A method and system for intelligently collecting frosted particle size on PET film surfaces

Abstract

The present invention discloses a method and system for intelligently collecting frosted particle size on the surface of a PET film, relating to the field of PET films. Specifically, the method involves collecting film images of multiple PET films under illumination at different brightness levels; identifying the contrast between particles on the film surface and the substrate using each of the film images; determining whether the contrast of each of the film images meets a preset standard contrast threshold under changes in the minimum brightness unit; if so, using the corresponding brightness variation interval as the optimal brightness range for the film image; and re-collecting the PET film image based on the optimal brightness range. The present invention can collect images of different PET film surfaces at appropriate brightness levels, thereby improving the accuracy of image recognition of frosted particle size, and thereby facilitating high-precision processing control of PET films.

Description

Technical Field

[0001] The present invention relates to the field of PET films, and in particular to a method and system for intelligently collecting frosted particle size on the surface of a PET film. Background Art

[0002] As a high-performance polymer material, polyethylene terephthalate (PET) film has been widely used in a variety of fields, including packaging, electronics, optics, and medical treatments, due to its excellent mechanical properties, chemical stability, optical transparency, and good barrier properties. In the food packaging field, PET film can effectively block oxygen, moisture, and microorganisms, extending the shelf life of food. At the same time, its good printability and glossiness can enhance the product's appearance. In the electronics industry, PET film is used as a substrate for flexible circuit boards, a packaging material for electronic components, and a protective film for display screens. Its insulation properties, high-temperature resistance, and flexibility meet the manufacturing needs of precision electronic devices. In the optical field, PET film can be prepared into functional optical films such as polarizers and brightness enhancement films, providing key optical performance support for optoelectronic devices such as liquid crystal displays.

[0003] However, the surface quality of PET film plays a decisive role in its performance and application results. The presence of surface particles, whether originating from impurities in the raw materials, agglomeration of additives during processing, or wear debris from production equipment, can cause numerous problems. These particles can lead to a decrease in the film's optical properties. For example, in optical film applications, light scattering and increased haze can affect display clarity. In packaging applications, they can also reduce the product's appearance, resulting in poor printing results and uneven gloss. Furthermore, particles can weaken the film's mechanical properties, acting as stress concentration points, reducing the film's tensile strength and impact resistance. These particles can easily trigger crack propagation when subjected to external forces, ultimately leading to film rupture.

[0004] Accurately identifying particle and substrate features on the PET film surface, and thereby achieving precise control of the film's surface quality, is a critical step in the production and application of PET film. Image acquisition and processing technologies play a central role in this identification process. By acquiring image information of the PET film surface and analyzing it using image processing algorithms, these surface microscopic features can be converted into intuitive quantitative data. The image's brightness range, a key parameter, significantly influences the highlighting of particle and substrate features. Different brightness settings alter the grayscale distribution of pixels in the image, thereby affecting the contrast between the particles and the substrate. An appropriate brightness range enhances the visual distinction between particles and the substrate, making them more clearly distinguishable in the image and providing strong support for subsequent feature extraction and quality assessment. Conversely, an inappropriate brightness range can cause particles to be submerged in the substrate background, leading to misidentification or missed detection, seriously compromising the accuracy and reliability of surface quality inspection. The contrast between particles and the substrate on the PET film surface primarily stems from the significant differences in their material properties. PET, the substrate material, is a highly crystalline polymer. Its molecular chains are formed by the esterification and polycondensation of terephthalic acid and ethylene glycol. The molecules are arranged in a regular and orderly pattern, forming a tight lattice structure. This structure imparts excellent mechanical properties, chemical stability, and optical transparency to the PET substrate. However, the composition of surface particles is complex and diverse, potentially originating from impurities in the raw materials, additive agglomeration during processing, and debris from equipment wear. Common particulate impurities include silica (SiO2), calcium carbonate (CaCO3), metal oxides (such as Fe2O3 and TiO2), and organic polymer particles. For example, silica has a quartz-like crystal structure, with silicon and oxygen atoms covalently bonded in tetrahedral formations, forming a highly stable three-dimensional network. This structure contributes to the silica particles' high hardness and chemical stability, a stark contrast to the flexible polymer chain structure of the PET substrate. In terms of optical properties, the refractive index of silica is approximately 1.46, while that of PET is typically between 1.57 and 1.64. This difference in refractive index results in distinct light propagation behaviors at the interface between the particle and substrate. Calcium carbonate particles typically exist as calcite or aragonite crystals, with a crystal structure composed of calcium and carbonate ions characterized by ionic bonds. Compared to the covalently bonded polymer structure of PET, calcium carbonate particles are relatively chemically more reactive and prone to dissolution in certain acidic environments. Optically, the refractive index of calcium carbonate is approximately 1.58 to 1.66, similar to that of PET. However, due to the anisotropy of its crystal structure, light propagation within the particles is more complex, resulting in more pronounced scattering. Metal oxide particles, such as Fe2O3, have a typical ionic crystal structure, with iron and oxygen ions ionically bonded to form a tightly packed crystalline lattice.These metal oxide particles often have high density and magnetic properties, contrasting with the low density and non-magnetic properties of the PET substrate. Regarding optical properties, Fe2O3 has a high refractive index of approximately 2.94-3.22 and strong light absorption, particularly in the long-wave region of the visible spectrum. This significantly reduces the transmittance of the PET film surface containing these particles in this wavelength range, resulting in a different color and brightness from the substrate. Organic polymer particles are typically formed by the aggregation of additives (such as antioxidants, lubricants, and plasticizers) added during processing under specific conditions. While the molecular structure of these organic polymer particles is similar to that of PET, their chemical and physical properties differ due to the type of additives and degree of polymerization. For example, some low-molecular-weight organic polymer particles may have a lower glass transition temperature, resulting in a softer state at room temperature, contrasting with the rigidity of the PET substrate. In terms of optical properties, the refractive index and absorptivity of organic polymer particles depend on the functional groups in their molecular structure. For example, polymers containing benzene rings typically have a higher refractive index, while polymers containing electron-withdrawing functional groups such as carbonyl groups may have a stronger absorption capacity for specific wavelengths of light. These material differences, ranging from chemical composition and crystal structure to intermolecular forces, lead to significant differences in the optical behaviors of the particles and the substrate, such as light reflection, refraction, and absorption, which in turn lay the foundation for the formation of contrast during image acquisition.

