

[0002] Early rubber defect detection mainly relied on manual inspection and simple mechanical inspection. These methods are not only time-consuming and labor-intensive, but also easily affected by human factors, making it difficult to ensure consistency and high precision. With the rapid development of computer vision technology, machine vision systems have begun to be introduced into the field of rubber inspection. Early machine vision systems used simple image processing algorithms, such as edge detection and template matching. Although these methods can detect some basic defects, they have limited recognition capabilities for complex defect types and minor flaws. After entering the 21st century, the introduction of deep learning technology has significantly improved the detection capabilities of machine vision systems. Through convolutional neural networks (CNNs) and image classification models, modern inspection systems are able to automatically identify and classify a variety of defects. These deep learning models can learn from a large amount of labeled data, identify more complex defect patterns, and have high accuracy and robustness. However, the current traditional defect detection methods cannot accurately detect and locate subtle defects, and lack comprehensive detection of multiple angles or surfaces, resulting in the inability to fully identify all potential defects, which in turn leads to low accuracy and comprehensiveness of defect detection. Summary of the invention

[0003] Based on this, it is necessary to provide a method and system for detecting appearance defects of a rubber mold based on machine vision to solve at least one of the above technical problems.

[0004] To achieve the above object, a method for detecting appearance defects of a rubber mold based on machine vision is provided, the method comprising the following steps:

[0005] Step S1: Acquire parameter data of the rubber mold; set the inner and outer diameters of the O-ring of the rubber mold based on the parameter data of the rubber mold to obtain adjustment data of the inner and outer diameters of the O-ring built into the rubber mold; and take an overall photo of the first surface of the rubber mold according to the adjustment data of the inner and outer diameters of the O-ring built into the rubber mold to generate a first overall appearance image of the standard rubber mold;

[0006] Step S2: dividing the first overall appearance image of the standard rubber mold into detection areas to generate rubber mold detection area data; comparing the rubber mold detection area data with a preset detection area quantity range to generate rubber mold product specification data; performing trajectory positioning on the first overall appearance image of the standard rubber mold based on the trajectory positioning camera according to the rubber mold product specification data to generate rubber mold product defect shooting trajectory data;

[0007] Step S3: adjusting the focal length of the defect camera lens based on the rubber mold product specification data to generate defect camera focal length adjustment data; performing rubber mold appearance defect detection on the rubber mold product defect shooting trajectory data based on the defect camera focal length adjustment data, thereby obtaining an overall appearance defect detection image of the rubber mold; color marking the overall appearance defect detection image of the rubber mold to generate defect product positioning mark data and normal product positioning mark data; color mapping the first overall appearance image of the standard rubber mold through the defect product positioning mark data and the normal product positioning mark data to generate a first overall appearance defect detection image of the rubber mold;

[0008] Step S4: photographing the second surface of the rubber mold as a whole according to the first overall appearance defect detection image of the rubber mold, generating a second overall appearance image of the rubber mold and performing second surface appearance defect detection until the second overall appearance defect detection image of the rubber mold is generated; uploading the first overall appearance defect detection image of the rubber mold and the second overall appearance defect detection image of the rubber mold to the central processing system for appearance defect data storage, thereby generating a rubber mold appearance defect detection report.

[0009] The present invention ensures that the size of the rubber mold meets the specifications by accurately setting the inner and outer diameters of the O-ring, thereby improving the standardization of subsequent images. By generating a standard first overall appearance image through overall shooting, a stable benchmark is provided for subsequent detection, which is helpful for comparative analysis and accurate positioning of defects. The system automatically divides the detection area, reduces the error of manual operation, and ensures that each area is properly inspected. By comparing the detection area data with the preset specifications, accurate product specification data is generated, which helps to locate the specific area of ​​the rubber mold and improves the accuracy of defect detection. Track positioning is performed based on the product specification data to ensure that the shooting track of the defect camera is accurate, reducing the possibility of missed detection or false detection. The focal length of the defect camera is adjusted according to the product specification data of the rubber mold to ensure the clarity and detail accuracy of the image and improve the accuracy of defect detection. The positioning data of the defect and normal area are generated by color marking, and the standard image is color mapped to obtain a high-precision defect detection image, which improves the ability to identify defects. The defect marking and normal area marking of the standard image by color mapping technology make the defect position and type more intuitive, which is helpful for subsequent analysis and processing. The second side of the rubber mold is photographed as a whole and defect detection is performed to ensure that all defect areas are detected to avoid missed detection. The detection images of the first side and the second side are uploaded to the central processing system to centrally store and manage defect data, which is convenient for subsequent analysis, statistics and review. By comprehensively analyzing the uploaded detection images, a detailed rubber mold appearance defect detection report is generated to provide data support for quality control and improvement, and improve the traceability and reliability of the detection results. Therefore, the present invention improves the accuracy and comprehensiveness of defect detection through precise parameter setting, automated area division, focal length adjustment, high-precision defect detection and comprehensive report generation.

[0010] Preferably, step S1 comprises the following steps:

[0011] Step S11: Acquire rubber mold parameter data;

[0012] Step S12: setting the inner and outer diameters of the O-ring of the rubber mold based on the rubber mold parameter data to obtain inner and outer diameter adjustment data of the O-ring built into the rubber mold;

[0013] Step S13: photographing the first surface of the rubber mold as a whole according to the inner and outer diameter adjustment data of the O-ring built into the rubber mold to generate a first overall appearance image of the rubber mold;

[0014] Step S14: performing image preprocessing on the first overall appearance image of the rubber mold to generate a first overall appearance image of a standard rubber mold, wherein the image preprocessing includes image denoising, image filtering and brightness enhancement.

[0015] The present invention ensures that subsequent operations have accurate basic data by obtaining rubber mold parameter data. Obtaining detailed mold parameter data can provide necessary references, so that the setting of the inner and outer diameters of the O-ring is more accurate, thereby improving the quality of the final rubber mold. By accurately adjusting the inner and outer diameters of the O-ring, the sealing and fit of the mold are optimized, and production problems caused by improper parameter settings, such as air leakage or size discrepancies, are avoided. This can improve the performance and service life of the rubber mold. An overall appearance image of the first side is generated to provide a visual basis for subsequent image analysis and quality inspection. Through system shooting, detailed appearance information can be obtained, which is helpful to discover existing defects or inconsistencies. Image preprocessing (including denoising, filtering and brightness enhancement) can improve the clarity and contrast of the image, making subsequent image analysis more accurate. Standardized images are easier to perform quality assessment and defect detection, thereby improving overall inspection efficiency and accuracy.

[0016] Preferably, step S2 comprises the following steps:

[0017] Step S21: dividing the first overall appearance image of the standard rubber mold into detection areas to generate rubber mold detection area data;

[0018] Step S22: Calculating the number of detection areas for the rubber mold detection area data to obtain detection area number data;

[0019] Step S23: comparing the detection area quantity data with the preset detection area quantity range, when the detection area quantity data is less than the preset detection area quantity range, the corresponding rubber mold is marked as a small-scale rubber mold product; when the detection area quantity data is within the preset detection area quantity range, the corresponding rubber mold is marked as a medium-scale rubber mold product; when the detection area quantity data is greater than the preset detection area quantity range, the corresponding rubber mold is marked as a large-scale rubber mold product;

[0020] Step S24: integrating the small-scale rubber mold overall products, the medium-scale rubber mold products and the large-scale rubber mold products into product types to generate rubber mold product specification data;

[0021] Step S25: performing trajectory positioning on the first overall appearance image of the standard rubber mold based on the trajectory positioning camera according to the rubber mold product specification data, and generating rubber mold product defect shooting trajectory data.

[0022] The present invention can systematically perform local inspection on the rubber mold by dividing the image into inspection areas. This method can help refine the quality inspection process, make the inspection more accurate, and ensure that each inspection area is fully analyzed. Calculating the number of inspection areas provides basic data for further classification and analysis. By quantifying the number of inspection areas, an objective basis can be provided for subsequent product scale classification and defect detection. By comparing the actual number of inspection areas with the preset range, the rubber mold products can be divided into different scales (small scale, medium scale, large scale). This classification helps to formulate appropriate inspection and treatment plans according to products of different scales, thereby optimizing production management and quality control. Integrating product data of different scales to generate rubber mold product specification data helps to standardize product management. This integration can support the standardization of production processes, improve the organization and efficiency of product production, and facilitate the formulation of targeted quality inspection standards. Track positioning of the rubber mold image by a track positioning camera can generate accurate defect shooting track data. This positioning helps to accurately capture the defect location, improve the accuracy of defect detection, and provide specific data support for subsequent quality improvement and defect repair.

[0023] Preferably, step S25 comprises the following steps:

[0024] Step S251: adjusting the pixel value of the track positioning camera based on the rubber mold product specification data to generate the track positioning camera pixel adjustment data;

[0025] Step S252: performing initial product positioning on the first overall appearance image of the standard rubber mold by using the track positioning camera pixel adjustment data to generate initial positioning data of the rubber mold product; performing target overlap detection on the initial positioning data of the rubber mold product to generate overlapping detection target positioning data and non-overlap detection target positioning data;

[0026] Step S253: performing multi-dimensional feature detection on the overlapping detection target positioning data to generate overlapping target multi-dimensional feature data, wherein the multi-dimensional feature detection includes area range detection, aspect ratio range detection and color feature detection; performing confidence calculation on the overlapping target multi-dimensional feature data to obtain overlapping target confidence;

[0027] Step S254: performing overlapping target positioning filtering on the overlapping detection target positioning data according to the overlapping target confidence level to generate overlapping target optimized positioning data; integrating the non-overlapping detection target positioning data and the overlapping target optimized positioning data to generate a rubber mold product positioning data set;

[0028] Step S255: generating a trajectory for the rubber mold product positioning data set to obtain the rubber mold product defect shooting trajectory data.

