Image analysis-based low bubble adhesive label quality monitoring method and system thereof

Abstract

The application provides a low-bubble adhesive label quality monitoring method and system based on image analysis, and belongs to the technical field of adhesive labels. The low-bubble adhesive label quality monitoring method based on image analysis comprises the following steps: acquiring image acquisition data of a low-bubble adhesive label, wherein the image acquisition data is digital image data obtained by imaging the low-bubble adhesive label containing a pattern area under preset imaging conditions; performing image processing on the image acquisition data to generate processed image data for representing label region brightness distribution, gray scale distribution and texture distribution; analyzing image abnormalities formed by bubble points in an adhesive layer at corresponding apparent positions of a face material layer according to the processed image data to generate bubble point candidate region data; and performing quality determination on the low-bubble adhesive label according to the bubble point candidate region data to obtain a quality monitoring result.

Description

Technical Field

[0001] This invention belongs to the field of self-adhesive technology, and in particular to a method and system for quality monitoring of low-foaming self-adhesive labels based on image analysis. Background Technology

[0002] In the manufacturing process of label products, especially low-foaming self-adhesive labels, their visual appearance quality directly affects the packaging effect and market acceptance of downstream products. Currently, the methods commonly used for label quality inspection mostly rely on manual visual inspection or traditional machine vision methods. Although manual inspection is highly flexible, it suffers from problems such as low inspection efficiency, strong subjectivity, and the possibility of missed detection due to personnel fatigue. Traditional machine vision technology is mainly based on simple edge detection and color analysis, which makes it difficult to accurately identify tiny bubbles and subtle defects between the face material layer and the adhesive layer. Especially when the label has complex patterns and reflective backgrounds, the inspection effect is unstable.

[0003] For defects such as bubble points in low-foaming self-adhesive labels, these defects are usually formed during the coating, lamination and labeling process due to inconsistent surface tension of materials and failure of local gas to be discharged in time. These bubble points may appear as local brightness, grayscale and texture abnormalities in the visual image of the finished label, rather than obvious geometric deformation. Therefore, it is difficult to accurately identify these low-visibility defects by relying solely on traditional image feature extraction methods. Summary of the Invention

[0004] The purpose of this invention is to address the aforementioned problems in existing technologies by proposing a method and system for quality monitoring of low-foaming self-adhesive labels based on image analysis.

[0005] The objective of this invention can be achieved through the following technical solutions: A method for quality monitoring of low-foaming self-adhesive labels based on image analysis, the method comprising: Acquire image acquisition data of low-foam self-adhesive labels, wherein the image acquisition data is digital image data obtained by imaging a low-foam self-adhesive label containing a pattern area under preset imaging conditions; The acquired image data is processed to generate processed image data that characterizes the brightness distribution, grayscale distribution, and texture distribution of the label region. Based on the processed image data, the image anomalies formed by bubble points in the adhesive layer at the corresponding apparent positions in the surface material layer are analyzed to generate bubble point candidate region data. Based on the bubble point candidate area data, the quality of low-foaming self-adhesive labels is judged, and the quality monitoring results are obtained.

[0006] In the above method, acquiring image data of low-foam self-adhesive labels includes: The spatial position information of the low-foam self-adhesive label at the inspection station is obtained, and the image acquisition device is controlled to image the low-foam self-adhesive label at a preset shooting distance, shooting angle and imaging field of view based on the spatial position information, so as to generate original image data covering the entire inspection area of ​​the label. During the image acquisition process, the lighting device is controlled according to the preset imaging parameters so that the lighting source acts on the surface of the low-foam self-adhesive label with preset light intensity, light incident angle and light distribution, so that the bubble points in the adhesive layer form brightness changes and texture changes at the corresponding positions of the face material layer. The original image data is then acquired, cached, and retrieved as input data for subsequent image processing steps.