[0005] At present, there is a need for an intelligent collection method and system for the frosted particle size of the PET film surface, which can capture images of different PET film surfaces under appropriate brightness, thereby improving the accuracy of image recognition of frosted particle size, and thus facilitating high-precision processing control of PET films. Summary of the Invention

[0006] The technical problem to be solved by the present invention is how to select appropriate ambient brightness to capture images of different PET film surfaces, thereby improving the accuracy of image recognition of frosted particle size, and thus facilitating high-precision processing control of PET films. The purpose is to provide an intelligent method and system for collecting frosted particle size on the surface of PET films to solve the above problems.

[0007] The present invention is achieved through the following technical solutions:

[0008] A method for intelligently collecting frosted granularity of a PET film surface comprises: collecting film images of a plurality of PET films under illumination of different brightness;

[0009] Collecting images of each of the films to identify the contrast between particles on the film surface and the substrate;

[0010] Determining whether the contrast of each of the film captured images meets a preset standard contrast threshold under the change of the minimum brightness unit; if so, using the corresponding brightness change interval as the optimal brightness range of the film captured image;

[0011] The PET film image is re-collected according to the optimal brightness range.

[0012] After re-collecting the PET film image according to the optimal brightness range, the method further includes: collecting multiple sets of film image training data; each set of the film image training data includes the film collection image and the PET film image collected by the film collection image under the optimal brightness range;

[0013] A plurality of sets of the film image training data are trained through machine learning to obtain a film image training model; and the film image training model is used to output a plurality of PET film images of the films to be tested.

[0014] After re-collecting the PET film images according to the optimal brightness range, the method further includes: identifying the particle features and substrate features of each output PET film image according to an image recognition technology; and obtaining a particle image according to a pre-trained film image segmentation model;

[0015] Identify the particle area uniformity and particle distribution uniformity of the particle image; and adjust the processing parameters of the PET film according to the particle area uniformity and the particle distribution uniformity.

[0016] The adjusting of the processing parameters of the PET film according to the uniformity of the particle area and the uniformity of the particle distribution includes:

[0017] Determine whether the particle distribution uniformity is lower than the preset standard particle distribution uniformity. If so, reduce the film travel speed during sandblasting of the next PET film particles until the preset standard particle area uniformity is met; determine whether the particle area uniformity is lower than the preset standard particle area uniformity. If so, reduce the sanding roller speed during polishing of the next PET film particles or the film travel speed during polishing until the preset standard particle area uniformity is met.

[0018] The method for intelligently collecting the frosted particle size of a PET film surface also includes: collecting multiple sets of film processing training data; each set of the film processing training data includes output images of each PET film, the film travel speed during PET film particle sandblasting, and the frosted roller speed during PET film particle polishing / the film travel speed during polishing; and obtaining a film processing training model through machine learning of the multiple sets of film processing training data.

[0019] The method for intelligently collecting the frosted particle size of a PET film surface further includes: obtaining, through the film processing training model, the film travel speed of each film to be tested during sandblasting, and the frosted roller speed / film travel speed during polishing; and processing the film to be tested using the output film travel speed during sandblasting and the frosted roller speed / film travel speed during polishing.