[0029] The present invention can optimize image resolution and detail capture capabilities by adjusting the camera pixel value, making subsequent positioning and detection more accurate. Accurate pixel adjustment helps to improve image quality, thereby improving the accuracy of defect detection. The initial positioning of the product provides an accurate starting point, so that subsequent detection and analysis can be carried out on a correct basis. Overlap detection can help distinguish and identify different detection areas, ensure that the detection and analysis of each area are effective, and avoid detection errors caused by target overlap. Multi-dimensional feature detection (including area range, aspect ratio and color features) can provide a comprehensive understanding of the target, making the identification and classification of the target more accurate. Confidence calculation helps evaluate the reliability of the detection results and ensure that only highly reliable detection results are included in subsequent processing. Through overlapping target positioning filtering, inaccurate or redundant target data can be eliminated and the quality of positioning data can be improved. Integrating non-overlapping and optimized overlapping target positioning data to form a comprehensive positioning data set is helpful to build a complete product defect data foundation and improve the overall efficiency of data processing. Generating defect shooting trajectory data can guide the camera to shoot along a predetermined trajectory during the actual detection process. This not only improves the systematicness and comprehensiveness of detection, but also helps to accurately capture the location of defects, providing reliable data support for subsequent quality analysis and improvement.

[0030] Preferably, step S255 includes the following steps:

[0031] Step S2551: confirm the product inspection center point of the rubber mold product positioning data set to obtain the center point coordinate data of the rubber mold product;

[0032] Step S2552: Connect the center point coordinate data of the rubber mold product and the detection area data of the rubber mold product to generate detection area connection data of the rubber mold product;

[0033] Step S2253: generating a single-line flying shooting trajectory for the connection data of the inspection area of ​​the rubber mold product, and generating defect shooting trajectory data of the rubber mold product.

[0034] The present invention can provide an accurate reference point by confirming the center point coordinate data of the rubber whole mold product, so that subsequent inspection and shooting trajectory planning are more accurate. Center point confirmation helps to ensure that the entire product maintains consistent positioning during the inspection process, effectively avoiding inspection problems caused by position deviation. By connecting the product center point coordinate data with the inspection area data, a complete inspection area layout can be formed. This connection helps to ensure that all inspection areas are covered and the relationship between each area is effectively managed, making defect detection more systematic and comprehensive. Generating a single-line flying shot trajectory helps to formulate an optimized shooting path, thereby ensuring that each key area is effectively covered during the inspection process. By planning a single-line flying shot trajectory, the efficiency and accuracy of shooting can be improved, repeated shooting or missed areas can be reduced, and the quality and speed of defect detection can be improved.

[0035] Preferably, step S3 comprises the following steps:

[0036] Step S31: adjusting the lens focal length of the defect camera based on the rubber mold product specification data to generate defect camera focal length adjustment data; performing rubber mold appearance defect detection on the rubber mold product defect shooting trajectory data based on the defect camera focal length adjustment data, thereby obtaining an overall appearance defect detection image of the rubber mold;

[0037] Step S32: extracting color defect features from the rubber mold overall appearance defect detection image to generate rubber mold overall defect feature extraction data; locating defective products from the rubber mold overall appearance defect detection image based on the rubber mold overall defect feature extraction data to generate defective product location data and non-defective product location data;

[0038] Step S33: marking the defective product location data with a first color to generate defective product location marking data; marking the non-defective product location data with a second color to generate normal product location marking data;

[0039] Step S34: performing color mapping on the first overall appearance image of the standard rubber mold by using the defective product positioning mark data and the normal product positioning mark data to generate the first overall appearance defect detection image of the rubber mold.

[0040] The present invention ensures that the camera can clearly capture the details of the rubber mold through accurate adjustment of the lens focal length, and improves the resolution and clarity of the defect detection image. Accurate focal length setting makes defect detection more accurate, thereby effectively identifying and locating appearance defects. Accurate adjustment of the lens focal length ensures that the camera can clearly capture the details of the rubber mold, and improves the resolution and clarity of the defect detection image. Accurate focal length setting makes defect detection more accurate, thereby effectively identifying and locating appearance defects. By using different color markings for defective products and normal products, defective areas and normal areas can be intuitively presented. This visualization effect helps to quickly identify defective areas, reduce human errors, and facilitate further analysis and processing. The defect marking information is applied to the standard rubber mold image through color mapping, so that the defects are more prominent in the overall appearance image. This processing can effectively integrate defect information with product appearance, provide clear defect detection images, and support more effective quality control and problem location.

[0041] Preferably, step S32 includes the following steps:

[0042] Step S321: performing template search and rough positioning on the rubber mold appearance defect detection image to generate rough positioning data of the rubber mold product; performing shape feature extraction on the rubber mold appearance defect detection image to obtain appearance shape feature data of the rubber mold product; performing product fine positioning on the rough positioning data of the rubber mold product according to the appearance shape feature data of the rubber mold product to generate fine positioning data of the rubber product;

[0043] Step S322: using the rubber product precise positioning data to delineate the inner and outer contours of the rubber mold appearance defect detection image, and generate a partial product extraction image of the rubber mold; performing red, green and blue layer color conversion on the partial product extraction image of the rubber mold, and generate a partial product color conversion image of the rubber mold;

[0044] Step S323: performing color difference region analysis on the color conversion image of the local product of the rubber mold through the rubber mold defect feature extraction data to generate the color difference region of the local product of the rubber mold, wherein the color difference region of the local product of the rubber mold includes the color difference region of the red layer of the local product of the rubber mold, the color difference region of the green layer of the local product of the rubber mold, and the color difference region of the blue layer of the local product of the rubber mold; performing color difference repeated region screening on the color difference region of the red layer of the local product of the rubber mold, the color difference region of the green layer of the local product of the rubber mold, and the color difference region of the blue layer of the local product of the rubber mold to obtain an image of the dominant defect region of the appearance of the rubber mold product; performing traditional visual defect detection on the image of the dominant defect region of the appearance of the rubber mold product to generate the dominant defect feature data of the appearance of the rubber mold product;

[0045] Step S324: screening the color difference non-repetitive area of ​​the local product color difference area of ​​the rubber mold according to the image of the visible defect area of ​​the rubber mold product appearance, and obtaining the image of the invisible defect area of ​​the rubber mold product appearance; performing deep AI visual defect detection on the image of the invisible defect area of ​​the rubber mold product appearance, and generating the invisible defect feature data of the rubber mold product appearance;

[0046] Step S325: Integrate the hidden defect feature data of the rubber mold product appearance and the explicit defect feature data of the rubber mold product appearance to generate rubber mold defect feature extraction data; locate the defective product of the rubber mold appearance defect detection image according to the rubber mold defect feature extraction data to generate defective product location data and non-defective product location data.

[0047] The present invention can preliminarily determine the defect area by performing rough positioning and shape feature extraction on the appearance defect detection image of the rubber whole mold, and can accurately locate it through shape features. Rough positioning quickly locates the potential problem area, while fine positioning provides more detailed defect locations to ensure the accuracy and comprehensiveness of the detection. By accurately delineating the inner and outer contours of the product, the detection area can be further divided to facilitate subsequent detailed analysis. Color conversion separates the different color layers of the image, helps to distinguish and analyze color-related defects, and makes color feature extraction clearer and more effective. By analyzing the color difference area, the area of ​​color deviation can be identified. By screening the color difference repetitive area, the dominant defect can be determined and further confirmed by traditional visual inspection. This helps to clearly identify and classify dominant defects and ensure the accuracy of quality control. By screening the non-repetitive color difference area, the hidden defects can be identified. Using deep AI visual inspection technology, these hidden defects can be found more efficiently and accurately, which are not easily detected by traditional methods. Ensure that all potential defects are fully detected and analyzed. Integrating the dominant and recessive defect feature data can provide a comprehensive defect characteristic data set. This integration can fully reflect the defects of the product, make the defect analysis more in-depth, and provide comprehensive data support for subsequent product improvement and quality control.

[0048] Preferably, performing deep AI visual defect detection on the image of the hidden defect area of ​​the appearance of the rubber mold product includes:

[0049] Perform regional focusing analysis on the image of the hidden defect area of ​​the appearance of the rubber mold product to generate the focused hidden defect feature data of the rubber mold product; divide the focused hidden defect feature data of the rubber mold product into data sets to generate a model training set and a model test set;

[0050] The model training set is trained by deep learning classification algorithm to generate a hidden defect classification pre-model; the hidden defect classification pre-model is tested by model test set to generate a hidden defect classification model; the image of the hidden defect area of ​​the appearance of the rubber mold product is imported into the hidden defect classification model to perform hidden defect classification and generate hidden defect classification data;

[0051] Multimodal defect verification is performed on the image of the hidden defect area on the appearance of the rubber whole mold product through the hidden defect classification data to generate hidden defect feature data of the appearance of the rubber whole mold product, wherein the multimodal defect verification includes optical verification and thermal imaging verification.