[0007] The steps in the above method for processing image acquisition data to generate processed image data include: Multi-channel image information is acquired from the image acquisition data, and channel separation, channel reconstruction, and channel mapping processing are performed on the multi-channel image information to generate single-channel image data for characterizing the brightness information of the detection area of ​​the low-foam self-adhesive label. The single-channel image data is subjected to noise suppression processing. By spatially smoothing and frequency domain suppressing the pixel gray values ​​in the image, random gray-level fluctuations caused by imaging noise, ambient light changes, and non-bubble structure are reduced. After noise suppression, brightness normalization and grayscale remapping are performed on the image data to generate processed image data.

[0008] In the above method, the step of generating bubble point candidate region data based on the processed image data includes: The processed image data is scanned region by region to obtain grayscale distribution information of the detection area and pixel area; Based on preset local grayscale change judgment conditions, the grayscale distribution information is compared and analyzed to screen out the initial abnormal regions that have abnormal grayscale changes relative to adjacent regions. For the initial abnormal region, calculate the area parameter, boundary continuity parameter, and gray-scale change parameter within the region. Based on the parameters, the initial abnormal regions are filtered, merged, or segmented to generate bubble point candidate region data.

[0009] In the above method, the step of quality determination based on the bubble point candidate region data includes: Obtain the spatial location information, area information, morphological information, and grayscale distribution information of each bubble point candidate region in the bubble point candidate region data; Based on the spatial location information, area information, morphological information and grayscale distribution information, bubble point determination input data is constructed and input into the preset bubble point determination model. According to the set of bubble point determination rules, each bubble point candidate region is determined to meet the bubble point determination conditions one by one, so as to distinguish the abnormal regions formed by bubble points in the adhesive layer from the non-bubble point regions formed by pattern structure, surface texture and inherent material distribution. After determining the bubble point areas, the number, area, and spatial distribution of the areas determined to be bubble points are statistically analyzed to generate bubble point statistics. Based on the correspondence between the bubble point statistics and the preset quality judgment conditions, the quality monitoring results of the low-foaming self-adhesive label are generated.

[0010] In the above method, the method further includes: obtaining structural parameter information of low-foaming self-adhesive labels, wherein the structural parameter information includes at least the thickness of the face material layer, the thickness of the adhesive layer, and the type of the release liner layer; Based on the structural parameter information, the grayscale determination conditions used in the image processing steps and the bubble point candidate region generation steps are adjusted; The bubble point detection process is then performed based on the adjusted judgment criteria.

[0011] In the above method, the method further includes: Acquire multiple frames of image data of the same low-foam self-adhesive label at different time points; Image registration is performed on the acquired multi-frame image data to generate time-series corresponding image data; The candidate regions for bubble points are confirmed based on the image data corresponding to the time sequence.

[0012] In the above method, the method further includes: The quality monitoring results are correlated with the corresponding low-foam self-adhesive label information; Generate quality record data that includes label identification information and quality monitoring results; The quality record data is then stored in the data storage unit.

[0013] The low-foaming self-adhesive label quality monitoring system based on image analysis includes: The acquisition module acquires image acquisition data of low-foam self-adhesive labels, wherein the image acquisition data is digital image data obtained by imaging a low-foam self-adhesive label containing a pattern area under preset imaging conditions. The processing module performs image processing on the acquired image data to generate processed image data that characterizes the brightness distribution, grayscale distribution, and texture distribution of the label area. The generation module analyzes the image anomalies formed by bubble points in the adhesive layer at the corresponding apparent positions in the surface material layer based on the processed image data, and generates bubble point candidate region data. The quality module performs quality judgment on the low-foaming self-adhesive labels based on the bubble point candidate area data, and obtains the quality monitoring results.