[0020] The film image segmentation model is obtained by the following steps:

[0021] A plurality of sets of film image segmentation data are collected; each set of the film image segmentation data includes a particle image and its particle features, a substrate image and its substrate features; and the film image segmentation model is obtained by training the plurality of sets of the film image segmentation data.

[0022] The particle characteristics include any one or more characteristics of particle area, shape, brightness, and color; the substrate characteristics include any one or more characteristics of substrate area, shape, brightness, and color.

[0023] A system applied to any of the above-mentioned methods for intelligently collecting the frosted particle size of a PET film surface comprises:

[0024] Image acquisition module: used to acquire images of multiple PET films under different brightness;

[0025] Image recognition module: used to collect images of each film to identify the contrast between particles on the film surface and the substrate;

[0026] Optimal brightness module: used to determine whether the contrast of each of the film captured images meets a preset standard contrast threshold under the change of the minimum brightness unit; if so, the corresponding brightness change interval is used as the optimal brightness range of the film captured image;

[0027] Image updating module: used for re-collecting the PET film image according to the optimal brightness range.

[0028] An electronic device comprises a memory, a processor and a computer program running on the processor, wherein when the processor executes the computer program, the steps of any one of the methods for intelligently collecting the frosted particle size of a PET film surface are implemented.

[0029] Compared with the prior art, the present invention has the following advantages and beneficial effects:

[0030] The present invention captures images of multiple PET films under illumination at varying brightness levels, identifies the contrast between particles on the film surface and the substrate, and determines whether the contrast of each film image meets a standard contrast threshold under varying minimum brightness units. If so, the corresponding brightness variation interval that highlights the particle features is used as the optimal brightness range for the film image, which is then applied to PET film image acquisition. The present invention can capture images of different PET film surfaces at appropriate brightness levels, thereby improving the accuracy of image recognition of frosted grain size and facilitating high-precision processing of PET films. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] In order to more clearly illustrate the technical solutions of the exemplary embodiments of the present invention, the following briefly introduces the drawings required for use in the examples. It should be understood that the following drawings only illustrate certain embodiments of the present invention and should not be considered as limiting the scope. A person of ordinary skill in the art can also derive other relevant drawings based on these drawings without inventive effort. In the drawings:

[0032] Figure 1 This is a schematic diagram of the intelligent collection method of the frosted particle size on the surface of the PET film according to an embodiment of the present application. DETAILED DESCRIPTION

[0033] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with examples and drawings. The exemplary embodiments of the present invention and their descriptions are only used to explain the present invention and are not intended to limit the present invention.

[0034] Example 1

[0035] like Figure 1 As shown, the embodiment of the present application provides a method for intelligently collecting the frosted particle size of a PET film surface, comprising: collecting film images of a plurality of PET films under illumination of different brightness;

[0036] Collecting images of each of the films to identify the contrast between particles on the film surface and the substrate;

[0037] Determining whether the contrast of each of the film captured images meets a preset standard contrast threshold under the change of the minimum brightness unit; if so, using the corresponding brightness change interval as the optimal brightness range of the film captured image;

[0038] The PET film image is re-collected according to the optimal brightness range.

[0039] The preset standard contrast threshold can be manually set based on the target contrast. Optionally, the preset standard contrast threshold can be determined by performing multiple experiments on film images that meet standard quality requirements at brightness levels that meet standard quality requirements. The brightness and standard quality requirements for film images can be set based on image clarity, a method known to those skilled in the art and not specifically defined herein. The minimum brightness unit is 1 candela per square meter (cd / m²). Experiments at different brightness levels determine a brightness variation range that meets the contrast requirements for particle recognition in PET film images, and PET film images are captured using the corresponding brightness variation range.

[0040] After re-collecting the PET film image according to the optimal brightness range, the method further includes: collecting multiple sets of film image training data; each set of the film image training data includes the film collection image and the PET film image collected by the film collection image under the optimal brightness range;

[0041] A plurality of sets of film image training data are trained through machine learning to obtain a film image training model; and the film image training model is used to input a plurality of images of films to be tested to obtain re-collected PET film images.

[0042] After re-collecting the PET film images according to the optimal brightness range, the method further includes: identifying the particle features and substrate features of each output PET film image according to an image recognition technology; and obtaining a particle image according to a pre-trained film image segmentation model;

[0043] Identify the particle area uniformity and particle distribution uniformity of the particle image; and adjust the processing parameters of the PET film according to the particle area uniformity and the particle distribution uniformity.

[0044] Among them, the image recognition technology identifies the particle features and substrate features of the PET film image, and uses the existing image segmentation model to analyze the particle features and substrate features, and directly distinguishes the particle image by image segmentation. This belongs to the existing technology and does not need to be specifically limited here.