[0052] The present invention can focus on detecting the features of the hidden defect area through regional focusing analysis, providing higher details and accuracy. The generated focused hidden defect feature data can help accurately locate and identify hidden defects and improve the sensitivity and reliability of detection. Dividing the hidden defect feature data into a model training set and a model test set is helpful to build and evaluate the performance of the deep learning model. The training set is used for learning and training the model, while the test set is used to verify the accuracy and generalization ability of the model. This method ensures that the model can effectively identify hidden defects and perform well in practical applications. The hidden defect classification model is generated by the deep learning classification algorithm, so that the model can identify and classify different types of hidden defects. This model can improve the detection ability of hidden defects, reduce missed detection and false detection, and improve the accuracy of overall detection. Using the classification model to classify the hidden defect area image, specific hidden defect classification data can be generated. This data can provide detailed information about the defect type and location, which is helpful for subsequent quality analysis and improvement measures. Through multimodal verification methods such as optical verification and thermal imaging verification, the accuracy of hidden defects can be verified from different detection angles and technical means. Optical verification provides a detailed view on the image, while thermal imaging verification can detect temperature changes to further confirm the presence of defects. This multi-modal verification helps to improve the reliability and comprehensiveness of the inspection results, ensuring the accuracy and consistency of defect detection.

[0053] Preferably, step S4 comprises the following steps:

[0054] Step S41: photographing the second surface of the rubber mold as a whole according to the first overall appearance defect detection image of the rubber mold to generate a second overall appearance image of the rubber mold;

[0055] Step S42: performing image preprocessing on the second overall appearance image of the rubber mold to generate a second overall appearance image of the standard rubber mold; returning to step S21 based on the second overall appearance image of the rubber mold to start second surface appearance defect detection until a second overall appearance defect detection image of the rubber mold is generated;

[0056] Step S43: uploading the first overall appearance defect detection image of the rubber mold and the second overall appearance defect detection image of the rubber mold to the central processing system for storing appearance defect data, thereby generating a rubber mold appearance defect detection report.

[0057] The present invention takes an overall shot of the second side of the rubber mold to obtain appearance images at different angles, thereby ensuring comprehensive detection of appearance defects. This multi-angle shooting method helps to discover hidden defects that cannot be detected on the first side, thereby improving the coverage of detection. Preprocessing the second overall appearance image of the rubber mold to generate a standard image helps to improve the accuracy and consistency of subsequent detection. Returning to step S21 to repeat the detection process of the first side, ensure that the second side is also subjected to detailed defect detection. This method can ensure that each side of the rubber mold undergoes the same strict detection procedure, thereby reducing omissions and enhancing the integrity of the detection. Uploading the appearance defect detection images of the first side and the second side to the central processing system for data storage helps to build a comprehensive defect data archive. The generated rubber mold appearance defect detection report provides a detailed record of product quality, which can be used for quality analysis, problem tracing and subsequent production improvement. This systematic data management method helps to improve the transparency and traceability of the production process and ensure the continuous improvement of product quality.

[0058] In this specification, a rubber mold appearance defect detection system based on machine vision is provided, which is used to execute the above-mentioned rubber mold appearance defect detection method based on machine vision. The rubber mold appearance defect detection system based on machine vision includes:

[0059] The overall appearance shooting module is used to obtain the parameter data of the rubber mold; set the inner and outer diameters of the O-ring of the rubber mold based on the parameter data of the rubber mold to obtain the inner and outer diameter adjustment data of the O-ring built into the rubber mold; shoot the first surface of the rubber mold as a whole according to the inner and outer diameter adjustment data of the O-ring built into the rubber mold to generate the first overall appearance image of the standard rubber mold;

[0060] The product trajectory positioning module is used to divide the first overall appearance image of the standard rubber mold into detection areas to generate the rubber mold detection area data; compare the rubber mold detection area data with the preset detection area quantity range to generate the rubber mold product specification data; based on the trajectory positioning camera, the first overall appearance image of the standard rubber mold is tracked according to the rubber mold product specification data to generate the rubber mold product defect shooting trajectory data;

[0061] A product defect detection module is used to adjust the lens focal length of a defect camera based on the product specification data of the rubber whole mold to generate defect camera focal length adjustment data; perform rubber whole mold appearance defect detection on the rubber whole mold product defect shooting trajectory data based on the defect camera focal length adjustment data, thereby obtaining an overall appearance defect detection image of the rubber whole mold; perform color marking on the overall appearance defect detection image of the rubber whole mold to generate defect product positioning marking data and normal product positioning marking data; perform color mapping on a first overall appearance image of a standard rubber whole mold through the defect product positioning marking data and the normal product positioning marking data to generate a first overall appearance defect detection image of the rubber whole mold;

[0062] The product defect report module is used to shoot the second side of the rubber mold as a whole according to the first overall appearance defect detection image of the rubber mold, generate a second overall appearance image of the rubber mold and perform second side appearance defect detection until the second overall appearance defect detection image of the rubber mold is generated; upload the first overall appearance defect detection image of the rubber mold and the second overall appearance defect detection image of the rubber mold to the central processing system for appearance defect data storage, thereby generating a rubber mold appearance defect detection report.

[0063] The beneficial effect of the present invention is that by ensuring that the inner and outer diameters of the O-ring are set to meet the design requirements, a high-standard first overall appearance image is generated. This helps to accurately detect and evaluate the appearance of the rubber mold in subsequent steps. Through standardized shooting conditions and parameters, a consistent reference image is provided to provide a reliable reference for subsequent defect detection. By accurately dividing the detection area, each area is ensured to be properly inspected, the error of manual operation is reduced, and the comprehensiveness and accuracy of the detection are improved. Automatically compare the preset area quantity range to generate accurate product specification data, thereby optimizing the subsequent track positioning and defect detection process. By adjusting the focal length of the defect camera, the image clarity is ensured to be optimal, and the detection accuracy of the defect is improved. Defect detection is performed based on the focal length adjustment data, and defects and normal areas are accurately located by color marking, which improves the accuracy of defect identification and the readability of the detection results. The second side of the rubber mold is photographed to ensure that all defect areas are fully inspected to avoid omissions. The defect detection images of the first side and the second side are uploaded to the central processing system to generate a comprehensive appearance defect detection report, which helps to systematically manage and analyze defect data, and improves the detection efficiency and the comprehensiveness of the report. Therefore, the present invention improves the accuracy and comprehensiveness of defect detection through precise parameter setting, automated area division, focal length adjustment, high-precision defect detection and comprehensive report generation. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] Figure 1 The figure is a schematic diagram of the steps of a method for detecting appearance defects of a rubber mold based on machine vision;

[0065] Figure 2 for Figure 1 Detailed implementation steps of step S2 in the flowchart;

[0066] Figure 3 for Figure 1 Detailed implementation steps of step S3 in FIG.

[0067] Figure 4 for Figure 1 Detailed implementation steps of step S4 in FIG.

[0068] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0069] The technical method of the present invention is described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are 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 technicians in this field without creative work are within the scope of protection of the present invention.

[0070] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0071] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0072] To achieve this, please refer to Figures 1 to 4 A method for detecting appearance defects of a rubber mold based on machine vision, the method comprising the following steps:

[0073] Step S1: Acquire parameter data of the rubber mold; set the inner and outer diameters of the O-ring of the rubber mold based on the parameter data of the rubber mold to obtain adjustment data of the inner and outer diameters of the O-ring built into the rubber mold; and take an overall photo of the first surface of the rubber mold according to the adjustment data of the inner and outer diameters of the O-ring built into the rubber mold to generate a first overall appearance image of the standard rubber mold;

[0074] Step S2: dividing the first overall appearance image of the standard rubber mold into detection areas to generate rubber mold detection area data; comparing the rubber mold detection area data with a preset detection area quantity range to generate rubber mold product specification data; performing trajectory positioning on the first overall appearance image of the standard rubber mold based on the trajectory positioning camera according to the rubber mold product specification data to generate rubber mold product defect shooting trajectory data;

[0075] Step S3: adjusting the focal length of the defect camera lens based on the rubber mold product specification data to generate defect camera focal length adjustment data; performing rubber mold appearance defect detection on the rubber mold product defect shooting trajectory data based on the defect camera focal length adjustment data, thereby obtaining an overall appearance defect detection image of the rubber mold; color marking the overall appearance defect detection image of the rubber mold to generate defect product positioning mark data and normal product positioning mark data; color mapping the first overall appearance image of the standard rubber mold through the defect product positioning mark data and the normal product positioning mark data to generate a first overall appearance defect detection image of the rubber mold;

[0076] Step S4: photographing the second surface of the rubber mold as a whole according to the first overall appearance defect detection image of the rubber mold, generating a second overall appearance image of the rubber mold and performing second surface appearance defect detection until the second overall appearance defect detection image of the rubber mold is generated; uploading the first overall appearance defect detection image of the rubber mold and the second overall appearance defect detection image of the rubber mold to the central processing system for appearance defect data storage, thereby generating a rubber mold appearance defect detection report.