[0014] Compared with the prior art, this application has the following advantages: This method does not rely solely on the geometric shape and obvious edge features of bubble points. Instead, it comprehensively analyzes the brightness distribution, grayscale distribution, and texture distribution in the label image to identify subtle image anomalies formed by bubble points in the adhesive layer at corresponding positions in the face material layer. For common defects in low-bubble self-adhesive labels, such as tiny bubbles, dark bubbles, and hidden bubbles, even if they are not easily distinguishable to the naked eye, they can still be effectively captured through changes in multidimensional image features, thus improving the detection capability of low-visibility defects. Attached Figure Description

[0015] Figure 1 This is a flowchart of the low-foaming self-adhesive label quality monitoring method based on image analysis in this application; Figure 2 This is a block diagram of the low-foaming self-adhesive label quality monitoring system based on image analysis in this application. Detailed Implementation

[0016] The technical solutions in the embodiments of the present invention have been clearly and completely described. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0017] like Figure 1 As shown, an image analysis-based method for quality monitoring of low-foaming self-adhesive labels includes the following steps: S100. Acquire image acquisition data of low-foam self-adhesive labels. The image acquisition data is digital image data obtained by imaging low-foam self-adhesive labels containing pattern areas under preset imaging conditions.

[0018] S200: Perform image processing on the acquired image data to generate processed image data that characterizes the brightness distribution, grayscale distribution, and texture distribution of the label area.

[0019] S300. Based on the processed image data, analyze the image anomalies formed by bubble points in the adhesive layer at the corresponding apparent positions in the surface material layer, and generate bubble point candidate region data.

[0020] S400. Based on the bubble point candidate area data, the quality of low-foaming self-adhesive labels is judged to obtain the quality monitoring results.

[0021] This method does not rely solely on the geometric shape and obvious edge features of bubble points. Instead, it comprehensively analyzes the brightness distribution, grayscale distribution, and texture distribution in the label image to identify subtle image anomalies formed by bubble points in the adhesive layer at corresponding positions in the face material layer. For common defects in low-bubble self-adhesive labels, such as tiny bubbles, dark bubbles, and hidden bubbles, even if they are not easily distinguishable to the naked eye, they can still be effectively captured through changes in multidimensional image features, thus improving the detection capability of low-visibility defects.

[0022] Because the method acquires the label image containing the pattern area under preset imaging conditions and extracts various feature information such as brightness, grayscale and texture in the subsequent processing, it can effectively distinguish the visual changes caused by the pattern itself from the abnormal changes caused by the bubble dots. Compared with traditional machine vision methods that judge based on color or a single threshold, this method still has high detection stability and robustness even when the label has complex printed patterns and high gloss surface material.

[0023] This method automates the processing of image acquisition data and generates bubble point candidate region data. Then, it performs quality judgment based on the candidate regions, avoiding the problems of high subjectivity and low efficiency in manual visual inspection. It can be stably integrated into the high-speed coating, laminating and slitting production line of self-adhesive labels to achieve quality monitoring.

[0024] In this embodiment, the low-foaming self-adhesive label is a continuous roll of material that has completed the coating and printing processes but has not yet been cut into individual labels. It includes a face layer, an adhesive layer, and a release liner layer. Specifically, on the label production line, image acquisition devices are set at preset positions along the label's running path. These devices include industrial cameras and supporting light sources. The acquired image data is preprocessed, including grayscale conversion, noise suppression, and brightness normalization. Based on this, brightness distribution information, grayscale distribution information, and texture distribution information of each region in the label image are extracted to generate processed image data characterizing the label's appearance. Based on the processed image data, areas in the label's surface material layer exhibiting local brightness anomalies, abrupt grayscale changes, and texture continuity disruptions are analyzed. When the image features of the abnormal area match the feature pattern formed by the adhesive layer's bubble points at the corresponding appearance positions in the surface material layer, the corresponding area is marked as a bubble point candidate area, generating bubble point candidate area data. Based on this data, the number, area, and distribution characteristics of the bubble point candidate areas are comprehensively judged. When the bubble point candidate areas meet preset defect judgment conditions, the low-foaming self-adhesive label is determined to be a non-conforming product; otherwise, it is determined to be a conforming product, thus obtaining the corresponding quality monitoring results.