[0045] The adjusting of the processing parameters of the PET film according to the uniformity of the particle area and the uniformity of the particle distribution includes:

[0046] Determine whether the particle distribution uniformity is lower than the preset standard particle distribution uniformity. If so, reduce the film travel speed during sandblasting of the next PET film particles until the preset standard particle area uniformity is met; determine whether the particle area uniformity is lower than the preset standard particle area uniformity. If so, reduce the sanding roller speed during polishing of the next PET film particles or the film travel speed during polishing until the preset standard particle area uniformity is met.

[0047] The particle area uniformity of a particle image can be determined by identifying different particle area features within the particle image, such as diameter, shape, and color. The particle distribution uniformity of a particle image can be determined by identifying whether all particles within the particle array arrangement in the particle image are missing or redundant, and whether the distances between particles are consistent. Based on these characteristics of particle area uniformity and particle distribution uniformity, it can be determined whether the preset requirements for the corresponding characteristics are met. Therefore, the preset standard particle area uniformity and the corresponding feature size of the preset standard particle area uniformity are both set based on actual needs. The specific numerical values ​​are known to those skilled in the art based on routine experience and are not specifically limited here.

[0048] Since PET film frosting involves evenly spraying frosting particles onto the film, solidifying them, and then polishing the frosting particles to achieve uniform size, the film travels at a uniform speed during the sandblasting process. If the frosting particles are unevenly distributed after sandblasting, it is determined that the sandblasting speed was too fast. The sandblasting speed of the film is reduced to improve the uniformity of the particle distribution on the next film to be sandblasted, ensuring that the uniformity standard is met. Then, depending on whether the size of the frosted particles after polishing is uniform, the polishing speed of the roller or the speed of the film is reduced to improve the uniformity of the particle distribution on the next film to be sandblasted, ensuring that the uniformity standard is met. The above-mentioned reduction in travel speed is used to improve the uniformity of particle distribution of the next film, thereby obtaining a film that meets the distribution uniformity standard, and the reduction in the grinding speed of the roller during grinding or the travel speed of the film during grinding is used to improve the uniformity of particle area of ​​the next film, thereby obtaining a film that meets the size uniformity standard. The specific size settings are obtained through experiments, and the configuration for evaluating the uniformity can be based on the routine experience of technicians in this field, and there is no need to limit it here.

[0049] The method for intelligently collecting the frosted particle size of a PET film surface also includes: collecting multiple sets of film processing training data; each set of the film processing training data includes output images of each PET film, the film travel speed during PET film particle sandblasting, and the frosted roller speed during PET film particle polishing / the film travel speed during polishing; and obtaining a film processing training model through machine learning of the multiple sets of film processing training data.

[0050] The method for intelligently collecting the frosted particle size of a PET film surface further includes: obtaining, through the film processing training model, the film travel speed of each film to be tested during sandblasting, and the frosted roller speed / film travel speed during polishing; and processing the film to be tested using the output film travel speed during sandblasting and the frosted roller speed / film travel speed during polishing.

[0051] Through the particle quality of the PET film image, the sandblasting film travel speed that needs to be optimized during processing, the sanding roller speed and film travel speed during grinding are obtained, thereby obtaining a film processing training model.

[0052] The film image segmentation model is obtained by the following steps:

[0053] A plurality of sets of film image segmentation data are collected; each set of the film image segmentation data includes a particle image and its particle features, a substrate image and its substrate features; and the film image segmentation model is obtained by training the plurality of sets of the film image segmentation data.

[0054] The particle characteristics include any one or more of particle area, shape, brightness, and color; the substrate characteristics include any one or more of substrate area, shape, brightness, and color. Characteristics such as particle area distribution and average roundness may also be included.

[0055] Among them, the relevant data on the area size, shape, brightness and color of the particles and the substrate can be obtained through image recognition technology, and the particles and the substrate can be obtained through feature comparison, so as to distinguish them, which belongs to the existing technology and is not specifically limited here. For example, the relevant data on particle shape can be circularity. When evaluating the degree of distribution uniformity, the average circularity obtained after statistical analysis of the extracted circularity can be used to directly determine whether the average circularity meets the requirements. When evaluating the degree of size uniformity, the average area obtained after statistical analysis of the extracted particle area and the average circularity obtained after statistical analysis of the circularity can be used to determine whether the corresponding requirements are met using the size of the average area and the average circularity. The statistical analysis process can use a Gaussian mixture model (GMM), and the algorithm for the statistical analysis average value can use the existing technology. The specific target data set is directly obtained according to the film processing parameters required for actual application and is not limited to the content of the present invention.