[0077] The present invention ensures that the size of the rubber mold meets the specifications by accurately setting the inner and outer diameters of the O-ring, thereby improving the standardization of subsequent images. By generating a standard first overall appearance image through overall shooting, a stable benchmark is provided for subsequent detection, which is helpful for comparative analysis and accurate positioning of defects. The system automatically divides the detection area, reduces the error of manual operation, and ensures that each area is properly inspected. By comparing the detection area data with the preset specifications, accurate product specification data is generated, which helps to locate the specific area of ​​the rubber mold and improves the accuracy of defect detection. Track positioning is performed based on the product specification data to ensure that the shooting track of the defect camera is accurate, reducing the possibility of missed detection or false detection. The focal length of the defect camera is adjusted according to the product specification data of the rubber mold to ensure the clarity and detail accuracy of the image and improve the accuracy of defect detection. The positioning data of the defect and normal area are generated by color marking, and the standard image is color mapped to obtain a high-precision defect detection image, which improves the ability to identify defects. The defect marking and normal area marking of the standard image by color mapping technology make the defect position and type more intuitive, which is helpful for subsequent analysis and processing. The second side of the rubber mold is photographed as a whole and defect detection is performed to ensure that all defect areas are detected to avoid missed detection. The detection images of the first side and the second side are uploaded to the central processing system to centrally store and manage defect data, which is convenient for subsequent analysis, statistics and review. By comprehensively analyzing the uploaded detection images, a detailed rubber mold appearance defect detection report is generated to provide data support for quality control and improvement, and improve the traceability and reliability of the detection results. Therefore, the present invention improves the accuracy and comprehensiveness of defect detection through precise parameter setting, automated area division, focal length adjustment, high-precision defect detection and comprehensive report generation.

[0078] In the embodiment of the present invention, reference Figure 1 The above is a schematic flow chart of the steps of a method for detecting appearance defects of a rubber mold based on machine vision of the present invention. In this example, the method for detecting appearance defects of a rubber mold based on machine vision includes the following steps:

[0079] Step S1: Acquire parameter data of the rubber mold; set the inner and outer diameters of the O-ring of the rubber mold based on the parameter data of the rubber mold to obtain adjustment data of the inner and outer diameters of the O-ring built into the rubber mold; and take an overall photo of the first surface of the rubber mold according to the adjustment data of the inner and outer diameters of the O-ring built into the rubber mold to generate a first overall appearance image of the standard rubber mold;

[0080] In an embodiment of the present invention, by obtaining a design drawing or CAD file of a rubber mold. Obtain the technical specifications and dimensional data of the mold from the manufacturer. Use a measuring tool to measure the actual mold on site to obtain accurate dimensional data. Record the inner diameter, outer diameter and related dimensions of the O-ring. Record the physical properties of the rubber material, such as hardness, elasticity, etc. Record the overall size and geometry of the mold. Enter the inner diameter and outer diameter parameters of the O-ring in the design software and set the correct size. Use the software to simulate the installation and adjustment process of the O-ring to ensure that the parameter settings meet the design requirements. Calculate the adjustment amount of the O-ring according to the design requirements and the actual size, and record and save the adjustment data of the O-ring for subsequent shooting and testing. Select a high-resolution camera, set appropriate lighting conditions, avoid shadows and reflections, fix the rubber mold on the shooting table, and ensure that the first side is completely visible. Select multiple angles or use a panoramic camera to shoot the first side of the rubber mold to ensure that a comprehensive image is captured. Perform preliminary processing (such as denoising, contrast adjustment) on the captured image to ensure image quality. The first side image taken is preprocessed to ensure that the image meets standard requirements (such as denoising and contrast enhancement), and the image is adjusted to a uniform size and format for subsequent analysis.

[0081] Step S2: dividing the first overall appearance image of the standard rubber mold into detection areas to generate rubber mold detection area data; comparing the rubber mold detection area data with a preset detection area quantity range to generate rubber mold product specification data; performing trajectory positioning on the first overall appearance image of the standard rubber mold based on the trajectory positioning camera according to the rubber mold product specification data to generate rubber mold product defect shooting trajectory data;

[0082] In an embodiment of the present invention, by ensuring that the first overall appearance image of the standard rubber mold has been obtained and preprocessed, the image is divided into regions using an image segmentation algorithm (such as k-means clustering, superpixel segmentation, edge detection, etc.), and the boundaries and features of each detection area are determined according to the division results. The coordinates, size and regional features of each detection area are recorded, and the detection area data is saved in a format suitable for analysis and further processing (such as JSON, CSV). The specification range of the detection area (such as the minimum and maximum area or size) is set. The area, shape and other features of each detection area are measured, and the actual area features are compared with the preset specifications to confirm whether they meet the specification requirements, and a data report that meets the specifications is generated, including the number of detection areas, area size, etc., and the specification data is saved in a standard format (such as JSON, CSV). Set the trajectory positioning camera, including the camera position, shooting angle and trajectory control parameters, and plan the camera's shooting trajectory according to the product specification data to ensure that all detection areas are covered. Use the camera to shoot according to the preset trajectory, record the image of each position, and record the camera's trajectory data, including the shooting position, angle and image information.

[0083] Step S3: adjusting the focal length of the defect camera lens based on the rubber mold product specification data to generate defect camera focal length adjustment data; performing rubber mold appearance defect detection on the rubber mold product defect shooting trajectory data based on the defect camera focal length adjustment data, thereby obtaining an overall appearance defect detection image of the rubber mold; color marking the overall appearance defect detection image of the rubber mold to generate defect product positioning mark data and normal product positioning mark data; color mapping the first overall appearance image of the standard rubber mold through the defect product positioning mark data and the normal product positioning mark data to generate a first overall appearance defect detection image of the rubber mold;

[0084] In an embodiment of the present invention, the product specification data of the rubber mold is obtained from step S2, including the main dimensions and the detection area information. According to the product specification data and the shooting requirements, the focal length of the camera lens is adjusted to ensure that the detection area is clearly visible, and the automatic focus function of the camera is used to perform automatic focus adjustment in the detection area, and the focus adjustment data is recorded, including the actual focal length value and the setting parameters. According to the focus adjustment data, the focal length and shooting parameters of the camera are set, and the shooting is performed according to the trajectory data in step S2 to ensure that all detection areas are covered. The overall appearance image of the rubber mold is captured to ensure that the image quality meets the defect detection requirements, and the captured defect detection image is saved for subsequent analysis. The defect area is marked using image processing technology (such as segmentation algorithm, edge detection, color threshold, etc.), and a specific color is assigned to the defect area to distinguish between normal areas and defect areas, and defect product positioning mark data and normal product positioning mark data are generated, including the coordinates of the marked area, color information, etc. The marked data is applied to the standard image to generate an image with marked defects and normal areas, the defect and normal marked information is fused into the standard rubber whole mold image, and the generated marked data is applied to the standard image to obtain an image containing defect marks.

[0085] Step S4: photographing the second surface of the rubber mold as a whole according to the first overall appearance defect detection image of the rubber mold, generating a second overall appearance image of the rubber mold and performing second surface appearance defect detection until the second overall appearance defect detection image of the rubber mold is generated; uploading the first overall appearance defect detection image of the rubber mold and the second overall appearance defect detection image of the rubber mold to the central processing system for appearance defect data storage, thereby generating a rubber mold appearance defect detection report.

[0086] In an embodiment of the present invention, the camera angle, focal length and light source setting are adjusted according to the experience of shooting the first side to ensure the clarity and consistency of the image shot on the second side. The second side of the rubber mold is fully photographed using a camera to ensure that the entire surface of the rubber mold is covered. Generate a second overall appearance image of the rubber mold and save it in a standard format (such as JPEG, PNG). Use a previously trained defect detection model or algorithm to analyze the second side image, identify and mark the defect area in the image, generate an image containing defect marks, and display the location information of the defect area. Integrate the defect detection images of the first side and the second side into a data set, and convert the image data into a format suitable for uploading (such as a compressed package, a JSON description file, etc.). Connect to the central processing system through a network to upload image data and related defect detection information. Extract the uploaded image data and detection information from the central processing system, generate a standardized detection report format (such as PDF, HTML), the report includes image data, defect marks, detection analysis results and suggestions, and save the report as an electronic document and distribute it to relevant personnel.

[0087] Preferably, step S1 comprises the following steps:

[0088] Step S11: Acquire rubber mold parameter data;

[0089] Step S12: setting the inner and outer diameters of the O-ring of the rubber mold based on the rubber mold parameter data to obtain inner and outer diameter adjustment data of the O-ring built into the rubber mold;

[0090] Step S13: photographing the first surface of the rubber mold as a whole according to the inner and outer diameter adjustment data of the O-ring built into the rubber mold to generate a first overall appearance image of the rubber mold;

[0091] Step S14: performing image preprocessing on the first overall appearance image of the rubber mold to generate a first overall appearance image of a standard rubber mold, wherein the image preprocessing includes image denoising, image filtering and brightness enhancement.