[0025] Furthermore, image acquisition data of low-foam self-adhesive labels is obtained, including: During image acquisition, the lighting device is controlled according to preset imaging parameters, so that the lighting source acts on the surface of the low-foam self-adhesive label with preset light intensity, light incident angle and light distribution, so that the bubble points in the adhesive layer form brightness and texture changes at the corresponding positions of the face material layer.

[0026] During image acquisition, this technical solution parametrically controls the lighting device, so that the lighting source acts on the label surface with preset light intensity, light incident angle and light distribution, thereby artificially inducing brightness and texture changes caused by bubble points in the adhesive layer at corresponding positions in the face material layer, which can enhance the appearance characteristics of bubble points.

[0027] The original image data is then acquired, cached, and retrieved as input data for subsequent image processing steps.

[0028] Further, the steps of image processing on the acquired image data to generate processed image data include: The system acquires multi-channel image information from the image acquisition data and performs channel separation, channel reconstruction, and channel mapping processing on the multi-channel image information to generate single-channel image data that characterizes the brightness information of the detection area of ​​the low-foam self-adhesive label. Noise suppression processing is performed on single-channel image data. By performing spatial smoothing, frequency domain suppression, and statistical distribution-based filtering operations on the pixel gray values ​​in the image, random gray-level fluctuations caused by imaging noise, ambient light changes, and non-bubble-point structures are reduced. After noise suppression, brightness normalization and grayscale remapping are performed on the image data to generate processed image data.

[0029] Building upon the previously achieved stable imaging conditions and enhanced bubble point significance, this step performs targeted image processing on the acquired image data to make bubble point-related image anomalies more prominent in the processed image data. This significantly improves the reliability of subsequent bubble point candidate region analysis and quality assessment. Its advantages are mainly reflected in the following aspects: Low-foaming self-adhesive labels typically contain color-printed patterns, text, and gradient backgrounds in actual production. The original images are often multi-channel color images, where different channels have different responses to bubble points. This technical solution acquires multi-channel image information from image acquisition data and performs channel separation, channel reconstruction, and channel mapping processing on it. This effectively filters and reconstructs channel information that is more sensitive to changes in the appearance of bubble points. It transforms the color changes caused by complex patterns into a unified brightness representation, thereby avoiding feature redundancy and interference problems caused by direct analysis on multi-channel color images.

[0030] Under controlled imaging conditions, the original image may still contain random grayscale fluctuations caused by imaging device noise, slight changes in ambient light, surface texture, and printing details. These fluctuations can easily interfere with the identification of bubble point anomalies. By performing noise suppression processing on single-channel image data and using spatial smoothing, frequency domain suppression, or filtering operations based on statistical distribution, the random grayscale fluctuations caused by non-bubble point structures can be effectively reduced; the relatively stable brightness and texture anomalies formed by the bubble points of the adhesive layer at the corresponding positions in the surface layer can be preserved; the signal-to-noise ratio of bubble point anomaly features in the image can be improved, and the risk of false detection can be reduced.

[0031] Furthermore, different batches of labels may vary in surface reflectivity, printing depth, and production environment conditions. Directly analyzing unnormalized images can easily lead to detection threshold drift. After noise suppression, performing brightness normalization and grayscale range remapping on the image data can eliminate the impact of overall brightness shift on bubble point detection results. Mapping the image grayscale distribution uniformly to a preset range makes bubble point anomalies comparable across different labels. This provides stable and standardized processed image data for subsequent bubble point candidate region extraction and quality assessment.

[0032] Furthermore, the generation of bubble point candidate region data based on the processed image data includes: The processed image data is scanned region by region to obtain the grayscale distribution information of the pixel regions within the detection area; Based on the preset local grayscale change judgment conditions, the grayscale distribution information is compared and analyzed to screen out the initial abnormal areas that have abnormal grayscale changes relative to the adjacent areas. For the initial abnormal region, the area parameter, boundary continuity parameter, and gray-level change parameter within the region are further calculated. Based on the parameters, the initial abnormal regions are filtered, merged, and segmented to generate candidate regions for bubble points.