[0056] When the embodiment of the present application is used, a high-resolution camera can be used to capture images of multiple PET films under different brightness levels. The light source used for illumination at different brightness levels provides uniform and stable lighting conditions, reduces shadows and reflections during image acquisition, and improves image processing accuracy. The system can use a custom-designed LED lighting array that is evenly distributed across the entire width of the film based on the characteristics of the PET film and the speed of the production line. The brightness and color temperature of the light source are adjustable to accommodate different frosted particle sizes and film colors, ensuring high-quality images under various conditions. To further achieve uniform lighting, the following methods can be selected: 1. Multi-angle illumination: By setting multiple LED modules in the imaging area, the PET film is illuminated from different angles to reduce shadows caused by particle shape and surface irregularities; 2. Optical diffuser: An optical diffuser is installed in front of the LED light source to evenly diffuse the light and avoid hot spots and uneven brightness. 3. Reflection suppression technology: A special anti-reflective coating or structure is set between the light source and the imaging device to reduce image distortion caused by reflections on the film surface. When the PET film passes through the production line at a speed of 100 meters per minute, the light source system on the production line automatically adjusts to the optimal brightness range and color temperature to ensure real-time and accurate image acquisition.

[0057] Optionally, the particle and substrate images used in film image segmentation model training can be preprocessed using film image acquisition, including grayscale conversion, filtering and denoising, and edge enhancement, to eliminate irrelevant information and noise interference. Image segmentation is then performed on the frosted particles in the film image acquisition to produce a segmented particle image. Image segmentation algorithms such as region growing and threshold segmentation can be used.

[0058] Optionally, edge enhancement can use the Canny operator to perform edge detection to obtain edge information of frosted particles. The Canny edge detection algorithm can be expressed as:

[0059] ;

[0060] ;

[0061] ;

[0062] .

[0063] is the gradient operator, the film captures the image about Partial derivatives of directions; is the gradient operator, the film captures the image about Partial derivatives of directions; Represents the edge information of frosted particles; express The angle of the vector in the two-dimensional coordinate system.

[0064] When the region growing algorithm is used to segment the frosted particles, the point set on the segmented image is obtained. Contains thin film acquisition images All points (x, y) on the graph that satisfy the similarity condition of frosted particles can be expressed as:

[0065] ;

[0066] in, is the set after region growing; Indicates the film acquisition image Point on ; Indicates a point In two-dimensional space The value of the direction.

[0067] According to the area of ​​the segmented particle image, the particle area feature is extracted and expressed as: ;

[0068] in, is the area of ​​the segmented particle image, N is the length of the segmented particle image in the x-axis direction; M is the length of the segmented particle image in the y-axis direction; Indicates the film acquisition image Frosted grain points on .

[0069] The extracted circularity feature can be expressed as:

[0070] ;

[0071] Where C is the circularity and P is the particle circumference.

[0072] Optionally, before extracting features such as particle area and circularity from the segmented particle image, the shape of the frosted particles obtained from the image can be optimized through morphological operations, such as using dilation and erosion operations, to optimize the obtained particle area, circularity and other features.

[0073] The connected component labeling algorithm is an image processing algorithm used to identify and label connected regions within an image. It primarily locates and labels connected regions within an image for subsequent analysis and processing. Connected component labeling algorithms are typically implemented by traversing an image, determining the connectivity between pixels to identify pixels belonging to the same connected region and assigning a unique label to each connected region.

[0074] Optionally, a U-Net network is used to segment the frosted particles in the film image to obtain a segmented particle image. The identified particle image is then used to calculate the geometric features of the image using a U-Net network structure based on deep learning. The core formula or structure of the U-Net network can be summarized as follows:

[0075] Encoder (Contraction Path): Extracts image features through a series of convolutional layers and pooling layers, and gradually reduces the spatial resolution of the image. This process can be expressed as:

[0076] The convolution operation is expressed as: ;

[0077] The pooling operation is expressed as: ;

[0078] in, is the input particle image, It is The convolutional feature map of the layer, It is Pooling result of the layer.

[0079] Decoder (expansion path): The decoder part restores the spatial resolution of the image through a series of upsampling layers and convolutional layers, and merges the corresponding feature maps from the encoder. This process can be expressed as:

[0080] Upsampling operation: ;

[0081] Convolution operation and feature merging: ;

[0082] in, It is The upsampling result of the layer, is the feature map skipped from the encoder, is the merged feature map.

[0083] For example, the following is the complex operation structure of the U-Net network:

[0084] Skip connection: directly connect the feature map in the encoder to the corresponding upsampling layer in the decoder , j is the decoder layer corresponding to i, and the skip connection process can be expressed as:

[0085] ;

[0086] Final segmentation output: The combined feature map is processed through a series of convolutional layers to obtain the final convolution result .

[0087] ;

[0088] in, is the output image, which contains the particle image of the segmentation output.