[0092] In an embodiment of the present invention, the rubber mold is accurately measured by using a digital measuring device or a three-dimensional scanning device to obtain its key dimension data, including the inner and outer diameters of the O-ring, the overall shape of the mold, the surface smoothness, and the material properties. By arranging and archiving these parameter data, a rubber mold parameter data set is generated. According to the rubber mold parameter data obtained in step S11, the inner and outer diameters of the O-ring built into the rubber mold are optimized using a dedicated design software (such as CAD). The optimization setting includes adjusting the size of the inner and outer diameters of the O-ring to ensure that it is consistent with the actual application requirements. Through simulation and iterative optimization, the inner and outer diameter adjustment data of the O-ring built into the rubber mold is finally generated to guide subsequent shooting and processing operations. After completing the optimization adjustment of the inner and outer diameters of the O-ring, the rubber mold is fixed on a dedicated shooting platform to ensure that its first side is completely exposed to the field of view of the camera device. Use a high-resolution industrial camera to shoot the first side of the rubber mold as a whole to capture its appearance details. During the shooting process, it is necessary to ensure that the lighting is uniform to avoid shadows and reflections. After the shooting is completed, the first overall appearance image of the rubber mold is generated as the basis for subsequent image processing. The first overall appearance image of the rubber mold obtained in step S13 is input into the image processing system and a series of image preprocessing operations are performed. First, a denoising algorithm is used to remove noise in the image to improve the clarity of the image. Then, an image filtering technique (such as Gaussian filtering) is applied to smooth the image to eliminate texture unevenness. Finally, brightness enhancement is performed to optimize the brightness and contrast of the image to ensure clear details. After these preprocessing steps, a first overall appearance image of the standard rubber mold is generated, providing a high-quality data basis for subsequent analysis and processing.

[0093] As an example of the present invention, refer to Figure 2 As shown, in this example, step S2 includes:

[0094] Step S21: dividing the first overall appearance image of the standard rubber mold into detection areas to generate rubber mold detection area data;

[0095] Step S22: Calculating the number of detection areas for the rubber mold detection area data to obtain detection area number data;

[0096] Step S23: comparing the detection area quantity data with the preset detection area quantity range, when the detection area quantity data is less than the preset detection area quantity range, the corresponding rubber mold is marked as a small-scale rubber mold product; when the detection area quantity data is within the preset detection area quantity range, the corresponding rubber mold is marked as a medium-scale rubber mold product; when the detection area quantity data is greater than the preset detection area quantity range, the corresponding rubber mold is marked as a large-scale rubber mold product;

[0097] Step S24: integrating the small-scale rubber mold overall products, the medium-scale rubber mold products and the large-scale rubber mold products into product types to generate rubber mold product specification data;

[0098] Step S25: performing trajectory positioning on the first overall appearance image of the standard rubber mold based on the trajectory positioning camera according to the rubber mold product specification data, and generating rubber mold product defect shooting trajectory data.

[0099] In an embodiment of the present invention, the first overall appearance image of the standard rubber mold generated in step S14 is imported into an image processing system. An image segmentation algorithm (such as an algorithm based on edge detection or threshold segmentation) is used to analyze the image to identify and divide the key detection areas on the surface of the rubber mold. These detection areas include the inner and outer surfaces of the O-ring, the edges of the mold, the interfaces of key components, etc. After the division is completed, the rubber mold detection area data is generated to identify the specific location, size and shape information of each detection area. After the detection area division is completed, the system will count the generated rubber mold detection area data and calculate the total number of detection areas. The calculation can be completed by a simple counting operation to obtain the detection area quantity data. This data represents the total number of areas on the surface of the rubber mold that need to be focused on, providing a basis for subsequent product scale classification. According to actual production needs, the detection area quantity range corresponding to rubber mold products of different scales is preset. Then, the detection area quantity data obtained in step S22 is compared with these preset ranges: if the detection area quantity data is less than the lower limit of the preset range, the rubber mold product is marked as a "small-scale rubber mold product"; if the detection area quantity data is within the preset range, it is marked as a "medium-scale rubber mold product"; if the detection area quantity data is greater than the upper limit of the preset range, it is marked as a "large-scale rubber mold product". This classification process helps to optimize the production and inspection process according to the complexity and number of the detection areas. After the classification is completed, all marked rubber mold products are integrated according to their scale to form a complete product specification data set. This data set includes specific specification information for each scale product, such as size, number of detection areas, applicable scenarios, etc. The rubber mold product specification data will be used to guide subsequent production, quality control and inventory management. Using the track positioning camera system, the first overall appearance image of the standard rubber mold is tracked in detail according to the rubber mold product specification data generated in step S24. The track positioning camera will plan the optimal shooting path according to the location, size and shape of the detection area to ensure that all key areas can be accurately captured. During the shooting process, the system will record the shooting trajectory and the corresponding inspection area, and generate the shooting trajectory data of the rubber mold product defects. This data will be used for subsequent automated inspection to help identify potential defects on the surface of the rubber mold.

[0100] Preferably, step S25 comprises the following steps:

[0101] Step S251: adjusting the pixel value of the track positioning camera based on the rubber mold product specification data to generate the track positioning camera pixel adjustment data;

[0102] Step S252: performing initial product positioning on the first overall appearance image of the standard rubber mold by using the track positioning camera pixel adjustment data to generate initial positioning data of the rubber mold product; performing target overlap detection on the initial positioning data of the rubber mold product to generate overlapping detection target positioning data and non-overlap detection target positioning data;

[0103] Step S253: performing multi-dimensional feature detection on the overlapping detection target positioning data to generate overlapping target multi-dimensional feature data, wherein the multi-dimensional feature detection includes area range detection, aspect ratio range detection and color feature detection; performing confidence calculation on the overlapping target multi-dimensional feature data to obtain overlapping target confidence;

[0104] Step S254: performing overlapping target positioning filtering on the overlapping detection target positioning data according to the overlapping target confidence level to generate overlapping target optimized positioning data; integrating the non-overlapping detection target positioning data and the overlapping target optimized positioning data to generate a rubber mold product positioning data set;

[0105] Step S255: generating a trajectory for the rubber mold product positioning data set to obtain the rubber mold product defect shooting trajectory data.

[0106] In an embodiment of the present invention, the specification data of the rubber mold product generated in step S24 is imported into the track positioning camera system. According to the rubber mold products of different specifications, the pixel value of the camera is adjusted accordingly to ensure that the best resolution and image quality can be obtained during shooting. These adjustments include resolution setting, focal length adjustment and optimization of exposure parameters. After these adjustments, the pixel adjustment data of the track positioning camera is generated to provide technical support for subsequent image capture and positioning. After the pixel value adjustment is completed, the track positioning camera is used to perform initial positioning of the rubber mold product. The system generates initial positioning data of the rubber mold product by analyzing the first overall appearance image of the standard rubber mold and combining the pixel adjustment data. Subsequently, the system performs overlap detection on the initial positioning data to identify the existing overlapping areas or targets. Overlap detection distinguishes the overlapping parts and non-overlapping parts in the image and generates two sets of data: overlapping detection target positioning data and non-overlapping detection target positioning data. After identifying the overlapping areas, the system will perform multi-dimensional feature detection on these overlapping areas. Specifically, the multi-dimensional feature detection includes: area range detection: measuring the area of ​​the overlapping area and judging whether it is within a preset reasonable range; aspect ratio range detection: analyzing the aspect ratio of the overlapping area to judge whether it meets the standard ratio of the rubber mold product; color feature detection: analyzing the color of the overlapping area to ensure that its color feature is consistent with the product standard. Through these detections, the system generates multi-dimensional feature data of the overlapping target. Next, the system will calculate the confidence of these feature data to obtain the confidence of each overlapping target for evaluating its detection reliability. According to the overlapping target confidence calculated in step S253, the overlapping detection target positioning data is filtered. Only those targets with higher confidence will be retained to generate overlapping target optimization positioning data. For overlapping targets with lower confidence, they will be marked as abnormal for further inspection. Then, the overlapping target optimization positioning data is integrated with the non-overlapping detection target positioning data to generate a complete rubber mold product positioning data set, covering all areas that need to be focused on. Using the rubber mold product positioning data set, the camera shooting trajectory is planned. The system will generate the optimal shooting path based on the regional distribution, size, shape and other characteristics in the positioning data set. This trajectory will ensure that the camera can cover all key areas in the most effective way and capture high-quality images. Ultimately, the defect shooting trajectory data of the rubber mold product is generated to provide a basis for subsequent defect detection and quality control.

[0107] Preferably, step S255 includes the following steps:

[0108] Step S2551: confirm the product inspection center point of the rubber mold product positioning data set to obtain the center point coordinate data of the rubber mold product;

[0109] Step S2552: Connect the center point coordinate data of the rubber mold product and the detection area data of the rubber mold product to generate detection area connection data of the rubber mold product;

[0110] Step S2253: generating a single-line flying shooting trajectory for the connection data of the inspection area of ​​the rubber mold product, and generating defect shooting trajectory data of the rubber mold product.

[0111] In an embodiment of the present invention, the detection center point of the rubber mold product is determined by the positioning data set of the rubber mold product generated according to step S254. The system will analyze each detection area in the positioning data set and calculate the geometric center or mass center position of the entire rubber mold product. This position will be used as a reference point for subsequent detection and shooting to ensure that the camera can accurately locate based on the center point. After calculation, the system generates the center point coordinate data of the rubber mold product. After the center point is confirmed, the system connects the center point coordinate data of the rubber mold product with the rubber mold detection area data. By analyzing the relative position between the center point and each detection area, the system generates an optimal connection path. This path connects the center point with each detection area in sequence to ensure that the camera can move smoothly from one area to the next without missing any key areas. Finally, the system generates the connection data of the rubber mold product detection area, laying the foundation for subsequent trajectory generation. After the connection path is determined, the system will generate a single-line flying shooting trajectory based on the connection data of the rubber mold product detection area. The single-line flying shooting trajectory means that the camera shoots along a continuous path without stopping or retracting in the middle. This trajectory design helps improve shooting efficiency and reduce motion blur or errors during shooting. Through this process, the system ultimately generates defect shooting trajectory data for the rubber mold product, ensuring that the camera can cover all important inspection areas according to the preset trajectory for efficient defect detection.