[0033] This step further transforms visible differences into computable candidate regions.

[0034] By scanning the processed image data pixel by pixel and region by region, full coverage analysis of the detection area can be achieved without relying on manual selection or fixed templates. It is especially suitable for multi-scale defects with bubble point sizes ranging from tiny dots to local clusters, and can reduce the probability of missed detection.

[0035] The local grayscale change judgment enhances robustness to complex pattern backgrounds. Compared with the direct use of global threshold judgment, this solution uses local grayscale changes relative to adjacent areas as the judgment basis, which can effectively resist color block changes and gradient changes in the label printing pattern itself. The overall brightness drift caused by slight reflection of the surface material is further suppressed on the basis of normalization. Therefore, it can more stably screen out anomalies rather than patterns in complex backgrounds.

[0036] The initial anomalous area may contain non-bubble structures such as printing noise, paper texture, scratch edges, and reflective hotspots. Further calculations of area parameters, boundary continuity parameters, and internal grayscale variation parameters can be performed to filter out single-pixel burrs or excessively large areas.

[0037] A real bubble point may appear as multiple small anomalies connected together or a bubble point fragmented into multiple small pieces by noise. By merging or segmenting the initial anomaly region, we can avoid the same bubble point being counted repeatedly; prevent multiple bubble points from being incorrectly merged into a single oversized defect; and make the final output candidate region more consistent with the actual defect morphology.

[0038] Furthermore, quality assessment is performed based on the candidate bubble point region data, including: Obtain the spatial location information, area information, morphological information, and grayscale distribution information of each bubble point candidate region in the bubble point candidate region data; Based on spatial location information, area information, morphological information and grayscale distribution information, bubble point determination input data is constructed and input into the preset bubble point determination model. Based on the bubble point determination model, each candidate bubble point region is determined to meet the bubble point determination conditions one by one, so as to distinguish the abnormal regions formed by bubble points in the adhesive layer from the non-bubble point regions formed by pattern structure, surface texture and inherent material distribution. After determining the bubble point areas, the number, area, and spatial distribution of the areas determined to be bubble points are statistically analyzed to generate bubble point statistics. Based on the correspondence between bubble point statistics and preset quality judgment conditions, the quality monitoring results of low-foaming self-adhesive labels are generated.

[0039] In the preceding steps, controlled imaging (step S100), image processing (step S200), and point candidate region data (step S300) have gradually transformed the bubble point problem from being difficult to visually understand into a quantifiable and computable data form. This step further completes quality judgment based on multi-dimensional candidate region information, and its technical advantages are mainly reflected in the following aspects: By combining multi-dimensional features for joint judgment, it is possible to effectively distinguish between real anomalies formed by bubble points in the adhesive layer at corresponding positions in the face material layer; under preset imaging conditions, false anomalies caused by label pattern structure, printing lines, substrate texture, and inherent material distribution can be identified, thereby significantly reducing the probability of false detection and misjudgment. Multi-dimensional features include: spatial location information, area information, morphological information, and grayscale distribution information.

[0040] By judging each bubble point candidate region individually, rather than judging the entire image as a whole, we can avoid local anomalies being overwhelmed by global features; and ensure accurate identification even when the number of bubble points is small and their distribution is scattered.

[0041] Bubble spot statistics and quality monitoring results generation: Bubble spot quantity statistics; total bubble spot area and individual bubble spot area statistics; spatial distribution statistics of bubble spots within the label detection area.

[0042] The above bubble point statistics are compared with preset quality judgment conditions. For example, if the number of bubble points exceeds the preset threshold, the label is judged to be unqualified; or if the total area of ​​bubble points exceeds the preset ratio, the label is judged to be unqualified; or if bubble points are concentrated in key display areas, the label is judged to be unqualified. Based on this, the corresponding low-bubbling self-adhesive label quality monitoring results are generated.