[0089] Optionally, a Gaussian mixture model (GMM) is used to perform statistical analysis on characteristic data such as size, distribution, and density of the frosted particles detected in the particle image to obtain frosted particle features. The specific process includes:

[0090] For a data point x, its probability density function p(x) is expressed by the following formula:

[0091] ;

[0092] in, is the mixing coefficient of the i-th Gaussian distribution; is a single Gaussian component of the probability density function, which represents the probability density function of the Gaussian distribution, which describes the data point The probability distribution under the i-th component; where the mixing coefficient represents the contribution ratio of the i-th distribution to the overall distribution among all Gaussian distributions; Represents the number of Gaussian distributions.

[0093] in:

[0094] ;

[0095] is the mean vector of the i-th Gaussian distribution; is the covariance matrix of the i-th Gaussian distribution; d is the dimension of the data point; express The vector value of .

[0096] Use the complex operations provided by Gaussian mixture models:

[0097] Expectation step (E-step): In the E-step, it is necessary to calculate the posterior probability of each data point belonging to each Gaussian distribution ;

[0098] ;

[0099] represents the probability that the j-th data point belongs to the i-th Gaussian distribution.

[0100] Maximization step (M-step): In the M-step, the parameters of each Gaussian distribution are updated:

[0101] The updated mixing coefficient can be expressed as: ;

[0102] Where N is the number of iterative updates.

[0103] The updated mean can be expressed as: ;

[0104] The updated covariance can be expressed as: ;

[0105] Iterative process: Repeat the E-step and M-step until the likelihood function L converges, where the likelihood function is usually expressed as:

[0106] ;

[0107] Indicates the number of iterations of the convergence process;

[0108] Through the above steps, GMM can adapt to multimodal characteristics and provide more accurate statistical information for complex operations.

[0109] To further investigate the contrast variation between the particles and the substrate on the PET film surface under varying brightness conditions, a large amount of collected image data was carefully analyzed. As brightness increased, the grayscale values ​​of both the particle and substrate regions showed an upward trend. This is consistent with theoretical expectations that increased brightness increases the intensity of light reflected from the surface, leading to an increase in the pixel grayscale values ​​captured by the camera. However, the rates of increase were not completely consistent. At lower brightness levels, the grayscale values ​​in the particle region grew relatively slowly, while those in the substrate region grew slightly faster. As brightness further increased, the growth rate of the grayscale values ​​in the particle region gradually accelerated. In the higher brightness range, the grayscale values ​​in the particle region rose at a significantly higher slope than those in the substrate region.

[0110] This difference in the rate of change of grayscale values ​​is directly reflected in the change in contrast. Initially, the contrast is relatively low at low brightness levels. As the brightness gradually increases, the contrast shows a trend of first slowly rising, then rapidly increasing within a certain brightness range. Once the brightness exceeds a certain threshold, the contrast growth levels off, and in some samples, it even decreases slightly. This trend indicates that within an appropriate brightness range, increasing brightness can effectively enhance the contrast between particles and the substrate, making the particle features more prominent in the image. However, when the brightness is too high, factors such as overexposure and light scattering may lead to a decline in image quality, reducing the difference between particles and the substrate and lowering the contrast.

[0111] Further experiments on PET film samples with different materials and particle distribution characteristics revealed that while the overall contrast ratio showed similar trends with brightness, there were differences in the specific details of this change. For film samples with larger, more sparsely distributed particles, the contrast increase was relatively gradual, and the brightness required to achieve maximum contrast was relatively high. In contrast, for films with finer, denser particles, contrast changes were more sensitive at lower brightness levels, and a significant contrast increase could be achieved within a relatively small brightness adjustment range. These differences provide important basis for subsequently determining the optimal brightness range based on the characteristics of different films.