[0112] As an example of the present invention, refer to Figure 3 As shown, in this example, step S3 includes:

[0113] Step S31: adjusting the lens focal length of the defect camera based on the rubber mold product specification data to generate defect camera focal length adjustment data; performing rubber mold appearance defect detection on the rubber mold product defect shooting trajectory data based on the defect camera focal length adjustment data, thereby obtaining an overall appearance defect detection image of the rubber mold;

[0114] Step S32: extracting color defect features from the rubber mold overall appearance defect detection image to generate rubber mold overall defect feature extraction data; locating defective products from the rubber mold overall appearance defect detection image based on the rubber mold overall defect feature extraction data to generate defective product location data and non-defective product location data;

[0115] Step S33: marking the defective product location data with a first color to generate defective product location marking data; marking the non-defective product location data with a second color to generate normal product location marking data;

[0116] Step S34: performing color mapping on the first overall appearance image of the standard rubber mold by using the defective product positioning mark data and the normal product positioning mark data to generate the first overall appearance defect detection image of the rubber mold.

[0117] In an embodiment of the present invention, the lens focal length of the defect camera is adjusted according to the product specification data of the rubber mold to ensure that a clear appearance image of the rubber mold can be captured during shooting. The system uses these adjustment data to generate focal length adjustment data of the defect camera and applies them to the actual shooting process. Subsequently, the system uses these focal length adjustment data to gradually detect the appearance defects of the rubber mold along the preset rubber mold product defect shooting trajectory data. Through a series of image capture and processing, the overall appearance defect detection image of the rubber mold is finally generated. After obtaining the overall appearance defect detection image of the rubber mold, the system will extract the color defect features in the image. These color defect features include color abnormality, uneven brightness, or color difference. By extracting these features, the system generates rubber mold defect feature extraction data. Then, based on these feature data, the system further analyzes and locates the appearance defect detection image of the rubber mold. The system will locate the defect area and its specific location, and generate defect product location data; at the same time, for the part where the defect is not detected, non-defect product location data is generated. According to the positioning data generated in step S32, the system performs a first color marking on the detected defective product positioning data, usually using a more eye-catching color, such as red, to mark the defective area. At the same time, the non-defective product positioning data is marked with a second color, usually using green or other contrasting colors to distinguish between normal areas and defective areas. Finally, the system generates defective product positioning marking data and normal product positioning marking data, which will be used for further image processing and analysis. Finally, the system applies the defective product positioning marking data and the normal product positioning marking data to the first overall appearance image of the standard rubber mold for color mapping. The color mapping process will merge the data of different marks into one image, so that the final generated rubber mold first overall appearance defect detection image can intuitively display defects and normal areas. In this way, users can quickly identify the appearance defects of rubber mold products through this defect detection image and take corresponding treatment measures.

[0118] Preferably, step S32 includes the following steps:

[0119] Step S321: performing template search and rough positioning on the rubber mold appearance defect detection image to generate rough positioning data of the rubber mold product; performing shape feature extraction on the rubber mold appearance defect detection image to obtain appearance shape feature data of the rubber mold product; performing product fine positioning on the rough positioning data of the rubber mold product according to the appearance shape feature data of the rubber mold product to generate fine positioning data of the rubber product;

[0120] Step S322: using the rubber product precise positioning data to delineate the inner and outer contours of the rubber mold appearance defect detection image, and generate a partial product extraction image of the rubber mold; performing red, green and blue layer color conversion on the partial product extraction image of the rubber mold, and generate a partial product color conversion image of the rubber mold;

[0121] Step S323: performing color difference region analysis on the color conversion image of the local product of the rubber mold through the rubber mold defect feature extraction data to generate the color difference region of the local product of the rubber mold, wherein the color difference region of the local product of the rubber mold includes the color difference region of the red layer of the local product of the rubber mold, the color difference region of the green layer of the local product of the rubber mold, and the color difference region of the blue layer of the local product of the rubber mold; performing color difference repeated region screening on the color difference region of the red layer of the local product of the rubber mold, the color difference region of the green layer of the local product of the rubber mold, and the color difference region of the blue layer of the local product of the rubber mold to obtain an image of the dominant defect region of the appearance of the rubber mold product; performing traditional visual defect detection on the image of the dominant defect region of the appearance of the rubber mold product to generate the dominant defect feature data of the appearance of the rubber mold product;

[0122] Step S324: screening the color difference non-repetitive area of ​​the local product color difference area of ​​the rubber mold according to the image of the visible defect area of ​​the rubber mold product appearance, and obtaining the image of the invisible defect area of ​​the rubber mold product appearance; performing deep AI visual defect detection on the image of the invisible defect area of ​​the rubber mold product appearance, and generating the invisible defect feature data of the rubber mold product appearance;

[0123] Step S325: Integrate the hidden defect feature data of the rubber mold product appearance and the explicit defect feature data of the rubber mold product appearance to generate rubber mold defect feature extraction data; locate the defective product of the rubber mold appearance defect detection image according to the rubber mold defect feature extraction data to generate defective product location data and non-defective product location data.

[0124] In an embodiment of the present invention, the rubber mold appearance defect detection image is roughly positioned by using the template search technology to quickly determine the approximate position of the rubber mold product and generate the rough positioning data of the rubber mold product. Then, the system extracts the appearance shape feature data of the rubber mold from the image and analyzes its key shape features such as edges and contours. Based on the extracted shape features, the system further refines the rough positioning data and finally generates accurate rubber product fine positioning data. According to the fine positioning data, the system accurately delineates the inner and outer contours of the rubber mold product to obtain a local product extraction image of the rubber mold. Then, the local extraction image is color-converted by the red, green, and blue (RGB) layers to enhance the color information expression of the image, and a color conversion image of the local product of the rubber mold is generated, which provides a basis for subsequent color difference analysis. Based on the color conversion image, the system performs color difference region analysis on each RGB layer of the rubber mold, and identifies the color difference region in each layer, including the color difference region of the red, green, and blue layers. Then, the system screens these color difference regions, excludes repeated color difference regions, and identifies the appearance dominant defect regions of the rubber mold. Finally, the system performs traditional visual defect detection on these images of obvious defect areas to generate the appearance obvious defect feature data of the rubber mold product. After screening out the obvious defects, the system further screens those non-repetitive color difference areas to identify potential invisible defect areas. For these invisible defect areas, the system conducts a deeper analysis through deep learning AI visual inspection technology, and finally generates the appearance hidden defect feature data of the rubber mold product. The hidden defect feature data is integrated with the obvious defect feature data to obtain comprehensive rubber mold defect feature extraction data. Based on these comprehensive extracted data, the system locates the defects of the rubber mold appearance defect detection images, and generates defect product location data and non-defect product location data respectively, providing a basis for subsequent processing and analysis.

[0125] Preferably, performing deep AI visual defect detection on the image of the hidden defect area of ​​the appearance of the rubber mold product includes:

[0126] Perform regional focusing analysis on the image of the hidden defect area of ​​the appearance of the rubber mold product to generate the focused hidden defect feature data of the rubber mold product; divide the focused hidden defect feature data of the rubber mold product into data sets to generate a model training set and a model test set;

[0127] The model training set is trained by deep learning classification algorithm to generate a hidden defect classification pre-model; the hidden defect classification pre-model is tested by model test set to generate a hidden defect classification model; the image of the hidden defect area of ​​the appearance of the rubber mold product is imported into the hidden defect classification model to perform hidden defect classification and generate hidden defect classification data;

[0128] Multimodal defect verification is performed on the image of the hidden defect area on the appearance of the rubber whole mold product through the hidden defect classification data to generate hidden defect feature data of the appearance of the rubber whole mold product, wherein the multimodal defect verification includes optical verification and thermal imaging verification.

[0129] In an embodiment of the present invention, the image quality is ensured by photographing the appearance hidden defect area of ​​the rubber mold product with a high-resolution camera. Image enhancement techniques, such as histogram equalization and contrast stretching, are applied to enhance the significance of defects. Potential defect areas are extracted using edge detection algorithms (such as Canny edge detection) or image segmentation-based methods (such as U-Net). The extracted defect area is refined, and morphological operations (such as dilation and corrosion) are applied to remove noise and enhance the edges of the defect area. Focused invisible defect feature data is extracted, and high-dimensional features are extracted from the defect area using a deep learning feature extraction network (such as a convolutional neural network CNN). The focused invisible defect feature data is divided into a training set and a test set. Typically, the training set accounts for 70%-80% and the test set accounts for 20%-30%. The defect type or location is annotated for each image in the training set to generate label data. Select a suitable deep learning classification algorithm, such as a convolutional neural network such as ResNet, VGG or EfficientNet. Use the training set to train the model, tune the hyperparameters, and optimize the model performance. Evaluate the model performance on the validation set, and perform hyperparameter tuning to prevent overfitting. Input the image of the hidden defect area of ​​the rubber mold product appearance into the trained hidden defect classification model to classify the defects and generate hidden defect classification data, including the defect type and its confidence score. Use an optical microscope or a high-resolution camera to further collect images of the defect area to inspect the defects in detail. Verify the accuracy of the classification results by comparing the hidden defect classification data and the optical image. Use a thermal imaging camera to capture the thermal image of the defect area and detect the temperature change caused by the defect. Combine the thermal imaging data for further verification to confirm the existence and type of the defect.