[0043] Furthermore, the method also includes: Obtain the structural parameter information of low-foaming self-adhesive labels. The structural parameter information includes at least the thickness of the face stock layer, the thickness of the adhesive layer, and the type of the release liner layer. Based on the structural parameter information, the grayscale determination conditions used in the image processing steps and the bubble point candidate region generation steps are adjusted; The bubble point detection process is then performed based on the adjusted judgment criteria.

[0044] The aforementioned method has already achieved the identification and quality monitoring of bubble point defects in low-foaming self-adhesive labels through controlled imaging, image processing, bubble point candidate region generation, and multi-dimensional judgment. However, different low-foaming self-adhesive labels often have significant differences in structural parameters, such as different thicknesses of the face stock layer, adhesive layer, and release liner layer. These structural differences directly affect the appearance of bubble points in the image.

[0045] The thickness of the face stock layer, adhesive layer, and release liner layer can lead to significant differences in the brightness variation, grayscale contrast, and diffusion range of bubble points at corresponding locations on the face stock layer. By acquiring the structural parameters of low-bubbling self-adhesive labels and adjusting the grayscale judgment conditions used in the image processing and bubble point candidate region generation steps based on these parameters, it is possible to avoid underestimating the apparent changes of bubble points due to a thicker face stock, thus preventing missed detections; to avoid misjudging normal structures as bubble points due to a thinner adhesive layer and different reflective properties of the release liner; and to match the grayscale judgment conditions with the actual label structural characteristics, thereby improving detection accuracy. For example, when the face stock layer is thicker, the local grayscale change judgment threshold can be increased to match the gradual brightness changes formed by bubble points in thicker face stock; when the adhesive layer is thicker, the grayscale change judgment range can be expanded to cover the diffuse brightness anomalies caused by bubble points; and when the release liner layer is a high-reflectivity release liner, the grayscale contrast judgment conditions can be compensated and corrected to reduce the impact of release liner reflection on the detection results.

[0046] Furthermore, the methods also include: Acquire multiple frames of image data of the same low-foam self-adhesive label at different time points; Image registration is performed on multi-frame image acquisition data to generate time-series corresponding image data; The candidate regions for bubble points are confirmed based on the image data corresponding to the time sequence.

[0047] In the aforementioned method, bubble point detection is mainly based on single-frame and single-shot image data acquired under controlled imaging conditions. Although the probability of false detection has been reduced through multi-channel processing, candidate region screening, and multi-dimensional judgment, false anomalies caused by transient interference may still occur in high-speed production lines and complex lighting environments.

[0048] Bubble points formed in the adhesive layer are typically spatially stable and persistent, while false anomalies caused by reflective jitter, transient noise, and material micro-movements often appear only at a single point in time. By acquiring multiple frames of images of the same low-foaming self-adhesive label at different time points and performing time-series correspondence analysis, the persistence of bubble point candidate regions in the time dimension is verified; transient anomalies appearing only in a single frame image are eliminated; and false detections caused by instantaneous changes in illumination and material jitter are significantly reduced.

[0049] Furthermore, the method also includes: The quality monitoring results are correlated with the corresponding low-foam self-adhesive label information; Generate quality record data that includes label identification information and quality monitoring results; The quality record data is then stored in the data storage unit.

[0050] like Figure 2 As shown, the low-foaming self-adhesive label quality monitoring system based on image analysis includes: The acquisition module 10 acquires image acquisition data of the low-foam self-adhesive label. The image acquisition data is digital image data obtained by imaging the low-foam self-adhesive label containing the pattern area under preset imaging conditions. Processing module 20 performs image processing on the image acquisition data to generate processed image data that characterizes the brightness distribution, grayscale distribution, and texture distribution of the label area; The generation module 30 analyzes the image anomalies formed by bubble points in the adhesive layer at the corresponding apparent positions in the surface material layer based on the processed image data, and generates bubble point candidate region data. Quality module 40 performs quality judgment on low-foaming self-adhesive labels based on the bubble point candidate area data, and obtains quality monitoring results.