[0112] The contrast between particles on the PET film surface and the substrate changes with brightness, influenced by a combination of factors, with particle size being a significant factor. Larger particles occupy a larger pixel area in the image, resulting in more significant light scattering and reflection. At low brightness, due to limited light energy, the scattered light intensity of large particles is relatively weak, resulting in a less pronounced brightness difference with the substrate and lower contrast. As brightness increases, larger particles reflect light more effectively, causing the brightness of the particle area to rise rapidly and the contrast with the substrate to increase. However, at high brightness, light reflected from the surface of large particles may create a halo effect in the surrounding area, blurring the boundary between the particle and the substrate and causing a decrease in contrast. Particle shape also has a significant impact on contrast changes. Spherical particles reflect light more evenly in all directions, resulting in relatively smooth contrast changes. Irregularly shaped particles, such as flakes or needles, have more complex reflection and refraction paths on the particle surface due to the diverse orientations of their surface normals. At different brightness levels, different parts of these irregular particles exhibit different brightness characteristics, resulting in an uneven overall brightness distribution and complex fluctuations in contrast with the substrate. At certain brightness levels, the prominent areas of particles may reflect strong light, creating bright spots and enhancing contrast. At other brightness levels, shadows in recessed areas may blend in with the brightness of the substrate, reducing contrast. Particle density also alters how contrast changes with brightness. When particles are sparsely distributed, their interactions are minimal, and the contrast of each particle depends primarily on its own characteristics, the substrate, and the brightness conditions. In this case, as brightness increases, each particle becomes more prominent, gradually improving contrast. However, due to the small number of particles, the overall contrast increase is relatively slow. For densely distributed particle clusters, at lower brightness levels, the shadows between particles overlap, making the overall particle area appear darker and the contrast with the substrate lower. As brightness increases, the shadows gradually brighten, the overall brightness of the particle cluster rapidly increases, and the contrast also increases dramatically. However, as brightness continues to rise, the particle cluster may become overexposed, forming a bright area, further reducing its distinction from the substrate and decreasing contrast. Substrate roughness is also a key factor influencing contrast variations. A rough substrate surface causes multiple scattering of incident light, resulting in diffuse reflections. This results in a more uniform brightness distribution in the substrate area, but a relatively low overall brightness. At low brightness, the contrast between the particles and the rough substrate is relatively small. As the brightness increases, the reflected light intensity of the particles increases more significantly, and the contrast with the substrate gradually increases. However, if the brightness is too high, the diffuse reflected light intensity of the rough substrate will also increase significantly, making the brightness of the substrate close to or even exceeding that of the particles, resulting in a sharp drop in contrast.

[0113] In addition, the stability of the light source has a crucial impact on the accuracy of the experimental results and the stability of the contrast. If the light source experiences unstable phenomena such as light intensity fluctuations and spectral drift during the brightness adjustment process, the lighting conditions for image acquisition will be inconsistent, resulting in random errors in the brightness changes of the particles and the substrate, which in turn affects the measurement accuracy of the contrast. During long-term experiments, the heat generated by the light source may also cause changes in its performance. For example, as the temperature of an LED light source increases, the luminous efficiency and spectral characteristics may change, making the actual brightness output under the same driving current different from the initial state, interfering with the study of the law of contrast change with brightness. Therefore, ensuring the high stability of the light source and equipping it with a high-precision light intensity monitoring and feedback control system are necessary prerequisites for obtaining reliable experimental data and in-depth exploration of the contrast change mechanism.

[0114] In the field of electronic component packaging, experiments were conducted on PET films used for chip protection. Hundreds of film samples from different batches and production processes were collected. Surface images of the films were captured at luminance levels increasing from 50 cd / m² to 500 cd / m² in 50 cd / m² increments, and the increase in contrast between particles and the substrate was calculated. The experimental results showed that when the contrast increase was less than 30%, tiny particles sized 10-20μm were difficult to discern in the image and easily confused with background noise, resulting in a false positive rate exceeding 30%. However, when the contrast increase reached 40% or above, these tiny particles were clearly separated from the background, with a false positive rate of less than 5%. Considering the extremely high reliability requirements for electronic components in this field, 40% was set as the lower threshold for the contrast increase of this type of PET film in electronic component packaging applications, ensuring that potentially risky film products can be effectively identified and rejected during subsequent production inspections.

[0115] In the context of food packaging, similar experiments were conducted on PET film used in products such as beverage bottle labels and food wrap. Due to the primary focus on hygiene and safety in food packaging, the focus was on detecting the impact of larger particles on packaging appearance and barrier properties. Experimental data showed that within the brightness range, for particles larger than 50μm, when the contrast increase was less than 20%, the particles appeared blurred in the image, making it difficult to accurately determine their shape, size, and distribution. This could result in defective film being mistakenly deemed unqualified and released into the market. However, when the contrast increase was increased to 25% or above, the particle characteristics were significantly enhanced, allowing inspectors or automated inspection systems to quickly and accurately identify particle defects, ensuring the quality of food packaging. Based on this, 25% was established as the contrast increase threshold for PET film used in food packaging, providing food packaging manufacturers with a clear quantitative indicator for quality control.

[0116] After acquiring images of PET film at different brightness settings, we first apply the contrast calculation method described above to calculate the contrast between the particles and the substrate under each brightness condition. For a specific PET film sample, at the initial brightness (L_0), we use grayscale value comparison or spectral reflectance comparison to determine the average pixel value (I_p^0) for the particle region and (I_b^0) for the substrate region, and calculate the initial contrast (C_0). Then, we gradually adjust the brightness, for example by increasing the minimum brightness unit (\Delta L), to obtain the particle and substrate pixel values ​​(I_p^1) and (I_b^1) at the new brightness (L_1 = L_0 + \Delta L). From this, we calculate the contrast (C_1). This process continues, generating a series of contrast data ({C_n}) under varying brightness conditions, and calculating the contrast increase (\Delta C_n = C_n - C_{n - 1}). Compare the calculated contrast increase (\Delta C_n) with the preset standard contrast change threshold (T). If (\Delta C_n > T), the image contrast improvement within this brightness range has met the expected standard, effectively highlighting the particle features. The corresponding brightness range is recorded as one of the potential optimal brightness ranges. If (\Delta C_n < T), the contrast enhancement effect under this brightness adjustment is not as expected, and the distinction between particles and the background is still unsatisfactory. Continue adjusting and judging the next brightness unit until the entire set brightness range has been traversed.