[0130] As an example of the present invention, refer to Figure 4 As shown, in this example, step S4 includes:

[0131] Step S41: photographing the second surface of the rubber mold as a whole according to the first overall appearance defect detection image of the rubber mold to generate a second overall appearance image of the rubber mold;

[0132] Step S42: performing image preprocessing on the second overall appearance image of the rubber mold to generate a second overall appearance image of the standard rubber mold; returning to step S21 based on the second overall appearance image of the rubber mold to start second surface appearance defect detection until a second overall appearance defect detection image of the rubber mold is generated;

[0133] Step S43: uploading the first overall appearance defect detection image of the rubber mold and the second overall appearance defect detection image of the rubber mold to the central processing system for storing appearance defect data, thereby generating a rubber mold appearance defect detection report.

[0134] In an embodiment of the present invention, the effect of external factors on image quality is reduced by ensuring that the shooting environment of the second surface is consistent with the shooting environment of the first surface, the lighting is uniform, and the background is clean. Use the same high-resolution camera as the first surface detection to ensure that the shooting parameters are consistent (such as exposure time and focal length). Fix the rubber mold on the shooting table to ensure that the second surface is completely visible. Perform panoramic shooting or multi-angle shooting to ensure that the full image of the second surface of the rubber mold is obtained. Apply filtering technology (such as median filtering and Gaussian filtering) to remove image noise. Improve image quality by contrast adjustment, histogram equalization and other methods. Adjust the image to a uniform size and format for subsequent processing. Perform image preprocessing on the second overall appearance image of the rubber mold to generate a standard second overall appearance image of the rubber mold; based on the second overall appearance image of the rubber mold, return to step S21 to start the second surface appearance defect detection until the second overall appearance defect detection image of the rubber mold is generated. Convert the first overall appearance defect detection image of the rubber mold and the second overall appearance defect detection image of the rubber mold into a standard format (such as JPEG, PNG) to ensure data compatibility, and upload the image and related data to a central processing system or database. Obtain defect detection data and images from the central processing system and generate detailed defect detection reports based on the stored data, including information such as defect type, location, severity, etc.

[0135] In this specification, a rubber mold appearance defect detection system based on machine vision is provided, which is used to execute the above-mentioned rubber mold appearance defect detection method based on machine vision. The rubber mold appearance defect detection system based on machine vision includes:

[0136] The overall appearance shooting module is used to obtain the parameter data of the rubber mold; set the inner and outer diameters of the O-ring of the rubber mold based on the parameter data of the rubber mold to obtain the inner and outer diameter adjustment data of the O-ring built into the rubber mold; shoot the first surface of the rubber mold as a whole according to the inner and outer diameter adjustment data of the O-ring built into the rubber mold to generate the first overall appearance image of the standard rubber mold;

[0137] The product trajectory positioning module is used to divide the first overall appearance image of the standard rubber mold into detection areas to generate the rubber mold detection area data; compare the rubber mold detection area data with the preset detection area quantity range to generate the rubber mold product specification data; based on the trajectory positioning camera, the first overall appearance image of the standard rubber mold is tracked according to the rubber mold product specification data to generate the rubber mold product defect shooting trajectory data;

[0138] A product defect detection module is used to adjust the lens focal length of a defect camera based on the product specification data of the rubber whole mold to generate defect camera focal length adjustment data; perform rubber whole mold appearance defect detection on the rubber whole mold product defect shooting trajectory data based on the defect camera focal length adjustment data, thereby obtaining an overall appearance defect detection image of the rubber whole mold; perform color marking on the overall appearance defect detection image of the rubber whole mold to generate defect product positioning marking data and normal product positioning marking data; perform color mapping on a first overall appearance image of a standard rubber whole mold through the defect product positioning marking data and the normal product positioning marking data to generate a first overall appearance defect detection image of the rubber whole mold;

[0139] The product defect report module is used to shoot the second side of the rubber mold as a whole according to the first overall appearance defect detection image of the rubber mold, generate a second overall appearance image of the rubber mold and perform second side appearance defect detection until the second overall appearance defect detection image of the rubber mold is generated; upload the first overall appearance defect detection image of the rubber mold and the second overall appearance defect detection image of the rubber mold to the central processing system for appearance defect data storage, thereby generating a rubber mold appearance defect detection report.

[0140] The beneficial effect of the present invention is that by ensuring that the inner and outer diameters of the O-ring are set to meet the design requirements, a high-standard first overall appearance image is generated. This helps to accurately detect and evaluate the appearance of the rubber mold in subsequent steps. Through standardized shooting conditions and parameters, a consistent reference image is provided to provide a reliable reference for subsequent defect detection. By accurately dividing the detection area, each area is ensured to be properly inspected, the error of manual operation is reduced, and the comprehensiveness and accuracy of the detection are improved. Automatically compare the preset area quantity range to generate accurate product specification data, thereby optimizing the subsequent track positioning and defect detection process. By adjusting the focal length of the defect camera, the image clarity is ensured to be optimal, and the detection accuracy of the defect is improved. Defect detection is performed based on the focal length adjustment data, and defects and normal areas are accurately located by color marking, which improves the accuracy of defect identification and the readability of the detection results. The second side of the rubber mold is photographed to ensure that all defect areas are fully inspected to avoid omissions. The defect detection images of the first side and the second side are uploaded to the central processing system to generate a comprehensive appearance defect detection report, which helps to systematically manage and analyze defect data, and improves the detection efficiency and the comprehensiveness of the report. Therefore, the present invention improves the accuracy and comprehensiveness of defect detection through precise parameter setting, automated area division, focal length adjustment, high-precision defect detection and comprehensive report generation.

[0141] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0142] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A method for detecting appearance defects of rubber molds based on machine vision, characterized in that: The following steps are involved: Step S1: Acquire parameter data of the rubber mold; set the inner and outer diameters of the O-ring of the rubber mold based on the parameter data of the rubber mold to obtain adjustment data of the inner and outer diameters of the O-ring built into the rubber mold; and take an overall photo of the first surface of the rubber mold according to the adjustment data of the inner and outer diameters of the O-ring built into the rubber mold to generate a first overall appearance image of the standard rubber mold; Step S2: dividing the first overall appearance image of the standard rubber mold into detection areas to generate rubber mold detection area data; comparing the rubber mold detection area data with a preset detection area quantity range to generate rubber mold product specification data; performing trajectory positioning on the first overall appearance image of the standard rubber mold based on the trajectory positioning camera according to the rubber mold product specification data to generate rubber mold product defect shooting trajectory data; Step S3: adjusting the focal length of the defect camera lens based on the rubber mold product specification data to generate defect camera focal length adjustment data; Based on the defect camera focal length adjustment data, the rubber mold product defect shooting trajectory data is used to perform the rubber mold appearance defect detection, thereby obtaining the rubber mold overall appearance defect detection image; the rubber mold overall appearance defect detection image is color-marked to generate defect product positioning mark data and normal product positioning mark data; the standard rubber mold first overall appearance image is color-mapped through the defect product positioning mark data and the normal product positioning mark data to generate the rubber mold first overall appearance defect detection image; Step S4: photographing the second surface of the rubber mold as a whole according to the first overall appearance defect detection image of the rubber mold, generating a second overall appearance image of the rubber mold and performing second surface appearance defect detection until the second overall appearance defect detection image of the rubber mold is generated; uploading the first overall appearance defect detection image of the rubber mold and the second overall appearance defect detection image of the rubber mold to the central processing system for appearance defect data storage, thereby generating a rubber mold appearance defect detection report.

2. The method for detecting appearance defects of rubber molds based on machine vision according to claim 1, characterized in that: Step S1 includes the following steps: Step S11: Acquire rubber mold parameter data; Step S12: setting the inner and outer diameters of the O-ring of the rubber mold based on the rubber mold parameter data to obtain inner and outer diameter adjustment data of the O-ring built into the rubber mold; Step S13: photographing the first surface of the rubber mold as a whole according to the inner and outer diameter adjustment data of the O-ring built into the rubber mold to generate a first overall appearance image of the rubber mold; Step S14: performing image preprocessing on the first overall appearance image of the rubber mold to generate a first overall appearance image of a standard rubber mold, wherein the image preprocessing includes image denoising, image filtering and brightness enhancement.

3. The method for detecting appearance defects of rubber molds based on machine vision according to claim 1, characterized in that: Step S2 includes the following steps: Step S21: dividing the first overall appearance image of the standard rubber mold into detection areas to generate rubber mold detection area data; Step S22: Calculating the number of detection areas for the rubber mold detection area data to obtain detection area number data; Step S23: comparing the detection area quantity data with the preset detection area quantity range, when the detection area quantity data is less than the preset detection area quantity range, the corresponding rubber mold is marked as a small-scale rubber mold product; when the detection area quantity data is within the preset detection area quantity range, the corresponding rubber mold is marked as a medium-scale rubber mold product; when the detection area quantity data is greater than the preset detection area quantity range, the corresponding rubber mold is marked as a large-scale rubber mold product; Step S24: integrating the small-scale rubber mold overall products, the medium-scale rubber mold products and the large-scale rubber mold products into product types to generate rubber mold product specification data; Step S25: performing trajectory positioning on the first overall appearance image of the standard rubber mold based on the trajectory positioning camera according to the rubber mold product specification data, and generating rubber mold product defect shooting trajectory data.