[0051] All of the above components are general standard parts or components known to those skilled in the art. Their structure and principles can be learned by those skilled in the art through technical manuals or conventional experimental methods.

[0052] For example, the computer program may be divided into one or more modules / units, which are stored in the memory and executed by the processor to complete the present invention. The one or more modules / units may be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of the computer program in the electronic device.

[0053] The electronic device may be a desktop computer, laptop, handheld computer, or smart tablet, etc. The electronic device may include, but is not limited to, a processor and memory. Those skilled in the art will understand that the above components are merely examples of electronic devices and do not constitute a limitation on the electronic device. It may include more or fewer components than described above, or combine certain components, or different components. For example, the electronic device may also include input / output devices, network access devices, buses, etc.

[0054] The processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor or any conventional processor. The processor is the control center of the electronic device, connecting all parts of the electronic device via various interfaces and lines.

[0055] The memory can be used to store the computer programs and / or modules. The processor implements various functions of the electronic device by running or executing the computer programs and / or modules stored in the memory and by calling data stored in the memory. The memory may mainly include a program storage area and a data storage area. The program storage area may store the operating system, at least one application program required for a function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created according to the use of the mobile phone (such as audio data, phonebook, etc.). In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as hard disk, memory, plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0056] Wherein, if the modules / units integrated in the electronic device are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments of the present invention can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the content included in the computer-readable medium can be appropriately added or removed according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electrical carrier signals and telecommunication signals.

[0057] It should be noted that the device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Furthermore, in the accompanying drawings of the device embodiments provided by this invention, the connection relationships between modules indicate that they have communication connections, which can be specifically implemented as one or more communication buses or signal lines. Those skilled in the art can understand and implement this without any creative effort.

[0058] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above descriptions are merely specific embodiments of the present invention and are not intended to limit the scope of protection of the present invention. In particular, it should be noted that any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention for those skilled in the art.

Claims

1. A method for quality monitoring of low-foaming self-adhesive labels based on image analysis, characterized in that, The method includes: Acquire image acquisition data of low-foam self-adhesive labels, wherein the image acquisition data is digital image data obtained by imaging a low-foam self-adhesive label containing a pattern area under preset imaging conditions; The acquired image data is processed to generate processed image data that characterizes the brightness distribution, grayscale distribution, and texture distribution of the label region. Based on the processed image data, the image anomalies formed by bubble points in the adhesive layer at the corresponding apparent positions in the surface material layer are analyzed to generate bubble point candidate region data. Based on the bubble point candidate area data, the quality of low-foaming self-adhesive labels is judged, and the quality monitoring results are obtained.

2. The method for quality monitoring of low-foaming self-adhesive labels based on image analysis according to claim 1, characterized in that, Acquire image data of low-foam self-adhesive labels, including: The spatial position information of the low-foam self-adhesive label at the inspection station is obtained, and the image acquisition device is controlled to image the low-foam self-adhesive label at a preset shooting distance, shooting angle and imaging field of view based on the spatial position information, so as to generate original image data covering the entire inspection area of ​​the label. During the image acquisition process, the lighting device is controlled according to the preset imaging parameters so that the lighting source acts on the surface of the low-foam self-adhesive label with preset light intensity, light incident angle and light distribution, so that the bubble points in the adhesive layer form brightness changes and texture changes at the corresponding positions of the face material layer. The original image data is then acquired, cached, and retrieved as input data for subsequent image processing steps.