[0117] In summary, the embodiments of the present application provide a method and system for intelligently collecting frosted particle size on the surface of a PET film. The method captures images of multiple PET films illuminated at varying brightness levels, identifies the contrast between particles on the film surface and the substrate, and thereby determines whether the contrast of each film image meets a standard contrast threshold under variations in the minimum brightness unit. If so, the corresponding brightness variation interval that highlights the particle features is used as the optimal brightness range for the film image, which is then applied to the PET film image acquisition. The present invention can capture images of different PET film surfaces at appropriate brightness levels, thereby improving the accuracy of image recognition of frosted particle size and facilitating high-precision processing of PET films.

[0118] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for intelligently collecting the frosted particle size of a PET film surface, characterized in that: include: Collect images of multiple PET films under different brightness; Collecting images of each of the films to identify the contrast between particles on the film surface and the substrate; Determining whether the contrast of each of the film captured images meets a preset standard contrast threshold under the change of the minimum brightness unit; if so, using the corresponding brightness change interval as the optimal brightness range of the film captured image; reacquiring the PET film image according to the optimal brightness range; Collecting multiple sets of film image training data; each set of the film image training data includes the film acquisition image and the PET film image acquired by the film acquisition image under the optimal brightness range; A plurality of sets of film image training data are trained by machine learning to obtain a film image training model; and a plurality of PET film images of films to be tested are outputted using the film image training model; Identify the particle features and substrate features of each output PET film image using image recognition technology; and obtain a particle image using a pre-trained film image segmentation model; Identifying the particle area uniformity and particle distribution uniformity of the particle image; adjusting the processing parameters of the PET film according to the particle area uniformity and the particle distribution uniformity; Collect multiple sets of film processing training data; each set of the film processing training data includes the output PET film images, the film travel speed when the PET film particles are sandblasted, and the sanding roller speed when the PET film particles are polished / the film travel speed during polishing; and obtain a film processing training model through machine learning of the multiple sets of the film processing training data.

2. The intelligent collection method for frosted particle size of a PET film surface according to claim 1, characterized in that: The adjusting of the processing parameters of the PET film according to the uniformity of the particle area and the uniformity of the particle distribution includes: Determine whether the particle distribution uniformity is lower than the preset standard particle distribution uniformity. If so, reduce the film travel speed during sandblasting of the next PET film particles until the preset standard particle area uniformity is met; determine whether the particle area uniformity is lower than the preset standard particle area uniformity. If so, reduce the sanding roller speed during polishing of the next PET film particles or the film travel speed during polishing until the preset standard particle area uniformity is met.

3. The intelligent collection method of frosted particle size of a PET film surface according to claim 2, characterized in that: Also includes: The film processing training model is used to obtain the film travel speed of each film to be tested during sandblasting and the sanding roller speed / film travel speed during polishing; The film to be tested is processed using the output film travel speed during sandblasting and the sanding roller speed / film travel speed during polishing.

4. The intelligent collection method of frosted particle size on the surface of a PET film according to claim 2, characterized in that: The film image segmentation model is obtained by the following steps: Collecting multiple sets of film image segmentation data; each set of film image segmentation data includes a particle image and its particle features, a base image and its base features; The film image segmentation model is obtained by training multiple sets of the film image segmentation data.

5. The intelligent collection method of frosted particle size of a PET film surface according to claim 2, characterized in that: The particle characteristics include any one or more characteristics of particle area, shape, brightness, and color; The substrate characteristics include any one or more characteristics of substrate area, shape, brightness, and color.

6. A system for intelligently collecting the frosted particle size of a PET film surface according to any one of claims 1 to 5, characterized in that: include: Image acquisition module: used to acquire images of multiple PET films under different brightness; Image recognition module: used to collect images of each film to identify the contrast between particles on the film surface and the substrate; Optimal brightness module: used to determine whether the contrast of each of the film captured images meets a preset standard contrast threshold under the change of the minimum brightness unit; if so, the corresponding brightness change interval is used as the optimal brightness range of the film captured image; Image updating module: used for re-collecting the PET film image according to the optimal brightness range.

7. An electronic device comprising a memory, a processor, and a computer program running on the processor, characterized in that: When the processor executes the computer program, the steps of the intelligent collection method of frosted particle size on the surface of a PET film as described in any one of claims 1 to 5 are implemented.

Images