4. The method for detecting appearance defects of rubber molds based on machine vision according to claim 3, characterized in that: Step S25 includes the following steps: Step S251: adjusting the pixel value of the track positioning camera based on the rubber mold product specification data to generate the track positioning camera pixel adjustment data; Step S252: performing initial product positioning on the first overall appearance image of the standard rubber mold by using the track positioning camera pixel adjustment data to generate initial positioning data of the rubber mold product; performing target overlap detection on the initial positioning data of the rubber mold product to generate overlapping detection target positioning data and non-overlap detection target positioning data; Step S253: performing multi-dimensional feature detection on the overlapping detection target positioning data to generate overlapping target multi-dimensional feature data, wherein the multi-dimensional feature detection includes area range detection, aspect ratio range detection and color feature detection; performing confidence calculation on the overlapping target multi-dimensional feature data to obtain overlapping target confidence; Step S254: performing overlapping target positioning filtering on the overlapping detection target positioning data according to the overlapping target confidence level to generate overlapping target optimized positioning data; integrating the non-overlapping detection target positioning data and the overlapping target optimized positioning data to generate a rubber mold product positioning data set; Step S255: generating a trajectory for the rubber mold product positioning data set to obtain the rubber mold product defect shooting trajectory data.

5. The method for detecting appearance defects of rubber molds based on machine vision according to claim 4, characterized in that: Step S255 includes the following steps: Step S2551: confirm the product inspection center point of the rubber mold product positioning data set to obtain the center point coordinate data of the rubber mold product; Step S2552: Connect the center point coordinate data of the rubber mold product and the detection area data of the rubber mold product to generate detection area connection data of the rubber mold product; Step S2253: generating a single-line flying shooting trajectory for the connection data of the inspection area of ​​the rubber mold product, and generating defect shooting trajectory data of the rubber mold product.

6. The method for detecting appearance defects of rubber molds based on machine vision according to claim 1, characterized in that: Step S3 includes the following steps: Step S31: adjusting the lens focal length of the defect camera based on the rubber mold product specification data to generate defect camera focal length adjustment data; performing rubber mold appearance defect detection on the rubber mold product defect shooting trajectory data based on the defect camera focal length adjustment data, thereby obtaining an overall appearance defect detection image of the rubber mold; Step S32: extracting color defect features from the rubber mold overall appearance defect detection image to generate rubber mold overall defect feature extraction data; locating defective products from the rubber mold overall appearance defect detection image based on the rubber mold overall defect feature extraction data to generate defective product location data and non-defective product location data; Step S33: marking the defective product location data with a first color to generate defective product location marking data; marking the non-defective product location data with a second color to generate normal product location marking data; Step S34: performing color mapping on the first overall appearance image of the standard rubber mold by using the defective product positioning mark data and the normal product positioning mark data to generate the first overall appearance defect detection image of the rubber mold.

7. The method for detecting appearance defects of rubber molds based on machine vision according to claim 6, characterized in that: Step S32 includes the following steps: Step S321: performing template search and rough positioning on the rubber mold appearance defect detection image to generate rough positioning data of the rubber mold product; performing shape feature extraction on the rubber mold appearance defect detection image to obtain appearance shape feature data of the rubber mold product; performing product fine positioning on the rough positioning data of the rubber mold product according to the appearance shape feature data of the rubber mold product to generate fine positioning data of the rubber product; Step S322: using the rubber product precise positioning data to delineate the inner and outer contours of the rubber mold appearance defect detection image, and generate a partial product extraction image of the rubber mold; performing red, green and blue layer color conversion on the partial product extraction image of the rubber mold, and generate a partial product color conversion image of the rubber mold; Step S323: performing color difference region analysis on the color conversion image of the local product of the rubber mold through the rubber mold defect feature extraction data to generate the color difference region of the local product of the rubber mold, wherein the color difference region of the local product of the rubber mold includes the color difference region of the red layer of the local product of the rubber mold, the color difference region of the green layer of the local product of the rubber mold, and the color difference region of the blue layer of the local product of the rubber mold; performing color difference repeated region screening on the color difference region of the red layer of the local product of the rubber mold, the color difference region of the green layer of the local product of the rubber mold, and the color difference region of the blue layer of the local product of the rubber mold to obtain an image of the dominant defect region of the appearance of the rubber mold product; performing traditional visual defect detection on the image of the dominant defect region of the appearance of the rubber mold product to generate the dominant defect feature data of the appearance of the rubber mold product; Step S324: screening the color difference non-repetitive area of ​​the local product color difference area of ​​the rubber mold according to the image of the visible defect area of ​​the rubber mold product appearance, and obtaining the image of the invisible defect area of ​​the rubber mold product appearance; performing deep AI visual defect detection on the image of the invisible defect area of ​​the rubber mold product appearance, and generating the invisible defect feature data of the rubber mold product appearance; Step S325: Integrate the hidden defect feature data of the rubber mold product appearance and the explicit defect feature data of the rubber mold product appearance to generate rubber mold defect feature extraction data; locate the defective product of the rubber mold appearance defect detection image according to the rubber mold defect feature extraction data to generate defective product location data and non-defective product location data.

8. The method for detecting appearance defects of rubber molds based on machine vision according to claim 7, characterized in that: Deep AI visual defect detection of hidden defect areas on the appearance of rubber mold products includes: Perform regional focusing analysis on the image of the hidden defect area of ​​the appearance of the rubber mold product to generate the focused hidden defect feature data of the rubber mold product; divide the focused hidden defect feature data of the rubber mold product into data sets to generate a model training set and a model test set; The model training set is trained by deep learning classification algorithm to generate a hidden defect classification pre-model; the hidden defect classification pre-model is tested by model test set to generate a hidden defect classification model; the image of the hidden defect area of ​​the appearance of the rubber mold product is imported into the hidden defect classification model to perform hidden defect classification and generate hidden defect classification data; Multimodal defect verification is performed on the image of the hidden defect area on the appearance of the rubber whole mold product through the hidden defect classification data to generate hidden defect feature data of the appearance of the rubber whole mold product, wherein the multimodal defect verification includes optical verification and thermal imaging verification.

9. The method for detecting appearance defects of rubber molds based on machine vision according to claim 1, characterized in that: Step S4 includes the following steps: Step S41: photographing the second surface of the rubber mold as a whole according to the first overall appearance defect detection image of the rubber mold to generate a second overall appearance image of the rubber mold; Step S42: performing image preprocessing on the second overall appearance image of the rubber mold to generate a second overall appearance image of the standard rubber mold; returning to step S21 based on the second overall appearance image of the rubber mold to start second surface appearance defect detection until a second overall appearance defect detection image of the rubber mold is generated; Step S43: uploading the first overall appearance defect detection image of the rubber mold and the second overall appearance defect detection image of the rubber mold to the central processing system for storing appearance defect data, thereby generating a rubber mold appearance defect detection report.

10. A rubber mold appearance defect detection system based on machine vision, characterized in that: Used to perform the method for detecting appearance defects of a rubber mold based on machine vision as claimed in claim 1, the rubber mold appearance defect detection system based on machine vision comprises: The overall appearance shooting module is used to obtain the parameter data of the rubber mold; set the inner and outer diameters of the O-ring of the rubber mold based on the parameter data of the rubber mold to obtain the inner and outer diameter adjustment data of the O-ring built into the rubber mold; shoot the first surface of the rubber mold as a whole according to the inner and outer diameter adjustment data of the O-ring built into the rubber mold to generate the first overall appearance image of the standard rubber mold; The product trajectory positioning module is used to divide the first overall appearance image of the standard rubber mold into detection areas to generate the rubber mold detection area data; compare the rubber mold detection area data with the preset detection area quantity range to generate the rubber mold product specification data; based on the trajectory positioning camera, the first overall appearance image of the standard rubber mold is tracked according to the rubber mold product specification data to generate the rubber mold product defect shooting trajectory data; A product defect detection module is used to adjust the lens focal length of a defect camera based on the product specification data of the rubber whole mold to generate defect camera focal length adjustment data; perform rubber whole mold appearance defect detection on the rubber whole mold product defect shooting trajectory data based on the defect camera focal length adjustment data, thereby obtaining an overall appearance defect detection image of the rubber whole mold; perform color marking on the overall appearance defect detection image of the rubber whole mold to generate defect product positioning marking data and normal product positioning marking data; perform color mapping on a first overall appearance image of a standard rubber whole mold through the defect product positioning marking data and the normal product positioning marking data to generate a first overall appearance defect detection image of the rubber whole mold; The product defect report module is used to shoot the second side of the rubber mold as a whole according to the first overall appearance defect detection image of the rubber mold, generate a second overall appearance image of the rubber mold and perform second side appearance defect detection until the second overall appearance defect detection image of the rubber mold is generated; upload the first overall appearance defect detection image of the rubber mold and the second overall appearance defect detection image of the rubber mold to the central processing system for appearance defect data storage, thereby generating a rubber mold appearance defect detection report.

Images