3. The method for quality monitoring of low-foaming self-adhesive labels based on image analysis according to claim 2, characterized in that, The steps for processing image acquisition data to generate processed image data include: Multi-channel image information is acquired from the image acquisition data, and channel separation, channel reconstruction, and channel mapping processing are performed on the multi-channel image information to generate single-channel image data for characterizing the brightness information of the detection area of ​​the low-foam self-adhesive label. The single-channel image data is subjected to noise suppression processing. By spatially smoothing and frequency domain suppressing the pixel gray values ​​in the image, random gray-level fluctuations caused by imaging noise, ambient light changes, and non-bubble structure are reduced. After noise suppression, brightness normalization and grayscale remapping are performed on the image data to generate processed image data.

4. The method for quality monitoring of low-foaming self-adhesive labels based on image analysis according to claim 3, characterized in that, The steps for generating bubble point candidate region data based on the processed image data include: The processed image data is scanned region by region to obtain the grayscale distribution information of the pixel regions within the detection area; Based on preset local grayscale change judgment conditions, the grayscale distribution information is compared and analyzed to screen out the initial abnormal regions that have abnormal grayscale changes relative to adjacent regions. For the initial abnormal region, calculate the area parameter, boundary continuity parameter, and gray-scale change parameter within the region. Based on the parameters, the initial abnormal regions are filtered, merged, or segmented to generate bubble point candidate region data.

5. The method for quality monitoring of low-foaming self-adhesive labels based on image analysis according to claim 4, characterized in that, The steps for quality assessment based on candidate bubble point regions include: Obtain the spatial location information, area information, morphological information, and grayscale distribution information of each bubble point candidate region in the bubble point candidate region data; Based on the spatial location information, area information, morphological information and grayscale distribution information, bubble point determination input data is constructed and input into the preset bubble point determination model. According to the bubble point determination model, each bubble point candidate region is determined to meet the bubble point determination conditions one by one, so as to distinguish the abnormal regions formed by bubble points in the adhesive layer from the non-bubble point regions formed by pattern structure, surface texture and inherent material distribution. After determining the bubble point areas, the number, area, and spatial distribution of the areas determined to be bubble points are statistically analyzed to generate bubble point statistics. Based on the correspondence between the bubble point statistics and the preset quality judgment conditions, the quality monitoring results of the low-foaming self-adhesive label are generated.

6. The method for quality monitoring of low-foaming self-adhesive labels based on image analysis according to claim 1, characterized in that, The method further includes: Obtain structural parameter information of low-foaming self-adhesive labels, wherein the structural parameter information includes at least the thickness of the face material layer, the thickness of the adhesive layer, and the type of the release liner layer; Based on the structural parameter information, the grayscale determination conditions used in the image processing steps and the bubble point candidate region generation steps are adjusted; The bubble point detection process is then performed based on the adjusted judgment criteria.

7. The method for quality monitoring of low-foaming self-adhesive labels based on image analysis according to claim 1, characterized in that, The method further includes: Acquire multiple frames of image data of the same low-foam self-adhesive label at different time points; Image registration is performed on the acquired multi-frame image data to generate time-series corresponding image data; The candidate regions for bubble points are confirmed based on the image data corresponding to the time sequence.

8. The method for quality monitoring of low-foaming self-adhesive labels based on image analysis according to claim 1, characterized in that, The method further includes: The quality monitoring results are correlated with the corresponding low-foam self-adhesive label information; Generate quality record data that includes label identification information and quality monitoring results; The quality record data is then stored in the data storage unit.

9. A low-foaming self-adhesive label quality monitoring system based on image analysis, including: The acquisition module acquires image acquisition data of low-foam self-adhesive labels, wherein the image acquisition data is digital image data obtained by imaging a low-foam self-adhesive label containing a pattern area under preset imaging conditions. The processing module performs image processing on the acquired image data to generate processed image data that characterizes the brightness distribution, grayscale distribution, and texture distribution of the label area. The generation module analyzes the image anomalies formed by bubble points in the adhesive layer at the corresponding apparent positions in the surface material layer based on the processed image data, and generates bubble point candidate region data. The quality module performs quality judgment on the low-foaming self-adhesive labels based on the bubble point candidate area data, and obtains the quality monitoring results.

Images